From jelman at ucsd.edu Sat Sep 1 14:04:49 2007 From: jelman at ucsd.edu (Jeff Elman) Date: Sat, 1 Sep 2007 11:04:49 -0700 Subject: Connectionists: 3 faculty positions in Cognitive Science at UC San Diego Message-ID: <12C3CBCC14A69E4BBEB9AD88F6860F2301645A50@Shrek.AD.UCSD.EDU> The Department of Cognitive Science at the University of California, San Diego http://www.cogsci.ucsd.edu/ invites applications for three (3) faculty positions at the Assistant Professor level (tenure-track) starting July 1, 2008, the salary commensurate with the experience of the successful applicant and based on the UC pay scale. The Department of Cognitive Science at UCSD was the first of its kind in the world, and, as part of an exceptional scientific community, it remains a dominant influence in the field it helped to create. The department is truly interdisciplinary, with a faculty whose interests span anthropology, computer science, human development, linguistics, neuroscience, philosophy, psychology, and sociology. The department is looking for several top-caliber junior researchers in cognitive science. Applicants must have a Ph.D. (or ABD). We seek applicants with a solid foundation in neuroscience and/or computation broadly construed, although a broad interdisciplinary perspective and experience with multiple methodologies will be highly valued. Women and minorities are encouraged to apply. UCSD is an Equal Opportunity/Affirmative Action Employer with a strong institutional commitment to excellence through diversity. All applications received by November 15, 2007 will receive thorough consideration until position is filled. Candidates should submit, via our online application, a vita, reprints of up to four representative publications, a short cover letter describing their background and interests, and at least three references (name, title, address and email). Applicants are welcome to include in their cover letter a personal statement summarizing their contributions to diversity. Go to http://ssfacrecruit.ucsd.edu/cogsci0708/login.php to apply on-line. For more information, please contact Marine Sinanyan (msinanya at cogsci.ucsd.edu). From stefan.wermter at sunderland.ac.uk Wed Sep 5 12:01:26 2007 From: stefan.wermter at sunderland.ac.uk (Stefan Wermter) Date: Wed, 05 Sep 2007 17:01:26 +0100 Subject: Connectionists: Job Announcement: Research Scientist Neuro-Robotics Message-ID: <46DED2D6.6000908@sunderland.ac.uk> Job announcement School of Computing & Technology, University of Sunderland Research Scientist Neuro-Robotics (MiCRAM) Fixed term ? 24 months 27,466 - 32,796 pounds per annum Ref: CTR016/1436 At Sunderland, our focus in this EPSRC project is to develop and validate biomimetic robots, computational neural models and a neuroscience database for the development of a biologically realistic model of auditory processing (MICRAM project). Your job will involve the development of a biomimetic robot that uses neural computational modeling to simulate the auditory midbrain. You should be educated to PhD level or possess equivalent research experience and a proven ability in research and publication. A degree in a computing discipline is essential and knowledge of biomimetic robotics is desirable. Experience with GENESIS or similar neural modelling and knowledge of the auditory system in mammals and of bioacoustics would be advantageous. For informal discussions please contact Dr. Harry Erwin (+44-191 515 3227; harry.erwin at sunderland.ac.uk) or Professor Stefan Wermter (+44 191-515-3279 stefan.wermter at sunderland.ac.uk ). Interviews for this post will be held on 8th October 2007. Application form and Role Profile can be obtained by contacting Human Resources on 0191 515 2057 or www.sunderland.ac.uk/jobs Closing Date: 28th September 2007 *************************************** Professor Stefan Wermter Hybrid Intelligent Systems School of Computing and Technology University of Sunderland St Peters Way Sunderland SR6 0DD United Kingdom phone: +44 191 515 3279 fax: +44 191 515 3553 email: stefan.wermter AT sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** From bminnery at mitre.org Tue Sep 4 09:23:31 2007 From: bminnery at mitre.org (Minnery, Brad) Date: Tue, 4 Sep 2007 09:23:31 -0400 Subject: Connectionists: Cognitive/Computational Neuroscientist Position at the MITRE Corporation Message-ID: The MITRE Corporation, a not-for-profit organization in McLean VA (http://www.mitre.org/), has several opportunities to work with forward-looking government sponsors seeking to apply the mechanisms and principles of biological intelligence to longstanding problems of national importance. Job Title: SENIOR ARTIFICIAL INTELLIGENCE ENGINEER Key Functions include: -- Assist Government Program Managers in developing and managing research programs that exploit our growing understanding of the neurobiological basis of intelligent behavior. -- Monitor and assess the technical state-of-the-art in cognitive and computational neuroscience, and identify opportunities for applying emerging insights from neuroscience research towards problems in the domains of: artificial intelligence, automated perception, robotics, human performance, human-computer interaction, biotechnology and medicine. -- Perform original research as necessary to answer specific questions or to provide a proof of concept. -- Prepare technical presentations, reports and tutorials as necessary to communicate progress and findings to colleagues and government sponsors. Desired Education / Experience: PhD in Neuroscience, Cognitive Science, Artificial Intelligence or related discipline. Experience in both experimental and computational neuroscience methods is preferred. Required Skills: -- Familiarity with quantitative and qualitative concepts in the computational and cognitive neurosciences -- Proficiency in one or more of the leading computational/cognitive neuroscience modeling tools and/or frameworks -- Outstanding oral and written communication skills, including the ability to clearly present complex technical concepts to both technical and non-technical audiences -- Ability to plan, conduct and publish original scientific research -- including the ability to consider alternative approaches and to identify factors affecting cost or risk Desired Skills: -- Computer programming skills, particularly in Matlab and C/C++ -- Proficiency in PDP++/Emergent, NEURON, Genesis, or any of several popular neural modeling tools -- Strong knowledge of current theoretical and experimental trends in the areas of learning, memory, and visual attention -- Familiarity with hardware-based implementations of neural systems, e.g. neuromorphic VLSI (preferred but not required) Please apply online at: http://www.mitre.org/employment/index.html When applying, please reference Req ID: 8212 From large at ccs.fau.edu Tue Sep 4 15:10:12 2007 From: large at ccs.fau.edu (Edward Large) Date: Tue, 4 Sep 2007 15:10:12 -0400 Subject: Connectionists: Postdoctoral position available Message-ID: <2177B022-9187-4BD3-900C-6AE855496E46@ccs.fau.edu> POSTDOCTORAL POSITION in NONLINEAR DYNAMICS of MUSIC and AUDITORY PERCEPTION Center for Complex Systems and Brain Sciences Florida Atlantic University Our music and auditory dynamics laboratory seeks a postdoctoral research associate to work on dynamical systems modeling of auditory perceptual processes. We use the most advanced mathematical techniques to model auditory and music perception (see http:// www.ccs.fau.edu). The postdoc will coordinate all aspects of this project, including: * analysis and development of nonlinear dynamical models of perception * development of MATLAB toolbox for auditory modeling * evaluation of model predictions; comparison with perceptual and neural data * preparation of journal articles, grants, and presentations * collaboration with industrial research partners Qualifications: * Knowledge of nonlinear dynamical systems required * Advanced degree in Physics or Mathematics strongly preferred * Knowledge of auditory perception and/or neuroscience preferred * Strong interpersonal and communication skills, both verbal and written * Computer programming experience required * MATLAB expertise preferred * Recent PhD graduate Postdoctoral position pays NIH scale, starting at $36,996. Open immediately, with preferred start date 15 Oct 2007 or earlier. Minimum one year commitment preferred. Please send a curriculum vitae with the contact details of three references to Dr. Edward W. Large: large at ccs.fau.edu From franco at dii.unisi.it Wed Sep 5 13:01:07 2007 From: franco at dii.unisi.it (Franco Scarselli) Date: Wed, 05 Sep 2007 19:01:07 +0200 Subject: Connectionists: NEUROCOMPUTING CFP: Special Issue on "Pattern Recognition in Graphical Domains" Message-ID: <46DEE0D3.7030607@dii.unisi.it> ** Our apologies if you receive multiple copies of this announcement ** Call for Papers NEUROCOMPUTING Special Issue on PATTERN RECOGNITION IN GRAPHICAL DOMAINS Neurocomputing is seeking original and unpublished manuscripts for a Special Issue on "Pattern Recognition in Graphical Domains", scheduled for publication in June/July 2008. 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 issue 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. Submitted articles must not have been previously published and must not be currently submitted for publication elsewhere. Topics of interest include, but are not limited to, the following: - 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 procedure: Manuscript should follow the standard guidelines of the Neurocomputing journal. Guidelines for formatting papers can be found in the Guide for Authors at http://www.elsevier.com/wps/find/journaldescription.cws_home/505628/authorinstructions Prospective authors should submit an electronic copy of their complete manuscript through the Elsevier online submission system at http://ees.elsevier.com/neucom/ by November 5, 2007. Important dates: Manuscript submission deadline: November 5, 2007 First notification: January 25, 2008 Revised manuscript submission: February 29, 2008 Notification of final decision: April 11, 2008 Final manuscript due: April 25, 2008 Publication of special issue: June/July 2008 Guest Editors: Monica Bianchini Universit? di Siena Siena, Italy e-mail: monica at dii.unisi.it Franco Scarselli Universit? di Siena Siena, Italy e-mail: franco at dii.unisi.it Information on the Special Issue are also available at http://www.dii.unisi.it/~monica/NeuroSI/ From longlifelee at gmail.com Thu Sep 6 03:43:57 2007 From: longlifelee at gmail.com (Soo-Young Lee) Date: Thu, 6 Sep 2007 16:43:57 +0900 Subject: Connectionists: Special Issue of NIP-LR Message-ID: I would like to inform you that the newest issue of NIP-LR (Neural Information Processing - Letters and Reviews) is available online at www.nip-lr.info It is a special issue on Artificial Brain with Emotion and Learning. Vol.11, Nos.4-6, 2007 Guest Editorial for Volume 11 Numbers 4-6 : Special Issue on Artificial Brain with Emotion and Learning Rhee Man Kil, Minho Lee Letters Visual Motion Analysis by a Neural Network Kunihiko Fukushima Functional Connectivity Measurement of the Brain Dae-Shik Kim Cross-Modal Learning - The Learning Methodology Inspired by Human's Intelligence Bo Zhang, Dayong Ding, and Ling Zhang Separating Pose and Expression in Face Images: A Manifold Learning Approach Jihun Ham and Daniel D. Lee Attentional Modulation of Tilt Aftereffect Caused by Cholinergic Basal Forebrain Projections Ketan Bajaj and Basabi Bhaumik Mind Model Seems Necessary for the Emergence of Communication Andr?s L?rincz, Viktor Gyenes, Melinda Kiszlinger and Istv?n Szita Experiments with Computational Creativity Wlodzislaw Duch and Maciej Pilichowski Synaptic Plasticity and Spike-based Computation in VLSI Networks of Integrate-and-Fire Neurons Giacomo Indiveri Proposal of a Micromachined Tactile Sensor Having Four Stories and Its Information Processing Method using Module Networks Seiji Aoyagi and Takaaki Tanaka -- Soo-Young Lee Director, Brain Science Research Center, KAIST From chenyu6 at gmail.com Thu Sep 6 21:44:22 2007 From: chenyu6 at gmail.com (Chen Yu) Date: Thu, 6 Sep 2007 21:44:22 -0400 Subject: Connectionists: Postdoc Position at Indiana University Message-ID: The following postdoc position in machine learning and computational modeling as applied to cognitive learning is available at Indiana University, Program in Cognitive Science. Applications are invited for a postdoctoral position working with Dr. Chen Yu and Dr. Linda B. Smith to study issues in statistical learning, multimodal learning, and embodied cognition. The research involves data mining of multisensory data and/or eye tracking and/or statistical modeling. The successful candidate will have a Ph.D. in Computer Science, Cognitive Science, Psychology, Engineering or a related field. Excellent programming skills, experience with C/C++ and Matlab, and a background in machine learning, and computer vision or statistical language learning, are highly desirable. The initial appointment will be for one year but renewable for another two years. The position is open immediately and salary is commensurate with NIH levels (plus benefits). Applicants should send a cover letter, a CV, representative publications, and the names of three references directly to Chen Yu chenyu6 at gmail.com Indiana University is an Affirmative Action/Equal Opportunity employer. Applicants need not be US citizens, and women and minority candidates are especially encouraged to apply. From risto at cs.utexas.edu Thu Sep 6 22:23:07 2007 From: risto at cs.utexas.edu (Risto Miikkulainen) Date: Thu, 6 Sep 2007 21:23:07 -0500 Subject: Connectionists: NERO 2.0 machine learning game (www.nerogame.org) Message-ID: <200709070223.l872N7ur014458@mainsa.cs.utexas.edu> We are pleased to announce the release of NERO 2.0 machine learning game. In this game, the player trains teams of agents to perform complex tasks in a simulated 3D environment. The agents are controlled by neural networks that learn based on the rtNEAT neuroevolution method. The training is evaluated in autonomous battle mode against other teams; the game also provides a territory-control mode for interactive game play. The territory mode is new in 2.0; this release also includes a new user interface and more extensive training tools. NERO can be downloaded freely from http://nerogame.org for Linux, OS X, and Windows platforms. It is intended to serve three purposes: - It is an engaging game that demonstrates a new genre of video games where machine learning plays a central role. The site includes videos illustrating the gameplay and evolved behaviors, and the game includes a tutorial mode that makes it easy to get started. - It is a "killer application" of rtNEAT, demonstrating how it can be used to learn complex behaviors in real time. For more details on rtNEAT and its application in NERO, see the paper at http://nn.cs.utexas.edu/keyword?stanley:ieeetec05. The rtNEAT (and NEAT) software is available at http://nn.cs.utexas.edu/soft-list.php. - It is a prototype of a research platform that will allow developing and testing new machine learning methods in a complex video game environment, as well as a demonstration tools for various AI methods in general. We would like to get your feedback especially on this last point. In the near future, we will put together an open-source version of NERO (v2.0 is based on the Torque game engine) and plan to extend it to serve as a general research platform for the community. How can the NERO environment best support research in machine learning and embedded artificial agents? How can it best serve as a demonstration platform e.g. for AI courses? At this point, we invite you to try out NERO 2.0 and give us feedback and suggestions on how to make OpenNERO a useful such tool for the future. -- Risto Miikkulainen, Ken Stanley, Igor Karpov, and the NERO development team From vcu at cs.stir.ac.uk Fri Sep 7 06:13:30 2007 From: vcu at cs.stir.ac.uk (Vassilis Cutsuridis) Date: Fri, 7 Sep 2007 11:13:30 +0100 Subject: Connectionists: Neural accumulator model, superior colliculus, antisaccade task, decision making Message-ID: <00b801c7f137$bd4b4330$6ffd998b@cs.ad.stir.ac.uk> The following article is now available at: http://www.cs.stir.ac.uk/~vcu/papers/CutSmyEvdPer.pdf Cutsuridis, V, Smyrnis, N, Evdokimidis, I, Perantonis, S. (2007) A Neural Model of Decision Making by the Superior Colliculus in an Antisaccade Task Neural Networks, 20(6): 690-704 ABSTRACT In the antisaccade paradigm subjects are instructed to perform eye movements in the opposite direction from the location of a visually appearing stimulus while they are fixating on a central stimulus. A recent study investigated saccade reaction times (SRTs) and percentages of erroneous prosaccades (towards the peripheral stimulus) of 2006 young men performing visually guided antisaccades. A unimodal distribution of SRTs (ranging from 80 to 600 ms) as well as an overall 25% of erroneous prosaccade responses was reported in that large sample. In this article, we present a neural model of saccade initiation based on competitive integration of planned and reactive saccade decision signals in the intermediate layer of the superior colliculus. In the model the decision processes grow nonlinearly towards a preset criterion level and when they cross it, a movement is initiated. The resultant model reproduced the unimodal distributions of SRTs for correct antisaccades and erroneous prosaccades as well as the variability of SRTs and the percentage of erroneous prosaccade