From mgiugliano at gmail.com Mon Sep 1 04:58:21 2008 From: mgiugliano at gmail.com (Michele Giugliano) Date: Mon, 01 Sep 2008 10:58:21 +0200 Subject: Connectionists: Postdoctoral position in Neuroengineering Message-ID: <48BBAEAD.6070402@gmail.com> Dear Colleagues, Dear Friends, a new postdoctoral position in Neuroengineering is available immediately at the Brain Mind Institute, for a joint research project between the EPFL and my new institution in Belgium (the University of Antwerp). Please feel free to post it in your institute and to circulate it among your excellent collaborators and graduate students who might be interested. Thanks in advance, Yours sincerely, Michele Giugliano The EPFL and the Brain Mind Institute (http://bmi.epfl.ch) are seeking an outstanding and highly motivated Postdoctoral researcher for a challenging project with focus on the biophysical interactions between neuronal networks and conductive nanoparticles (see references below). The successful candidate is expected to join a new generation of neuro-nano engineers and neuroscientists, consolidating and developing unique interdisciplinary skills, at the interface among (neuro)biology, (nano)technology and (micro)electronics, mastering both the languages of ?neurons? (i.e. cellular electrophysiology and neurosciences) and of ?nanotechnology? (i.e. carbon nanotubes and conductive nanoparticles). Requirements/qualifications: Candidates must have strong experimental skills, but also interest and motivation to actively build on existing scientific collaborations and on-campus facilities. Preferred educational background is a PhD in Neuroscience, Bioengineering or Nanotechnology. Experience with patch-clamp recordings, cell / slice culturing and computational modeling is an advantage. The successful candidate should also possess a high degree of motivation, excellent written and verbal communication skills and a demonstrated ability to work independently and interact with a multi-disciplinary team of scientists. Environment: The Laboratory of Neural Microcircuitry at the Brain Mind Institute, based at the Swiss federal Institute of Technology (EPFL) The Dept. of Biomedical Sciences, University of Antwerp (Belgium) Contact: Interested applicants should submit a one-page description of past research experience, a resume of educational and research experience, including publications, and names of three people that could provide letters of reference, to Prof. Dr. M. Giugliano (email: michele .dot. giugliano .at. epfl .dot. ch) Theoretical Neurobiology, Dept. of Biomedical Sciences, University of Antwerp (Belgium) and Laboratory of Neural Microcircuitry, Brain Mind Institute, Ecole Polytechnique Federale de Lausanne We do not respond to obvious mass mailing. Ref: Mazzatenta et al., Journal of Neuroscience, 2007 Sucapane et al., Journal of Nanoneuroscience, 2008 Giugliano et al., Drug Discovery Today: Disease Models, 2008 Giugliano et al., in "In Progress in Nanotechnology Neurosciences", 2008 (reprints available from http://www.giugliano.info) See also: Lovat et al., Nano Letters, 2005 Silva, Nat. Rev. Neurosci. 2006 Keefer et al., Nat. Nanotech., 2008 -- Michele Giugliano Brain Mind Institute Ecole Polytechnique Federale de Lausanne (EPFL) Station 15 - CH-1015, Lausanne - Switzerland voice : +41 21 693 1658 fax: +41 21 693 5350 email: michele.giugliano at epfl.ch url: http://people.epfl.ch/michele.giugliano -- Michele Giugliano Brain Mind Institute Ecole Polytechnique Federale de Lausanne (EPFL) Station 15 - CH-1015, Lausanne - Switzerland voice : +41 21 693 1658 fax: +41 21 693 5350 email: michele.giugliano at epfl.ch url: http://people.epfl.ch/michele.giugliano From terry at salk.edu Mon Sep 1 16:17:21 2008 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 01 Sep 2008 13:17:21 -0700 Subject: Connectionists: NEURAL COMPUTATION - October, 2008 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 20, Number 10 - October 1, 2008 Article Neural Integrator - a Sandpile Model Alex Koulakov and Maxim Nikitchenko Letters Type I and Type II Neuron Models are Selectively Driven by Differential Stimulus Features German Mato and Ines Samengo Rapid Convergence to Feature Layer Correspondences Jorg Lucke, Christian Keck, and Christoph von der Malsburg Normalization Enables Robust Validation of Disparity Estimates from Neural Populations Eric Tsang and Bertram Shi Understanding Parkinsonian Handwriting through a Computational Model of Basal Ganglia Srinivasa Chakravarthy, Garipelli Gangdhar, and Denny Joseph Sparse Coding via Thresholding and Local Competition in Neural Circuits Chris Rozell, Don Johnson, Richard Baraniuk, and Bruno Olshausen Adaptive Classification of Temporal Signals in Fixed-Weight Recurrent Neural Networks: An Existence Proof Ivan Tuykin, Danil Prokhorov, and Cees van Leeuwen ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2009 - VOLUME 21 - 12 ISSUES USA/Canada Others Electronic only Student/Retired $60 $123 $54 Individual $110 $173 $99 Institution $849 $912 $756 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 Jean-Marc.Bollon at inrialpes.fr Tue Sep 2 05:48:23 2008 From: Jean-Marc.Bollon at inrialpes.fr (Jean-Marc Bollon) Date: Tue, 2 Sep 2008 11:48:23 +0200 Subject: Connectionists: Probabilistic Reasoning and Decision Making in Sensory-Motor Systems - NEW BOOK Message-ID: <5B496F90-8A5B-4D62-8604-D05EFFC8C57D@inrialpes.fr> Probabilistic Reasoning and Decision Making in Sensory-Motor Systems ****************************************************************************** Both living organisms and robotic systems must face the same central difficulty: How to survive being ignorant? How to use an incomplete and uncertain model of their environment to perceive, infer, decide, learn and act efficiently? Indeed, any model of a real phenomenon is incomplete: there are always some hidden variables, not taken into account in the model, that influence the phenomenon. The effect of these hidden variables is that the model and the phenomenon never behave exactly alike. Uncertainty is the direct and unavoidable consequence of incompleteness. A model may not foresee exactly the future observations of a phenomenon as these observations are biased by the hidden variables. It may neither predict exactly the consequences of its decisions. Probability theory, considered as an alternative to logic to model rational reasoning, is the perfect mathematical framework to face this difficult challenge. Learning is used in a first step to transform incompleteness into uncertainty, inference is then used to reason and take decisions based on the probability distributions constructed by learning. This so-called subjectivist approach to probability allows uncertain reasoning as complex and formal as the ones made using logic with exact knowledge. This book presents twelve different implementations of this approach to very different sensory-motor systems either by programming robots or by modeling living systems. Each of these works summarizes a PhD dissertation defended in different European universities. All these works use Bayesian Programming: a mathematical formalism, which defines in simple mathematical terms the way probability, can be used as an alternative to logic. Bayesian Programming also proposes a programming and modeling methodology as, to respect the mathematical formalism, the programmer should follow always the same steps to build his model. Finally, Bayesian Programming is a common language to understand and compare the different models. This language is used all along this book by all the authors and insures the global coherence of these twelve very different examples. More information : http://emotion.inrialpes.fr/BP/spip.php?article18 How to buy : http://www.springer.com/engineering/book/978-3-540-79006-8 http://www.amazon.com/Probabilistic-Reasoning-Decision-Sensory-Motor-Springer/dp/3540790063/ref=sr_1_7ie=UTF8&s=books&qid=1205844732&sr=1-7 -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080902/d4c93264/attachment.html -------------- next part -------------- A non-text attachment was scrubbed... Name: arton18-98x150.jpg Type: image/jpeg Size: 11134 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080902/d4c93264/arton18-98x150.jpg From uta.noppeney at tuebingen.mpg.de Tue Sep 2 11:58:57 2008 From: uta.noppeney at tuebingen.mpg.de (Uta Noppeney) Date: Tue, 02 Sep 2008 17:58:57 +0200 Subject: Connectionists: PhD/PostDoc - Computational Cognitive Neuroimaging Message-ID: <48BD62C1.8070103@tuebingen.mpg.de> PhD/PostDoc - Computational Cognitive Neuroimaging Applications are invited for a PhD or PostDoc position in the ?Cognitive Neuroimaging Group? (http://www.kyb.mpg.de/noppeneygroup/index.html) at the Max Planck Institute for Biological Cybernetics. Projects will combine fMRI and computational modelling to investigate the neural basis of category learning. The position is supervised by Dr Uta Noppeney, in collaboration with Prof Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) and Prof Bernhard Sch?lkopf (machine learning department, MPI). The Max Planck Institute for Biological Cybernetics provides an excellent multi-disciplinary and interactive research environment combining expertise in neurophysiology, psychophysics, machine learning and development of MRI methodology. Applicants should combine interest in neuroscience with a strong mathematical and analytical background and have a master/diploma or equivalent degree in Neuroscience, Physics, Computer Science or related areas. The Ph.D./PostDoc position is funded by a MPI stipend. Applications including a CV, a statement of research interests, and the names and full contact details of two referees should be sent to: uta.noppeney at tuebingen.mpg.de The closing date for applications is 2 October 2008. From elli.chatzopoulou at incf.org Thu Sep 4 10:12:13 2008 From: elli.chatzopoulou at incf.org (INCF - Elli Chatzopoulou) Date: Thu, 04 Sep 2008 16:12:13 +0200 Subject: Connectionists: INCF newsletter service Message-ID: <48BFECBD.8030404@incf.org> The INCF Secretariat has recently launched a bi-monthly Newletter service, publishing the latest developments and activities of the INCF and related neuroinformatics initiatives. The first two newsletters are available here: http://www.incf.org/news/newsletters The September-October INCF newsletter is featuring: -the latest news about the INCF Software Center -a presentation of the INCF German Node and the Bernstein Network -information about the upcoming INCF Neuroinformatics Congress -a short interview of Gaute Einevoll, coordinator of the INCF Norwegian Node You can subscribe to the INCF newsletter mailing list simply by sending a message to incf-info-subscribe at incf.org -- Elli Chatzopoulou, Ph.D. Scientific Information and Public Relations Officer International Neuroinformatics Coordinating Facility Secretariat Karolinska Institutet Nobels v?g 15A SE-171 77 Stockholm Sweden Email: elli.chatzopoulou at incf.org Phone: +46 8 524 87491 Mobile: +46 7 614 87491 Fax: +46 8 524 87150 web: www.incf.org From zoubin at eng.cam.ac.uk Wed Sep 3 09:09:03 2008 From: zoubin at eng.cam.ac.uk (Zoubin Ghahramani) Date: Wed, 3 Sep 2008 14:09:03 +0100 Subject: Connectionists: Professorship of Information Engineering, University of Oxford Message-ID: The following Professorship at Oxford may be of interest to senior academics in Machine Learning, Signal and Image Processing, Computer Vision, Biomedical Engineering, and other related areas. Further details at: http://www.admin.ox.ac.uk/fp/wd86-068.shtml ---- UNIVERSITY OF OXFORD BP Professorship of Information Engineering Applications are invited for the above post, tenable from 1 January 2009, or as soon as possible thereafter. The professorship will be held in the Department of Engineering Science, in association with a non-stipendiary professorial fellowship at Keble College. The successful candidate will have an international reputation for scholarship and research in information engineering (broadly interpreted). He or she will be expected to pursue a research programme at the forefront of the subject, providing research leadership to colleagues working in this and similar fields; to play a major role in securing long-term funding for research; to contribute to the broadening of the department?s research portfolio, seeking new strategic directions; to contribute to both undergraduate and postgraduate teaching and training programmes. Further particulars, including details of how to apply, are available from http://www.admin.ox.ac.uk/fp/ or from the Registrar, University Offices, Wellington Square, Oxford OX1 2JD, UK (tel: +44(0)1865 270200). The closing date for applications is Monday 22 September 2008. ---- Zoubin Ghahramani Professor of Information Engineering University of Cambridge http://learning.eng.cam.ac.uk/zoubin/ zoubin at eng.cam.ac.uk From mbethge at tuebingen.mpg.de Mon Sep 8 09:18:22 2008 From: mbethge at tuebingen.mpg.de (Matthias Bethge) Date: Mon, 8 Sep 2008 15:18:22 +0200 Subject: Connectionists: Junior Research Group Positions in Tuebingen (Germany) Message-ID: <04695540-1E1C-4AB8-ADAB-A6155B2C7EAE@tuebingen.mpg.de> Junior Research Group Positions for Cognitive Neuroscience and Systems Neuroscience at the Werner Reichardt Centre for Integrative Neuroscience (CIN) http://www.neuroscience-tuebingen.de/cin/ The Werner Reichardt Centre for Integrative Neuroscience (CIN) is a newly established interdisciplinary institution at the Eberhard Karls University Tuebingen funded by the German Excellence Initiative program. The CIN strives to deepen our understanding of how the brain generates function and how brain diseases impair functions. It will make use of newly acquired insights to help people with brain disorders and to launch new mind- and brain-inspired applications in many areas of engineering and computer science. Its scientific program is guided by the conviction that progress in the understanding of brain function can only be achieved with an integrative approach spanning multiple levels of organization and pooling the knowledge of researchers from many different fields. In order to strengthen the CINs' specific research aims, we are offering several junior group leader (JRG) positions (equivalent to Assistant Professorship) with tenure track options in the fields of ?Systems Neuroscience? and ?Cognitive Neuroscience? including ?Neurophilosophy? and ?Neurorobotics/Medical Robotics?. Submission deadline is Oct. 15th, 2008 (for Neurophilosophy Oct. 31st, 2008). Framework: The intended duration of the position is for 5 years with evaluations by external experts at regular intervals. In case of positive evaluations after 3 years, the JRG will obtain a tenure track option, which may ultimately lead to a professorship at the University of Tuebingen. Start-up funds as well as substantial funding for personnel and running costs will be available, but will depend on the qualification and prior experience of the applicant. Appointees will be full members and active participants in the CIN, which will also provide laboratory and/or office space. The JRG leader will be provided opportunities to contribute to research oriented training within the framework of the CIN Graduate Training Centre and the faculties involved in the CIN will provide opportunities for the German habilitation according to established rules, if desired. According to German law, severely disabled persons with equal occupational aptitude will be given preferred consideration. The University of Tuebingen strives to promote equal opportunities in science and is committed to increasing the percentage of female scientists in teaching and research. Qualified female candidates are thus strongly encouraged to apply. Application: Applicants should submit a curriculum vitae, pdf files of up to 5 key publications, statements of research achievements and future directions (not to exceed 3 pages) as well as the names and addresses of at least three referees. All documents should be submitted electronically to the Acting Director of the Werner Reichardt Centre for Integrative Neuroscience Tuebingen, Prof. Dr. Peter Thier, at cin at uni-tuebingen.de . For further information on the CIN see: http://www.neuroscience-tuebingen.de/cin/ . Submission deadline for all applications is Oct. 15th, for applications in the field of Neurophilosophy Oct. 31st. ___________________________________________ Dr. Matthias Bethge, Group Leader Computational Vision & Neuroscience Group MPI for Biological Cybernetics, T"ubingen [ http://www.kyb.mpg.de/bethgegroup/ ] -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080908/f7b1c69e/attachment.html From mikio at cs.tu-berlin.de Tue Sep 9 04:37:03 2008 From: mikio at cs.tu-berlin.de (Mikio Braun) Date: Tue, 09 Sep 2008 10:37:03 +0200 Subject: Connectionists: Call for Submissions: Workshop on Machine Learning Open Source Software (MLOSS), NIPS*08 Message-ID: <48C635AF.1090504@cs.tu-berlin.de> ********************************************************************** Call for Submissions Workshop on Machine Learning Open Source Software 2008 http://mloss.org/workshop/nips08 held at NIPS*08, Whistler, Canada, December 12th, 2008 ********************************************************************** The NIPS workshop on Workshop on Machine Learning Open Source Software (MLOSS) will held in Whistler (B.C.) on the 12th of December, 2008. Important Dates =============== * Submission Date: October 1st, 2008 * Notification of Acceptance: October 14th, 2008 * Workshop date: December 12 or 13th, 2008 Call for Contributions ====================== The organizing committee is currently seeking abstracts for talks at MLOSS 2008. MLOSS is a great opportunity for you to tell the community about your use, development, or philosophy of open source software in machine learning. This includes (but is not limited to) numeric packages (as e.g. R,octave,numpy), machine learning toolboxes and implementations of ML-algorithms. The committee will select several submitted abstracts for 20-minute talks. The submission process is very simple: * Tag your mloss.org project with the tag nips2008 * Ensure that you have a good description (limited to 500 words) * Any bells and whistles can be put on your own project page, and of course provide this link on mloss.org On 1 October 2008, we will collect all projects tagged with nips2008 for review. Note: Projects must adhere to a recognized Open Source License (cf. http://www.opensource.org/licenses/ ) and the source code must have been released at the time of submission. Submissions will be reviewed based on the status of the project at the time of the submission deadline. Description =========== We believe that the wide-spread adoption of open source software policies will have a tremendous impact on the field of machine learning. The goal of this workshop is to further support the current developments in this area and give new impulses to it. Following the success of the inaugural NIPS-MLOSS workshop held at NIPS 2006, the Journal of Machine Learning Research (JMLR) has started a new track for machine learning open source software initiated by the workshop's organizers. Many prominent machine learning researchers have co-authored a position paper advocating the need for open source software in machine learning. Furthermore, the workshop's organizers have set up a community website mloss.org where people can register their software projects, rate existing projects and initiate discussions about projects and related topics. This website currently lists 123 such projects including many prominent projects in the area of machine learning. The main goal of this workshop is to bring the main practitioners in the area of machine learning open source software together in order to initiate processes which will help to further improve the development of this area. In particular, we have to move beyond a mere collection of more or less unrelated software projects and provide a common foundation to stimulate cooperation and interoperability between different projects. An important step in this direction will be a common data exchange format such that different methods can exchange their results more easily. This year's workshop sessions will consist of three parts. * We have two invited speakers: John Eaton, the lead developer of Octave and John Hunter, the lead developer of matplotlib. * Researchers are invited to submit their open source project to present it at the workshop. * In discussion sessions, important questions regarding the future development of this area will be discussed. In particular, we will discuss what makes a good machine learning software project and how to improve interoperability between programs. In addition, the question of how to deal with data sets and reproducibility will also be addressed. Taking advantage of the large number of key research groups which attend NIPS, decisions and agreements taken at the workshop will have the potential to significantly impact the future of machine learning software. Invited Speakers ================ * John D. Hunter - Main author of matplotlib. * John W. Eaton - Main author of Octave. Tentative Program ================= The 1 day workshop will be a mixture of talks (including a mandatory demo of the software) and panel/open/hands-on discussions. Morning session: 7:30am - ?10:30am * Introduction and overview * Octave (John W. Eaton) * Contributed Talks * Discussion: What is a good mloss project? o Review criteria for JMLR mloss o Interoperable software o Test suites Afternoon session: 3:30pm - ?6:30pm * Matplotlib (John D. Hunter) * Contributed Talks * Discussion: Reproducible research o Data exchange standards o Shall datasets be open too? How to provide access to data sets. o Reproducible research, the next level after UCI datasets. Program Committee ================= * Jason Weston (NEC Princeton, USA) * Gunnar R?tsch (FML Tuebingen, Germany) * Lieven Vandenberghe (University of California LA, USA) * Joachim Dahl (Aalborg University, Denmark) * Torsten Hothorn (Ludwig Maximilians University, Munich, Germany) * Asa Ben-Hur (Colorado State University, USA) * William Stafford Noble (Department of Genome Sciences Seattle, USA) * Klaus-Robert Mueller (Fraunhofer Institute First, Germany) * Geoff Holmes (University of Waikato, New Zealand) * Alain Rakotomamonjy (University of Rouen, France) Organizers ========== * Soeren Sonnenburg Fraunhofer FIRST Kekul?str. 7, 12489 Berlin, Germany * Mikio Braun Technische Universit?t Berlin, Franklinstr. 28/29, FR 6-9, 10587 Berlin, Germany * Cheng Soon Ong ETH Z?rich, Universit?tstr. 6, 8092 Z?rich, Switzerland Funding ======= The workshop is supported by PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning) From ica2009 at dmo.fee.unicamp.br Mon Sep 8 12:32:52 2008 From: ica2009 at dmo.fee.unicamp.br (ICA2009) Date: Mon, 8 Sep 2008 13:32:52 -0300 (BRT) Subject: Connectionists: CALL FOR PAPERS - ICA 2009: Intl. Conf. on Independent Component Analysis and Signal Separation Message-ID: Dear Colleagues, Next year, the 8th International Conference on Independent Component Analysis and Signal Separation (ICA2009) will be held in Paraty, one of Brazil's most charming tourist destinations. In accordance with the tradition established by the previous ICA conferences, our wish is that next year's event be a special moment for our community to share ideas and experiences in a most pleasant environment. In the following, you will find the Call for Papers of ICA2009, which contains all relevant information about the event. We look forward to receiving your technical contribution and meeting you in Paraty! Best regards, Allan Kardec Barros and Joao Marcos T. Romano. General Chairs, ICA2009 Tulay Adali and Christian Jutten Technical Chairs, ICA2009 ----------------------------------- 8th International Conference on Independent Component Analysis and Signal Separation Paraty, Brazil 15-18 March 2009 http://www.dspcom.fee.unicamp.br/ica2009 The 8th International Conference on Independent Component Analysis and Signal Separation, ICA 2009, will be held in Paraty, Brazil, March 15-18, 2009. The meeting will feature keynote addresses by leading researchers, as well as invited and contributed papers. Prospective authors are invited to submit papers in the following areas (but not limited to): * Algorithms and Architectures: non-linear ICA, probabilistic models, sparse coding, linear & nonlinear models, convolutive & noisy models; * Theory: optimization, complex methods, time-frequency representations; * Applications: audio, bio-informatics, biomedical engineering, communications, finance, text, image processing, psychology; * Emerging Technologies: analogue and digital VLSI implementations, photonics; * Functional Neuroimaging: EEG, MEG, fMRI analysis, applications in neuroscience; * Speech and Musical Audio: source separation, denoising, dereverberation, temporal models, computational auditory scene analysis (CASA), beamforming; * Visual and Sensory Processing: image processing and coding, image separation. SPECIAL SESSION ON EVALUATION ICA 2009 will feature a special session on the first community-based Signal Separation Evaluation Campaign (http://sisec.wiki.irisa.fr/). Researchers entering the campaign are encouraged to submit a paper to this session describing their approach. Papers discussing new algorithms or application strategies for existing algorithms (e.g. signal representation, parameter settings) are both welcome. Accepted papers will be published in the proceedings of ICA 2009, after review by the evaluation chairs and the program chairs. ADDITIONAL INFORMATION Proceedings will be published in Springer-Verlag's Lecture Notes in Computer Science Series (LNCS). LNCS is published, in parallel to the printed books, in full-text electronic form. All contributions must be original, and must not have been previously published, nor be under review for presentation elsewhere. Extended versions of a selection of papers presented at the conference will be considered for a special issue of a journal to appear in 2009. Detailed instructions for submission to ICA 2009 and further information will be available in the conference website. IMPORTANT DATES: * October 15, 2008 - Submission deadline * December 5, 2008 - Notification of acceptance * December 15, 2008 - Final paper due From mail at jan-peters.net Tue Sep 9 05:04:13 2008 From: mail at jan-peters.net (Jan Peters) Date: Tue, 9 Sep 2008 11:04:13 +0200 Subject: Connectionists: Junior Research Groups for Systems Neuroscience, Cognitive Neuroscience and Neurorobotics/Medical Robotics Message-ID: <63382CE4-A719-4C12-87E7-D8425EFCEA99@jan-peters.net> Junior Research Groups for Cognitive Neuroscience and Systems Neuroscience at the Werner Reichardt Centre for Integrative Neuroscience (CIN) The Werner Reichardt Centre for Integrative Neuroscience (CIN) is a newly established interdisciplinary institution at the Eberhard Karls University T?bingen funded by the German Excellence Initiative program. The CIN strives to deepen our understanding of how the brain generates function and how brain diseases impair functions. It will make use of newly acquired insights to help people with brain disorders and to launch new mind- and brain-inspired applications in many areas of engineering and computer science. Its scientific program is guided by the conviction that progress in the understanding of brain function can only be achieved with an integrative approach spanning multiple levels of organization and pooling the knowledge of researchers from many different fields. In order to strengthen the CINs' specific research aims, we are offering several junior group leader (JRG) positions (equivalent to Assistant Professorship) with tenure track options in the fields of ?Systems Neuroscience?, ?Cognitive Neuroscience?, ?Neurophilosophy? and ?Neurorobotics/Medical Robotics?. Submission deadline is Oct. 15th, 2008 (for Neurophilosophy Oct. 31st, 2008). Framework The intended duration of the position is for 5 years with evaluations by external experts at regular intervals. In case of positive evaluations after 3 years, the JRG will obtain a tenure track option, which may ultimately lead to a professorship at the University of T?bingen. Start-up funds as well as substantial funding for personnel and running costs will be available, but will depend on the qualification and prior experience of the applicant. Appointees will be full members and active participants in the CIN, which will also provide laboratory and/or office space. The JRG leader will be provided opportunities to contribute to research oriented training within the framework of the CIN Graduate Training Centre and the faculties involved in the CIN will provide opportunities for the German habilitation according to established rules, if desired. According to German law, severely disabled persons with equal occupational aptitude will be given preferred consideration. The University of T?bingen strives to promote equal opportunities in science and is committed to increasing the percentage of female scientists in teaching and research. Qualified female candidates are thus strongly encouraged to apply. Application Applicants should submit a curriculum vitae, pdf files of up to 5 key publications, statements of research achievements and future directions (not to exceed 3 pages) as well as the names and addresses of at least three referees. All documents should be submitted electronically to the Acting Director of the Werner Reichardt Centre for Integrative Neuroscience T?bingen, Prof. Dr. Peter Thier, at cin at uni-tuebingen.de. For further information on the CIN see: http://www.neuroscience-tuebingen.de/cin/. Submission deadline for all applications is Oct. 15th, for applications in the field of Neurophilosophy Oct. 31st. From pascal.fua at epfl.ch Wed Sep 10 03:31:26 2008 From: pascal.fua at epfl.ch (Pascal Fua) Date: Wed, 10 Sep 2008 09:31:26 +0200 Subject: Connectionists: PhD Candidate Positions in Computer Vision at EPFL Message-ID: <48C777CE.20906@epfl.ch> EPFL's Computer Vision laboratory (http://cvlab.epfl.ch) has two openings for PhD candidates interested in working on 3D shape and motion recovery from video. Topics of immediate interest include modeling crowd behavior using multiple cameras, real-time tracking for visual servoing of a robotic plane, and automated analysis of brain imagery. For more details about our research activities, see http://cvlab.epfl.ch/research/. For practical information about EPFL's doctoral program and life in Lausanne, see http://acide.epfl.ch/webdav/site/acide/shared/phdguide.pdf. Education: Masters degree in Computer Science or related field with experience in the areas of Computer Vision or Computer Graphics. A strong background in Mathematics is desirable. Applying: 1. Apply to our doctoral program, as explained under http://phd.epfl.ch/page55508.html. 2. Specify in the application form that you are interested by Prof. Fua's CVLab. There is no need to contact him directly. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From James.Henderson at unige.ch Wed Sep 10 09:58:09 2008 From: James.Henderson at unige.ch (James HENDERSON) Date: Wed, 10 Sep 2008 15:58:09 +0200 Subject: Connectionists: PhD studentship in statistical natural language processing Message-ID: <48C7D271.4010404@unige.ch> The following PhD studentship would involve work with neural network and latent variable models of language processing. People with questions about in the neural network aspect of this project should contact me. -------- Doctoral student position in Natural Language Processing, University of Geneva The University of Geneva, Departments of Computer Science and Linguistics, invite applications for a doctoral research assistant position in natural language processing. The successful candidate will be part of a group whose research focuses on statistical models of natural language. They will participate in a project on integrated statistical models of syntactic-semantic parsing for both English and French, with application to spoken dialogue system and possibly machine translation. For more information listing our recent publications and current research projects, see the web pages http://www.classic-project.org/ http://www.latl.unige.ch/personal/paola.html http://cui.unige.ch/~hendersj/ Applicants will have received a Master's degree or equivalent in Computer Science or Computational Linguistics. Good programming skills are required. Knowledge of English and French is highly desirable, and good mastery of one is required. Previous experience in natural language processing is a plus. Funding is guaranteed for 3 years, with a possible extension for a fourth year. Starting salary 38'400 CHF. The doctoral dissertation can be pursued either in the Department of Computer Science or the Department of Linguistics, depending on qualifications. The University of Geneva is one of the leading research universities in Europe and offers excellent working conditions, as well as a stimulating scientific environment. Review of the applications will start immediately and will continue until the position is filled. The appointment will start as soon as the necessary work permits and documents are obtained, but no sooner than the 1st of october 2008. Applicants should send a curriculum vitae indicating all classes and grades, a short statement of interest, and names and email addresses of at most 2 references. Electronic applications are strongly preferred. Send your application to merlo at lettres.unige.ch with CANDOC as the subject line. If electronic application is not possible, send you application package to Paola Merlo Linguistics Department University of Geneva 5 rue de Candolle CH-1211 Geneve 4 Switzerland Informal inquiries can be addressed to James Henderson (james.henderson at cui.unige.ch) or to Paola Merlo (merlo at lettres.unige.ch). The University of Geneva wishes to increase the proportion of female academic staff and, for this reason, especially welcomes applications from women. From ilafiete at caltech.edu Wed Sep 10 16:37:25 2008 From: ilafiete at caltech.edu (Ila Fiete) Date: Wed, 10 Sep 2008 15:37:25 -0500 Subject: Connectionists: available: postdoctoral position in computational neuroscience Message-ID: <48C83005.8090207@caltech.edu> Dear Colleagues, I apologize for the cross-posting. I'd appreciate it if you would pass this on to anybody looking for a postdoc position in computational neuroscience. Best regards, Ila Fiete ======================================= Postdoctoral position in Computational Neuroscience I'm writing to announce an immediate opening for a postdoctoral position in computational neuroscience at the Center for Learning and Memory, at the University of Texas at Austin. Projects will involve modeling the dynamics of neural activity and learning in networks that underlie complex behaviors, as well as studying properties of the neural code in sensory and motor systems. Example systems include, but are not limited to, neural integrators, song production and learning in songbirds, and navigation in ants and rodents. Collaborations and interactions with the greater neuroscience community are encouraged, and projects will typically involve collaborations with experimentalists. The initial appointment will be for 1 year with a possibility of extension up to 3 years. Environment: The Center for Learning and Memory is a center for integrative neuroscience at the University of Texas, Austin, and consists of an energetic mix of junior and senior faculty who use imaging, electrophysiology, molecular biology and biochemistry, genetics, psychology, physics, and computer science techniques to study the brain. The CLM is part of a much larger neuroscience community at UT Austin. UT Austin has excellent programs in engineering, non-linear dynamical systems, and the sciences. For more information, please see http://www.klab.caltech.edu/~ila/ and http://www.clm.utexas.edu/ and http://www.utexas.edu/neuroscience/. Austin is the 16th-largest US city, and is home to many hi-tech and Fortune 1000 corporations. To Apply: Applicants must have strong quantitative training, and should have received a Ph.D. in Physics, Mathematics, Computational Neuroscience, Computer Science, or Engineering by the start date of the position. The ability to program in Matlab or C and some knowledge of neuroscience is desirable but not necessary. A demonstrated dedication to and enthusiasm for research is a must. If interested, please email me with 1) a copy of your CV or resume, 2) a statement of research interests, and 3) please arrange to have 3 letters of recommendation sent to me by email. I will review applications once I have received the requested information. Application review will begin immediately, and continue until the position is filled. With best regards, Ila Fiete From I.Bojak at donders.ru.nl Thu Sep 11 14:41:14 2008 From: I.Bojak at donders.ru.nl (Ingo Bojak) Date: Thu, 11 Sep 2008 20:41:14 +0200 Subject: Connectionists: PhD position in Computational Neuroscience (4 year contract), Radboud University Nijmegen Message-ID: <48C9664A.1080401@donders.ru.nl> Candidate profile The successful candidate has a strong background in physics and/or mathematics, is competent in applying numerical methods, and shows some grasp of, and great interest in, computational neuroscience. The main tasks of this research project involve theoretical calculations, computer simulations and experimental data analyses, using MATLAB. Specific methods and relevant background knowledge will be taught to the candidate ?on the job?, providing an excellent opportunity for an enthusiastic