responses. Keywords: Eye movements; Antisaccades; Buildup neurons; Burst neurons; Nonlinear accumulator model; Decision making; Saccade reaction times; Superior colliculus -- 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 murphyk2 at gmail.com Fri Sep 7 12:29:11 2007 From: murphyk2 at gmail.com (Kevin Murphy) Date: Fri, 7 Sep 2007 09:29:11 -0700 Subject: Connectionists: CFP - NIPS workshop on statistical models of networks In-Reply-To: References: Message-ID: Dear colleagues, I would like to invite you to participate in a workshop on "Statistical models of networks" on the 7th or 8th of December at NIPS'07 in Whistler, B.C. See this URL for details: http://www.cs.ubc.ca/~murphyk/nips07NetworkWorkshop/ The purpose of the workshop is to bring together people from different disciplines - computer science, statistics, biology, physics, social science, etc - to discuss foundational issues in the modeling of network and relational data. In particular, we hope to discuss various open research issues, such as - How to represent graphs at varying levels of abstraction, whose topology is potentially condition-specific and time-varying - How to combine techniques from the graphical model structure learning community with techniques from the statistical network modeling community - How to integrate relational data with other kinds of data (e.g., gene expression or text data) Six stellar invited speakers (Adrian Raftery, Peter Hoff, Stephen Fienberg, Stanley Wasserman, Volker Tresp, Jasmine Zhou) have already accepted. However, we are seeking additional contributions from the community, in order to broaden the scope and to form the basis of fruitful discussion. If you would like to contribute, then please send a 1-2 page abstract by October 15, 11:59pm PST to murphyk at cs.ubc.ca. (Details below.) I am looking forward to seeing you there! Kevin Murphy Lise Getoor Eric Xing Raphael Gottardo SUBMISSION INSTRUCTIONS Researchers interested in contributing should send an extended abstract of 1-2 pages in PDF format to murphyk at cs.ubc.ca by October 15, 2007, 11:59pm PST. No special style is required. Note that previously published work *is* acceptable (unless it appears in the main NIPS'07 conference), as long as it is clearly marked as such. Acceptance decisions will be made by October 31st. Decisions will be made by the four organizers, based on relevance, quality and balance of topics. Due to time constraints, accepted abstracts can only be presented as a poster and/or a short spotlight. However, all accepted abstracts will also be posted in the online proceedings. From netta at comp.leeds.ac.uk Tue Sep 11 07:20:27 2007 From: netta at comp.leeds.ac.uk (N Cohen) Date: Tue, 11 Sep 2007 12:20:27 +0100 (BST) Subject: Connectionists: Openings in biorobotics and C elegans neurobiology Message-ID: Apologies for cross posting. Two Postdoctoral Research Fellows: Neural control of locomotion behaviour in biology and machines: A systems biology approach University of Leeds, Leeds, UK Applications are invited for two Postdoctoral Research Fellowships to join a multi-disciplinary research team and study motor control of locomotion in C. elegans nematode worms. Post 1: The use of fluorescent imaging tools to record neuronal and/or muscle activity in C. elegans nematode worms Post 2: Construction of a bio-robotic model of the worm Background: C. elegans is an exciting model system for biologists, modellers and roboticists alike. A relatively simple animal, with a small and fully mapped anatomy and nervous system and experimentally accessible, C. elegans is a leading model system in genetics and development as well as neurobiology. Dubbed the "hydrogen atom" of systems neuroscience, it is also the subject of intensifying efforts to model this creature completely -- integrating bottom up and top-down approaches. You will join a multi-disciplinary, dynamic, and creative BioSystems group within the School of Computing at the University of Leeds, with close ties to the Faculty of Biological Sciences, where all biological experimental facilities are housed, and Mechanical Engineering, housing all robotic construction and testing facilities. Post 1: The use of fluorescent imaging tools to record neuronal and/or ------- muscle activity in C. elegans nematode worms (Job Ref: 312252) Your research will involve neuronal and muscle imaging experiments to link between neuronal and muscle activity and the behaviour of the worm. Work will include: the design and implementation of assays; their application to wildtype and mutant worms; data collection using computer imaging and relevant data analysis. Possible scope also exists for the development and implementation of novel molecular probes. This work will involve close interaction and collaboration with other aspects of the C. elegans project, in particular, to do with the behavioural studies and modelling of the worm's neural and motor control. The development of novel imaging tools is a possible extension of the project. Experience in microscopy and fluorescent imaging is required. Experience in invertebrate neurobiology is a plus, but not a requirement. You will be based in a laboratory that has been dedicated to C. elegans research for over 15 years. Previously, interest has concentrated on genomics approaches to the study of gene expression and nervous system modulation. The arrival of Netta Cohen has led to the collaborations in the systems biology of C. elegans with which you would be involved. The laboratory is fully equipped for C. elegans research: transformation of C. elegans is performed regularly by microinjection and microparticle bombardment; genetic and RNAi analyses are approaches followed routinely; confocal, fluorescence and DIC microscopy are fundamental technologies upon which much of this laboratory's activity relies. Post 1 is available immediately (and no later than January 2008) for a period of two years. Post 2: Construction of a bio-robotic model of the worm ------- (Job Ref: 312253) Your research will involve the design, construction and testing of robots mimicking C. elegans locomotion. Robots will be designed with a view to constructing a research tool to complement experiments on the biological worm. Work will include the design and implementation and testing of suitable sensors and actuators and lead to the design and construction of a robot of an entire worm. This work will involve close interaction and collaboration with other aspects of the C. elegans project, in particular, to do with the modelling of the worm's neural and motor control. Prior experience in biological motor control or bio-robotics is a plus. A strong previous track record in robot design and construction is required. Robotics research will be conducted in close collaboration with the Mechatronics and Robotics Research Group in the School of Mechanical Engineering at Leeds, an international leader in research on biomimetic sensors and actuators. The Mechatronics & Robotics Research Group (MRRG) in the School carries out fundamental and applied multidisciplinary research in close collaboration with a number of staff in other Schools of the University and also with many industrial partners. Research interests and activities of the group cover a broad area including: general mechatronics and robotics, biomechatronics/biorobotics/ biomimetics such as research in distributed smart sensors, actuators, machine intelligence and control, and machine vision, for a wide range of applications. Relevant laboratories to the group research are: Mechatronics and Control Lab, Advanced mechatronics lab and robotics lab. Post 2 is flexible in start time, and may start immediately and ideally no later than spring 2008 for a period of one year. ----------------------- Full adverts and application instructions can be found on http://jobs.leeds.ac.uk/ -- Click on "Research" under "In this section" and look for Job Ref: 312252 and 312253 Informal enquiries to Dr Netta Cohen, tel +44 (0)113 343 6789, email netta at comp.leeds.ac.uk Application packs and further details are available from Judi Drew, tel +44 (0)113 343 5432, email j.a.drew at leeds.ac.uk Closing date for both posts 8 October 2007 Interviews are planned for the week commencing 22 October 2007. ====================================================================== Netta Cohen BioSystems Group, School of Computing & Inst Membrane and Systems Biology Phone: +44 (0)113 3436789 University of Leeds Fax: +44 (0)113 3435457 Leeds, LS2 9JT Email: netta at comp.leeds.ac.uk United Kingdom www.comp.leeds.ac.uk/netta/ From roland.baddeley at bristol.ac.uk Mon Sep 10 11:30:17 2007 From: roland.baddeley at bristol.ac.uk (Roland Baddeley) Date: Mon, 10 Sep 2007 16:30:17 +0100 Subject: Connectionists: PhD position in Animal camouflage available in Bristol University Message-ID: <01a401c7f3bf$7dce6590$796b30b0$@baddeley@bristol.ac.uk> PhD position into a Computational and Psychophysical investigation into how animals camouflage motion (or why the leopard got its spots) This could potentially be explored using machine learning techniques so may be of interest to this mailing list. The details follow: A three year Qinetic funded case studentship based in the Department of Experimental Psychology in the University of Bristol is available to study animal camouflage. In particular the project will investigate how moving animals minimize their visibility. There will be a fair amount of flexibility on how this problem is approached, including approaches based on 1) psychophysics using human observers: manipulating various characteristics of artificial animal camouflage patterns within natural realistic backgrounds and observing which factors affect their visibility. 2) Natural image statistics and the statistics of animal coloration patterns: viewing both backgrounds and animal coloration patterns as textures, and using machine learning techniques to look at the mapping between environmental niche, and the coloration patterns displayed. 3) Looking at the spatio-temporal statistics of animal environments with a view to seeing which aspects of animal coloration will aid in reducing the visibility of a moving animal; and 4) Constructing and comparing various simple ideal observer models of predator/prey detection, and comparing these with observed behavior. This list is not exclusive, but as can be seen, the position would be of potential interest not only to a behavioral ecologist that wants to learn a bit of vision, but also a more computational person who would like to apply their skills in a really very interesting area. The list of supervisors includes people with interests and skills in areas ranging from motion perception, to image modeling, to behavioral ecology, to the application of these ideas to designing man made camouflage. For more information or to apply, email Roland at: Roland.Baddeley at bristol.ac.uk The last date for applications is September 23rd, and the starting date is flexible but should be before mid January. Please when applying send a CV and including the names of two referee's. Supervisors: Roland Baddeley (Department of Experimental Psychology, University of Bristol) Adam Shohet (QinetiQ) Nick Scott-Samuel (Department of Experimental Psychology, University of Bristol) Innes Cuthill (School of Biological Sciences, University of Bristol) From aburkitt at bionicear.org Sun Sep 9 03:03:58 2007 From: aburkitt at bionicear.org (Anthony BURKITT) Date: Sun, 9 Sep 2007 17:03:58 +1000 Subject: Connectionists: Job Announcement: Postdoctoral position available Message-ID: <878D1E4EA053B049A372ECE97FF4AECEBA46CF@GKAR.medoto.unimelb.edu.au> POSTDOCTORAL POSITION in Neural Modelling of Music & Voice Perception Salary: AUD$68,256 - AUD$81,052 (dependent on experience) http://www.bionicear.org/jobs/BEIResearchFellowLBMusic&VoicePerception.h tml The Bionic Ear Institute, Melbourne, Australia The aim of the proposed research is to determine how best to encode the frequency and time information contained in an auditory signal in order to maximise the perception of music and voice pitch information for people with cochlear implants. We are seeking a postdoctoral researcher to work on modeling of the auditory system and perceptual processes. Key Responsibilities include: - Assisting in the development of a computer model that accurately accounts for the mechanical and neural response of the ear to sound. - Assisting in the development of models to compare pitch perception data against existing cochlear implant systems. - Carrying out research in relation to modifying electrical stimulation models to reflect the recommendations for the design of future stimulating electrodes and hardware of cochlear implants. - Preparation of journal articles, presentations, and grants. - Co-supervision of postgraduate research projects within this research program. Qualifications: - A Postgraduate qualification in Mathematics or Engineering or equivalent qualification (essential). - Previous experience with neural modelling or other relevant field (desirable). - Previous MATLAB experience (desirable). Applications should include a detailed CV and be sent via e-mail only to: hr-applications at bionicear.org Closing Date: 24th September 2007 Position open immediately, with preferred start date early 2008 or earlier. For informal discussions please contact Prof. Tony Burkitt (aburkitt at bionicear.org) The Bionic Ear Institute is an independent, not-for-profit medical research organisation specialising in bionics to find new and better ways to restore brain function and to help deaf children and adults communicate. http://www.bionicear.org ====================ooOOOoo==================== Anthony N. Burkitt Assistant Director and Professor The Bionic Ear Institute 384-388 Albert Street East Melbourne, VIC 3002 Australia Email: aburkitt at bionicear.org http://www.bionicear.org/people/burkitta Phone: +61 - 3 - 9667 7529 Fax: +61 - 3 - 9667 7518 =====================ooOOOoo=================== From neuralassembly at yahoo.co.jp Mon Sep 10 04:16:01 2007 From: neuralassembly at yahoo.co.jp (Takashi KANAMARU) Date: Mon, 10 Sep 2007 17:16:01 +0900 (JST) Subject: Connectionists: Two papers on chaotic synchronization in PNN Message-ID: <20070910081601.84815.qmail@web3215.mail.kcd.yahoo.co.jp> Dear all, I would like to announce two papers on chaotic synchronization in PNN are available from the following page. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/ 1) ########## Takashi Kanamaru, "Chaotic pattern transitions in pulse neural networks," Neural Networks, vol.20, issue 7 (2007) pp.781-790. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/kanamaru-nn2007.pdf Simulator (Please note that Java applet will be launched.) http://brain.cc.kogakuin.ac.jp/~kanamaru/Chaos/e/PnnAM/ [Abstract] In models of associative memory composed of pulse neurons, chaotic pattern transitions where the pattern retrieved by the network changes chaotically were found. The network is composed of multiple modules of pulse neurons, and when the inter-module connection strength decreased, the stability of pattern retrieval changed from stable to chaotic. It was found that the mixed pattern of stored patterns plays an important role in chaotic pattern transitions. 2) ########## Takashi Kanamaru, "Blowout bifurcation and on-off intermittency in pulse neural networks with multiple modules," International Journal of Bifurcation and Chaos, vol.16, no.11 (2006) pp.3309-3321. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/kanamaru-ijbc2006.pdf [Abstract] To study the mechanism by which high-dimensional chaos emerges in neural systems, the synchronization of chaotic firings in class 1 pulse neural networks composed of excitatory and inhibitory ensembles was analyzed. In the system with two modules (i.e., two pulse neural networks), blowout bifurcation and on-off intermittency were observed when the inter-module connection strengths were reduced from large values. In the system with three modules, rearrangement of synchronized clusters and chaotic itinerancy were observed. Such dynamics may be one of the mechanisms through which high-dimensional chaos is generated in neural systems. Best regards, Takashi KANAMARU http://brain.cc.kogakuin.ac.jp/~kanamaru/ Department of Innovative Mechanical Engineering, Faculty of Global Engineering, Kogakuin University, 2665-1 Nakano, Hachioji-city, Tokyo 192-0015, Japan From mpoel at cs.utwente.nl Tue Sep 11 09:09:25 2007 From: mpoel at cs.utwente.nl (Mannes Poel) Date: Tue, 11 Sep 2007 15:09:25 +0200 Subject: Connectionists: BCI Vacancies at UT-HMI Message-ID: <46E69385.6090107@cs.utwente.nl> Five Research Positions on "Games and BCI" at HMI-Twente At the Human Media Interaction (HMI) group of the University of Twente, Enschede, the Netherlands, positions are available for three Ph.D.s, a Postdoc and a junior researcher or programmer. Research will be done in the context of the Dutch national BrainGain project (www.nici.ru.nl/braingain/), a large-scale project that aims at applying recent developments in the area of analyzing and influencing brain activity for the improvement of quality of life and performance for both patients and healthy users. The emphasis of the research at HMI will be on BCI applications for the healthy users and it will focus on brain-computer interfacing and games. In this research the potential role of brain signals will be investigated in combination with other input modalities for games, including bio-signals and non-verbal means of communication. The research will be done in cooperation with TNO (Soesterberg), NICI (Nijmegen), F.C. Donders Center (Nijmegen) and Philips Research (Eindhoven). The postdoc (3-4 years) and the junior researcher (2 years) will work on the topics mentioned below and they will support and advise the Ph.D. researchers. The three Ph.D. students will each focus on a particular issue. Issue 1. What can brain signals tell us about the user experience? The focus here is on understanding the relation between experience, brain signals, and affective information obtained from other input modalities. Designing experiments and performing reliability studies are among the research approaches. The inferences about the cognitive and affective state of the user that can be made on the basis of the information from the various measures will be used in the development of adaptive interfaces for games. Issue 2. How to measure and decode brain signals for control of game environments? Designing experiments and performing reliability studies are among the research approaches. The focus is on (machine learning) algorithms to extract information from brain signals in situations where a gamer has to perform various tasks in parallel. Results of this research will be used in the development of hybrid interfaces for games that allow control obtained from, among other things, brain signals. Issue 3. How to design interfaces and engaging game environments for both patients and healthy users? These intelligent interfaces and environments know about the user's mental state and allow, among other things, multimodal commands to control the game environment and the game actors. This multimodality includes commands derived or supplemented from conscious mental activity. The focus is on game design, in particular the blending of a gamer's mental activities and the game intelligence, allowing the issuing of high-level commands that can be interpreted and executed by the game environment. Human-computer interaction issues such as usability and experience measures are also part of this research. The HMI Department of the University of Twente comprises more than forty researchers (including 20 Ph.D. students). It is involved in many European and national projects and Networks of Excellence on smart surroundings, ambient intelligence, multimodal interaction, speech and natural language processing, multimedia retrieval, embodied agents, virtual reality, adaptive user interfaces and affective computing, games and entertainment computing. The HMI department is also responsible for the Master of Science track "Human Media Interaction" with more than fifty students. Gross Ph.D. salary starts with ? 1.956, - per month in the first year and increases to ? 2.734, - in the fourth year of employment. Salary of postdoc and junior researchers depends on expertise and experience. More information is available on request. Please send applications (with CV) or requests for more information by email to Prof.dr. Anton Nijholt (anijholt at cs.utwente.nl). From sugi at cs.titech.ac.jp Tue Sep 11 09:57:44 2007 From: sugi at cs.titech.ac.jp (Masashi Sugiyama) Date: Tue, 11 Sep 2007 22:57:44 +0900 Subject: Connectionists: CFP: 1st Workshop on Cognitive Information Processing Message-ID: <83486b630709110657j2a399a90gf0ab584b05e244c7@mail.gmail.com> CALL for PAPERS 1st Workshop on *Cognitive Information Processing* June 9-10, 2008, Santorini, Greece http://cip2008.di.uoa.gr Sponsored by the International Association for Pattern Recogntion (IAPR) In co-operation with the IEEE Signal Processing Society and the European Association for Signal Processing (EURASIP) General Co-Chairs: Prof. Simon Haykin Prof. Sergios Theodoridis Program Co-Chairs: Prof. Tulay Adali Prof. Eleftherios Kofidis Plenary Speakers: Prof. Simon Haykin (McMaster University, Canada) Prof. Timo Honkela (Helsinki University of Technology, Finland) Prof. Jose Principe (University of Florida, U.S.A.) Prof. Ali Sayed (University of California LA, U.S.A) Prof. Bernhard Scholkopf (Max Planck Institute, Germany) Prof. Naftali Tishby (The Hebrew University, Israel) Important Dates: Submission of full paper: January 5, 2008 Notification of acceptance: March 5, 2008 Camera-ready paper: March 31, 2008 ----------------------- Overview ----------------------- Over the recent years there is an increased need for *Cognitive Information Processing *(CIP) that extends the current systems engineering paradigm to one with the ability to perceive, learn, reason and interact robustly in open-ended changing environments. Real world problems and large digital environments (such as Internet) usually are too complex to be modelled within a limited set of predifined specifications. Thus, there will inevitably be a need for robust decisions and behaviour in novel situations based on the capability and knowledge of artificial cognitive systems. Further, there will be a need for automatic extraction and organization of meaning, purpose and intentions in interplay with the environment, beyond current systems, with built-in semantic representations and ontologies. Research in CIP is widely interdisciplinary. The aim of this series of workshops is to bring together researchers from the Machine Learning, Pattern Recognition, Signal Processing and Communications communities, in an effort to encourage cross-fertilization of ideas and tools. ------------------------ Topics of Interest ------------------------ * Learning theory and modelling * Bayesian learning and models * Information theoretic learning * Graphical and kernel methods * Adaptive learning algorithms * Ensembles: committees, mixtures, boosting, etc. * Data representation and analysis, PCA, ICA, CCA, etc. * Other related topics * Cognitive radio * Cognitive component analysis * Cogntive dynamical systems * Distributed, cooperative and adaptive processing * Other related topics -- ---------------------------------- Masashi Sugiyama (Ph.D) Associate Professor, Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, 2-12-1-W8-74 O-okayama, Meguro-ku, Tokyo 152-8552, Japan. E-Mail: sugi at cs.titech.ac.jp URL: http://sugiyama-www.cs.titech.ac.jp/~sugi/ TEL & Fax: +81-3-5734-2699 From g.h.bakir at gmail.com Wed Sep 12 11:28:24 2007 From: g.h.bakir at gmail.com (=?ISO-8859-1?Q?G=F6khan_Hasan_BakIr?=) Date: Wed, 12 Sep 2007 17:28:24 +0200 Subject: Connectionists: Book announcement: Predicting Structured Data Message-ID: <39b2ea990709120828v1b6eaaffgf399b21b58d96ce5@mail.gmail.com> Dear colleagues, hereby I would like to announce a new book on Predicting Structured Data, MIT Press, 2007. This book summarizes developments in a new domain of machine learning, in which the prediction must satisfy the additional constraints found in structured data and poses one of machine learning greatest challenges: learning functional dependencies between arbitrary input and output domains. This volume presents and analyzes the state of the art in machine learning algorithms and theory in this novel field. The contributors discuss applications as diverse as machine translation, document markup, computational biology, and information extraction, among others, providing a timely overview of an exciting field. The book contains three introductory chapters in the beginning and is accompanied by selected chapters summarizing the current state of the art. Table of contents: I Introduction 1 Measuring Similarity with Kernels 2 Discriminative Models 3 Modeling Structure via Graphical Models II Structured Prediction Based on Discriminative Models 4 Joint Kernel Maps 5 Support Vector Machine Learning for Interdependent and Structured Output Spaces 6 Efficient Algorithms for Max-Margin Structured Classification 7 Discriminative Learning of Prediction Suffix Trees with the Perceptron Algorithm 8 A General Regression Framework for Learning String-to-String Mappings 9 Learning as Search Optimization 10 Energy-Based Models 11 Generalization Bounds and Consistency for Structured Labeling III Structured Prediction Using Probabilistic Models 12 Kernel Conditional Graphical Models 13 Density Estimation of Structured Outputs in Reproducing Kernel Hilbert Spaces 14 Gaussian Process Belief Propagation For more information, please visit http://mitpress.mit.edu/0262026171/ Apologies if you get this mail more than once. Best regards, Goekhan Bakir Google Switzerland GmbH From vcu at cs.stir.ac.uk Wed Sep 12 11:39:34 2007 From: vcu at cs.stir.ac.uk (Vassilis Cutsuridis) Date: Wed, 12 Sep 2007 16:39:34 +0100 Subject: Connectionists: Parkinson's disease, dopamine, reciprocal inhibition, spinal cord, rigidity, neural model Message-ID: <00b701c7f553$1eab1e10$6ffd998b@cs.ad.stir.ac.uk> Dear connectionists, The following article is now available at: http://www.cs.stir.ac.uk/~vcu/papers/IJNS2007.pdf Cutsuridis, V. (2007) Does Abnormal Spinal Reciprocal Inhibition Lead to Co-contraction of Antagonist Motor Units? A Modeling Study International Journal of Neural Systems, 17(4): 319-327 ABSTRACT It is suggested that co-contraction of antagonist motor units perhaps due to abnormal disynaptic Ia reciprocal inhibition is responsible for Parkinsonian rigidity. A neural model of Parkinson's disease bradykinesia is extended to incorporate the effects of spindle feedback on key cortical cells and examine the effects of dopamine depletion on spinal activities. Simulation results show that although reciprocal inhibition is reduced in DA depleted case, it doesn't lead to co-contraction of antagonist motor neurons. Implications to Parkinsonian rigidity are discussed. KEYWORDS: Parkinson's disease, dopamine, reciprocal inhibition, spinal cord, rigidity, neural model -- 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 aolifer at emory.edu Wed Sep 12 14:54:46 2007 From: aolifer at emory.edu (Andrey Olypher) Date: Wed, 12 Sep 2007 14:54:46 -0400 Subject: Connectionists: A new paper on activity constraints and neuronal variability Message-ID: <46E835F6.4000300@emory.edu> The following article is now available at http://calabreselx.biology.emory.edu/andrey/pub/olypher_calabrese_07_jnphys_epub.pdf (4.7M) Using constraints on neuronal activity to reveal compensatory changes in neuronal parameters. Andrey V. Olypher and Ronald L. Calabrese J Neurophysiol, 2007 (in press). ABSTRACT: In this study, we developed a general description of parameter^ combinations for which specified characteristics of neuronal^ or network activity are constant. Our approach is based on^ the implicit function theorem and is applicable to activity^ characteristics which smoothly depend on parameters. Such smoothness^ is often intrinsic to neuronal systems when they are in stable^ functional states. The conclusions about how parameters compensate^ each other, developed in this study, can thus be used even without^ regard to the specific mathematical model describing a particular^ neuron or neuronal network. We showed that near a generic point^ in the parameter space there are infinitely many other points,^ or parameter combinations, for which specified characteristics^ of activity are the same as in the original point. These parameter^ combinations form a smooth manifold. This manifold can be extended^ as long as the gradients of characteristics are defined and^ independent. All possible variations of parameters compensating^ each other are simply all possible charts of the same manifold.^ The number of compensating parameters (but not parameters themselves)^ is fixed and equal to the number of the independent characteristics^ maintained. The algorithm that we developed shows how to find^ compensatory functional dependencies between parameters numerically.^ Our method can be used in the analysis of the homeostatic regulation,^ neuronal database search, model tuning and other applications. -- Andrei Olifer (Andrey Olypher) Biology Department Emory University 1510 Clifton Rd Atlanta, GA 30322 aolifer at emory.edu tel: 404-727-4202 fax: 404-727-2880 From djin at phys.psu.edu Thu Sep 13 15:12:35 2007 From: djin at phys.psu.edu (Dezhe Jin) Date: Thu, 13 Sep 2007 15:12:35 -0400 Subject: Connectionists: A new paper on self-organizion of synfire chain Message-ID: <12F037EC-D7AA-4ED3-8F47-C2CB7BBFA449@phys.psu.edu> Dear Colleagues, I would like to announce publication of a new paper on self-organized growth of synfire chains. The abstract and link to the paper is as follows: Title: Development of neural circuitry for precise temporal sequences through spontaneous activity, axon remodeling, and synaptic plasticity. Joseph K. Jun and Dezhe Z. Jin Abstract: Temporally precise sequences of neuronal spikes that span hundreds of milliseconds are observed in many brain areas, including songbird premotor nucleus, cat visual cortex, and primary motor cortex. Synfire chains-networks in which groups of neurons are connected via excitatory synapses into a unidirectional chain-are thought to underlie the generation of such sequences. It is unknown, however, how synfire chains can form in local neural circuits, especially for long chains. Here, we show through computer simulation that long synfire chains can develop through spike-time dependent synaptic plasticity and axon remodeling-the pruning of prolific weak connections that follows the emergence of a finite number of strong connections. The formation process begins with a random network. A subset of neurons, called training neurons, intermittently receive superthreshold external input. Gradually, a synfire chain emerges through a recruiting process, in which neurons within the network connect to the tail of the chain started by the training neurons. The model is robust to varying parameters, as well as natural events like neuronal turnover and massive lesions. Our model suggests that long synfire chain can form during the development through self- organization, and axon remodeling, ubiquitous in developing neural circuits, is essential in the process. Available in an open access journal PLoS ONE: http://www.plosone.org/article/fetchArticle.action? articleURI=info:doi/10.1371/journal.pone.0000723 Also at http://phys.psu.edu/~djin/publications.html Best, -Dezhe Jin ---- Dezhe Z. Jin Assistant Professor of Physics Department of Physics The Pennsylvania State University University Park, PA 16802 814-863-6673 (tel), 814-865-3604 (fax) Web: http://phys.psu.edu/~djin/ From stiber at u.washington.edu Fri Sep 14 18:07:14 2007 From: stiber at u.washington.edu (Michael Stiber) Date: Fri, 14 Sep 2007 15:07:14 -0700 Subject: Connectionists: Reminder: Student/Postdoc Travel Support to Neural Coding 2007, Montevideo, Uruguay Message-ID: A gentle reminder that the deadline for applications is fast approaching. Though we have listed the deadline as today, we will NOT reject applications that arrive over this weekend. ---------------------------- Neural Coding 2007 -- Student/Postdoc Travel Support Funding is available for US postdoctoral and predoctoral (graduate and undergraduate) researchers to attend the 2007 Neural Coding meeting and its associated Joint US/Uruguay Workshop on Neural Dynamics, to be held in Montevideo, Uruguay on November 4-12, 2007. Support in the amount of $2000, to be used toward registration fees, hotel expenses, and other travel costs, will include post-meeting travel to research laboratories in the southern cone region of South America; contacts to research laboratories will be provided (participants will be responsible for arranging the specifics of their own travel). This will be an excellent opportunity to establish contacts with international experts and a small but very valuable and growing community of Uruguayan and Latin American scientists. The Neural Coding symposia bring together scientists from different fields with the conviction that multidisciplinary approaches are essential for better understanding neural coding mechanisms as well as their disturbances in clinical cases. Hence, the attendees of the Neural Coding Workshop should be prepared to cross the borders of their own disciplines. Intense discussions of experimental, modeling, and analytical approaches are expected. Major emphasis will be placed on biologically inspired formal and computer models which could elucidate the functionally relevant dynamics of the neural coding mechanisms, including their possible roles in causing and treating neurological and related diseases. For more information on the meeting, please see the meeting web site at . The deadline for applications is September 14. In your application, please include: 1. For postdoctoral researchers and graduate students, an abstract prepared in accordance with the instructions at the Neural Coding web site. Alternatively, you may indicate that you are a co-author of an already submitted paper (please indicate the title and author list of the paper as well). You will be expected to present your research during the Joint Workshop. 2. A personal statement describing your research interests and plans and how this experience will factor into them. Your personal statement should also indicate: your commitment to attend both the Joint Workshop and the main Neural Coding meeting, a plan for your stay in the southern cone area of South America beyond these (see the Neural Coding web site for a list of contacts), and your agreement to submit afterwards a brief summary of your experiences at the Joint Workshop and during your travels in the region, including prospective new collaborations. 3. A curriculum vitae. 