researcher to specialize in an exciting new field. Research topic Neuronal oscillations in the gamma frequency range (30-100 Hz) play a crucial role in information processing. Since gamma activity is effective in activating other neurons, the question arises which mechanism prohibits gamma activity to activate an ever-increasing number of neurons. Many focal epileptic seizures start with an increase of gamma activity with abnormal spreading. We will investigate the special role of inhibitory interneurons in the generation of a robust gamma rhythm. The hypothesis that some inhibitory regulation is disturbed in epileptic patients will be tested using mathematical analyses and extensive computer simulations of interactions between single neurons and populations of neurons. The results of these approaches will be compared to data in large databases at the Academic Hospital of the University Utrecht, obtained by subdural recordings in patients with normal task-related gamma activity and with epileptic seizures. The results of this project may allow pro-active recognition of starting epileptic activity. Research environment The Department of Biophysics of the Radboud University Nijmegen is part of the Centre for Neuroscience (http://www.ru.nl/dcn) within the Donders Institute for Brain, Cognition and Behaviour (http://www.ru.nl/donders/). The Donders Institute hosts many excellent researchers and owns advanced infrastructure and equipment, such as a PC-cluster for fast computer simulations. The offered PhD position is part of a large project in Computational Life Science, funded by the Dutch Science Foundation (NWO). The grant also includes 2 post-docs and another PhD student, and is a collaboration of several senior researchers at Radboud University and at the Mathematics Department of the University of Twente. Living in The Netherlands / Nijmegen The Netherlands are well-known as a liberal and modern European country with a unique and distinguished culture. It is one of most densely populated urban regions of the world, but the vibrant border city of Nijmegen (http://www.nijmegen.nl/) also offers access to the beautiful Dutch/German ?Lower Rhine? countryside. Salary Estimated gross salary: from about ?2050/month in the first year to ?2600/month in the last year (Dutch University Salaryscale 10), plus an 8% annual supplement and end-of-year bonus. For more information, please contact Prof. Dr. C. Gielen (S.Gielen at donders.ru.nl). From esann at dice.ucl.ac.be Sat Sep 13 15:03:49 2008 From: esann at dice.ucl.ac.be (esann) Date: Sat, 13 Sep 2008 21:03:49 +0200 Subject: Connectionists: ESANN'2009 call for papers Message-ID: ESANN'2009 17th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 22-23-24, 2009 Announcement and call for papers =============================================== The call for papers for the ESANN'2009 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 21, 2008 ***** You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2009 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, machine 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'2009 conference will follow this tradition, while adapting its scope to the new developments in the field. The ESANN conferences cover artificial neural networks, 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'2009 are: 1) Semi-supervised learning Ant?nio de P?dua Braga (Federal Univ. Minas Gerais, Brazil) 2) Learning (with) Preferences Fabio Aiolli, Alessandro Sperduti (Univ. degli Studi di Padova, Italy) 3) Brain Computer Interfaces: from theory to practice Luc Boullart (Ghent University), Patrick Santens (Ghent University Hospital), George Otte (Dr. Guislain Institute), Bart Wyns (Ghent University, Belgium) 4) Efficient learning in recurrent networks Benjamin Schrauwen (Ghent University, Belgium), Jochen J. Steil (Bielefeld University, Germany), Barbara Hammer (Clausthal University of Technology, Germany) 5) Weightless Neural Systems Massimo De Gregorio (Istituto di Cibernetica-CNR, Italy), Priscila M. V Lima, Felipe M. G. Fran?a (Universidade Federal do Rio de Janeiro, Brazil) Neural Maps and Learning Vector Qunatization - Theory and Applications Thomas Villmann, Frank-Michael Schleif (Univ. Leipzig, 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 21, 2008. 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, 2009; 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 21 November 2008 Notification of acceptance 17 January 2009 ESANN conference 22-24 April 2009 Conference secretariat ---------------------- ESANN'2009 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) Peter Bartlett Univ.California, Berkeley (USA) Michael Biehl University of Groningen (NL) 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) 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) Damien Fran?ois Univ. cat Louvain (B) 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) Paulo Lisboa Liverpool John Moores University (UK) Erzsebet Merenyi Rice Univ. (USA) David Meunier University of Cambridge (UK) 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) Alfredo Vellido Polytechnic University of Catalonia (E) 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 - Advances in Computational Intelligence and Learning http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews, registrations: 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 uclouvain.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 uclouvain.be ======================================================== From aonken at cs.tu-berlin.de Sat Sep 13 07:54:53 2008 From: aonken at cs.tu-berlin.de (Arno Onken) Date: Sat, 13 Sep 2008 13:54:53 +0200 Subject: Connectionists: Call for Abstracts: NIPS Workshop 2008 Message-ID: <48CBAA0D.6050809@cs.tu-berlin.de> You are invited to participate in the post-conference NIPS workshop "Statistical Analysis and Modeling of Response Dependencies in Neural Populations", taking place in Whistler, Canada, on December 12-13, 2008. It is well known that sensory and motor information is represented in the activity of large populations of neurons. Encoding and decoding is subject of active research. The two dominant theories of neural coding are rate and temporal coding. They are studied by considering the dependencies between responses of several neurons. In the typical theoretical framework, response dependencies are characterized by correlation coefficients and cross-correlograms. The main goal of this workshop is to challenge the dependency concepts that are typically applied and to disseminate more sophisticated concepts to a wider public. It will bring together experts from different fields and encourage exchange of insights between experimentalists and theoreticians. To participate in the workshop please submit an extended abstract as a two-page PDF attachment via email to aonken at cs.tu-berlin.de. The deadline for submission is October 15. The workshop chairs will select a couple of abstracts for oral presentation at the workshop. The other abstracts will be presented as posters on December 12. We are looking forward to seeing you in Whistler. Klaus Obermayer, Valentin Dragoi, Arno Onken, Steffen Gruenewaelder and Denise Berger (Workshop organizers) List of speakers (confirmed): * Wyeth Bair (University of Oxford) * Jeff Beck (University of Rochester) * Pietro Berkes (Brandeis University) * Valentin Dragoi (University of Texas, Workshop Chair) * Arnulf Graf (New York University) * Sonja Gr?n (RIKEN Brain Science Institute) * Rick Jenison (University of Wisconsin-Madison) * Dimitris Karlis (Athens University) * Stephen Lisberger (University of California, San Francisco) * Jakob Macke (Max Planck Institute for Biological Cybernetics) * Naoki Masuda (University of Tokyo) Workshop URL: http://ni.cs.tu-berlin.de/projects/nips2008/ From v.steuber at herts.ac.uk Mon Sep 15 06:48:21 2008 From: v.steuber at herts.ac.uk (Volker Steuber) Date: Mon, 15 Sep 2008 11:48:21 +0100 Subject: Connectionists: PhD Studentship in Computational Neuroscience Message-ID: <48CE3D75.6040807@herts.ac.uk> PhD Studentship in Computational Neuroscience Science and Technology Research Institute University of Hertfordshire UK Applications are invited for a 3 year PhD Studentship in Computational Neuroscience in the Science and Technology Research Institute at the University of Hertfordshire, UK. The studentship will cover a stipend of ?12,940 per year plus payment of the standard UK student fees. Candidates should be interested in information processing in biologically detailed models of neuronal networks. Our research involves close collaboration with experimentalists in Europe and the USA. More details can be found in these recent publications: Steuber, V., Mittmann, W., Hoebeek, F.E., Silver, R.A., De Zeeuw, C.I., Hausser, M. and De Schutter, E. (2007). Cerebellar LTD and pattern recognition by Purkinje cells. Neuron 54, 121-136. Gleeson, P., Steuber, V. and Silver, R.A. (2007). neuroConstruct: A tool for modeling networks of neurons in 3D space. Neuron 54, 219-35. Calcraft L., Adams R. and Davey N. (2007). Efficient Architectures for Sparsely-Connected High Capacity Associative Memory Models, Connection Science 6, 163-75. Applicants should have good computational and numerical skills and a good first degree in maths, computer science, physics, neuroscience or biology. Previous experience in neuroscience is not required but would be an advantage. The UH Science and Technology Research Institute has been rated as 4 (national excellence with evidence of international excellence) at the last UK university research assessment exercise. It is located in Hatfield in Hertfordshire, just north of London. For informal enquiries contact Dr Volker Steuber (v.steuber at herts.ac.uk ) or Dr Neil Davey (n.davey at herts.ac.uk ). Further information and an application form can be obtained from Mrs Lorraine Nicholls, Research Student Administrator, STRI, Faculty of Engineering and Information Sciences, University of Hertfordshire, College Lane, Hatfield, Herts, AL10 9AB. Tel: +44 1707 286083 Fax: +44 1707 284185 email: l.nicholls at herts.ac.uk. The short-listing process will begin on 1 October 2008. Dr Volker Steuber Senior Lecturer (Research) in Biocomputation Science and Technology Research Institute University of Hertfordshire Hatfield Herts AL10 9AB UK Tel +44 1707 284350 http://homepages.feis.herts.ac.uk/~comqvs/ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080915/e6b239f9/attachment.html From vcu at cs.stir.ac.uk Thu Sep 11 04:35:12 2008 From: vcu at cs.stir.ac.uk (Dr. Vassilis Cutsuridis) Date: Thu, 11 Sep 2008 11:35:12 +0300 Subject: Connectionists: Second CfP Neural Networks journal Special Issue on Cortical Microcircuits Message-ID: <002501c913e9$4eea5ea0$99e3e98f@Zeus> Second Call for Papers: Neural Networks Journal Special Issue on ======= Cortical Microcircuits ======== (formerly known as Neural models of Cortical microcircuits) Guest Editors: J.G. Taylor, T. Wennekers, B.P. Graham, I. Vida, V. Cutsuridis Special issue of the Elsevier Journal of Neural Networks http://helen.pion.ac.uk/microcircuits08 = SCOPE = To understand how perception, attention, action, learning and memory work, we need to gather data from multiple levels of complexity and from various brain states (normal and diseased) and integrate them at the brain-scale level. We need to identify the neuronal groups involved in these functions, their laminar distributions and their different types of neurons, draw detailed circuit diagrams, determine the forms of synaptic transmission and plasticity between different neurons and study the dynamics of the cortical microcircuits at the cellular and synaptic level that comprise these neuronal groups. Recent years have witnessed a dramatic accumulation of knowledge about the morphological, physiological and molecular characteristics, as well as the connectivity and synaptic properties of cortical neurons. Despite these advances, however, only limited insight was gained into the computational function of the neurons; in particular, the role of the various types of interneurons remains elusive. Mathematical and computational microcircuit models play an instrumental role in exploring microcircuit functions and facilitate the dissection the operations performed by diverse interneurons. The goal of the special issue is to provide a snapshot and a resum? of the current state-of-the-art of the ongoing research avenues concerning cortical microcircuits with particular emphasis on the functional roles of the various inhibitory interneurons in information processing within normal and diseased behavioural and cognitive states. The emphasis will be on computational models that are tightly grounded on experimental data. = SPECIFIC AIMS = - The interaction between the local micro circuit activity and global processing to achieve the desired overall processing functionality observed, say in perception and action, attention, learning and memory - Microcircuit architectures: networks of principal and inhibitory inter-neurons within and between lamina, columns, mini-columns, modules, areas and/or across areas in the brain and their functional roles in the network. -- Neo-cortex -- Hippocampus -- Sensory and Motor Systems - Cross-comparison of architectures from different brain areas - Identified computations performed by each type of neuron in a network - Identified modes of operation of a neuronal type and how they are related potentially to behaviour and cognition - What synaptic plasticity rules are used = SUBMISSIONS = New *extended* submission deadline: February 1st, 2009 Electronic submissions for the Neural Networks journal can be found under http://ees.elsevier.com/neunet/ Please indicate in your cover letter that your article is for the special issue "Cortical Microcircuits" Regards, Vassilis ---------------------------------------------------------------------------------- Dr. Vassilis Cutsuridis Department of Computing Science and Mathematics University of Stirling Stirling FK9 4LA SCOTLAND Tel: +44 1786 467422 Fax: +44 1786 464551 Email: vcu at cs.stir.ac.uk Web: http://www.cs.stir.ac.uk/~vcu/ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080911/446ecccc/attachment.html From mark.plumbley at elec.qmul.ac.uk Tue Sep 9 05:43:50 2008 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Tue, 9 Sep 2008 10:43:50 +0100 Subject: Connectionists: PhD Studentship in Compressed Sensing of Audio Scenes (Ddln: 19 Sept 2008) Message-ID: <9A6BBBBE2AAD6746A6D961B57357426236F6E4C5@staff-mail2.vpn.elec.qmul.ac.uk> [Apologies for cross-posting. Please forward to any potentially interested candidates. Thanks, Mark.] ---------------------------------------------------------------- PhD Studentship in Compressed Sensing of Audio Scenes (Application deadline: 19 September 2008) Applications are invited for a 3-year PhD studentship to investigate the analysis of musical and environmental audio, using the technique of compressed sensing, to commence in October 2008, or as soon as possible thereafter. Compressed sensing is a new technique concerned with reducing the number of measurements necessary to reconstruct an object. It is based on the principle that the object has some underlying sparse representation, i.e. that it can be described using a small number of non-zero coefficients. Audio scenes may be sparse in the time domain, if each source sounds only rarely; in the frequency domain, if the sound sources use a small number of frequencies; or in the spatial domain, if there are only a small number of discrete sound sources. The aim of the PhD project is to investigate compressed sensing techniques to extract audio from such sound scenes, and compare with existing methods for audio source separation and audio enhancement. This PhD will be supervised by Dr Mark D Plumbley (www.elec.qmul.ac.uk/people/markp), and will take place in the School of Electronic Engineering and Computer Science at Queen Mary University of London, within the world-leading Centre for Digital Music (although the research is not limited to musical audio). The work will form part of a new programme of research in "Machine Listening using Sparse Representations", supported by a Leadership Fellowship from the UK Engineering and Physical Sciences Research Council (EPSRC). This is to be a concerted programme of research in machine listening (the automatic analysis and understanding of sounds from the world around us), using methods from sparse representations, and to establish machine listening as a key enabling technology to improve our ability to interact with the world. Applicants must have a first degree in electronic engineering, mathematical science, physics, statistics, computer science, or allied disciplines (minimum: good 2:1 or equivalent), and excellent mathematical and programming skills. Previous experience of digital signal processing of audio is desirable, although not mandatory. The 3-year studentship will comprise full fees for "home" (UK/EU) students and an annual stipend commencing at ?14,600 including London Allowance (stipends are exempt of UK tax), subject to satisfactory progress. For informal enquiries, please contact Dr Mark D Plumbley, Queen Mary, University of London, mark.plumbley at elec.qmul.ac.uk. For application forms and information on how to apply, see http://www.elec.qmul.ac.uk/study/phd/res-stud.htm. Deadline: 19 September 2008 -- Dr Mark D Plumbley Electronic Engineering and Computer Science Queen Mary University of London Mile End Road, London E1 4NS, UK Tel: +44 (0)20 7882 7518 Fax: +44 (0)20 7882 7997 Email: mark.plumbley at elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/markp/ From Wray.Buntine at nicta.com.au Mon Sep 15 06:01:46 2008 From: Wray.Buntine at nicta.com.au (Wray Buntine) Date: Mon, 15 Sep 2008 20:01:46 +1000 Subject: Connectionists: Machine Learning Researcher Wanted (all levels) Message-ID: Junior and Senior Machine Learning Researchers The Statistical Machine Learning Research Group, based in Canberra, is a team of junior and senior researchers, software engineers and PhD students who pursue fundamental research in principled methods for data analysis and its applications to a variety of fields, including document and text analysis, computer vision and pattern recognition. We work at the intersection of theory, methods and applications. As such, our staff and students are encouraged to collaborate broadly and we are committed to using machine learning to address diverse areas. We are looking for applicants at the senior level and the junior level who have a strong track record of basic research and research leadership in one or more of the following areas: ? Document Analysis, ? Computer Vision ? Graphical Models ? Kernel Methods ? Learning Theory The successful applicants will have an excellent publication record and experience with supervising students. The group is particularly interested in candidates with both a strong methodological background and experience in practical domains or commercialisation. A record of industry or government collaboration is also desirable. The appointees will be eligible for an adjunct position at the College of Engineering and Computer Science, Australian National University. Consequently, appointees will have the opportunity to teach at the postgraduate level and supervise PhD students. Interested applicants should look at the following websites for more information: ? Group website: http://sml.nicta.com.au/ ? About NICTA: http://nicta.com.au/about Please direct enquires to the Project Leader Prof. Wray Buntine, wray.buntine at nicta.com.au. Applications will be assessed during 2008 and a selection made when a meritorious candidate has been identified. -- Wray Buntine Principal Researcher Statistical Machine Learning NICTA | Locked Bag 8001 | Canberra ACT 2601 T +61 2 6267 6323 | F +61 2 6267 6230 www.nicta.com.au | wray.buntine at nicta.com.au >From imagination to impact. From s.li.1 at bham.ac.uk Tue Sep 16 04:24:45 2008 From: s.li.1 at bham.ac.uk (Sheng Li) Date: Tue, 16 Sep 2008 09:24:45 +0100 Subject: Connectionists: Research Fellow in Vision and NeuroImaging Message-ID: <468E635F877FE94BBEFFC0309BCA1954E75E60@psgfs4.adf.bham.ac.uk> Research Fellow in Vision and NeuroImaging A Post-doctoral Research Fellow position in Vision and NeuroImaging is available at the School of Psychology, University of Birmingham, UK. The work focuses on the neural basis of shape perception and learning combining behavioural paradigms, functional imaging and advanced computational methods for the analysis of multimodal imaging signals (fMRI-EEG). Research will be conducted within well-equipped labs that incorporate a range of bespoke equipment. The School of Psychology provides an excellent working environment with a pronounced research focus and international expertise in Vision Science, Behavioural Neuroscience and Cognitive Neuroscience. Facilities include an Imaging Centre with integrated equipment for the study of human brain and behaviour (3T scanner, EEG) as well as numerous virtual reality devices and eye trackers. Candidates should hold or expect to hold a Ph.D. in Experimental Psychology, Neuroscience, Computer Science, Engineering, Physics, Mathematics or a related field. Programming skills (e.g. Matlab, C, OpenGL) are necessary and experience with behavioural, imaging, signal processing methods and modelling is desirable. Further details on the project and informal enquiries can be addressed to Zoe Kourtzi: z.kourtzi at bham.ac.uk. Andrew Welchman : a.e.welchman at bham.ac.uk From aprieto at ugr.es Tue Sep 16 04:54:56 2008 From: aprieto at ugr.es (Alberto Prieto) Date: Tue, 16 Sep 2008 10:54:56 +0200 Subject: Connectionists: IWANN2009 Call for papers Message-ID: <20080916085458.3E7D0F201@smtp1.ugr.es> IWANN (and related) conferences http://www.iwann-conference.es/ Apologies for cross-posting Dear colleague, On behalf of the Organizing Committee of the 10th International Work-Conference on Artificial Neural Networks (IWANN2009), we are pleased to invite you to participate in this event that will be held on June 10-12, 2009 in Salamanca (Spain). This biennial meeting seeks to provide a discussion forum for scientists, engineers, educators and students about the latest discoveries and realizations in the foundations, theory, models and applications of systems inspired on nature (neural networks, fuzzy logic and evolutionary systems) as well as in emerging areas related to the above items. As in previous editions, IWANN also aims to create a friendly environment that could lead to the establishment or to strengthen scientific collaborations and exchanges among attendees. The proceedings will include all the presented communications to the conference (invited talks, tutorials, and oral and poster presentations). As in previous editions of IWANN, we are arranging the publication of the proceedings with Springer-Verlag on Lecture Notes in Computer Science (LNCS) series, and the books will be available on-site. It is also foreseen the publication of an extended version of selected papers in a special issue of the Neurocomputing journal (Elsevier). IWANN is included in the ranking of the best conferences established by the Computer Science Conference Ranking based on the "Estimated Impact of Conference (EIC)", concretely in position 55 among 620 considered (in the Artificial Intelligence field). Also IWANN papers are indexed by CiteSeer.IST, and by the organization Computing Research and Education Association (CORE). You are cordially encouraged to participate by submitting a paper and/or organizing a special session. Please, find extended information concerning special sessions at the page: http://iwann.ugr.es/2009/contenido.php?apartado=contributions&sub=sesions Special sessions organizers have the autonomy in promoting their sessions, appointing the possible additional reviewers for the session papers (possible including the organizer him/herself), chairing their respective sessions and proposing their co-organizer and/or co-chair. Besides, the session organizers will get a reduction of 30% in the registration fees. You can obtain and freely print a copy of this Call For Papers at: http://iwann.ugr.es/2009/pdf/cfp_iwann2009.pdf Do not hesitate to access the conference web or contact us by e-mail for further questions or suggestions at: http://iwann.ugr.es/2009/contenido.php?apartado=home&sub=home iwann2009pc at dte.uma.es We hope this conference will be of your interest. Best wishes Joan Cabestany Alberto Prieto Francisco Sandoval Co-Chairmen IWANN 2009 ================================================ You have been included in this list because, to the best of our knowledge, you have once shown interest in IWANN or computational intelligence conferences. If this is not the case, please, accept our apologies and unsubscribe via e-mail: To: InfoIwann-request at ctima.uma.es Subject: unsubscribe From nips2008publicity at gmail.com Tue Sep 16 21:42:18 2008 From: nips2008publicity at gmail.com (Antonio Torralba) Date: Tue, 16 Sep 2008 21:42:18 -0400 Subject: Connectionists: NIPS: Call for Demonstrations Reminder Message-ID: Reminder: The Call for Demos ends this Friday, Sept. 19. Please go here for detailed information: http://nips.cc/Conferences/2008/CallForDemos From tobias at nld.ds.mpg.de Wed Sep 17 09:36:04 2008 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Wed, 17 Sep 2008 15:36:04 +0200 Subject: Connectionists: Postdoctoral and PhD student positions in cellular neurophysics/neurophysiology In-Reply-To: <482D546D.4050402@nld.ds.mpg.de> References: <46F11EC2.6060905@nld.ds.mpg.de> <47DF9A97.1000408@nld.ds.mpg.de> <482D3F9A.6020609@nld.ds.mpg.de> <482D546D.4050402@nld.ds.mpg.de> Message-ID: <48D107C4.1060202@nld.ds.mpg.de> The Bernstein Center for Computational Neuroscience G?ttingen invites applications for a Postdoctoral and PhD student positions in cellular neurophysics/neurophysiology The candidates?s research will experimentally analyze the dynamical properties of sodium channels in neocortical neurons in situ and model their role in the operation of cortical neurons and networks and will be part of an integrated international project of the Max Planck Institutes for Dynamics and Self-Organization (G?ttingen) and the Koret School of Veterinary Medicine of the Hebrew University of Jerusalem (Israel), supported by the German-Israeli Foundation for Scientific Research and Development. PhD students will work towards their doctorate either in G?ttingen University?s newly established Graduate School, GGNB or at the Hebrew University of Jerusalem. We are looking for young researchers with a background in biophysics, cellular electrophysiology, or cell biology and a keen interest in interdisciplinary research at the border of experimental and theoretical neuroscience. The ideal candidate will have the ability and desire to push the characterization of cortical sodium currents in intact cortical neurons to a new level of quantitative precision and to analyze their role in the operation of cortical neurons under physiologically realistic conditions. Prior experience with the biophysics of ion channels, with the electrophysiology of neurons, or with cellular imaging methods would be advantageous. Prior knowledge of Neurobiology is desirable but not required. G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including three Max Planck Institutes, the European Neuroscience Institute, the German Primate Research Center, and G?ttingen University's Centers for Systems Neuroscience (ZNV) and for the Molecular Physiology of the Brain (CMPB). The BCCN integrates theoretical and experimental research groups from these institutions to foster interdisciplinary research in computational neuroscience specifically supporting close collaboration between theorists and experimental researchers. Please submit your application preferably in one single PDF-document, including cover letter, CV, list of publications, names of possible referees, relevant certificates until October 15, 2008, to: jobs at bccn-goettingen.de (Subject: NPhysNaCh) While e-mail is preferred, applications may also be submitted in hardcopy to the following address: Dr. Fred Wolf Subject: NPhysNaCh Bernstein Center for Computational Neuroscience (BCCN) G?ttingen Max-Planck-Institute for Dynamics and Self-Organization Bunsenstrasse 10 D - 37073 G?ttingen, Germany http://www.ds.mpg.de The MPIDS is an equal opportunity employer. From rhaschke at techfak.uni-bielefeld.de Wed Sep 17 10:36:08 2008 From: rhaschke at techfak.uni-bielefeld.de (Robert Haschke) Date: Wed, 17 Sep 2008 16:36:08 +0200 Subject: Connectionists: postdoc position in explorative motor learning at CoR-Lab, Bielefeld University Message-ID: <48D115D8.6030103@techfak.uni-bielefeld.de> CoR-Lab at Bielefeld University invites applications from outstanding Postdocs in the area of autonomous explorative motor learning The successful candidate has a strong background in at least two of the areas visual servoing, dynamical systems and control, and machine learning. The research project will cover dimension reduction methods, development of adaptive vision-based controllers, their evaluation in physics-based simulations and on real robot hands, and the development of explorative learning strategies. The candidate should be able to autonomously acquaint oneself with new research topics, supervise undergraduate students, and integrate into the existing team. Research topic Humans gradually increase their manual competence by active exploration of the manipulation capabilities of their fingers. As compared to learning from sensory data, active learning incorporates the exploration into the skill acquisition process. The project targets to research such active learning paradigms, and to apply them to real-world scenarios such as object-in-hand-manipulation with dexterous robot hands. One interesting example is to learn to rotate a cube so that certain faces become visible one after the other. The learning scheme should exploit multimodal perception, such as joint angle sensors, tactile sensors in the fingertips, and visual information, and integrate these cues with the movement control scheme of a dexterous 20 DOF Shadow Robot Hand. A major goal of the project would be to implement a vertical slice of explorative skills, ranging from learning low level finger control (extending eye-hand to eye-finger coordination) to realizing desired movement skills of an object held in the hand. Generic insights should be gained about how proprioceptive, visual, and haptic information has to be combined to drive the exploration process and about suitable principles for shaping the exploration. This will touch the research areas of reinforcement learning, active learning driven by information maximization, or imitation of previously learnt episodes. Research environment The CoR-Lab has been established at Bielefeld University, Germany, as a research centre for intelligent systems and human-machine interaction. The CoR-Lab forms a strategic partnership between Bielefeld University and the Honda Research Institute Europe GmbH, Germany. It pursues fundamental research in the field of cognitive robots and intelligent systems. A particular focus of the CoR-Lab is the interdisciplinary integration of expertise in engineering, computer science, brain science, and cognitive sciences, including the humanities and social sciences. The Graduate School that is associated with the CoR-Lab provides an exciting and stimulating environment for 20 enthusiastic and creative PhDs and Postdocs, allowing them to pursue research in international teams in close collaboration with an industrial research institute. Scholarship The CoR-Lab offers a three-year scholarship to pursue the research goals of the project. For more information please see: http://www.cor-lab.de/corlab/html/graduate_school/index.php A complete application should include certificates and transcripts of records of the completed course of studies, a detailed curriculum vitae, a cover letter providing information about the qualification for this project, your past and future research interests including your research projects in related areas, as well as your motivation to do research in the Graduate School. Please send your application until 31 October 2008 (preferably in PDF format) to the Managing Director of the Graduate School: Bielefeld University CoR-Lab Graduate School Dr. Carola Haumann 33594 Bielefeld Germany email: chaumann at cor-lab.uni-bielefeld.de From D.Hardoon at cs.ucl.ac.uk Wed Sep 17 15:19:20 2008 From: D.Hardoon at cs.ucl.ac.uk (David R. Hardoon) Date: Wed, 17 Sep 2008 20:19:20 +0100 Subject: Connectionists: Learning from Multiple Sources Workshop, 13 Dec '08 Whistler Canada Message-ID: Apologies if multiple copies are received. Call for Papers: ---------------------------------------------------------------------- NIPS 2008 WORKSHOP on LEARNING FROM MULTIPLE SOURCES http://web.mac.com/davidrh/LMSworkshop08/ http://nips.cc/ ---------------------------------------------------------------------- BACKGROUND While the machine learning community has primarily focused on analysing output of a single data source, there has been relatively few attempts to develop a general framework, or heuristics, for analysing several data sources in terms of a shared dependency structure. Learning from multiple data sources (or alternatively, the data fusion problem) is a timely research area. Due to the increasing availability and sophistication of data recording techniques and advances in data analysis algorithms, there exists many scenarios in which it is necessary to model multiple, related data sources, i.e. in fields such as bioinformatics, multimodal signal processing, information retrieval etc. The relevance of this research area is inspired by the human brain's ability to integrate five different sensory input streams into a coherent representation of its environment. The open question is to find approaches to analyse data which consists of more than one set of observations (or view) of the same phenomenon. In general, existing methods use a discriminative approach, where a set of features for each data set is found in order to explicitly optimise some dependency criterion. Existing approaches include canonical correlation analysis (Hotelling, 1936), a standard statistical technique for modeling two data sources, and its multiset variation (Kettenring, 1971) which find linearly correlated features between data sets, and kernel variants (Lai and Fyfe, 2000; Bach and Jordan, 2002; Hardoon et al., 2004) and approaches that optimise the mutual information between extracted features (Becker, 1996; Chechik et al., 2003). However, discriminative approaches may be ad hoc, require regularisation to ensure erroneous shared features are not discovered, and it is difficult to incorporate prior knowledge about the shared information. Generative probabilistic approaches address this problem by jointly modeling each data stream as a sum of a shared component and a 'private' component that models the within-set variation (Bach and Jordan, 2005; Leen and Fyfe, 2006; Klami and Kaski, 2006). These approaches assume a simple relationship between (two) data sources, i.e.assuming a so-called 'flat' data structure where the data consists of N independent pairs of related data variables; whereas in practice, related data sources may exhibit extremely complex co- variation (for instance, audio and visual streams related to the same video). A potential solution to this problem could be a fully probabilistic approach, which could be used to impose structured variation within and between data sources. Additional methodological challenges include determining what is the 'useful' information we are trying to learn from the multiple sources and building models for predicting one data source given the others. As well as the unsupervised learning of multiple data sources detailed above, there is the closely related problem of multitask learning (Bickel et al., 2008), or transfer learning, where a task is learned from other related tasks. WORKSHOP The aim of the workshop is to promote discussion amongst leading machine learning and applied researchers about learning from multiple, related sources of data, with a focus on both methodological issues and applied research problems. Topics of the workshop include (but not limited to): - unsupervised learning (generative / discriminative modeling) of multiple related data sources - canonical correlation analysis-type methods - data fusion for real world applications, such as bioinformatics, sensor networks, multimodal signal processing, information retrieval - multitask /transfer learning - multiview learning INVITED SPEAKERS Prof. Michael Jordan University of California, Berkeley http://www.cs.berkeley.edu/~jordan/ Dr. Francis Bach ?cole normale sup?rieure http://www.di.ens.fr/~fbach/ Dr. Tobias Scheffer Max-Planck-Institut fur Informatik http://www.mpi-inf.mpg.de/~scheffer/ ORGANISERS David R. Hardoon (University College London) Gayle Leen (Helsinki University of Technology) Samuel Kaski (Helsinki University of Technology) John Shawe-Taylor (University College London) PROGRAM COMMITTEE Andreas Argyriou (University College London) Tom Dieithe (University College London) Colin Fyfe (University of the West of Scotland) Jaakko Peltonen (Helsinki University of Technology) SUBMISSIONS We invite the submission of high quality extended abstracts (2 to 4 pages) in the NIPS style http://nips.cc/PaperInformation/StyleFiles. Abstracts should be sent (in .pdf/.ps) to D.Hardoon at cs.ucl.ac.uk, gleen at cis.hut.fi . A selection of the submitted abstracts will be