4. The name and contact information (including email) for a faculty member or other scientific reference who will be sending a (separate) letter of reference for you. Please arrange for this letter to be sent directly to us. All application materials should be sent via email to . Awardees will be notified of the grant within two weeks after the deadline date. Support is provided by the US National Science Foundation under grant number OISE-0652336. From jose.millan at jrc.it Mon Sep 17 07:58:22 2007 From: jose.millan at jrc.it (Jose del R. Millan) Date: Mon, 17 Sep 2007 13:58:22 +0200 Subject: Connectionists: Call for Participation: BCI Meets Robotics Message-ID: <46D44A4A00000A57@cheetah-1.jrc.it> ++++++++++++++++++++++++++ BCI Meets Robotics: Challenging Issues in Brain-Computer Interaction and Shared Control http://www.maia-project.org/workshop-2007.php November, 19-20, 2007 KU Leuven, Belgium Last years have witnessed advances in Brain-Computer Interfaces (BCI), but how far is this new field from controlling robotics devices? The goal of the workshop is to introduce recent advances in brain-computer interfaces on the one hand, and on shared control and task recognition on the other. This workshop will give a new perspective on how humans and robots cooperate to fulfill a challenging task. The concept of adaptive shared autonomy will be introduced and its relevance for BCI applications will be illustrated. The presentations will consist of a series of invited talks and poster presentations. Also, the European MAIA project will report their achievements in non-invasive brain-controlled wheelchairs. Posters will be selected depending on relevance to the workshop topic, quality, and novelty. Abstract Submission --------------------------- Please send a one-page abstract (including figures and references, no less than 200 words) to workshop at maia-project.org Posters will be selected depending on relevance to the workshop topic, quality, and novelty. Important Dates ---------------------- Deadline for abstract submission: September 21, 2007 Notification of acceptance: October 5, 2007 Deadline for early registration: October 26, 2007 Conference dates: November 19-20, 2007 Organizing Committee ------------------------------ Prof. Jos? del R. Mill?n, IDIAP Research Institute, Martigny, Switzerland (co-chair) Prof. Marnix Nuttin, Katholieke Universiteit Leuven, Belgium (co-chair) Prof. Maria Grazia Marciani, IRCCS Fondazione Santa Lucia, Rome, Italy Dr. Sara Gonzalez Andino, Geneva University Hospital, Switzerland Prof. Fabio Babiloni, University of Rome "La Sapienza", Italy Ac.Prof. Kimmo kaski, Helsinki University of Technology, Finland Registration ---------------- The registration fee is: - 60 EUR for early registration (October 26, 2007) - 120 EUR from October 27th to November 11th - 180 EUR onsite registration Registration includes coffee breaks and workshop material. Sponsors ---------------- The workshop is organized by the EU's 6th Framework Programme MAIA project (http://www.maia-project.org). ++++++++++++++++++++++++++ -- Prof. Dr. Jos? del R. Mill?n IDIAP Research Institute Swiss Federal Institute of Technology Lausanne (EPFL) IDIAP. Rue du Simplon 4. 1920 Martigny. Switzerland Tel: +41-27-7217.770 Fax: +41-27-7217.712 jose.millan at idiap.ch From D.Hardoon at cs.ucl.ac.uk Mon Sep 17 12:17:02 2007 From: D.Hardoon at cs.ucl.ac.uk (David R. Hardoon) Date: Mon, 17 Sep 2007 18:17:02 +0200 Subject: Connectionists: NIPS 07 Workshop announcement In-Reply-To: <1E9B58AA-F593-4BB1-879E-957B83D8D10C@cs.ucl.ac.uk> References: <1E9B58AA-F593-4BB1-879E-957B83D8D10C@cs.ucl.ac.uk> Message-ID: Apologies for cross posting and please forward to whom ever this may be of interest to. NIPS'07 Workshop - Whistler, BC, December 7-8, 2007 Music, Brain & Cognition Day 1: "Learning the Structure of Music and its Effects on the Brain" Day 2: "Models of Sound and Music Cognition" ====================================================== http://homepage.mac.com/davidrh/MBCworkshop07/ Call for contributions ------------ We call for paper contribution of up to 8 pages to the workshop using NIPS style. The accepted papers will be available for downloading from this site. Selected papers will be considered for publication in a special issue of ?Journal of New Music Research?. Day 1 - Machine learning based models for learning the structure of music - Models for predicting style of performers - Analysis and models of fMRI/EEG/MEG scans from musical stimuli (as opposed tosimplistic auditory stimuli) - Predicting music generated patterns in fMRI/EEG/MEG - Strategies for embedding representations of musical experience into generative music / performance systems - Methods for generative musical performance and composition - Generative music and/or performance systems based on models of brain functioning - Similar and further models for learning and analysing the structure of music Day 2 - Computational models of cognitively inspired sound processing - Top down control of musical processing of pitch, onset, timbre - Models of musical memory, saliency, attention - Models of music development and learning - Computer aided sound design - Models as above, applied to other domains (e.g. speech and vision) with potential application in music Accepted papers will be either presented as a talk or poster (with poster spotlight) Papers should be submitted to the organisers D.Hardoon at cs.ucl.ac.uk, hpurwins at iua.upf.edu and please indicate if you wish to present on day 1 or day 2 and whether you only wish to present a poster. Important Dates ------------ Deadline for submissions: October 10, 2007 Notification of acceptance: October 31, 2007 Workshop taking place: December 7-8, 2007 Description ------------ Music is one of the most widespread of human cultural activities, existing in some form in all cultures throughout the world. The definition of music as organised sound is widely accepted today but a na?ve interpretation of this definition may suggest the notion that music exists widely in the animal kingdom, from the rasping of crickets' legs to the songs of the nightingale. However, only in the case of humans does music appear to be surplus to any obvious biological purpose, while at the same time being a strongly learned phenomenon and involving significant higher order cognitive processing rather than eliciting simple hardwired responses. A two day workshop will take place at NIPS 07 (Vancouver, Canada) and will span topics from signal processing and musical structure to the cognition of music and sound. In the first day the workshop will provide a forum for cutting edge research addressing the fundamental challenges of modeling the structure of music and analysing its effect on the brain. It will also provide a venue for interaction between the machine learning and the neuroscience/brain imaging communities to discuss the broader questions related to modeling the dynamics of brain activity. During the second day the workshop will focus on the modeling of sound, music perception and cognition. These have provide, with the crucial role of machine learning, a break-through in various areas of music technology, in particular: Music Information Retrieval (MIR), expressive music synthesis, interactive music making, and sound design. Understanding of music cognition in its implied top-down processes can help to decide which of the many descriptors in MIR are crucial for the musical experience and which are irrelevant. The organisers of the workshop are investigators for three main European projects; Learning the Structure of Music (Le StruM), Closing the loop of Evaluation and Design (CLOSED), Emergent Cognition through Active Perception (EmCAP) Mention. The target group is of researchers within the fields of (Music) Cognition, Music Technology, Machine Learning, Psychology, Sound Design, Signal Processing and Brain Imaging. For more details, please go to http://homepage.mac.com/davidrh/ MBCworkshop07/ Day 1 - http://homepage.mac.com/davidrh/MBCworkshop07/Day_1.html Day 2 - http://homepage.mac.com/davidrh/MBCworkshop07/Day_2.html Organisers ------------ Day 1 * David R. Hardoon (University College London) * Eduardo Reck-Miranda (University of Plymouth) * John Shawe-Taylor (University College London) Day 2 * Hendrik Purwins (Universitat Pompeu Fabra) * Xavier Serra (Universitat Pompeu Fabra) * Klaus Obermayer (Berlin University of Technology) ---------------------------------------------------------------------- "Who dares... wins" Dr. David R. Hardoon The Centre for Computational Statistics & Machine Learning Intelligent Systems Research Group Dept. of Computer Science University College, London Gower Street London, UK WC1E 6BT Tel: +44 (0) 20 7679 0425 Fax: +44 (0) 20 7387 1397 Email: D.Hardoon at cs.ucl.ac.uk www: http://homepage.mac.com/davidrh/ From thomas.j.palmeri at vanderbilt.edu Mon Sep 17 21:42:00 2007 From: thomas.j.palmeri at vanderbilt.edu (Thomas Palmeri) Date: Mon, 17 Sep 2007 20:42:00 -0500 Subject: Connectionists: Vanderbilt University: Tenure-Track Faculty Position in Cognition and Cognitive Neuroscience Message-ID: <000701c7f995$1ce0b400$0501000a@PalmeriT60p> Vanderbilt University: The Department of Psychology, College of Arts and Sciences, invites applications for a tenure-track assistant professor faculty position in the area of cognitive psychology or cognitive neuroscience. We seek candidates who study higher-level cognitive processes such as memory, concept formation, cognitive control, reasoning, and decision making in a manner that complements the existing strengths in our program. Special consideration will be given to applicants with demonstrated expertise in cognitive modeling or computational cognitive neuroscience. We particularly welcome applications from women and minority scholars. The Department of Psychology partners with the Department of Psychology and Human Development, Peabody College, to offer a graduate program in Psychological Sciences with five programmatic areas: Clinical Science, Cognition and Cognitive Neuroscience, Developmental Science, Neuroscience, and Quantitative Methods and Evaluation. We have excellent collaborative relations with a number of other allied departments and institutes, including the Learning Sciences Institute, the Vanderbilt Brain Institute, the Vanderbilt Institute of Imaging Sciences, the Vanderbilt Vision Research Center, the Center for Integrative and Cognitive Neuroscience, the Advanced Computing Center for Research and Education, the John F. Kennedy Center for Research on Human Development, and several departments affiliated with the Vanderbilt Medical Center. Applicants should send vitae, copies of relevant publications, a letter describing research and teaching interests, and at least three letters of reference to: Thomas Palmeri, Ph.D. Chair, Cognitive Search Committee Department of Psychology 301 Wilson Hall 111 21st Avenue South Vanderbilt University Nashville, TN 37203 Informal inquiries may be sent via email to thomas.j.palmeri at vanderbilt.edu. Review of applications will begin immediately. To receive full consideration, applications should arrive by December 15, 2007. Vanderbilt University is an affirmative action/equal opportunity employer. From nips2007publicity at msn.com Tue Sep 18 17:05:42 2007 From: nips2007publicity at msn.com (NIPS 2007 Publicity) Date: Tue, 18 Sep 2007 14:05:42 -0700 Subject: Connectionists: [NIPS2007] REMINDER: Call for Demos Message-ID: REMINDER: CALL FOR DEMONSTRATIONS - NIPS 2007 Neural Information Processing Systems -- Natural and Synthetic NIPS 2006 Conference -- December 3 - 6, 2007 Hyatt Regency Vancouver, BC, CANADA www.nips.cc Demonstration Proposal Deadline: September 21, 2007 Would you like to interactively demonstrate your novel hardware, software, or wetware technology, your robot, or your chip to people at the NIPS 2007 Conference? The Neural Information Processing Systems Conference has a Demonstration Track that will run in parallel with the popular evening Poster Sessions. Demonstrators will have a chance to show their live interactive demos in the areas of hardware technology, neuromorphic and biologically-inspired systems, robotics, and software systems. The only hard rules are that the demo must show novel technology and must be LIVE and INTERACTIVE! (It is not a back-door Poster Session.) The full call for demonstrations is at the following URL: http://nips.cc/Conferences/2007/Calls/CallForDemos Giacomo Indiveri and Xubo Song From pavel.laskov at first.fraunhofer.de Wed Sep 19 04:45:16 2007 From: pavel.laskov at first.fraunhofer.de (Pavel Laskov) Date: Wed, 19 Sep 2007 10:45:16 +0200 Subject: Connectionists: NIPS 2007 WORKSHOP: Machine Learning in Adversarial Environments for Computer Security Message-ID: <46F0E19C.4080207@first.fraunhofer.de> *** Apologies for multiple posting *** ========================= CALL FOR ABSTRACTS ========================= NIPS 2007 Workshop on Machine Learning in Adversarial Environments for Computer Security 7 or 8 December, 2007 Whistler, British Columbia, Canada Supported by the PASCAL network of excellence ---------------------------------------------------------------------- Organizers: Pavel Laskov (Fraunhofer Institute FIRST, Germany) Richard Lippmann (MIT Lincoln Laboratory, USA) Deadlines: Extended abstract submission: October 19, 2007 Notification of acceptance: November 2, 2007 Contact: Email: mls-nips07 at first.fraunhofer.de Web page: mls-nips07.first.fraunhofer.de Computer and network security has become an important research area due to the alarming recent increase in hacker activity motivated by profit and both ideological and national conflicts. Increases in spam, botnets, viruses, malware, key loggers, software vulnerabilities, zero-day exploits and other threats contribute to growing concerns about security. In the past few years, many researchers have begun to apply machine learning techniques to these and other security problems. Security, however, is a difficult area because adversaries actively manipulate training data and vary attack techniques to defeat new systems. A main purpose of this workshop is examine adversarial machine learning problems across different security applications to see if there are common problems, effective solutions, and theoretical results to guide future research, and to determine if machine learning can indeed work well in adversarial environments. Another purpose is to initiate a dialog between computer security and machine learning researchers already working on various security applications, and to draw wider attention to computer security problems in the NIPS community. The workshop will consist of invited and contributed presentations as well as panel discussions. Contributions are sought where researchers are applying machine learning to various areas of computer security including but not limited to the following: * Anomaly detection * Automatic signature generation * Intrusion detection * Learning adversary behavior * Spam detection * Performance evaluation of adaptive systems * Software vulnerability discovery * Learning with malicious noise * Adversary modeling * Hiding and detecting virtual machines * Adapting to adversarial behavior * Rootkit detection Submissions should be no longer than two pages and include author contact information and appropriate references to other work. Submissions can contain original contributions as well as summarize prior and recent work. Submissions should be aimed at initiating fruitful discussion of critical issues related to machine learning and computer security, for example by raising controversial issues, sharing open problems, and comparing competing approaches. A limited number of presentations will be given 12 minute oral presentation slots, the remaining accepted submissions will be presented as posters with a 3 minute spotlight. Authors of selected oral presentations are encouraged to present further details as a poster. Substantial time will be reserved for questions and discussion. -- +------------------------------------------------------+ Pavel Laskov, Ph.D. Fraunhofer Institute FIRST IDA Kekulestr. 