accepted as either an oral presentation or poster presentation. The best abstracts will be considered for extended versions in the workshop proceedings, and possibly as a special issue of a journal. IMPORTANT DATES 24 Oct 08 Submission deadline for extended abstracts 28 Oct 08 Notification of acceptance 13 Dec 08 Workshop at NIPS 08, Whistler, Canada REFERENCES BACH, F.R., & JORDAN, M.I. 2002. Kernel Independent Component Analysis. Journal of Machine Learning, 3, 1-48. BACH, F.R., & JORDAN, M.I. 2005. A Probabilistic Interpretation of Canonical Correlation Analysis. Tech. rept. 688. Dept of Statistics, University of California. BECKER, S. 1996. Mutual Information Maximization: models of cortical selforganisation. Network: Computation in Neural Systems, 7, 7-31. BICKEL, S., BOGOJESKA, J., LENGAUER, T., & SCHEFFER, T. Multi-task learning for HIV therapy screening. ICML 2008 CHECHIK, G., GLOBERSON, A., TISHBY, N., & WEISS, Y. 2003. Information Bottleneck for Gaussian variables. Pages 1213-1220 of: THRUN, S., SAUL, L.K., & SCH?OLKOPF, B. (eds), Advances in Neural Information Processing Systems, vol. 16. HARDOON, D. R., SZEDMAK, S. & SHAWE-TAYLOR, J. 2004 Canonical Correlation Analysis: An Overview with Application to Learning Methods. Neural Computation, 16(12), 2639-2664 HOTELLING, H. 1936. Relations between two sets of variates. Biometrika, 28, 312-377. KETTENRING, J. R. 1971. Canonical analysis of several sets of variables. Biometrika, 58(3), 433-451. KLAMI, A., & KASKI, S. 2006. Generative models that discover dependencies between two data sets. Pages 123-128 of: MCLOONE, S., ADALI, T., LARSEN, J., HULLE, M. VAN, ROGERS, A., & DOUGLAS, S.C. (eds), Machine Learning for Signal Processing XVI. IEEE. LAI, P. L., & FYFE, C. 2000. Kernel and Nonlinear Canonical Correlation Analysis. International Journal of Neural Systems, 10(5), 365-377. LEEN, G., & FYFE, C. 2006. A Gaussian Process Latent Variable Model Formulation of Canonical Correlation Analysis. Pages 413-418 of: Proceedings of the 14th European Symposium of Artificial Neural Networks (ESANN). From juergen at idsia.ch Wed Sep 17 08:59:49 2008 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Wed, 17 Sep 2008 14:59:49 +0200 Subject: Connectionists: Switzerland: 5 PhD and 4 PostDoc positions in reward-based learning Message-ID: <5FD42E7D-5AB2-4BBF-AD0C-44E741874086@idsia.ch> The Swiss National Science Foundation funds a new collaborative project involving 3 groups at the EPFL (Wulfram Gerstner, Carmen Sandi, Michael Herzog) as well as groups of Univ. Berne (Walter Senn) and IDSIA in Lugano (Juergen Schmidhuber). We are particularly interested in biologically plausible models for learning and memory which explain animal and human behavior. The current project aims to extend the theory of reward-based learning in spiking neurons to networks, link it to formal policy gradient and TD methods, and apply it to perceptual learning, spatial navigation, and sequence learning. Applications should be submitted to the individual labs: Wulfram Gerstner http://lcn.epfl.ch Laboratory of Computational Neuroscience, EPFL Carmen Sandi http://lgc.epfl.ch Laboratory of Behavioral Genetics, EPFL Michael Herzog http://lpsy.epfl.ch/ Laboratory of Psychophysics, EPFL Walter Senn (http://www.physio.unibe.ch/Positions/) Computational Neuroscience/Institute of Physiology, Berne Juergen Schmidhuber http://www.idsia.ch/~juergen/sinergia2008.html IDSIA, Lugano PS: Switzerland is a good place for scientists. It is the origin of special relativity (1905) and the World Wide Web (1990), is associated with 105 Nobel laureates, and boasts the world's highest number of Nobel prizes per capita, the highest number of publications per capita, the highest number of patents per capita, the highest citation impact factor, the most cited single-author paper, the biggest machine ever (LHC) for the most expensive experiment ever, etc. Switzerland also got the highest ranking in the list of happiest countries :-) -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080917/9a812110/attachment-0001.html From carnevalet at sbcglobal.net Thu Sep 18 23:07:39 2008 From: carnevalet at sbcglobal.net (Ted Carnevale) Date: Thu, 18 Sep 2008 23:07:39 -0400 Subject: Connectionists: Parallel simulations with NEURON on multicore Macs and PCs Message-ID: <48D3177B.3030406@sbcglobal.net> By now, most NEURON users are aware that simulations can be sped up by running NEURON on workstation clusters and parallel supercomputers. But did you know that the next official release of NEURON (version 7) will offer multithreaded execution, so you can run parallel simulations on standalone multicore Macs or PCs? An alpha release of version 7 is already available at http://www.neuron.yale.edu To learn how to take advantage of this yourself, come to the NEURON course on Friday, Nov. 14, in Washington, DC. For the course description and online registration form, see http://www.neuron.yale.edu/dc2008.html You should act soon, because the registration deadline is Friday, October 17--just four weeks from now. In the meantime, you might want to check out the "Multithreaded simulation Q & A" on the NEURON Forum https://www.neuron.yale.edu/phpBB/viewtopic.php?f=31&t=1384 for a sense of the benefits of, and prerequisites for using, multithreaded simulations. From ppoupart at cs.uwaterloo.ca Thu Sep 18 13:23:33 2008 From: ppoupart at cs.uwaterloo.ca (Pascal Poupart) Date: Thu, 18 Sep 2008 13:23:33 -0400 Subject: Connectionists: Call for papers: NIPS-08 Workshop on Model Uncertainty and Risk in Reinforcement Learning Message-ID: <48D28E95.3020806@cs.uwaterloo.ca> Call for papers NIPS-08 Workshop on Model Uncertainty and Risk in Reinforcement Learning http://www.cs.uwaterloo.ca/~ppoupart/nips08-workshop.html Whistler, BC, Canada December 13, 2008 Important Dates --------------- * Oct 30: submission deadline * Nov 4: notification of acceptance Overview -------- Reinforcement Learning (RL) problems are typically formulated in terms of Stochastic Decision Processes (SDPs), or a specialization thereof, Markovian Decision Processes (MDPs), with the goal of identifying an optimal control policy. In contrast to planning problems, RL problems are characterized by the lack of complete information concerning the transition and reward models of the SDP. Hence, algorithms for solving RL problems need to estimate properties of the system from finite data. Naturally, any such estimated quantity has inherent uncertainty. One of the interesting and challenging aspects of RL is that the algorithms have partial control over the data sample they observe, allowing them to actively control the amount of this uncertainty, and potentially trade it off against performance. Reinforcement Learning as a field of research, has over the past few years seen renewed interest in methods that explicitly consider the uncertainties inherent to the learning process. Indeed, interest in data-driven models that take uncertainties into account, goes beyond RL to the fields of Control Theory, Operations Research and Statistics. Within the RL community, relevant lines of research may be classified into the following (partially overlapping) sub-fields: 1- Bayesian RL. Bayesian methods attempt to explicitly model uncertainties using posterior probability distributions, computed using Bayes' rule. Such Bayesian modeling may be used in estimating the MDP's transition and reward distributions; or in estimating other quantities that are more directly related to performance, such as value function and policy gradient. 2- Risk sensitive and robust dynamic decision making. These methods use information beyond the expected return, to compute policies that are robust to inaccuracies in the estimated model. Such quantities include quantiles, as well as higher order moments of the return random variable. A closely related family of methods use expectations of non-linear mappings of the return, as their measures of performance. 3- RL with confidence intervals. This research is concerned with methods that employ Frequentist measures of model uncertainties, based on confidence intervals. Much of this research is focused on on-line algorithms, whose performance is evaluated concurrently with the learning process. 4- Applications of risk-aware and uncertainty-aware decision-making. Applications in mission critical tasks, finance, and other risk-sensitive domains, where uncertainties have to be taken into account, in order to establish a level of worst-case performance, or to guarantee a minimum level of performance that may be achieved with high probability. This workshop is aimed at bringing together researchers working in these and related fields, allow them to present their current research, and discuss possible directions for future work. We intend to focus on possible interactions between the sub-fields listed above, as well as on interactions with other related fields, which are outside of the current RL mainstream. Workshop format --------------- This is a one-day workshop consisting of: 1- Invited talks 2- Contributed talks 3- Panel discussions 3.1- Models that work and those that don't: participants will discuss specific applications and theoretical models and share experience regarding the effectiveness of different approaches. 3.2- Benchmarks and challenges: discussion of some proposals for sample problems that encompass the core challenges of model uncertainty and risk sensitive control that could serve as benchmarks and/or challenges. 4- Poster session Call for Contributions ---------------------- Participants are invited to submit either a technical paper (eight pages in the conference format) or an extended abstract (up to two pages) describing research relevant to the workshop. Submissions should be sent via email to Pascal Poupart at ppoupart at cs.uwaterloo.ca by Oct 30th in Postscript, PDF, or MS Word format. Previously published work that is reworded, summarized or extended may be submitted to the workshop. However, priority will be given to novel work. If the papers are of sufficient quantity and quality, we will seek to publish them as an edited book or journal special issue. Important Dates --------------- Oct 30: submission deadline Nov 4: notification of acceptance Dec 13: workshop in Whistler Workshop webpage ---------------- http://www.cs.uwaterloo.ca/~ppoupart/nips08-workshop.html Organizing Committee -------------------- 1- Yaakov Engel (yakiengel at gmail.com) 2- Mohammad Ghavamzadeh (INRIA - Team SequeL, mgh at cs.ualberta.ca), 3- Shie Mannor (McGill University, shie at ece.mcgill.ca) 4- Pascal Poupart (University of Waterloo, ppoupart at cs.uwaterloo.ca) -- ------------------------ Pascal Poupart Assistant Professor David R. Cheriton School of Computer Science University of Waterloo 200 University Avenue West Waterloo, Ontario Canada N2L 3G1 ------------------------ Web: http://www.cs.uwaterloo.ca/~ppoupart Email: ppoupart at cs.uwaterloo.ca Telephone: 1-519-888-4567x36239 Fax: 1-519-885-1208 ------------------------ From luecke at fias.uni-frankfurt.de Fri Sep 19 07:17:35 2008 From: luecke at fias.uni-frankfurt.de (=?iso-8859-1?q?J=F6rg_L=FCcke?=) Date: Fri, 19 Sep 2008 13:17:35 +0200 Subject: Connectionists: 3 PhD Positions for Research in Machine Learning and Computer Vision Message-ID: <200809191317.35865.luecke@fias.uni-frankfurt.de> PhD positions are available for research in the following areas: * non-linear component extraction * learning in visual object memories * visual object recognition In any of the projects above we are offering positions for qualified post-graduate students. Applicants should have a Master degree (or equivalent) in Physics, Mathematics, Computer Science, Electrical Engineering or Machine Learning. Strong analytical skills and programming experiences are required for all projects. An interest in computational and biological vision as well as in neuroscience is desirable. We are interested in applicants with experience in Machine Learning and/or Computer Vision as well as in applicants who graduated in other areas. Good communication skills in English are essential. The concrete PhD projects will be defined depending on the applicants' background knowledge and research interests. The offered positions are fully funded research positions with no or a limited amount of teaching activities. We offer competitive salaries in the range of the German BAT IIa level. Research is carried out within the German Bernstein Network for Computational Neuroscience (funded by the BMBF) and in collaboration with the Honda Research Institute Europe (HRI Europe). Successful applicants will work in international and interdisciplinary research groups at the Frankfurt Institute for Advanced Studies (FIAS), Goethe-Universit?t Frankfurt, Germany. Funding is planned to start in October 2008. The positions will be filled as soon as suitable candidates are found. For further information see: http://fias.uni-frankfurt.de/~luecke/OpenPositions/OpenPositions.html Application Procedure: The review of applications will begin immediately. Required application materials: * a complete scientific curriculum vitae * a copy of Master or Diploma certificate * a short statement of research interests and achievements * letters of reference (can also be provided at a later stage of the selection process) * if possible provide a proof of proficiency in English (e.g., TOEFL or similar) Please send electronic files and scanned-in versions of documents. Files should be compiled into a ZIP archive. Please direct your application to luecke at fias.uni-frankfurt.de, send a CC to julian.eggert at honda-ri.de, and use "Application for PhD Position" as subject. -- Dr. J?rg L?cke Frankfurt Institute for Advanced Studies (FIAS) Goethe-Universit?t Frankfurt Germany From nowozin at gmail.com Mon Sep 22 09:05:42 2008 From: nowozin at gmail.com (Sebastian Nowozin) Date: Mon, 22 Sep 2008 15:05:42 +0200 Subject: Connectionists: Optimization for Machine Learning, NIPS 2008 Workshop, Call for papers Message-ID: <48D79826.6070900@gmail.com> -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: cfp-opt2008.txt Url: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080922/f892ae2a/cfp-opt2008.txt From eero at cns.nyu.edu Mon Sep 22 09:43:11 2008 From: eero at cns.nyu.edu (Eero Simoncelli) Date: Mon, 22 Sep 2008 09:43:11 -0400 Subject: Connectionists: Doctoral studies in Vision at NYU Message-ID: <2989317B-380D-4F01-94DA-EB3795AEB7B6@cns.nyu.edu> New York University is home to a thriving interdisciplinary community of researchers in the visual sciences, spanning multiple departments. A listing of faculty, sorted by their primary departmental affiliation, is given below. Doctoral programs are flexible, allowing students to pursue research across departmental boundaries. Nevertheless, admissions are handled separately by each department, and students interested in pursuing graduate studies should submit an application to the program that best fits their goals and interests. Application deadlines vary per department, as indicated below. ** Center for Neural Science (CNS) (Deadline: 12 December) [http://www.cns.nyu.edu/doctoral/] * Michael Hawken (also in Psychology) - Neuronal mechanisms of visual perception. * Lynne Kiorpes (also in Psychology) - Development of visual function. * Tony Movshon (also in Psychology) - Vision and visual development. * Bijan Pesaran - Neuronal dynamics, visuo-motor control, and decision making. * John Rinzel (also in Mathematics) - Biophysical mechanisms and theory of neural computation. * Nava Rubin (also in Psychology) - Visual perception and the neural basis of vision. * Robert Shapley (also in Psychology and Biology) - Visual physiology and perception. * Eero Simoncelli (also in Mathematics and Psychology) - Computational vision. ** Psychology, Cognition & Perception program (Deadline: 18 December) [http://www.psych.nyu.edu/programs/cp/] * Marisa Carrasco (also in CNS) - Visual perception and attention. * David Heeger (also in CNS) - fMRI, computational neuroscience, vision, attention. * Michael Landy (also in CNS) - Computational approaches to vision. * Laurence Maloney (also in CNS) - Mathematical approaches to psychology and neuroscience. * Denis Pelli (also in CNS) - Object recognition. ** Computer Science (Deadline: 4 January) [http://www.cs.nyu.edu/web/Research/Areas/graphicsvisionui.html] * Chris Bregler - human motion modeling, computer vision, machine learning. * Rob Fergus - computer vision, machine learning, computer graphics. * Davi Geiger (also in CNS) - Computational vision and learning. * Yann LeCun - machine learning, hierarchical visual processing, robotics. ** Mathematics (Deadline: 18 December) [http://math.nyu.edu/degree/phd/] * David Cai - Nonlinear stochastic behavior in physical and biological systems. * David McLaughlin (also CNS) - Nonlinear wave equations, computational visual neuroscience. * Aaditya Rangan - computational neurobiology, numerical analysis. * Michael Shelley (also CNS) - Modeling and large-scale computation, computational visual neuroscience. ** Biology (Deadline: 12 December) [http://biology.as.nyu.edu/page/graduate.program] * Claude Desplan (also CNS) - Molecular/genetic basis for development, particularly color vision circuitry. * Daniel Tranchina (also Mathematics and CNS) - Information processing in the retina. ** Philsophy (Deadline: 4 January) [http://philosophy.fas.nyu.edu/page/graduate] * Ned Block (also psychology and CNS) - Foundations of consciousness. From jerryzhu at cs.wisc.edu Sat Sep 20 22:46:11 2008 From: jerryzhu at cs.wisc.edu (jerryzhu@cs.wisc.edu) Date: Sat, 20 Sep 2008 21:46:11 -0500 (CDT) Subject: Connectionists: Call for Posters: NIPS 2008 Workshop on Machine Learning Meets Human Learning Message-ID: <3038.75.100.86.252.1221965171.squirrel@webmail.cs.wisc.edu> NIPS 2008 Workshop on Machine Learning Meets Human Learning http://pages.cs.wisc.edu/~jerryzhu/nips08.html Whistler, Canada December 12, 2008 Description ----------- Can statistical machine learning theories and algorithms help explain human learning? Broadly speaking, machine learning studies the fundamental laws that govern all learning processes, including both artificial systems (e.g., computers) and natural systems (e.g., humans). It has long been understood that theories and algorithms from machine learning are relevant to understanding aspects of human learning. For example, hierarchical Bayesian models provide a way to understand how people could maintain uncertainty at different levels of abstraction; neural networks have been a valuable tool for psychologists as a computational model of the way brains learn; reinforcement learning agrees well with the neural activity of dopaminergic neurons during reward-based learning; and sparse representations in computer vision predict well the visual features found in the early visual cortex. Human cognition also carries potential lessons for machine learning research, since people still learn languages, concepts, and causal relationships from far less data than any automated system. There is a rich opportunity to develop a general theory of learning which covers both machines and humans, with the potential to deepen our understanding of human cognition and to take insights from human learning to improve machine learning systems. This workshop will consist of invited talks and contributed posters. The goal is to bring together the different communities that study machine learning, cognitive science, neuroscience and educational science. First, we seek to provide researchers with a common grounding in the study of learning, by translating different disciplines' proprietary knowledge, specialized methods, assumptions, goals into shared terminologies and problem formulation. Second, we will investigate the value of advanced machine learning theories and algorithms as computational models for certain human learning behaviors, including, but not limited to, the role of prior knowledge, learning from labeled and unlabeled data, learning from active queries, and so on. Finally, we wish to explore the insights from the cognitive study of human learning to inspire novel machine learning theories and algorithms. It is our hope that the NIPS workshop will provide a venue for cross-pollination of machine learning approaches and cognitive theories of learning to spur further advances in both areas. The 1-day workshop consists of invited talks, poster sessions, and panel discussions. Workshop webpage ---------------- http://pages.cs.wisc.edu/~jerryzhu/nips08.html Call for Poster Contributions ----------------------------- We invite poster submissions on all topics at the interface of machine learning and human learning. Please submit a 200-word to one-page extended abstract via email to Xiaojin Zhu (jerryzhu at cs.wisc.edu). The abstract must be in either plain text or PDF. Please include "NIPS Workshop Abstract" in the subject of your email. Important Dates --------------- * Poster Abstract Submission Date: Oct. 10, 2008 * Notification of Poster Acceptance: Oct. 17, 2008 * Workshop date: December 12, 2008 Organizers ---------- * Nathaniel Daw (New York University). * Tom Griffiths (Berkeley). * Josh Tenenbaum (MIT). * Xiaojin (Jerry) Zhu (University of Wisconsin-Madison). From bengioy at iro.umontreal.ca Fri Sep 19 09:26:31 2008 From: bengioy at iro.umontreal.ca (Yoshua Bengio) Date: Fri, 19 Sep 2008 09:26:31 -0400 Subject: Connectionists: Learning algorithms for deep AI architectures: open positions Message-ID: <7E707FC5-DB34-42F4-B1C3-494A7327410F@iro.umontreal.ca> Graduate studies and post-doctoral fellowships in learning algorithms for deep AI architectures Post-doctoral fellowships, studentships (Master and PhD) and Masters- level internships are available at the University of Montreal LISA group with faculty Yoshua Bengio, Douglas Eck, and Pascal Vincent, and research scientist Aaron Courville, to study deep learning. Join our vibrant community! Counting students, our lab includes over twenty passionate researchers working together to build better AI using deep architectures. * How do we get computers to have vision as good as humans? * How do we get computers to talk with humans in human language? * How do we get computers to understand and compose music as well as humans? * Can we get inspiring ideas from the natural world? from the brain? from child development? from human and animal learning? Deep architectures mimic how the brain works by decomposing intelligence into a processing hierarchy with multiple levels of abstractions representing concepts that the computer learns mostly by itself. Deep learning is a relatively new trend in artificial intelligence and we believe it is key to solve longstanding problems in machine vision and natural language processing. See Yoshua's research page and www.iro.umontreal.ca/~lisa/deepLearning for more details and pointers. See also the NSF's recent appraisal of the importance of this research. Applicants typically have a background in computer science or mathematics but interdisciplinary perspectives are welcome. Mathematical skills (especially probability, linear algebra, statistics and optimization) are important for understanding and analyzing learning algorithms. We value creative individuals interested in working with others. At the University of Montreal, courses are generally given in French with the option for turning in homework, exams and theses/ dissertations in English. Within the LISA group, the language is typically English. Of course, many English-speaking students have learned French in the course of their studies and through subsidized French classes. Please get in touch for more information! Yoshua Bengio (dot) (at sign) umontreal (dot) ca http://www.iro.umontreal.ca/~bengioy From BerndPorr at f2s.com Fri Sep 19 08:34:11 2008 From: BerndPorr at f2s.com (Bernd Porr) Date: Fri, 19 Sep 2008 13:34:11 +0100 Subject: Connectionists: UK/EU student for a PhD in computational neuroscience Message-ID: <48D39C43.7070605@f2s.com> Dear all, I'm looking for a PhD in computational neuroscience who has excellent skills in C programming. He/her task would be to add spike timing dependent plasticity (and beyond) to GENESIS. Funding is available for UK students and outstanding EU students. Please contact me for further information. /Bernd Porr -- www: http://www.berndporr.me.uk/ http://www.linux-usb-daq.co.uk/ Mobile: +44 (0)7840 340069 Work: +44 (0)141 330 5237 University of Glasgow Department of Electronics & Electrical Engineering Room 519, Rankine Building, Oakfield Avenue, Glasgow, G12 8LT From bard at math.pitt.edu Fri Sep 19 09:00:39 2008 From: bard at math.pitt.edu (G. Bard Ermentrout) Date: Fri, 19 Sep 2008 09:00:39 -0400 (EDT) Subject: Connectionists: postdoctoral position available in math neuro Message-ID: Announcing a postdoc position at University of Pittsburgh Postdoctoral position available immediately for computational neuroscience. Topics of interest include but are not restricted to modeling spontaneous activity, waves, and synchronous oscillations in neuronal models and phase reseting curves in noisy and complex milieus. Applicants should have a good knowledge of basic concepts in nonlinear dynamics and a strong interest in applying this to neurobiological problems. Knowledge of neurosceince is useful but not necessary. The ability to write simulation code (either in MatLab, XPP, or C/C++) is also useful. This position is NSF funded for two years, and a competitive salary is available for qualified candidates. Pittsburgh is a medium-sized city with a relatively low cost of living and many of the amenities and cultural opportunities of a larger city. The Neuroscience community in Pittsburgh is large and very diverse with more than 100 faculty members affiliated with the Center for Neuroscience at the University of Pittsburgh ( CNUP ). Successful candidates would also have the opportunity to join the Center for the Neural Basis of Cognition ( CNBC ) which is a joint University of Pittsburgh/CMU center that involves 70 Faculty from the two Universities. Interested candidates should send (preferably via e-mail) their c.v. and the names and addresses of three references to Professor Bard Ermentrout, Department of Mathematics, University of Pittsburgh Pittsburgh, PA 15260 e-mail: bard at pitt.edu For more information contact: Dr. Bard Ermentrout bard at pitt.edu http://www.pitt.edu/~phase/ From petrosino at uniparthenope.it Tue Sep 23 05:58:53 2008 From: petrosino at uniparthenope.it (Alfredo Petrosino) Date: Tue, 23 Sep 2008 11:58:53 +0200 Subject: Connectionists: Research Fellow in Machine Learning for Signal and Video Processing Message-ID: <48D8BDDD.9020908@uniparthenope.it> Research Fellow in Machine Learning for Signal and Video Processing CVPRLab Research Group, Department of Applied Science, University of Naples Parthenope, Italy http://cvprlab.uniparthenope.it/ The CVPRLab research group offers a research position to a highly motivated and skilled international candidate. The CVPRLab is a well established research group in Computer Vision and Pattern Recogntion and has developed mainly skills in high level image processing domains, such as the management of knowledge description and learning capabilities for vision tasks. Research areas are actually Soft Computing in Image Analysis, Structured Pattern Recognition, Intelligent Processing of Spatio-temporal signals, Videosurveillance. The position will develop and apply novel machine learning, soft computing and computer vision algorithms within the context of the MIUR- FIRB Project IntelliLogic (cod. RBIPO6MMBW), started on January 2nd 2008 and funded by Minister of Education, University and Research of Italy. The project is aimed at developing and integrating innovative computational intelligence techniques inside an IT platform for logistics. The open position will operate in the areas of attention based visual learning, temporal classification of human activity from multimodal data, temporal segmentation of human behavior, spatio-temporal signal mining. The candidate is expected to hold a Master's degree in computer science, mathematics or a closely related field. Candidates should have a research and professional skill in at least one of the following areas: machine learning, signal/video processing, computer vision, but at least a very solid programming skill and a solid mathematical background are required. The research position is for 3 years, on the basis of 1 year renewal. The yearly total of research grants is Euro 23.900,00 that includes all social contributions to be paid by the employer. The deadline for application is 27 October 2008. Details and the application form may be found at http://www.uniparthenope.it/personale/ccc/dsa04-08_i.pdf. Further enquires may be submitted by email to Prof Alfredo Petrosino: alfredo.petrosino at uniparthenope.it, coordinator of the MIUR-FIRB Project "IntelliLogic". ----------- Alfredo Petrosino Department of Applied Science University of Naples "Parthenope" Centro Direzionale Isola C4 I-80133 Naples, ITALY Phone: +39 081 5476601 Fax: +39 081 5476513 Email: alfredo.petrosino at uniparthenope.it From oksayakh at cs.iastate.edu Tue Sep 23 13:03:51 2008 From: oksayakh at cs.iastate.edu (Oksana Yakhnenko) Date: Tue, 23 Sep 2008 12:03:51 -0500 Subject: Connectionists: Call for papers: NIPS 2008 Workshop on Cost-Sensitive Learning Message-ID: <6CC0B77691C54CA5A5809B7F25E0CFE3@OksanaPC> ==Call for Papers: NIPS 2008 Workshop on Cost-Sensitive Learning== http://www.cs.iastate.edu/~oksayakh/cslworkshop_nips2008.html Description and background ------------------------ The goal of cost-sensitive learning is to minimize data acquisition costs while maximizing the accuracy of the learner/predictor. Many fields in machine learning attempt to solve cost-sensitive learning with strong simplifying assumptions. For example, in semi-supervised learning, class-labels are assumed to be expensive and features are implicitly assumed to have zero cost. In active learning, labels are again assumed to be expensive; however the learner may ask an oracle to reveal a label for unlabeled data for selected examples. Active feature acquisition assumes that obtaining features is expensive (but typically all features are assumed to be equally expensive), and the learner identifies instances for which complete information is most informative to classify a particular test sample. Inductive transfer learning and domain adaptation methods assume that training data for a particular task is expensive or but other data from other domains may be cheaper (although relative costs are usually not explicitly modeled). Cascaded classifier architectures are primarily designed in order to reduce the cost of acquiring features to classify a sample (a sample may be classified the moment the available data is sufficient to provide sufficient classification confidence, without waiting for all features to be obtained). There is an important but neglected common thread linking all of these different research communities. In particular, all these learning methods are motivated by the need to minimize the cost of data acquisition in many different application domains such as computer-aided medical diagnosis, computational linguistics, computational biology, and computer vision. Although all of these areas have felt the need for a principled solution to the problem, the partial solutions that have tried to solve the problem (eg semi-supervised learning, active learning, multi-task inductive transfer etc) rarely model the cost explicitly, and very little effort has been expended on modeling application specific characteristics. Recently to some papers have started modeling the acquisition costs directly, but there is a lot of scope for theoretically rigorous work on this topic. It is also important to explicitly model the requirements from real world application communities and to bridge it with the work on theory/algorithms. Goals --------------- The goal of the workshop is to bring together researchers interested in the application of cost-sensitive learning (computer vision, natural language processing, computer-aided diagnostics, computational biology) with researchers interested in theory & algorithms for learning when data acquisition is costly. The main aim is to focus attention on a practically important problem where practitioners have long sought theoretically sound algorithms but which has not been sufficiently addressed in the literature. A secondary goal is to bring together ideas from semi-supervised learning, active learning, feature acquisition, inductive transfer learning and other areas, in order that there may be more exchange of ideas across these (extremely active) communities. Topics of Interest ------------------------ We welcome both novel theory/algorithms and papers that highlight open problems and challenges in real-world applications which call for cost sensitive learning. Submissions on following topics are particularly encouraged: Algorithms/Theory: -active learning -semi-supervised learning -transfer learning -reinforcement learning -domain adaptation, -cascaded classifier learning -...and related. Applications which call for cost-sensitive learning: -computer vision -computational linguistics -natural language processing -computer-aided diagnosis -differential medical diagnosis -...and others. Paper submission ------------------------ We welcome papers of up to 8 pages in the NIPS 2008 format. The accepted papers will be available for downloading from the workshop website. Accepted papers will be either presented as a talk or poster (with poster spotlight). Papers should be emailed to the organizers at cslworkshop.nips.2008 at gmail.com. Please indicate whether you only wish to present a poster. Important Dates ------------------------ Deadline for submissions: October 17, 2008 Notification of acceptance: November 7, 2008 Workshop date: December 13, 2008 Organizers ------------------------ Balaji Krishnapuram (Siemens Medical Solutions USA) Shipeng Yu (Siemens Medical Solutions USA) Oksana Yakhnenko (Iowa State University) R. Bharat Rao (Siemens Medical Solutions USA) Lawrence Carin (Duke University) Invited Speakers ------------------------ John Shawe-Taylor (University College, London) Volker Tresp (University of Munich) Program Committee ------------------------ Chiru Bhattacharya (IISc, Bangalore) Rich Caruana (Cornell) Mario Figueiredo (IST, Portugal) Yves Grandvalet (UTC, France) Yan Liu (IBM) Prem Melville (IBM) Sunita Sarawagi (IIT Bombay) Fei Sha (USC & Yahoo research) Volker Tresp (Siemens) Kai Yu (NEC Research) Ulf Brefeld (Technische Universitaet, Berlin) Steffen Bickel (Max Planck Institute of Computer Science) Vikas Sindhwani (IBM) Johannes F?rnkranz (Darmstadt University) John Shawe-Taylor (University College, London) Sanjoy Dasgupta (University of California, San Diego) Steven Abney (University of Michigan) -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080923/3749e976/attachment.html From joanneti at usc.edu Sun Sep 21 13:19:57 2008 From: joanneti at usc.edu (Jo-Anne Ting) Date: Sun, 21 Sep 2008 10:19:57 -0700 Subject: Connectionists: Call for Abstracts: Workshop for Women in Machine Learning 2008 Message-ID: CALL FOR STUDENT ABSTRACTS Workshop for Women in Machine Learning Co-located with NIPS, Vancouver, BC December 8, 2008 http://www.wimlworkshop.org Deadline for student abstract submissions: October 10, 2008 INTRODUCTION Machine learning is one of the fastest growing areas of computer science research. Search engines, face recognition, DNA sequence analysis, speech and handwriting recognition, credit card fraud detection, premature baby monitoring and autonomous locomotion are just some of the applications in which machine learning is routinely used. In spite of the wide reach of machine learning and the variety of theory and applications it covers, the percentage of female researchers is lower than in many other areas of computer science. Most women working in machine learning rarely get the chance to interact with other female researchers, making it easy to feel isolated and hard to find role models. This day-long workshop gives female faculty, research scientists, and graduate students in the machine learning community an opportunity to meet, exchange ideas and learn from each other. Underrepresented minorities and undergraduates interested in pursuing machine learning research are encouraged to participate. A limited number of scholarships will be available for students to offset travel costs. Workshop registration is free. WORKSHOP FORMAT The one-day workshop will consist of talks by established researchers, a poster session for graduate students to showcase their research, and panel discussions to address current research trends and career choices in machine learning. STUDENT ABSTRACT SUBMISSION We strongly encourage female students in all areas of machine learning to submit an abstract (500 words or less) describing either new or previously published research. Authors of accepted abstracts will be asked to present their work in a poster session. Abstracts should be submitted via the workshop website: http://www.wimlworkshop.org IMPORTANT DATES Abstract submission deadline: October 10, 2008 Notification of acceptance: October 24, 2008 Registration deadline: November 15, 2008 Pre-workshop dinner: December 7, 2008 Workshop: December 8, 2008 ORGANIZERS Luiza Antonie, University of Alberta Anna Koop, University of Alberta Jo-Anne Ting, University of Southern California Joelle Pineau, McGill University (faculty advisor) From dechter at ics.uci.edu Wed Sep 24 01:54:45 2008 From: dechter at ics.uci.edu (Rina