7, 12489 Berlin tel: +49 30 6392 1870 fax: +49 30 6392 1805 email: pavel.laskov at first.fraunhofer.de University of Tuebingen WSI-RI Sand 13, 72076 Tuebingen tel: +49 7071 29 70574 email: laskov at ri.uni-tuebingen.de http://ida.first.fhg.de/~laskov/ +------------------------------------------------------+ From hitzler at aifb.uni-karlsruhe.de Wed Sep 19 07:09:14 2007 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Wed, 19 Sep 2007 13:09:14 +0200 Subject: Connectionists: Book announcement: Perspectives of Neural-Symbolic Integration In-Reply-To: <39b2ea990709120828v1b6eaaffgf399b21b58d96ce5@mail.gmail.com> References: <39b2ea990709120828v1b6eaaffgf399b21b58d96ce5@mail.gmail.com> Message-ID: <46F1035A.8030505@aifb.uni-karlsruhe.de> Dear colleagues, I would like to announce a new book on Perspectives of Neural-Symbolic Integration Springer 2007 Barbara Hammer and Pascal Hitzler (eds.) Cover text: ----------- The human brain possesses the remarkable capability of understanding, interpreting, and producing language, structures, and logic. Unlike their biological counterparts, artificial neural networks do not form such a close liason with symbolic reasoning: logic-based inference mechanisms and statistical machine learning constitute two major and very different paradigms in artificial intelligence with complementary strengths and weaknesses. Modern application scenarios in robotics, bioinformatics, language processing, etc., however require both the efficiency and noise-tolerance of statistical models and the generalization ability and high-level modelling of structural inference meachanisms. A variety of approaches has therefore been proposed for combining the two paradigms. This carefully edited volume contains state-of-the-art contributions in neural-symbolic integration, covering `loose' coupling by means of structure kernels or recursive models as well as `strong' coupling of logic and neural networks. It brings together a representative selection of results presented by some of the top researchers in the field, covering theoretical foundations, algorithmic design, and state-of-the-art applications in robotics and bioinformatics. Table of Contents: ------------------ PART I STRUCTURED DATA AND NEURAL NETWORKS 1 Kernels for Strings and Graphs Craig Saunders, Anthony Demco 2 Comparing Sequence Classification Algorithms for Protein Subcellular Localization Fabrizio Costa, Sauro Menchetti, Paolo Frasconi 3 Mining Structure-Activity Relations in Biological Neural Networks using NeuronRank Tayfun G?rel, Luc De Raedt, Stefan Rotter 4 Adaptive Contextual Processing of Structured Data by Recursive Neural Networks: A Survey of Computational Properties Barbara Hammer, Alessio Micheli, Alessandro Sperduti 5 Markovian Bias of Neural-based Architectures With Feedback Connections Peter Tino, Barbara Hammer, Mikael Boden 6 Time Series Prediction with the Self-Organizing Map: A Review Guilherme A. Barreto 7 A Dual Interaction Perspective for Robot Cognition: Grasping as a ?Rosetta Stone? Helge Ritter, Robert Haschke, Jochen J. Steil PART II LOGIC AND NEURAL NETWORKS 8 SHRUTI: A Neurally Motivated Architecture for Rapid, Scalable Inference Lokendra Shastri 9 The Core Method: Connectionist Model Generation for First-Order Logic Programs Sebastian Bader, Pascal Hitzler, Steffen H?ldobler and Andreas Witzel 10 Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory Helmar Gust, Kai-Uwe K?uhnberger, Peter Geibel 11 Advances in Neural-Symbolic Learning Systems: Modal and Temporal Reasoning Artur S. d?Avila Garcez 12 Connectionist Representation of Multi-Valued Logic Programs Ekaterina Komendantskaya, Maire Lane and Anthony Karel Seda Best Regards, Pascal Hitzler. -- PD Dr. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de fax: +49 721 608 6580 web: http://www.pascal-hitzler.de phone: +49 721 608 4751 http://logic.aifb.uni-karlsruhe.de http://www.neural-symbolic.org From esann at dice.ucl.ac.be Fri Sep 21 03:33:05 2007 From: esann at dice.ucl.ac.be (esann) Date: Fri, 21 Sep 2007 09:33:05 +0200 Subject: Connectionists: ESANN'2008 call for papers Message-ID: <002201c7fc21$a68bd250$43ed6882@maxwell.local> ESANN'2008 16th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 23-24-25, 2008 Announcement and call for papers =============================================== The call for papers for the ESANN'2008 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We make all possible efforts to avoid sending multiple copies of this call for papers; however we apologize if you receive this e-mail twice, despite our precautions. ***** Deadline for submission of papers: November 23, 2007 ***** You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2008 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). The conference is technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society, the IEEE Region 8, the IEEE Benelux Section (sponsors to be confirmed). Scope and topics ---------------- Since its first happening in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks, computational intelligence, learning and related topics. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2008 conference will follow this tradition, while adapting its scope to the new developments in the field. Artificial neural networks are viewed as a branch, or subdomain, of machine learning, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered. The following is a non-exhaustive list of machine learning, computational intelligence and artificial neural networks topics covered during the ESANN conferences: THEORY and MODELS Statistical and mathematical aspects of learning Feedforward models Kernel machines Graphical models, EM and Bayesian learning Vector quantization and self-organizing maps Recurrent networks and dynamical systems Blind signal processing Ensemble learning Nonlinear projection and data visualization Fuzzy neural networks Evolutionary computation Bio-inspired systems INFORMATION PROCESSING and APPLICATIONS Data mining Signal processing and modeling Approximation and identification Classification and clustering Feature extraction and dimension reduction Time series forecasting Multimodal interfaces and multichannel processing Adaptive control Vision and sensory systems Biometry Bioinformatics Brain-computer interfaces Neuroinformatics Papers will be presented orally (single track) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. It is important to mention that the topics of a paper decide if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors must indicate their preference for oral or poster presentation when submitting their paper. Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as submissions to regular sessions. They must also follow the same format, instructions, deadlines and submission procedure. The special sessions organized during ESANN'2008 are: 1) Computational Intelligence in Computer Games Colin Fyfe (University of Paisley, United Kingdom) 2) Methodology and standards for data analysis with machine learning tools Damien Fran?ois (Universit? catholique de Louvain, Belgium) 3) Neural Networks for Computational Neuroscience David Meunier, H?l?ne Paugam-Moisy (LIRIS-CNRS, France) 4) Machine learning methods in cancer research Alfredo Vellido (Pol. Univ. Catalonia, Spain), Paulo J.G.Lisboa (Liverpool John Moores University, United Kingdom) 5) Machine Learning Approches and Pattern Recognition for Spectral Data Thomas Villmann (Univ. Leipzig, Germany), Erzs?bet Mer?nyi (Rice University, USA), Udo Seiffert (IPK Gatersleben, Germany) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organized in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all levels of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Proceedings and journal special issue ------------------------------------- The proceedings will include all communications presented to the conference (tutorials, oral and posters), and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). Call for contributions ---------------------- Prospective authors are invited to submit their contributions before November 23, 2007. The electronic submission procedure is described on the ESANN portal http://www.dice.ucl.ac.be/esann/. Authors must also commit themselves that they will register to the conference and present the paper in case of acceptation of their submission (one paper per registrant). Authors of accepted papers will have to register before February 28, 2008; they will benefit from the advance registration fee. The ESANN conference applies a strict policy about the presentation of accepted papers during the conference: authors of accepted papers who do not show up at the conference will be blacklisted for future ESANN conferences, and the lists will be communicated to other conference organizers. Deadlines --------- Submission of papers 23 November 2007 Notification of acceptance 18 January 2008 ESANN conference 23 - 25 April 2008 Conference secretariat ---------------------- ESANN'2008 d-side conference services phone: + 32 2 730 06 11 24 av. L. Mommaerts Fax: + 32 2 730 06 00 B - 1140 Evere (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee ---------------------------- Fran?ois Blayo Ipseite (CH) Gianluca Bontempi Univ. Libre Bruxelles (B) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Mia Loccufier Univ. Gent (B) Bernard Manderick Vrije Univ. Brussel (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Cecilio Angulo Univ. Polit. de Catalunya (E) Miguel Atencia Univ. Malaga (E) Martin Bogdan Univ. T?bingen (D) Herv? Bourlard IDIAP Martigny (CH) Antonio Braga Federal University of Minas Gerais (Brazil) Joan Cabestany Univ. Polit. de Catalunya (E) Colin Campbell Bristol University (UK) St?phane Canu Inst. Nat. Sciences App. (F) Valentina Colla Scuola Sup. Sant'Anna Pisa (I) Nigel Crook Oxford Brookes University (UK) Holk Cruse Universit?t Bielefeld (D) Eric de Bodt Univ. Lille II (F) & UCL Louvain-la-Neuve (B) Dante Del Corso Politecnico di Torino (I) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton NXP Semiconductors (USA) Richard Duro Univ. Coruna (E) Andr? Elisseef IBM Research (CH) Deniz Erdogmus Oregon Health & Science University (USA) Anibal Figueiras-Vidal Univ. Carlos III Madrid (E) Jean-Claude Fort Universit? Paul Sabatier Toulouse (F) Leonardo Franco Univ. Malaga (E) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Mirta Gordon IMAG Grenoble (F) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Gu?rin-Dugu? IMAG Grenoble (F) Barbara Hammer Clausthal Univ. of Technology (D) Martin Hasler EPFL Lausanne (CH) Verena Heidrich-Meisner Ruhr-Univ. Bochum (D) Tom Heskes Univ. Nijmegen (NL) Katerina Hlavackova-Schindler Austrian Acad. of Sciences (A) Christian Igel Ruhr-Univ. Bochum (D) Jose Jerez Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinki Univ. of Technology (FIN) Samuel Kaski Helsinki Univ. Tech. (FIN) Stefanos Kollias National Tech. Univ. Athens (GR) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Beatrice Lazzerini Univ. Pisa (I) Erzsebet Merenyi Rice Univ. (USA) Anke Meyer-B?se Florida State university (USA) Jean-Pierre Nadal Ecole Normale Sup?rieure Paris (F) Erkki Oja Helsinki Univ. of Technology (FIN) Tjeerd olde Scheper Oxford Brookes University (UK) Arlindo Oliveira INESC-ID (P) Gilles Pag?s Univ. Paris 6 (F) Thomas Parisini Univ. Trieste (I) H?l?ne Paugam-Moisy Universit? Lumi?re Lyon 2 (F) Kristiaan Pelckmans K. U. Leuven (B) Alberto Prieto Universitad de Granada (E) Didier Puzenat Univ. Antilles-Guyane (F) Leonardo Reyneri Politecnico di Torino (I) Jean-Pierre Rospars INRA Versailles (F) Fabrice Rossi INRIA (F) Francisco Sandoval Univ.Malaga (E) Jose Santos Reyes Univ. Coruna (E) Craig Saunders Univ.Southampton (UK) Benjamin Schrauwen Univ. Gent (B) Udo Seiffert IPK Gatersleben (D) Bernard Sendhoff Honda Research Institute Europe (D) Alessandro Sperduti Universit? degli Studi di Padova (I) Jochen Steil Univ. Bielefeld (D) John Stonham Brunel University (UK) Johan Suykens K. U. Leuven (B) John Taylor King?s College London (UK) Peter Tino University of Birmingham (UK) Claude Touzet Univ. Provence (F) Marc Van Hulle KUL Leuven (B) Pablo Verdes Novartis Phrama (CH) David Verstraeten Univ. Gent (B) Thomas Villmann Univ. Leipzig (D) Heiko Wersing Honda Research Institute Europe (D) Axel Wism?ller Ludwig-Maximilians-Univ. M?nchen (D) Bart Wyns Ghent University (B) Michalis Zervakis Technical Univ. Crete (GR) ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From tijl.debie at gmail.com Fri Sep 14 04:30:18 2007 From: tijl.debie at gmail.com (Tijl De Bie) Date: Fri, 14 Sep 2007 09:30:18 +0100 Subject: Connectionists: Workshop: Math Models of Cognitive Behaviour - call for participation In-Reply-To: <8e1b06640709140118t63f3108fg38fc8ab6f2a8f257@mail.gmail.com> References: <8e1b06640708011401r2f7f3f1dpe2af28933c6dfd54@mail.gmail.com> <8e1b06640709140118t63f3108fg38fc8ab6f2a8f257@mail.gmail.com> Message-ID: <682af5170709140130p7c59b1f1s16618a4d6f3ea69e@mail.gmail.com> Workshop Announcement - Call for Participation Mathematical Models of Cognitive Behaviour Avon Gorge Hotel, Bristol November 9th, 2007 (9am - 5pm) http://patterns.enm.bris.ac.uk/cognitive-systems-workshop Workshop of the Pascal Network of Excellence and the euCognition Network Probabilistic approaches to Artificial Intelligence have become mainstream in the past decade. Statistical methods are routinely used in machine learning, machine translation, machine vision, speech recognition. We are interested in applying this methodology to the more general problem of modeling cognitive systems. The theoretical focus of this workshop is to model cognitive abilities as forms of probabilistic inference. In particular we want to focus on statistical and reactive models of behaviour, in various systems. The idea is to present recent models of natural cognitive systems together with recent advances in modeling of artificial cognitive systems, and discuss of relations. Learning, decision making, perception, and goal-seeking are significant aspects of cognitive behavior that will be covered. Preliminary List of Speakers *Ralf Herbrich * Microsoft Research *Behavior in Videogames * *Dennis Bray*, University of Cambridge *Bacterial Chemotaxis * *Nello Cristianini* University of Bristol *TBA* *James Marshall* , * Nigel Franks* University of Bristol *Collective Decision-Making in Social Insect Colonies * *Nick Chater* University College London General principles of cognition *Chris Watkins* Royal Holloway, University of London Behavioural Learning and Evolution: what can we deduce from first principles about behavioural learning, given that behaviour is evolved? *Richard Gregory* University of Bristol *TBA * *Alan Roberts * University of Bristol *Simple Nervous Systems * *Rafal Bogacz*, University of Bristol *Optimal Decision Making in Biological Systems * *Alan Winfield*, University of West of England, *Robot Behaviour * Panel Discussion: *Tom Troscianko* , *John Shawe-Taylor*, ... (more) REGISTRATION Registration is free, but the number of participants will be limited by space. So you will be required to register in advance, by following instructions in: http://patterns.enm.bris.ac.uk/cognitive-systems-workshop From murphyk2 at gmail.com Sun Sep 16 18:51:28 2007 From: murphyk2 at gmail.com (Kevin Murphy) Date: Sun, 16 Sep 2007 15:51:28 -0700 Subject: Connectionists: software release: Bayesian DAG learning Message-ID: I am pleased to announce the release of "BDAGL" (pronounced "be-daggle"), a Matlab/C package for learning Bayes net structures from fully observed data (discrete or continuous, static or time series). Its main novelty is that implements various algorithms for exact Bayesian inference of posterior features/ modes using dynamic programming. It also supports MCMC (on DAGs and orders) with various proposal distributions. Details are given at the URL below. Feedback is welcome. Kevin Murphy http://www.cs.ubc.ca/~murphyk/Software/BDAGL/index.html Major features - Computes the most probable graph G_map = arg max_G p(G|D) exactly using the dynamic programming (DP) algorithm of Silander & Myllymaki UAI'06, where G is a DAG and D is data. This takes O(d 2^d) time and space, so is limited to about 20 variables. This takes about 5 seconds for d=10 to about 5 minutes for d=20. - Computes exact edge marginals using Bayes model averaging, p(G_{ij}=1|D) = sum_G I(G(i,j)=1) p(G|D), using the DP algorithms of Koivisto & Sood JMLR'04, and Koivisto UAI'06. This takes O(d 2^d) time and space, so is limited to about 20 variables. This takes about 5 seconds for d=10 to about 5 minutes for d=20. - Computes edge marginals p(G_{ij}=1|D) (or other posterior features) approximately using MCMC in the space of DAGs with various proposal distributions. Options include the standard local proposal (add/ delete/ reverse edge), and a global proposal based on DP (see Eaton & Murphy, UAI'07) It also supports MCMC in the space of total orders (see Friedman & Koller, MLJ'03), and Gibbs sampling on the adjacency matrix. In principle, these algorithms avoid the 2^d bottleneck of exact DP, although the current implementation may not scale much beyond d=20.... - Supports various models of intervention (perfect, imperfect, uncertain, soft) for learning causal networks from experimental data; see Eaton & Murphy, AIStats'07 for details. - Supports BDe score for Multinomial models with Dirichlet priors, and BGe score for Gaussian models with Gaussian-Gamma priors. Could be extended to more flexible CPDs/priors using BIC. - Supports DBN learning from (fully observed) time series data. - Supports posterior predictive density modeling for test data, integrating over structures and parameters. (Also supports plug-in approximation.) - Efficiently computes the expected sufficient statistics for discrete CPDs from large data sets using ADtrees (see Moore & Lee, JAIR'98). From tobias at nld.ds.mpg.de Wed Sep 19 09:06:10 2007 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Wed, 19 Sep 2007 15:06:10 +0200 Subject: Connectionists: Two PostDoc or PhD Positions in Robotics and/or Computer Vision Message-ID: <46F11EC2.6060905@nld.ds.mpg.de> Job Offer: Two PostDoc or PhD Positions (Duration 3 years) At the Bernstein Center for Computational Neuroscience (BCCN) at the University of G?ttingen (Germany) there are two Postdoc openings in the fields of Robotics and/or Computer Vision based on neural information processing principles. In our group we are concerned with sensori-motor integration as well as motor-coordination problems towards solving complex robotic tasks like goal directed movement generation, reaching, grasping or bipedal walking. Central focus lies on dynamic robot systems that use adaptive methods (?learning?) solving these tasks employing neural network control. An example of this is RunBot (Manoonpong et al., PLoS CB, July 2007), a fast biped robot, which is able to adapt to novel situations using a multi-layered neural control structure. Its flexibility and dynamic performance has created quite some resonance in the press and on the internet. Information on our group and its research can be found at: http://www.bccn-goettingen.de/Groups/GroupCN. The goal of our future research is to extend these methods solving increasingly complex problems by integrating better sensorial information and by improving control and adaptivity. Our group at the BCCN works together with several groups in Europe (Glasgow, Odense, Barcelona) and Germany (Karlsruhe, Jena) offering the successful applicant interesting cooperation possibilities. G?ttingen itself (http://www.goettingen-tourismus.de/index.php?lang=en&menuid=2&topmenu=2&keepmenu=inactive ) is a beautiful, small, old university town in the center of Germany with a student community of more than 20,000 and a highly supportive research infrastructure especially in the neurosciences (http://www.uni-goettingen.de/de/sh/1.html). Salaries are based on the German TV?D system and start for a Postdoc at about 35,500 Euro before deductions annually. PhD students will be paid according to their experience. Desired starting date before 01/01/2008 (negotiable). Both openings will allow the successful applicant to develop his/her own line of research. Hence applications with an own research plan fitting to the above described scenarios are strongly encouraged. Good programming skills are absolutely essential and we are especially interested in candidates with expertise in electronic and/or mechanical hardware design. For further information call or write to: Prof. Dr. F. W?rg?tter +49 551 5176528 Or send your application with CV, publication list, and research interests/plan (preferably as PDF) to: Prof. Dr. F. W?rg?tter (worgott at bccn-goettingen.de) Bunsenstr. 10, D-37073 G?ttingen, Germany. From hava at cs.umass.edu Fri Sep 21 03:42:35 2007 From: hava at cs.umass.edu (Hava Siegelmann) Date: Fri, 21 Sep 2007 04:42:35 -0300 Subject: Connectionists: please post Message-ID: <46F375EB.5070100@cs.umass.edu> Last call for Postdoctoral Position in the Topic of Memory and Modeling The BINDS lab of UMass http://binds.cs.umass.edu/index.html is looking for extremely bright candidate with background in theoretical computer science, programming, dynamical systems and control, neurobiology, and some knowledge in memory too. Great opportunity for new research with collaboration with fantastic researchers of many fields. The focus will be computational and mathematical while background in other areas will be helpful to run the collaboration. Great atmosphere and conditions will be part of the deal please contact me directly Hava Siegelmann -- Hava T. Siegelmann http://www.cs.umass.edu/~hava/ From stephane.canu at insa-rouen.fr Fri Sep 21 08:37:46 2007 From: stephane.canu at insa-rouen.fr (Canu Stephane) Date: Fri, 21 Sep 2007 14:37:46 +0200 Subject: Connectionists: NIPS 2007 WORKSHOP on Topology Learning Message-ID: <46F3BB1A.3040109@insa-rouen.fr> ========================= CALL FOR PARTICIPATION ====================== NIPS 2007 Workshop *New challenges at the crossing of Machine Learning, Computational Geometry and Topology* 7 or 8 December, 2007 Whistler, British Columbia, Canada Supported by the PASCAL network of excellence ---------------------------------------------------------------------- E-mail: topolearn2007 at gmail.com Web site: http://topolearnnips2007.insa-rouen.fr/ Important dates * Submission deadline : october 12, 2007 * Notification of acceptance: october 19, 2007 *Invited speakers* * Pr. Herbert Edelsbrunner (Duke Univ., NC, USA) - Research on algebraic topological tools for high dimensional data analysis and the study of families of shapes. (http://www.cs.duke.edu/~edels/ ) * Pr. Partha Niyogi (Univ. of Chicago, IL, USA) - Research on Machine Learning and Information Extraction. ( http://people.cs.uchicago.edu/~niyogi/ ) * Pr. Jean-Daniel Boissonnat (INRIA Sophia Antipolis, France) - Research on Geometric Computing. ( http://www.inria.fr/personnel/Jean-Daniel.Boissonnat.en.html) * Pr. Mathias Hein (Saarland Univ., Saarbr?cken, Germany) - Research on semi-supervised learning and kernel-based algorithms. ( http://www.kyb.mpg.de/~mh ) * Dr. Vin de Silva (Pomona College, CA, USA) - Research on Computational and Statistical Topology. ( http://pages.pomona.edu/~vds04747/public/index.html ) *Topic * There is a growing interest in Machine Learning, in applying geometrical and topological tools to high-dimensional data analysis and processing. Considering a finite set of points in a high-dimensional space, the approaches developed in the field of Topology Learning intend to learn, explore and exploit the topology of the shapes (topological invariants such as the connectedness, the intrinsic dimension or the Betti numbers), manifolds or not, from which these points are supposed to be drawn. Applications likely to benefit from these topological characteristics have been identified in the field of Exploratory Data Analysis, Pattern Recognition, Process Control, Semi-Supervised Learning, Manifold Learning and Clustering. However it appears that the integration in the Machine Learning and Statistics frameworks of the problems we are faced with in Topology Learning, is still in its infancy. So we wish this workshop to ignite cross-fertilization between Machine Learning, Computational Geometry and Topology, likely to benefit to all of them by leading to new approaches, deeper understanding, and stronger theoretical results about the problems carried by Topology Learning. *Trends* We wish this workshop to do the spadework on the following open problems and discuss the proposed solutions: * Theory: How and under which conditions to ensure provably correct topology with respect to the data? Especially facing noisy, multi-scale, multidimensional or incomplete datasets? * Algorithms: How to cope with multidimensional or massive datasets in reasonable memory and time? Can we provide objective criteria to tune the hyper-parameters? * Applications: How can we insert the topological knowledge into Machine Learning algorithms? When is it beneficial to do so? How to visually represent the resulting topology to the analyst in case of exploratory data analysis? Can we define some benchmark of real and artificial data specific to this field? *Submission *Authors are invited to submit an abstract based on original research or already published results, describing new methods they developed, open problems they are faced with or applications they tackle, fitting the topic and trends given above. Abstracts should not exceed 2 single-spaced pages with figures and references. If the authors believe that more details are essential to substantiate the main claims of their abstract, they may include a clearly marked appendix that will be read at the discretion of the scientific committee. Abstracts shall be sent by e-mail to: topolearn2007 at gmail.com with subject "SUBMIT". *Organizers* * Micha?l Aupetit (chair), CEA-IDF, France * Fr?d?ric Chazal, INRIA-Futurs, France * Gilles Gasso, INSA-Rouen, France * David Cohen-Steiner, INRIA-Sophia, France * Pierre Gaillard, CEA-IDF, France *Registration* http://nips.cc/Conferences/2007/ -- Stephane Canu ---------------------------------------------------------------------- LITIS - INSA de Rouen - B.P. 08 76801 St Et du Rouvray, France +33 2 32 95 98 44 - scanu at insa-rouen.fr - asi.insa-rouen.fr/~scanu From yfreund at ucsd.edu Sat Sep 22 14:57:57 2007 From: yfreund at ucsd.edu (yoav freund) Date: Sat, 22 Sep 2007 11:57:57 -0700 Subject: Connectionists: A software package for boosting Message-ID: Hi All, If you are looking for a robust implementation of adaboost you might be interested in checking out JBOOST: http://www.cs.ucsd.edu/users/aarvey/jboost/ This implementation support adaboost, logitboost, alternating decision trees and boostexter. We are currently working on an implementation of NormalBoost, which is yet another boosting algorithm, we believe NormalBoost has significant advantages over previous boosting algorithm for noisy label data, cost-sensitive boosting and multi-class problems. THe software is distributed as GNU open source through source-forge: http://sourceforge.net/projects/jboost/ If you are interested in extending jboost please contact Aaron Arvey: aarvey at cs.ucsd.edu Have Fun! Yoav --- Prof. Yoav Freund EBU3B, Room 4126 Dept. of Comp. Sci. & Eng. http://www.cse.ucsd.edu/~yfreund/ Tel: (858) 534-1668 Email: yfreund at ucsd.edu From B.Kappen at science.ru.nl Fri Sep 21 12:03:15 2007 From: B.Kappen at science.ru.nl (Bert Kappen) Date: Fri, 21 Sep 2007 18:03:15 +0200 (CEST) Subject: Connectionists: job opening at SNN and Keygene, Netherlands Message-ID: Postdoc position available at Keygene and SNN, the Netherlands. Keygene is a biotechnology company that carries out innovative research to advance commercial plant breeding by using a number of proprietary genetic technologies and know-how. To expedite creation of new varieties by its customers, Keygenes main focus is the analysis, creation and exploitation of genetic variation. SNN is a research group at Nijmegen University dedicated to fundamental research in the areas of machine learning and computational neuroscience. Specific topics are Bayesian networks, approximate inference methods, time-series modeling, bio-informatics, expert systems, stochastic control and collaborative decision making. The group consists currently of 8 researchers and three programmers. Keygene and SNN are collaborating within the area of in silico breeding. Combining favorable alleles by crossing existing well-characterized plant lines with a minimum of efforts is a major challenge in marker-assisted crop breeding. An optimal crossing scenario has to be found that guarantees ending up with the desired combination of alleles in a single new plant line with a predefined probability. At Keygene, some initial research steps have been taken to develop algorithms that avoid calculating all possibilities but still end up with close to optimal solutions. The current project will built further on these initial methods, further improving these and enabling putting constraints on the chosen scenario, defined by demands from the breeding practice. For this novel research topic, we are looking for an ambitious and excellent postdoc quantitative genetics. The requirement for the postdoc position is a PhD and a good track record in the field of bioinformatics or machine learning. The postdoc position is full-time for a period of 3 years and will spend his time equally at both Keygene and SNN. The postdoc will be employed by Keygene as part of the Keygene postdoc program (see attached). For more information see www.snn.kun.nl/nijmegen or contact Prof. dr. H.J. Kappen (b.kappen at science.ru.nl, tlf. +31 24 3614241). -- Prof. dr. H.J. Kappen SNN Radboud University Nijmegen URL: www.snn.ru.nl/~bertk The Netherlands tel: +31 24 3614241 fax: +31 24 3541435 B.Kappen at science.ru.nl mobile: +31 6 520 78 210 From xubosong at csee.ogi.edu Fri Sep 21 16:23:36 2007 From: xubosong at csee.ogi.edu (Xubo Song) Date: Fri, 21 Sep 2007 13:23:36 -0700 Subject: Connectionists: faculty positions in CSEE at OGI/OHSU Message-ID: <46F42848.5090306@csee.ogi.edu> Following an institutional merger in 2001, the Oregon Graduate Institute of Science and Technology (OGI) became one of the four schools of Oregon Health & Science University (OHSU). This merger was based on the vision that computer science and electrical engineering will make major inroads in the life sciences during the coming decade, and that a uniquely close interdisciplinary relationship between a school of medicine and a school of engineering presents opportunities for playing a major role in this revolution. The CSEE Department is looking for individuals who understand not only how computer science and electrical engineering can be applied to the life sciences, but also how this new space of applications presents new and exciting fundamental computational research questions. The Department invites applications for faculty positions at all ranks. Specific areas of interest include, but are not limited to: * Computer vision * Sensors * Robotics The typical teaching load in CSEE is two quarter courses per year. OGI offers a generous startup package. OGI is located 12 miles west of Portland, Oregon, in the heart of the Silicon Forest. Portland's extensive high-tech community, diverse cultural amenities and spectacular natural surroundings combine to make the quality of life here extraordinary. To learn more about the department, OGI, OHSU and Portland, please visit http://www.ogi.edu/csee. To apply, send a brief description of your research interests, the names of at least three references, and a curriculum vitae with a list of publications to: Chair, Recruiting Committee Department of Computer Science and Electrical Engineering OGI School of Science and Engineering at OHSU 20000 NW Walker Road Beaverton, Oregon 97006 All applications will be reviewed. The email address for inquiries is: cseedept at csee.ogi.edu . CSEE has close ties with the recently-formed Department of Biomedical Engineering (BME), including research and teaching collaborations, and jointly appointed faculty. We encourage applicants with active interests in biomedical engineering applications to visit the BME website at http://ogi.edu/bme. OGI/OHSU is an Equal Opportunity/Affirmative Action employer. We particularly welcome applications from women, minorities, and individuals with disabilities.** * * From steve at cns.bu.edu Mon Sep 24 15:42:45 2007 From: steve at cns.bu.edu (Stephen Grossberg) Date: Mon, 24 Sep 2007 15:42:45 -0400 Subject: Connectionists: From stereogram to surface: How the brain sees the world in depth Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg: Fang, L. and Grossberg, S. From stereogram to surface: How the brain sees the world in depth. Spatial Vision, Special issue on Unresolved Questions in Stereopsis, in press. ABSTRACT How do we consciously see surfaces infused with lightness and color at the correct depths? Random Dot Stereograms (RDS) probe how binocular disparity between the two eyes can generate conscious surface percepts. Dense RDS do so despite the fact that they include multiple false binocular matches. Sparse stereograms do so across large contrast-free regions with no binocular matches. Stereograms that define occluding and occluded surfaces lead to surface percepts wherein partially occluded textured surfaces are completed behind occluding textured surfaces at a spatial scale much larger than that of the texture elements themselves. Earlier models suggest how the brain detects binocular disparity, but not how RDS generate conscious percepts of 3D surfaces. This article proposes a neural model that predicts and simulates how the layered circuits of visual cortex generate 3D surface percepts using interactions between boundary and surface representations that obey complementary computational rules. The model clarifies how interactions between layers 4, 3B, and 2/3A in V1 and V2 contribute to stereopsis, and proposes how 3D perceptual grouping laws in V2 interact with 3D surface filling-in operations in V1, V2, and V4 to generate 3D surface percepts in which figures are separated from their backgrounds. Keywords: stereopsis, visual cortex, surface perception, figure-ground separation, LAMINART model. From nnrev at atr.jp Tue Sep 25 03:23:41 2007 From: nnrev at atr.jp (Neural Networks Editorial Office) Date: Tue, 25 Sep 2007 16:23:41 +0900 Subject: Connectionists: Neural Networks: Special Issue 2008 "Neuroinformatics" Call for Papers Message-ID: ************************************************************************ CALL FOR PAPERS 2008 Special Issue of Neural Networks "Neuroinformatics" ************************************************************************ Neuroinformatics combines neuroscience and informatics research to develop and apply advanced tools and approaches essential for a major advancement in understanding the structure and function of the brain. The area of neuroinformatics has recently being submitted to a strategic analysis and planning process through the efforts of multidisciplinary expert groups, reporting to the MegaScience Forum and Global Science Forum of the Organization for Economic Cooperation and Development. These efforts have resulted in the emphasis of three main domains to be included in the term neuroinformatics: - neuroscience data and knowledge bases, increasingly capable of handling the full complexity and organization of the nervous system, from molecular to behavioral levels - tools for data-acquisition, analysis, visualization and distribution of nervous system data - theoretical, computational and simulation environments for modeling and understanding the brain In the United States, the Society for Neuroscience has also followed up on these initiatives, by establishing the Neuroscience Database Gateway -- serving as web-based ?yellow pages? for neuroinformatics tools and database resources worldwide. Their effort has documented the extensive developments that have taken place over the last few years. The present Special Issue will highlight the combined areas of databasing, tool developments, and modeling, all included in neuroinformatics. Submissions are solicited that demonstrate research and developments at the transition between two or more of the three main domains of neuroinformatics. The special issue will present new international coordination capabilities that are being established in the field, the establishment of national research platforms in neuroinformatics, and example projects from multiple levels of neuroscience investigations, all including two or more of the primary domains of neuroinformatics. Co-Editors: Sten Grillner (Karolinska