Dechter) Date: Tue, 23 Sep 2008 22:54:45 -0700 Subject: Connectionists: Results for UAI 2008 evaluation Message-ID: <48D9D625.705@ics.uci.edu> Dear colleagues, We are pleased to announce that the web-based report for the UAI 2008 evaluation is now available: http://graphmod.ics.uci.edu/uai08/Evaluation/Report The report presents the environment and setup for this year's evaluation and the results obtained. The evaluation was conducted prior to the UAI conference and the results were presented during the conference. The report compiles data for a number of evaluation measures that concern both exact and approximate inference, with analysis and discussion of these measures planned for a later stage. We welcome any feedback you might have. Rina and Adnan -- Rina Dechter dechter at ics.uci.edu Bren School of Information and Computer Sciences (949) 824-6556 University of California, Irvine fax: (949)-824-4056 Irvine, CA 92697-3425 http://www.ics.uci.edu/~dechter From dglanzma at mail.nih.gov Wed Sep 24 13:40:15 2008 From: dglanzma at mail.nih.gov (Glanzman, Dennis (NIH/NIMH) [E]) Date: Wed, 24 Sep 2008 13:40:15 -0400 Subject: Connectionists: Dynamical Neurosceince: Agenda and Final Call for Posters Message-ID: <0EE5F9DA83318D47B16FB45A5CBA4A4A02C189B5@nihcesmlbx2.nih.gov> 16th Annual Dynamical Neuroscience Satellite Symposium "Neuronal Variability and Its Functional Significance" FINAL CALL FOR POSTERS Abstract Deadline October 17, 2008 Preceding the 38th Annual Meeting of the Society for Neuroscience Thursday and Friday, November 13-14, 2008 The Capital Ballroom of the JW Marriott Hotel 1331 Pennsylvania Ave. NW Washington, DC The brain is restless. Physiological data recorded from the brain often have random-appearing components. Repeated stimuli evoke responses that are not identical from trial to trial. Not too long ago this variability was dismissed as noise and, through techniques such as signal averaging, removed from further consideration. More recent work has begun to examine the rich content of this variability and shed light on its functional consequences. Neural variability and noise has become an active field of research, generating a wealth of new knowledge and information. This symposium will assess the current status of four related areas: Characterizing Neuronal Variability Larry Abbott, Columbia University, Contrasting Internal and External Sources of Variability Emery Brown, MIT & Harvard, How Well Do We Know What Single Neurons Do? Dynamics of Neuronal Ensembles Henry Abarbanel, UC San Diego, Dissecting and Modeling Neurobiological Networks: Dynamical Electrophysiology Anna Roe, Vanderbilt University, Beyond Correlated Noise: Evidence for Intra- and Inter-Areal Baseline Biases in Temporal Coincidence Neuronal Variability and Cognition Daeyeol Lee, Yale University School of Medicine, Order and Chaos in Decision Making Akaysha Tang, University of New Mexico, Top-Down Versus Bottom-up Processing in the Human Brain: Distinct Directional Influences Revealed by Integrating Second-Order Blind Identification and Granger Causality Charles Gray, Montana State University, Dynamics of Cortico-Cortical Interactions in the Macaque Charles Schroeder, Columbia University, Neuronal Oscillations as Instruments of Sensory Selection Stephen Lisberger, UC San Francisco, Variation, Signal, And Noise in the Neural Circuit for Smooth Pursuit Eye Movements Neuronal Variability and Brain Disorders Helen Mayberg, Emory University School of Medicine, Modulating Depression Circuits Using Deep Brain Stimulation Terran Lane, University of New Mexico, Population Variability and Bayesian Inference Richard Stein, University of Alberta, Canada, Coding of Sensory Information about Limb Position Richard Coppola, NIMH, Bethesda, MEG Dynamic Methods in Neuropsychiatric Research Nicholas Schiff, Weill Cornell Medical College, The role of the central thalamus in behavioral variability following severe brain injury: Circuit mechanisms and potential interventions Keynote Address Presented by the inaugural recipient of the Swartz Prize for Theoretical and Computational Neuroscience Organizers: Mingzhou Ding, University of Florida and Dennis Glanzman, NIMH/NIH For programmatic information, please contact: D. Glanzman National Institute of Mental Health 6001 Executive Boulevard, Rockville, MD 20857 Telephone: (301) 443-1576 Register for the meeting, and to submit a poster abstract (October 17 deadline for abstracts) here: http://neuro.dgimeetingsupport.com, or, contact: Nakia Wilson Telephone: (877) 772-9111 From antonsc at microsoft.com Fri Sep 26 12:41:47 2008 From: antonsc at microsoft.com (Anton Schwaighofer) Date: Fri, 26 Sep 2008 17:41:47 +0100 Subject: Connectionists: CFP: NIPS*2008 Workshop "Beyond Search: Computational Intelligence for the Web", Dec 12-13, 2008 Message-ID: <9030628CBC5BA04C9C5AA5D36054AFDE14EB90D141@EA-EXMSG-C330.europe.corp.microsoft.com> Call for Abstracts Workshop "Beyond Search: Computational Intelligence for the Web" December 12-13, 2008, Whistler, BC, Canada http://research.microsoft.com/osa/adCenter/beyond_search ---------------------------------------------------------------- = Important Dates = * Submission Date: October 31st, 2008 * Notification of Acceptance: November 7, 2008 * Date of presentation: December 12 or 13th, 2008 = Call for Abstracts = The organizing committee is seeking contributions for a two-day workshop held in conjunction with NIPS*2008, a premier conference for machine learning research. The goal of the workshop is to advance the state-of-the-art in research related to the world wide web, and in particular foster discussion and work across the typical disciplinary boundaries. Contributions that demonstrate work related to the web in the following areas are welcome: * Machine learning and probabilistic modelling * Game theory, auction and mechanism design * Knowledge representation and reasoning * Social networks and collective intelligence * Privacy and privacy preserving learning We will give preference to submissions that link two or more of the above topics. The workshop format is a mix of discussion sessions, presentation of submitted work, and talks by invited speakers. Confirmed invited speakers are Chris Burges (Microsoft Research), Pedro Domingos (U Washington), Michael Schwarz (Yahoo), Tarek Najm (Microsoft), Doug Lenat (CyCorp), and Edward Chang (Google). = Submission Information = Please submit a 2-page extended abstract of your work. Detailed submission instructions and further information can be found on the workshop homepage, http://research.microsoft.com/osa/adCenter/beyond_search/ Authors of accepted contributions will be invited to give a 20-minute presentation at the workshop. = Organizers = * Anton Schwaighofer (primary contact. Microsoft Research) * Junfeng Pan (Google) * Thomas Borchert (Microsoft Research) * Olivier Chapelle (Yahoo) * Joaquin Qui?onero Candela (Microsoft Research) -- Anton Schwaighofer, Applied Researcher, Online Services and Advertising, Microsoft Research Ltd., 7 J J Thomson Avenue, Cambridge, CB3 0FB, UK, Tel: +44 (0)1223 479 700, Fax: +44 (0)1223 479 999 From gal.chechik at gmail.com Tue Sep 30 16:00:37 2008 From: gal.chechik at gmail.com (Gal Chechik) Date: Tue, 30 Sep 2008 13:00:37 -0700 Subject: Connectionists: Call for papers: NIPS-08 Workshop on Machine Learning in Computational Biology Message-ID: <8f229dfc0809301300o6c3d42beu40c88e8c9db02a3a@mail.gmail.com> Call for contributions New Problems and Methods in Computational Biology http://www.mlcb.org A workshop at the Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS 2008) Whistler, BC, Canada, December 12, 2008. Deadline for submission of extended abstracts: October 12, 2008 WORKSHOP DESCRIPTION The field of computational biology has seen dramatic growth over the past few years, in terms of newly available data, new scientific questions and new challenges for learning and inference. In particular, biological data is often relationally structured and highly diverse, and thus requires combining multiple weak evidence from heterogeneous sources. These sources include sequenced genomes of a variety of organisms, gene expression data from multiple technologies, protein sequence and 3D structural data, protein interaction data, gene ontology and pathway databases, genetic variation data (such as SNPs), and an enormous amount of text data in the biological and medical literature. These new types of scientific and clinical problems require novel supervised and unsupervised learning approaches that can use these growing resources. The workshop will host presentations of emerging problems and machine learning techniques in computational biology. We encourage contributions describing either progress on new bioinformatics problems or work on established problems using methods that are substantially different from standard approaches. Kernel methods, graphical models, feature selection and other techniques applied to relevant bioinformatics problems would all be appropriate for the workshop. This year the workshop will follow a mini-symposium on Computational Biology that will take place in Vancouver on the afternoon of Thursday Dec 11th. SUBMISSION INSTRUCTIONS Researchers interested in contributing should upload an extended abstract of 1-6 pages in PDF format to the MLCB submission web site http://www.easychair.org/conferences/?conf=mlcb2008 by October 12, 2008, 11:59pm (Samoa time). No special style is required. Authors may use the NIPS style file, but are also free to use other styles as long as they use standard font size (11-12 pt) and standard margins (same as the NIPS style file). All submissions will be anonymously peer reviewed and will be evaluated on the basis of their technical content. A strong submission to the workshop typically presents a new learning method that yields new biological insights, or applies an existing learning method to a new biological problem. However, submissions that improve upon existing methods for solving previously studied problems will also be considered. Examples of research presented in previous years can be found online at www.fml.tuebingen.mpg.de/nipscompbio/previous. Please note that accepted abstracts will be posted online at www.mlcb.org. Authors may submit two versions of their abstract, a longer version for review and a shorter version for posting to the web page. In addition, presentations will be video taped and published online as part of the videolectures.net website supported by Pascal. The workshop allows submissions of papers that are under review or have been recently published in a conference or a journal. This is done to encourage presentation of mature research projects that are interesting to the community. The authors should clearly state any overlapping published work at time of submission. Authors of accepted abstracts will be invited to submit full length versions of their contributions for publication in a special issue of BMC Bioinformatics. ORGANIZERS Gal Chechik, Google Research Christina Leslie, Memorial Sloan-Kettering Cancer Center William Stafford Noble, Department of Genome Sciences, University of Washington Gunnar Raetsch, Friedrich Miescher Laboratory of the Max Planck Society (Tuebingen, Germany) Quaid Morris, Terrence Donnelley Centre for Cellular and Biomolecular Research, University of Toronto PROGRAM COMMITTEE Pierre Baldi, UC Irvine Kristin Bennett, Rensselaer Polytechnic Institute Mathieu Blanchette, McGill University Florence d'Alche, Universite d'Evry-Val d'Essonne, Genopole Eleazar Eskin, UCLA Brendan Frey, University of Toronto Nir Friedman, The Hebrew University of Jerusalem Michael I. Jordan, UC Berkeley Alexander Hartemink, Duke University David Heckerman, Microsoft Research Michal Linial, The Hebrew University of Jerusalem Klaus-Robert Mueller, Fraunhofer FIRST Uwe Ohler, Duke University Dana Pe'er, Columbia University Alexander Schliep, Max Planck Institute for Molecular Genetics Bernhard Schoelkopf, Max Planck Institute for Biological Cybernetics Eran Segal, The Weizmann Institute Jean-Philippe Vert, Ecole des Mines de Paris Eric Xing, Carnegie Mellon University From terry at salk.edu Mon Sep 29 18:30:43 2008 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 29 Sep 2008 15:30:43 -0700 Subject: Connectionists: NEURAL COMPUTATION - November, 2008 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 20, Number 11 - November 1, 2008 Article Latent Features in Similarity Judgments: A Nonparametric Bayesian Approach Daniel Navarro and Thomas Griffiths Note Deep Narrow Sigmoid Belief Networks are Universal Approximators Ilya Sutskever and Geoffrey Hinton Letters Exact Solutions for Rate and Synchrony in Recurrent Networks of Coincidence Detectors Ernst Niebur and Shawn Mikula Mutual Information Expansion for Studying the Role of Correlations in Population Codes: How Important Are Auto-Correlations? Guglielmo Foffani, Alessandro Scaglione, Guilio Scannella, Sergio Cerutti, and Karen Moxon Parameters of the Diffusion Leaky Integrate-And-Fire Neuronal Model for a Slowly Fluctuating Signal Umberto Picchini, Susanne Ditlevsen, Andrea DeGaetano, and Petr Lansky Faithful Representation of Stimuli with a Population of Neurons Aurel Lazar and Eftychios Pnevmatikakis Just in Time Connectivity for Large Spiking Networks William Lytton, Ahmet Omurtag, Samuel Neymotin, Michael Hines Simultaneous Approximations of Polynomials and Derivatives and Their Applications to Neural Networks Yoshifusa Ito Boosting Method for Local Learning in Statistical Pattern Recognition Masanori Kawakita and Shinto Eguchi A Scalable Kernel-Based Semi-Supervised Metric Learning Algorithm with Out-of-Sample Generalization Ability Dit-Yan Yeung, Hong Chang, and Guang Dai ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2009 - VOLUME 21 - 12 ISSUES USA/Canada Others Electronic only Student/Retired $60 $123 $54 Individual $110 $173 $99 Institution $849 $912 $756 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 wjma at cpu.bcm.edu Wed Sep 24 11:03:26 2008 From: wjma at cpu.bcm.edu (Wei Ji Ma) Date: Wed, 24 Sep 2008 10:03:26 -0500 Subject: Connectionists: Postdoc in computational neuroscience Message-ID: <48071F74CBAD5B46973B3D2B90179BCB5D30@stan.hou-ad.hnl.bcm.tmc.edu> Applications are invited for a postdoctoral position (minimum 2 years) in the laboratory of Dr. Wei Ji Ma (http://neuro.bcm.edu/malab) in the Department of Neuroscience at Baylor College of Medicine, Houston, Texas. The long-range goal of our research is to understand the representation and processing of uncertainty in the human brain, both at the behavioral and at the neural level. The lab uses a combination of theoretical analysis, computational modeling, and theory-driven human experiments. Current areas of study include multisensory perception, decision-making, and visual search. The position provides an opportunity to take part in highly collaborative research programs within the Computational Psychiatry Unit (http://cpu.bcm.edu ) and the Department of Neuroscience as a whole. Applicants should have a Ph.D. in computational neuroscience, physics, mathematics, computer science, or a related field, and have a commitment to a research career in neuroscience. Programming experience with Matlab or C++ is very desirable. To apply, please send CV, statement of interest, and the names and contact information of two references to Wei Ji Ma at wjma at bcm.edu. Consideration of applications will begin immediately, and will end when the position is filled. Salary is competitive and will be commensurate with experience and qualifications. Baylor College of Medicine is an Equal-Opportunity, Affirmative-Action, and Equal-Access Employer. -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080924/ca7a3240/attachment.html From d.mandic at imperial.ac.uk Wed Sep 24 06:51:17 2008 From: d.mandic at imperial.ac.uk (Danilo Mandic) Date: Wed, 24 Sep 2008 11:51:17 +0100 Subject: Connectionists: New book on signal processing for information fusion Message-ID: <48DA1BA5.5060609@imperial.ac.uk> Our new edited book may be of interest for people active in the fusion of heterogeneous data for biomedical applications and brain computer interfaces. "Signal Processing Techniques for Knowledge Extraction and Information Fusion", Springer 2008. http://www.amazon.com/Processing-Techniques-Extraction-Information-Technology/dp/0387743669/ref=sr_1_1?ie=UTF8&s=books&qid=1222252907&sr=1-1 From the back cover: This book brings together the latest research achievements from various areas of signal processing and related disciplines in order to consolidate the existing and proposed new directions in DSP based knowledge extraction and information fusion. Within the book contributions presenting both novel algorithms and existing applications, especially those (but not restricted to) on-line processing of real world data are included. The areas of Knowledge Extraction and Information Fusion are naturally linked and aim at detecting and estimating the signal of interest and its parameters, and further at combining measurements from multiple sensors (and associated databases if appropriate) to achieve improved accuracies and more specific inferences which cannot be achieved by using only a single signal modality. The subject therefore is of major interest for modern biomedical, environmental, and industrial applications to provide a state of the art and propose new techniques in order to combine heterogeneous information sources. Enjoy! Danilo --------------------- Dr Danilo P. Mandic Department of Electrical and Electronic Engineering Imperial College London, UK From hava at cs.umass.edu Wed Sep 24 10:03:10 2008 From: hava at cs.umass.edu (Hava Siegelmann) Date: Wed, 24 Sep 2008 10:03:10 -0400 Subject: Connectionists: Position available for post-doc in Dynamical systems/ computational brain In-Reply-To: References: Message-ID: <48DA489E.6060403@cs.umass.edu> BINDS lab at the University of Massachusetts is looking to hire a Post-doctorate member in the areas of Dynamical Systems, Flexible Decision Making, and Memory Background: Statistics, probability, dynamical systems analysis, Machine learning, clustering and classification, computational neuro-science. The work will be related to various cognitive abilities and disorders developing in healthy and in affected memory and on systems pertaining to saliency and inhibition, application in addiction and diseases of the will. The position is available for 3 years but will be termed as a yearly position with an evaluation at the end of the year and continuation based on mutual interest. Questions about more details and applications (with CV, cover letter, names of references, research statement) can be referred to Hava Siegelmann at hava at cs.umass.edu . -- Hava T. Siegelmann http://www.cs.umass.edu/~hava/ From hava at cs.umass.edu Wed Sep 24 