Inst.) Jan Bjaalie (International Neuroinformatics Coordinating Facility) Shiro Usui (RIKEN, BSI) Submission: Deadline for submission: November 1, 2007 <-----CHANGED!! Notification of acceptance: February 1, 2008 Deadline for submission of revised papers: April 1, 2008 Notification of final acceptance: June 1, 2008 Deadline for submission of final papers: July 1, 2008 Format: as normal papers in the journal Address for Papers: Dr. Mitsuo Kawato ATR Computational Neuroscience Laboratories E-mail: nnrev at atr.jp Neural Networks Official home page: http://www.elsevier.com/wps/find/journaldescription.cws_home/841/description -- From petkov at cs.rug.nl Tue Sep 25 12:01:42 2007 From: petkov at cs.rug.nl (Nicolai Petkov) Date: Tue, 25 Sep 2007 18:01:42 +0200 Subject: Connectionists: FW: full-scholarship PhD position in Computer Science Message-ID: <000e01c7ff8d$5d598d10$af337d81@iwi175> Hello, May I ask you post the following message. Regards, NP A full-scholarship PhD position in Computer Science at a leading European university. http://www.cs.rug.nl/~petkov/vacancies/2007PhDstudent_shape.html PhD student position in Computer Science - Intelligent Systems - Biologically motivated object recognition Institute of Mathematics and Computing Science University of Groningen Topic of research The objective of the project is to develop an object recognition technique that is motivated by the function of the visual cortex. Major aspects are representation and learning. Type and level of the position This is a temporary research position at the level of a PhD student for a period of maximum four years. The tuition fees will be waived and the student will receive a full scholarship. In this period the student will follow relevant courses and prepare and defend a PhD thesis. The position is embedded in the research group Intelligent Systems. The tradition of the group is that PhD theses are based on excellent papers in high imact journals so that our PhD graduates have a very strong competative position on the academic market. Thesis director and supervisor will be professor N. Petkov. The University of Groningen is a leading European research university. Our requirements on your qualifications You are a university graduate (at the level of diploma or master of science level) in one of the following disciplines: computer science, artificial intelligence, computational neuroscience, electrical engineering, biophysics, physics. You have a demonstrated interest in the neurosciences. You have an excellent academic record (GPA) and belong to the top 5% of the graduates of your year and preferrably have a graduation with a distinction such as honors or cum laude. You are fluent in English language and able to write scientific articles and reports (to be proven by your graduation thesis or another comparable report or co-authorship of published scientific articles). How to apply Send the following information: 1) an application letter with a CV, 2) a specification of GPA and transcript of records, 3) an indication of your position in the class and year (e.g. 1st in a class of 20), 4) evidence of excellence (e.g. graduation with honors) and a list of relevant awards, 5) proofs of involvement in research (e.g. co-authorship of scientific articles), 6) a description of your ideas for research in the specified area, 7) names and email addresses of three scientists (typically your former professors) who can give a reference for you. to prof.dr. Nicolai Petkov (petkov at cs dot rug dot nl). Applicants will be asked to do a short assignment in order to demonstrate their research abilities. The position will be open until a suitable candidate is found. From robbie at bcs.rochester.edu Tue Sep 25 16:38:15 2007 From: robbie at bcs.rochester.edu (Robert Jacobs) Date: Tue, 25 Sep 2007 16:38:15 -0400 Subject: Connectionists: open faculty position --- University of Rochester Message-ID: <3273597483-87214688@cvs.rochester.edu> Open faculty position at the University of Rochester: The Department of Brain and Cognitive Sciences at the University of Rochester has a junior-level tenure-track position available in any of the following three areas: cognition (human or non-human, including development), learning and plasticity, or vision (from retina to object perception). We are open to consideration of candidates who approach these research topics employing any of the primary methods represented by our faculty: behavioral, cognitive neuroscience, computational, or neurobiological. The successful candidate will join a department that has strengths in natural language processing, developmental plasticity and learning, and visual system structure and function. A variety of research centers complement these three strengths and offer a rich array of colleagues and specialized equipment. Applicants should submit a CV, a brief statement of research interests, and three letters of reference to Dr. Richard Aslin, Department of Brain and Cognitive Sciences, University of Rochester, Rochester, NY, 14627. Review of applications will begin on November 15, 2007. The University of Rochester has a strong commitment to diversity and actively encourages applications from candidates from groups underrepresented in higher education. The University of Rochester is an Equal Opportunity Employer. ---------------------------------------------------------------------------------------- Robert Jacobs Department of Brain and Cognitive Sciences University of Rochester Rochester, NY 14627-0268 phone: 585-275-0753 fax: 585-442-9216 email: robbie at bcs.rochester.edu web: http://www.bcs.rochester.edu/people/robbie/jacobslab/people.html From leonb at nec-labs.com Wed Sep 26 14:35:59 2007 From: leonb at nec-labs.com (Leon Bottou) Date: Wed, 26 Sep 2007 14:35:59 -0400 Subject: Connectionists: Book annoucement: Large Scale Kernel Machines Message-ID: <200709261436.00031.leonb@nec-labs.com> Dear colleagues, We would like to announce a new book: Large-scale Kernel Machines MIT Press, 2007. http://mitpress.mit.edu/9780262026253/. http://leon.bottou.org/papers/lskm-2007 Pervasive and networked computers have dramatically reduced the cost of collecting and distributing large datasets. In this context, machine learning algorithms that scale poorly could simply become irrelevant. We need learning algorithms that scale linearly with the volume of the data while maintaining enough statistical efficiency to outperform algorithms that simply process a random subset of the data. This volume offers researchers and engineers practical solutions for training kernel machines from large scale datasets, with detailed descriptions of algorithms and experiments carried out on realistically large datasets. After a detailed description of state-of-the-art kernel machine technology, an introduction of the essential concepts discussed in the volume, and a comparison of primal and dual optimization techniques, the book progresses from well-understood techniques to more novel and controversial approaches. Many contributors have made their code and data available online for further experimentation. Topics covered include fast implementations of known algorithms, approximations that are amenable to theoretical guarantees, and algorithms that perform well in practice but are difficult to analyze theoretically. Best regards, - Leon Bottou, NEC Labs America, Princeton, NJ, Olivier Chapelle, Yahoo! Research, Santa Clara, CA, Dennis Decoste, Microsoft, Redmond, WA, and, Jason Weston, NEC Labs America, Princeton, NJ. Contents: 1. Support Vector Machine Solvers ? Bottou and Lin 2. Training a Support Vector Machine in the Primal ? Chapelle 3. Fast Kernel Learning with Sparse Inverted Index ? Haffner and Kanthak 4. Large-Scale Learning with String Kernels ? Sonnenburg, R?tsch and Rieck 5. Large-Scale Parallel SVM Implementation ? Durdanovic, Cosatto and Graf 6. A Distributed Sequential Solver for Large-Scale SVMs ? Yom-Tov 7. Newton Methods for Fast Semisupervised Linear SVMs ? Sindhwani and Keerthi 8. The Improved Fast Gauss Transform with Applications to Machine Learning ? Raykar and Duraiswami 9. Approximation Methods for Gaussian Process Regression ? Quinonero-Candela, Rasmussen and Williams 10. Brisk Kernel Independent Component Analysis ? Jegelka and Gretton 11. Building SVMs with Reduced Classifier Complexity ? Keerthi, Chapelle and DeCoste 12. Trading Convexity for Scalability ? Collobert, Sinz, Weston, and Bottou 13. Training Invariant SVMs Using Selective Sampling ? Loosli, Bottou and Canu 14. Scaling Learning Algorithms toward AI ? Bengio and LeCun From kenji at ieee.org Wed Sep 26 20:00:03 2007 From: kenji at ieee.org (Kenji Suzuki) Date: Thu, 27 Sep 2007 09:00:03 +0900 Subject: Connectionists: Faculty Positions in Cybernics at the University of Tsukuba Message-ID: <004501c80099$5b1c0b60$11542220$@org> * We apologize if you receive multiple copies of this announcement. Job announcement Department of Intelligent Interaction Technologies Graduate School of Systems and Information Engineering University of Tsukuba, Japan Ref: CYB01/F0709 Fixed-term Assistant/Associate Professor in Cybernics (3 posts) Applications are invited for three (3) fixed-term Assistant / Associate Professor positions in the area of Cybernics: fusion of human, machine and information systems, or relevant subjects. Cybernics is a new domain of interdisciplinary academic field of human-assistive technology to enhance, strengthen, and support human's cognitive and physical functions, which challenges to integrate and harmonize humans and robots (RT: robotics technology) with the basis of information technology (IT). The three primary research areas are: (i) Cybernoid: robot suits, cybernic limb and hand, implanted cybernic system, subjective cognition computing, virtual human-body kernel. (ii) Next-generation interface: brain-computer interface, somato-sensory media, humanoid, medical interface, ubiquitous sensing interface, intelligent robots. (iii) Management technology for next-generation advanced systems: network security, new-generation risk management, human factor, ethical, sociological, and conceptual readiness. Our primary focus is conducting research and pursuing education at the PhD level in the area of Cybernics. Responsibility also includes administrative tasks related to the program. The post is funded for five years, and these positions will be available immediately. The Cybernics project (Program leader, Prof. Yoshiyuki Sankai) is supported by the grant-in-aid science research under the Global COE program, and also is a part of a new strategic initiative in the University of Tsukuba. For more details on research areas, see the program website, http://www.cybernics.tsukuba.ac.jp/ Candidates are expected to have earned a Ph.D. degree in a relevant subject area and to have demonstrated achievement in their fields. Candidates recently graduated Ph.D., or expected to obtain their PhD degrees before the appointment begins are also encouraged to apply. Applications should include a full curriculum vitae, a list of publications, 5 reprints or preprints of relevant papers, an outline of future research plans and possible contribution to this project (about A4 2-pages), and the names and addresses of at least two referees. Applicants are requested, if possible, to list publications under the following main headings: Authored or Edited books, Refereed Journal papers, Review articles, Refereed conference proceedings, Non-refereed conference proceedings, Patents, Awards, External funding and grants, Others. The closing date for applications is 18 November 2007. Applications received after this date will not be considered. You should include the Ref. number and the Job Title you are applying for in the header of your e-mail, or standard mail envelope. Note that if applying for both posts (Assistant and Associate Professor), please submit one application form for each post. Please return your application either by email, preferably in PDF format, to jobs.faculty at cybernics.tsukuba.ac.jp, or by post to Prof. Takehisa Onisawa, Dept. of Intelligent Interaction Technologies, University of Tsukuba, Tennodai, Tsukuba, 305-0573, Japan. Tsukuba is a university and science city, located about 60 kilometers, about 1 hour by car, northeast of central Tokyo. Over 50 national and independently administered research organizations are concentrated in the Tsukuba Science City district, which is centered on the university. For informal inquiries please contact the Chair of the Department, Professor Takehisa Onisawa on email onisawa at iit.tsukuba.ac.jp. Application deadline: 18 November, 2007 * Program website http://www.cybernics.tsukuba.ac.jp/ --- Dr Kenji Suzuki kenji at ieee.org Assistant Professor University of Tsukuba, Japan http://www.iit.tsukuba.ac.jp/~kenji/ From sbasu at media.mit.edu Thu Sep 27 21:26:27 2007 From: sbasu at media.mit.edu (MLSys'07 Workshop Organizers) Date: Thu, 27 Sep 2007 18:26:27 -0700 Subject: Connectionists: Call for Abstracts: NIPS 2007 Workshop on Machine Learning for Systems Problems In-Reply-To: <1190942516.741.1213020367@webmail.messagingengine.com> References: <1190942516.741.1213020367@webmail.messagingengine.com> Message-ID: <1190942787.1400.1213021353@webmail.messagingengine.com> Call for Abstracts: NIPS 2007 Workshop on Machine Learning for Systems Problems In the last few years, there has been a budding interaction between machine learning and computer systems researchers. In particular, statistical machine learning techniques have found a wide range of successful applications in many core systems areas, from designing computer microarchitectures and analyzing network traffic patterns to managing power consumption in data centers and beyond. However, connecting these two areas has its challenges: while systems problems are replete with mountains of data and hidden variables, complex sets of interacting systems, and other exciting properties, labels can be hard to come by, and the measure of success can be hard to define. Furthermore, systems problems often require much more than high classification accuracy - the answers from the algorithms need to be both justifiable and actionable. Dedicated workshops in systems conferences have emerged (for example, SysML 2006 and SysML 2007) to address this area, though they have had little visibility to the machine learning community. A primary goal of this workshop is thus to expose these new research opportunities in systems areas to machine learning researchers, in the hopes of encouraging deeper and broader synergy between the two communities. During the workshop, through various planned overviews, invited talks, poster sessions, group discussions, and panels, we would like to achieve three objectives. First, we wish to discuss the unique opportunities and challenges that are inherent to this area. Second, we want to discuss and identify "low-hanging fruit" that are be more easily tackled using existing learning techniques. Finally, we will cover how researchers in both areas can make rapid progress on these problems using existing toolboxes for both machine learning and systems. We hope that this workshop will present an opportunity for intensive discussion of existing work in machine learning and systems, as well as inspire a new generation of researchers to become involved in this exciting domain. Call for Abstracts: We are seeking 2-page abstracts about recent work at the intersection of machine learning and systems. We welcome preliminary work and work you may plan to publish at a later conference: we are intentionally not creating proceedings for this workshop so that authors are free to submit work to later venues. However, if there is sufficient interest we will explore the possibility of a special issue of a journal or a book seeded with selected papers from the workshop. Please email your abstracts in PDF format to: mlsys07 at yahoogroups.com by October 31, 2007. We will select abstracts for presentation at the workshop by November 7, 2007. Please send any questions you may have about the workshop to this address as well. We look forward to hearing from you! Sincerely, Archana Ganapathi Sumit Basu Emre Kiciman Fei Sha More information is available at http://radlab.cs.berkeley.edu/MLSys From terry at salk.edu Fri Sep 28 06:50:04 2007 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 28 Sep 2007 03:50:04 -0700 Subject: Connectionists: NEURAL COMPUTATION - OCTOBER 2007 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 19, Number 10 - October 1, 2007 Article Synaptic Dynamics in Analog VLSI Chiara Bartolozzi and Giacomo Indiveri Note Exact Simulation of Integrate-and-Fire Models with Exponential Currents Romain Brette Letters The Relation Between Color Discrimination and Color Constancy: When Is Optimal Adaptation Task Dependent? David Brainard, Alicia Björnsdotter Abrams, and James Hillis Deviation from Weber's Law in the Non-Pacinian I Tactile Channel: A Psychophysical and Simulation Study of Intensity Discrimination Burak Güçlü Learning the Lie Groups of Visual Invariance Rajesh Rao and Xu Miao Learning with "Relevance": Using a Third Factor to Stabilize Hebbian Learning Bernd Porr and Florentin Wörgötter Synchrony-Induced Switching Behavior of Spike-Pattern Attractors Created by Spike-Timing-Dependent Plasticity Takaaki Aoki and Toshio Aoyagi Competition Between Synaptic Depression and Facilitation in Attractor Neural Networks Joaquin Torres, Jesus Cortes, Joaquin Marro, Bert Kappen Projected Gradient Methods for Nonnegative Matrix Factorization Chih-Jen Lin Integration of Stochastic Models by Minimizing -Divergence Shun-ichi Amari The Distortion of Neural Signals by Spike Coding David Goldberg and Andreas Andreou Gap-Based Estimation: Choosing the Smoothing Parameters for Probabilistic and General Regression Neural Networks Michael Georgiopoulos, Mingyu Zhong, Dave Coggeshall, Ehsan Ghaneie, Thomas Pope, Mark Rivera, Georgios Anagnostopoulos, Mansooreh Mollaghasemi, Sameul Richie 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 pcomp at hunter.cuny.edu Wed Sep 26 10:23:48 2007 From: pcomp at hunter.cuny.edu (pcomp@hunter.cuny.edu) Date: Wed, 26 Sep 2007 10:23:48 -0400 (EDT) Subject: Connectionists: Special 1-day MIT Workshop: Where Does Syntax Come From? Have We All Been Wrong Message-ID: <20070926102348.AKQ43667@mirapoint.hunter.cuny.edu> **************************************************************** Call for Participation Special 1-day MIT Workshop: Where Does Syntax Come From? Have We All Been Wrong? Cambridge, MA, October 19th, 2007 ***************************************************************** When: Friday, October 19th, 2007, 9 am - 5:30 pm (refreshments 9-9:30; lunch 12:30-1:30; afternoon refreshments) Where: Massachusetts Institute of Technology Room 34-401 (Grier Room), Cambridge, MA http://whereis.mit.edu/map-jpg?mapterms=34-401&mapsearch=go Who: Noam Chomsky, MIT, Remarks and Reflections Sandiway Fong, University of Arizona, Statistical Natural Language Parsing: Reliable Models of Language? Lila Gleitman, University of Pennsylvania, Human Simulations of Language Learning Howard Lasnik and Juan Uriagereka, University of Maryland, Structure Dependence, the Rational Learner, and Putnam's 'Sane Person' Chris Manning, Stanford University, Title TBA Partha Niyogi, University of Chicago, The Computational Nature of Language Learning William Gregory Sakas & Janet Dean Fodor, CUNY, 'Ideal' Language Learning and The Psychological Resource Problem Josh Tennenbaum, Amy Perfors, MIT, & Terry Regier, University of Chicago, Explorations in Language Learnability Using Probabilistic Grammars and Child-directed Speech Registration: No advance registration required, no fee - open to all. Open roundtable discussion at the end of the day. Organizers: Robert C. Berwick, MIT, berwick at csail.mit.edu Michael Coen, University of Wisconsin-Madison, mhcoen at cs.wisc.edu What: The impetus for this workshop, borrowing from a recent review by Yang in TICS (2004), is that "Recent demonstrations of statistical learning in infants have reinvigorated the innateness versus learning debate in language acquisition," particularly regarding syntax. We aim to reexamine this issue in a single forum from the computational, cognitive, and formal linguistics perspectives. Our intent is to examine recent applications of statistical learning theory to language acquisition. That machine learning has something to offer in understanding language acquisition is not in doubt. However, we would like to examine the basic premise that computational approaches should be linguistically informed. The hypothesis put forth is that statistical approaches should work within the framework of classical linguistics rather than supplant it. The goal of this workshop is to examine this hypothesis critically, be it wrong or right, and for each speaker to present evidence as they see fit. From yokoy at brain.riken.jp Thu Sep 27 08:41:58 2007 From: yokoy at brain.riken.jp (Yoko YAMAGUCHI) Date: Thu, 27 Sep 2007 21:41:58 +0900 Subject: Connectionists: "E. R. Caianiello" 12th Course DEAD LINE EXTENDED to Oct 7, 2007 Message-ID: ***** CALL FOR PARTICIPATION ***** International School on Neural Nets "E. R. Caianiello" 12th Course Dynamic Brain Date: from Dec. 5-12, 2007 Place: the Ettore Majorana Center in Erice, Italy EXTENDED Application dead line: Oct 7 (Sun) 2007 http://www.physics.unisa.it/dynamicbrain/ This school is held for graduate students and researchers with various backgrounds who wish to study computational neuroscience with the emphasis on recent experimental and theoretical studies of neural dynamics in the brain. The course is organized as a series of lectures from the fundamental to the cutting-edge of theoretical and experimental topics, complemented by participants' short presentations. We aim to promote informal interactions between all participants hopefully will lead to new professional relationships lasting beyond the school. Co-Directors Yoko Yamaguchi, RIKEN BSI Maria Marinaro, University of Salerno Silvia Scarpetta, University of Salerno Jointly organized by RIKEN Brain Science Institute(BSI) Dept. of Physics ?E.R.Caianiello?, University of Salerno, Italy Ettore Majorana Foundation and Center for Scientific Culture (EMFCSC) Sponsored by RIKEN Brain Science Institute International Institute for Advanced Scientific Studies (IIASS) Ettore Majorana Foundation and Center for Scientific Culture (EMFCSC) Lectures Markus Diesmann, RIKEN BSI Sonja Gruen, RIKEN BSI Michael Hasselmo, Boston University Leslie M. Kay, University of Chicago Maria Marinaro, University of Salerno Bruce McNaughton, University of Arizona John O'Keefe, University College London, Naoyuki Sato, RIKEN BSI Silvia Scarpetta, University of Salerno Wolf Singer, Max Planck Institute for Brain Research Nachum Ulanovsky, University of Maryland Yoko Yamaguchi, RIKEN BSI Important Dates: Application deadline: Oct 7 2007 Notification of acceptance: Oct 25 2007 Registration fee payment deadline: Nov 10 2007 Arrival Dec 5 2007 Departure Dec 12 2007 -- Yoko Yamaguchi Lab for Dynamics of Emergent Intelligence RIKEN Brain Science Institute http://www.dei.brain.riken.jp/~yokoy/ From petkov at cs.rug.nl Wed Sep 26 08:54:34 2007 From: petkov at cs.rug.nl (Nicolai Petkov) Date: Wed, 26 Sep 2007 14:54:34 +0200 Subject: Connectionists: on-line simulation tools for simple, complex, grating and dot-pattern selective cells Message-ID: <000401c8003c$63755210$af337d81@iwi175> On-line simulation tools for retinal-ganglion, LGN, simple, complex, grating and dot-pattern selective cells and non-classical receptive field inhibition are available at http://matlabserver.cs.rug.nl/ Gabor filters: visualize Gabor functions, use a Gabor filter and a Gabor-energy filter, perform edge detection, simulate simple and complex cells (visual cortex), extract texture features, simulate non-classical receptive field inhibition or surround suppression (visual cortex), perform contour detection, explain certain visual perception effects. Centre-Surround cell (DoG) operator and Dot-pattern selective cell operator: visualize Difference of Gaussian (DoG) functions, simulate retinal-ganglion and LGN cells, compute the convolution of an input image with a DoG (center-surround cell responses), detect intensity spots, detect groups of intensity spots, detect dot-pattern texture. Grating cell operator: Detect gratings From Christopher.Bishop at microsoft.com Thu Sep 27 11:44:27 2007 From: Christopher.Bishop at microsoft.com (Christopher Bishop) Date: Thu, 27 Sep 2007 16:44:27 +0100 Subject: Connectionists: Postdoctoral postion at Microsoft Research Cambridge with associated Darwin College Fellowship Message-ID: <2F858D2C53636A4A979CEB2A45B7E6FB0C4D4D213A@EA-EXMSG-C309.europe.corp.microsoft.com> MICROSOFT RESEARCH CAMBRIDGE Research position with associated college Fellowship Applications are invited for the post of researcher in the field of adaptive computing (including topics such as pattern recognition, probabilistic inference, machine learning and computer vision). The post will be associated with a Research Fellowship at Darwin College in Cambridge. Eligibility Men and women graduates of any university are eligible to apply, irrespective of age, provided they have a doctorate or an equivalent qualification, or expect to have submitted their thesis before taking up the Fellowship. Tenure The post will commence on l June 2008 (or on a date to be agreed, but in any case not sooner than 1 Mar 2008) and will be at postdoc level. The tenure of the post and the associated Fellowship will be 2 years. Further enquiries about the post may be made by email to cambhr at microsoft.com. The Research Laboratory The successful candidate will engage in research full-time at the Microsoft Research Laboratory in Cambridge. Microsoft Research (MSR) Cambridge was Microsoft Corp.'s first research laboratory to be established outside the United States and was set up in July 1997 and houses over 100 researchers, mostly from Europe, who are engaged in computer research at a purpose-built laboratory on the University's West Cambridge campus. Research at the Cambridge facility focuses on programming languages, security, information retrieval, machine learning, computer vision, operating systems and networking. MSR Cambridge maintains close links with the University of Cambridge, including the Computer Laboratory, the Engineering Department and the Statistical Laboratory. For further details see http://www.research.microsoft.com/labs/. Details of the scope of research at Microsoft Cambridge, going on in the specific areas of the research post, are given at http://www.research.microsoft.com/mlp/. College Research Fellowship The Fellow will be a member of the Governing Body of Darwin College and will be subject to the Statutes and Ordinances of the College which may be seen on request to the Bursar. The Statutes include the obligation to reside in or near Cambridge for at least two-thirds of each University term, but the Governing Body will normally excuse absences made necessary by the nature of the research undertaken. The Fellow will be able to take seven meals per week at the College table free of charge and additional meals at his or her own expense. Guests may be invited to all meals (within the limits of available accommodation), ten of them free of charge within any quarter of the year. College accommodation will be provided, subject to availability, or an accommodation allowance will be paid in lieu. Stipend and Emoluments The stipend will depend upon qualifications and experience, along with a number of Microsoft employee benefits. Applications Applications (in Word, PDF or txt format only) should be by Emailed to cambpdoc at microsoft.com with the subject line 'Darwin Microsoft Fellowship' by 15 October 2007 and include (1) a curriculum vitae, (2) an account, in not more than 1000 words, of the proposed research, including a brief statement of the aims and background to it, (3) the names and addresses of three referees (including telephone, fax and email addresses), who should be asked to email references immediately direct to the above email address, and (4) a list of published or unpublished work that would be available for submission if requested. Short-listed candidates may be asked to make themselves available for interview on a date to be arranged at the end of November 2007. The appointment will be made as soon as possible thereafter. Travelling expenses for overseas interviewees will be covered. From bhanupvsr at gmail.com Thu Sep 27 17:11:29 2007 From: bhanupvsr at gmail.com (Bhanu Prasad) Date: Thu, 27 Sep 2007 17:11:29 -0400 Subject: Connectionists: Neural models of intelligence Message-ID: <621812f80709271411o38d167bbi232348fb71c89120@mail.gmail.com> *Please forward to interested people* There is a sepcial session on Neural Models of Intelligence at the 2008 International Conference on Artificial Intelligence and Pattern Recognition (AIPR-08) will be held during July 7-10 2008 in Orlando, FL, USA. You can see more details about the conference (and some other conferences that will be held at the same place and time) at the website: www.PromoteResearch.org Please feel free to contact me. Best regards B. Prasad Program Committee Co-Chair of AIPR-08 From gcorani at gmail.com Fri Sep 28 06:24:50 2007 From: gcorani at gmail.com (Giorgio Corani) Date: Fri, 28 Sep 2007 12:24:50 +0200 Subject: Connectionists: JNCC2: an open source classifier based on imprecise probabilities Message-ID: JNCC2 is the Java implementation of the Naive Credal Classifier 2 (Corani and Zaffalon, 2007). NCC2 constitutes an extension of Naive Bayes towards imprecise probabilities; it is designed to return robust classification, even on small and/or incomplete data sets. A peculiar feature of NCC2 is that it returns set-valued (or imprecise) classifications (i.e., more than one class) when faced with doubtful instances. Imprecise classifications are valuable as they clearly highlight doubtful instances, preventing over-confident use of the issued judgments; however, they still convey an informative content, dropping unlikely classes. This could be appealing in contexts in which the classification outcome is especially sensitive, as for instance in medical area. Extensive empirical investigation shows that NCC2 returns imprecise judgments on instances whose classification is truly doubtful; in fact, Naive Bayes achieves a much higher classification accuracy on the instances precisely classified by NCC2, than on those imprecisely classified by NCC2. We say that NCC2 isolates area of ignorance, i.e. subsets of instances over which the accuracy of Naive Bayes sharply drops. JNCC2 is open source; it is released under the terms of the GNU GPL license; it is hence freely available together with manual, sources and javadoc documentation. For more information, visit http://www.idsia.ch/~giorgio/jncc2.html. From bengio at idiap.ch Sun Sep 30 10:14:58 2007 From: bengio at idiap.ch (Samy Bengio) Date: Sun, 30 Sep 2007 16:14:58 +0200 (CEST) Subject: Connectionists: FINAL CFP: NIPS workshop on efficient machine learning Message-ID: FINAL CALL FOR PAPER: -------------------- NIPS*2007 Workshop on Efficient Machine Learning Overcoming Computational Bottlenecks in Machine Learning Whistler, Canada, December 7-8, 2007 http://bigml.wikispaces.com/cfp Overview -------- The ever increasing size of available data to be processed by machine learning algorithms has yielded several approaches, from online algorithms to parallel and distributed computing on multi-node clusters. Nevertheless, it is not clear how modern machine learning approaches can either cope with such parallel machineries or take into account strong constraints regarding the available time to handle training and/or test examples. This workshop will explore two alternatives: * modern machine learning approaches that can handle real time processing at train and/or at test time, under strict computational constraints (when the flow of incoming data is continuous and needs to be handled) * modern machine learning approaches that can take advantage of new commodity hardware such as multicore, GPUs, and fast networks. This two-day workshop aims to set the agenda for future advancements by fostering a discussion of new ideas and methods and by demonstrating the potential uses of readily-available solutions. It will bring together both researchers and practitioners to offer their views and experience in applying machine learning to large scale learning. Topics of Interest ------------------ * efficient parallelization of machine learning algorithms and algorithms that make use of new hardware architectures * sub-linear training algorithms for virtually infinite datasets * new online boosting, online kernel, and other efficient non-linear online training algorithms * efficient feature extraction for classification and detection * adapted structures for very large number of features per example * evolving under strict time/space constraints * coarse-to-fine and "focusing" algorithms for detection Submission Procedure -------------------- We encourage the submissions of extended abstract. The suggested abstract length is about 2 pages. The invited speakers will be allocated between 40 and 60 minutes, while the authors of the accepted abstracts will be allocated between 30 and 40 minutes to present their work (to be determined according to submissions). In addition, the abstracts will be available to a broader audience on the dedicated web site. The authors should submit their extended abstract to bigml.nips at gmail.com in pdf. An email confirming the reception of the submission will be sent by the organizers. Important Dates --------------- * Aug 28: Workshop announcement / call for abstracts * Oct 12: Abstract submission deadline * Nov 1: Notification of acceptance * Dec 7 and 8: Workshop Invited Speakers ---------------- * Yali Amit, University of Chicago * Yoshua Bengio, University of Montreal * Michael Burl, NASA JPL * Corinna Cortes, Google * Dennis DeCoste, Microsoft * Don Geman, John Hopkins University * Dan Pelleg and Elad Yom-Tov, IBM Research * Yann LeCun, New York University * Srinivasan Parthasarathy, Ohio State University * Nicol N. Schraudolph, National ICT Australia Organizers ---------- * Samy Bengio, Google * Corinna Cortes, Google * Dennis DeCoste, Microsoft Live Labs * Francois Fleuret, IDIAP Research Institute * Ramesh Natarajan, IBM T.J. Watson Research Lab * Edwin Pednault, IBM T.J. Watson Research Lab * Dan Pelleg, IBM Haifa Research Lab * Elad Yom-Tov, IBM Haifa Research Lab Other Members of the Programme Committee ---------------------------------------- * Yali Amit, University of Chicago * Gilles Blanchard, Fraunhofer Institut FIRST, Berlin * Ronan Collobert, NEC * Yves Grandvalet * IDIAP Research Institute * Jiri Matas, Czech Technical University, Prague * Sam Roweis, Google ---- Samy Bengio Research Scientist in Machine Learning. Google, 1600 Amphitheatre Pkwy, Building 47-171D, Mountain View, CA 94043, USA tel:+1 (650) 253-2563, mailto:bengio at google.com, http://bengio.abracadoudou.com