09:39:16 2008 From: hava at cs.umass.edu (Hava Siegelmann) Date: Wed, 24 Sep 2008 09:39:16 -0400 Subject: Connectionists: two PhD students positions available In-Reply-To: <46D44A4A00000A57@cheetah-1.jrc.it> References: <46D44A4A00000A57@cheetah-1.jrc.it> Message-ID: <48DA4304.9060602@cs.umass.edu> BINDS lab at the University of Massachusetts is looking to hire two PhD students: 1. Research in Computational Neural Networks and Memory Background: Dynamical systems, Machine learning, Statistics or Bio-statistics, Algorithms, Probability. Plus: computational neuroscience, neural networks 2. Research in Drug Addiction and Diseases of the Will Background: Programming, Dynamical systems, Machine learning, Information systems, Statistics, Algorithms. Plus: Neuroscience Please Contact Hava Siegelmann at hava at cs.umass.edu -- Hava T. Siegelmann http://www.cs.umass.edu/~hava/ From oba at sys.i.kyoto-u.ac.jp Wed Sep 24 22:29:13 2008 From: oba at sys.i.kyoto-u.ac.jp (Shigeyuki Oba) Date: Thu, 25 Sep 2008 11:29:13 +0900 Subject: Connectionists: Postdoctoral Positions - Visuo-Motor Network Simulation Message-ID: Postdoctoral Researchers and Scientific Programmers Brain and Neural Systems Team Integrated Life Simulation Project The goal of the Brain and Neural Systems Team of the Integrated Life Simulation Project is to understand how the brain achieves adaptive behaviors by re-creating the nervous system through integrating neurobiological data available at multiple-levels spanning from genes and molecules to neurons and behaviors. As the first step toward a whole-brain simulation of the human brain, the Visuo-Motor Network Group focuses on the network linking retinal input to eye-movement output, for which rich accumulation of neurobiological knowledge, experimental data, and computational models are available. The simulation model aims to reproduce natural eye-movement behaviors in a real visual environment by integrating the molecular mechanisms for synaptic plasticity, the cellular mechanisms for network development and adaptation, and the network mechanisms for attention and motivation. The research project is sponsored by the Next-Generation Supercomputer Project of the Japanese Ministry of Education, Culture, Sports, Science and Technology (MEXT). The major goals in its first phase from FY2008 to 2010 are the following: 1) to set up a multi-scale neural simulation environment for linking dynamics at molecular, neuronal, and network levels; 2) to construct a model linking the retina, the superior colliculus, the oculomotor nuclei and the cerebellum to replicate spontaneous and visually evoked eye-movement behaviors. The simulation will be run on the next-generation super computer to boot up in 2011 with 10 peta-flops peak performance (http://www.nsc.riken.jp/project-eng.html). In the subsequent phase from FY2011, we will include the basal ganglia, the thalamus, and the cortical areas to achieve goal-directed visual search and human-like eye communication. We aim to understand the mechanisms of robust and flexible adaptation and to reveal the causes of eye-movement features found in disorders like schizophrenia, autism, and Parkinson's disease. Positions Available We have two postdoctoral researcher or scientific programmer positions starting October 2008. The candidate should have a strong computational background in areas including parallel programming, statistical machine learning, systems biology, image processing, and database management and have, or be willing to acquire, neurobiological knowledge to navigate the literature and databases. The research will be conducted at Kyoto University and other collaborating research institutes. Salary is commensurate with experience. The initial contract continues until March 2009 and is renewable yearly until March 2011. Candidates should send a CV, a list of publications and software projects, and a brief description of interests in science and computing by e-mail to bns08 at sys.i.kyoto-u.ac.jp by October 10, 2008. The search will continue until the position is filled. Brain and Neural Systems Team: Shin Ishii, Kyoto University Kenji Doya, Okinawa Institute of Science and Technology --- Posted by Shigeyuki Oba, Kyoto University From nips2008publicity at gmail.com Fri Sep 26 00:13:06 2008 From: nips2008publicity at gmail.com (Antonio Torralba) Date: Fri, 26 Sep 2008 00:13:06 -0400 Subject: Connectionists: NIPS Registration is now open Message-ID: Registration for NIPS 2008 is now open. You can register here: https://nips.cc/Register/ Go here to see the 2008 program highlights: http://nips.cc/Conferences/2008/Program/ Please note the following changes to NIPS in 2008: A new feature that is on the NIPS schedule this year is four Mini Symposia to be held in parallel during the afternoon of December 11, 2008 at the Hyatt Vancouver. The Mini Symposia will provide in depth explorations of current topics in a format that is less, formal than a plenary session but more structured than a workshop. Below are the topics and speakers for this year: Risi Kondor, Guy Lebanon and Jason Morton Gatsby Unit, UCL, Georgia Tech, Stanford University Algebraic and Combinatorial Methods in Machine Learning Bill Freeman and Bernhard Schoelkopf Massachusetts Institute of Technology, Max Planck Institute for Biological Cybernetics Computational Photography Gal Chechik, Christina Leslie, Quaid Morris, William Noble and Gunnar Raetsch Google, Memorial Sloan-Kettering Cancer Center, University of Toronto, University of Washington, Max Planck Society Machine Learning in Computational Biology Daniel Polani and Naftali Tishby University of Hertfordshire, Hebrew University Principled Theoretical Frameworks for the Perception-Action Cycle Attendence at the Mini-Symposia will be open to anyone who is registered for the main NIPS Conference or the NIPS Workshop in Whistler. *We've removed the cost of NIPS Items from Registration and are selling them as a la carte items: -Paper Programs -NIPS Coffee Mugs -NIPS T-Shirts *Refunds will not be given after November 14, 2008. *Payment is now done via Google Checkout. *Everyone will need to display their badge to participate in NIPS activities. We look forward to seeing you at NIPS 2008! From I.Bojak at donders.ru.nl Fri Sep 26 04:05:39 2008 From: I.Bojak at donders.ru.nl (Ingo Bojak) Date: Fri, 26 Sep 2008 10:05:39 +0200 Subject: Connectionists: Postdoc: Computational Neuroscience/Neuroimaging (1.5+3.5 years) Message-ID: <48DC97D3.5080209@donders.ru.nl> Candidate profile In a multidisciplinary project we will investigate resting state and sleep with co-registered EEG/fMRI in a novel model-driven, computational analysis. Thus our ideal candidate for this post combines skills in neuroimaging, applied mathematics, and scientific programming with a background in sleep research, connectivity studies or mean field modeling. However, candidates with qualifications in relevant aspects and enthusiasm for broadening their existing scientific portfolio will also be considered. This project is a collaboration between experimentalists and theorists at the Donders Institute?s Centres for Cognitive Neuroimaging (DCCN) and Neuroscience (DCN). Hence it provides a unique opportunity to become part of an emerging group of neuroscientists comfortably crossing traditional faculty boundaries. Research topic How is the ubiquitous EEG ?alpha rhythm? of the unstimulated brain linked to the resting state ?default mode network? that has been identified with fMRI? What happens to the BOLD response as rest turns into sleep, in different stages that we know from their EEG patterns? The complementary nature of EEG and BOLD data requires innovative methods for synergistic data analysis. We will use a realistic mean field model for inverting co-registered EEG/fMRI data to the underlying cortical state through an iterative optimization of its biologically motivated parameters, including cortical connectivity. We will start out with the analysis of previously acquired resting-state data. During this pilot study we will seek extended funding, which will allow us to carry out the planned investigation of sleep stages with co-registered EEG/fMRI. Research environment The Neuro-Physiology and -Informatics group (http://neuroPI.org) at the DCN and the MR-methods for Cognitive Neuroscience group (http://tinyurl.com/4md98p) at the DCCN are part of the new Donders Institute for Brain, Cognition, and Behaviour (http://www.ru.nl/donders/). The offered position is part of a large project supported by the Donders Institute with a start-up grant. Living in The Netherlands / Nijmegen The Netherlands is well-known as a modern and very urbanized European country. However, the vibrant border city of Nijmegen (http://www.nijmegen.nl/) also offers access to the beautiful Dutch/German ?Lower Rhine? countryside. Salary The estimated gross salary will be between ? 3129/month and ? 4284/month, commensurate with experience, plus two yearly 8% supplements (vacation and end-of-year). The 1.5 years initial contract will be extended to up to 5 years, if sufficient external funds are acquired. A generous moving/bridging package is being provided. Contacts Send your applications with full CV, list of publications, and three referees to Ms. Stijns (Tildie.Stijns at donders.ru.nl). Submission deadline is the 31st of October. For more information about the position, contact Prof. R. K?tter (rk at donders.ru.nl), Prof. D. Norris (D.Norris at donders.ru.nl), or Dr. I. Bojak (I.Bojak at donders.ru.nl). From g.goodhill at uq.edu.au Fri Sep 26 06:13:17 2008 From: g.goodhill at uq.edu.au (Geoffrey Goodhill) Date: Fri, 26 Sep 2008 20:13:17 +1000 Subject: Connectionists: Postdoc position in computational neuroscience Message-ID: A postdoc position is now available in the lab of Geoff Goodhill (http://cns.qbi.uq.edu.au) at the Queensland Brain Institute, University of Queensland, Brisbane, Australia. The position is funded by a 3-year HFSP grant entitled "Self-organized wiring of the cerebral cortex through thalamocortical growth cones: an integrated approach". Collaborators on the grant are Ole Paulsen (Oxford, UK), Tomomi Shimogori (Riken BSI, Japan), and Guillermina Lopez-Bendito (Alicante, Spain). The position will involve theoretical modelling of thalamocortical development, closely constrained by experimental data from all 4 labs. Applicants should have a background in mathematical modelling, ideally in a neuroscience context. To apply please send a CV, cover letter and contact information for at least 2 referees to Geoff Goodhill (g.goodhill at uq.edu.au). The Queensland Brain Institute (http://qbi.uq.edu.au) is part of the University of Queensland, one of the top 4 universities in Australia. The QBI is based in a new AU$63 million state-of-the-art facility and houses 24 Principal Investigators with research interests ranging from the molecular to cognitive level. It is one of the largest neuroscience institutes in the world dedicated to understanding the mechanisms underlying brain function and is funded by state, federal, university and philanthropic sources. Brisbane is a cosmopolitan city of 2 million people providing a vibrant cultural environment, a subtropical climate, and easy access to unspoilt beaches, rainforests, and the Great Barrier Reef. From juergen at idsia.ch Fri Sep 26 09:14:05 2008 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Fri, 26 Sep 2008 15:14:05 +0200 Subject: Connectionists: The Swiss AI Lab IDSIA: 20th Anniversary / Jobs Message-ID: <60EA8E6C-C3E7-4EA9-B022-51A31CFC8216@idsia.ch> The 20 year anniversary celebration of the Swiss AI Lab IDSIA will take place on 24 October 14:00-18:00 in Palazzo dei Congressi in the center of Lugano, Switzerland, during Ticino Informatica 2008: http://www.idsia.ch/Files/idsia20/Program.html Distinguished keynote speakers: 1. Mauro Dell'Ambrogio, Swiss State Secretary for Education and Research 2. Prof. Marco Dorigo, Pioneer of Ant Colony Optimization and Swarm Intelligence 3. Prof. Helge Ritter, A pioneer of Self-Organizing Maps; Leibniz Laureate Panel: The Future of AI Registration is free! Please register here: http://www.idsia.ch/Files/idsia20/Register.html? Juergen Schmidhuber http://www.idsia.ch/~juergen/ PS: Current jobs at IDSIA (all hired persons will closely interact): 1 Postdoc and 1 PhD student in biologically plausible reinforcement learning: http://www.idsia.ch/~juergen/sinergia2008.html 1 Postdoc and 1 Developer in handwriting recognition: http://www.idsia.ch/~juergen/kti2008.html 1 related Postdoc in medical image analysis: http://www.idsia.ch/~luca/PostDoc_2008_IDSIA_IN3.html 1 PhD fellowship in evolutionary computation: http://www.idsia.ch/~tino/evo2008.html More jobs on artificial curiosity and learning robots to be announced soon: http://www.idsia.ch/~juergen/interest.html http://www.idsia.ch/~juergen/learningrobots.html -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2415 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080926/dd7468e7/smime-0001.bin From tobias at nld.ds.mpg.de Tue Sep 30 04:49:32 2008 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Tue, 30 Sep 2008 10:49:32 +0200 Subject: Connectionists: =?windows-1252?q?Full_Professor_for_=93Sensory_Pr?= =?windows-1252?q?ocessing_in_the_Retina=94_=28W3=29?= In-Reply-To: <482D546D.4050402@nld.ds.mpg.de> References: <46F11EC2.6060905@nld.ds.mpg.de> <47DF9A97.1000408@nld.ds.mpg.de> <482D3F9A.6020609@nld.ds.mpg.de> <482D546D.4050402@nld.ds.mpg.de> Message-ID: <48E1E81C.5020909@nld.ds.mpg.de> The University of G?ttingen Medical School invites applications for the position of a Full Professor for ?Sensory Processing in the Retina? (W3) We are looking for scientists with an established and internationally recognized, original track of research on the processing of visual information in the retina. The successful candidate will coordinate research at the Department of Ophthalmology and will actively participate in further strengthening the Neuroscience Focus of the G?ttingen Research Campus. Ideally, the candidate will bring expertise in physiological, morphological and/or genetic approaches to synaptic transmission in the retina. She/he is expected to closely interact with molecular, cellular, systems and computational neuroscientists within existing (e.g. http://www.cmpb.uni-goettingen.de/, http://www.bccn-goettingen.de/) and novel collaborative research activities such as a planned research center on the cellular mechanisms of sensory processing. The candidate?s teaching activities will contribute to graduate programs of the G?ttingen Graduate School of Neurosciences and Molecular Biosciences (http://www.uni-goettingen.de/en/56640.html) and the Master and PhD program Molecular Medicine (http://www.molmed-goettingen.de/inter/links.php?sp=en) (teaching language: English). G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including the Centers for the Molecular Physiology of the Brain (CMPB) and for Systems Neuroscience (CSN), the European Neuroscience Institute and the Bernstein Center for Computational Neuroscience (BCCN) run jointly by the University of G?ttingen, three Max Planck Institutes and the German Primate Research Center. Qualifications required are the ?Habilitation? or an equivalent further qualification in research and university teaching; a sound teaching record is a further prerequisite. Experience with grant applications, research planning, as well as international research networking will be highly desirable. Appointments will be made by the Georg-August-Universit?t G?ttingen as a Public Law Foundation according to the Higher Education Law of Lower Saxony (Nieders?chsisches Hochschulgesetz Nds. GVBl. 2007, page 69). Further details will be provided on request. The position is open to German and foreign nationals. The University of G?ttingen is committed to employment equity and women are particularly encouraged to apply. Applicants with disabilities will be preferentially considered within the current legal regulations. Applications including a CV, a list of publications, reprints of the applicant?s five most significant publications, a description of achievements and future plans in teaching and research, as well as an overview of successful funding applications should reach the Faculty no later than 10th of October 2008 following announcement of the position. The Dean and Member of the Board of Directors for Research and Education of the University Medical School, Robert-Koch-Str. 42, D-37075 G?ttingen, Germany. Further general information for applicants and application forms are available on: http://www.universitaetsmedizin-goettingen.de/content/berufungen.html From thomas.shultz at mcgill.ca Tue Sep 30 12:59:58 2008 From: thomas.shultz at mcgill.ca (Thomas Shultz, Dr.) Date: Tue, 30 Sep 2008 12:59:58 -0400 Subject: Connectionists: Position in Cognition at McGill Message-ID: <40EF8CE75AEED54D9A5C542FD3B7AE3107E2C5BE@EXCHANGE2VS3.campus.mcgill.ca> may be of interest to readers of this list -- McGill University Department of Psychology Assistant Professor Position in Cognition The Department of Psychology of McGill University seeks applicants for a tenure-track position as Assistant Professor in Cognition with an anticipated starting date of September 1, 2009. We are interested in applicants studying issues in memory, attention, concepts, reasoning, problem solving, decision making, or development using human experimentation, modeling, and/or cognitive-neuroscience techniques. The Department has excellent facilities for interdisciplinary research through its links with related academic departments at McGill and other universities in Montreal. Review of applications will begin October 20, 2008 and continue until suitable candidates have been identified. Applicants should present evidence of the ability to establish a record of significant, externally-funded research and are expected to have an aptitude for both undergraduate and graduate teaching. Applicants should arrange for three confidential letters of recommendation to be sent to the address below. A curriculum vitae, description of current and proposed areas of research, selected reprints of published or in-press research articles, a description of areas of teaching competency, interest, and approaches, and other relevant material, should also be sent to: Chair, Cognition Search Committee Department of Psychology McGill University 1205 Dr. Penfield Avenue Montreal, Quebec, Canada H3A 1B1 All qualified candidates are encouraged to apply, however Canadians and permanent residents will be given priority. McGill University is committed to equity in employment. ----------------------------------------------------------------- Thomas Shultz, Professor, Department of Psychology McGill University, 1205 Penfield Ave., Montreal, Quebec, Canada H3A 1B1. Associate Member, School of Computer Science E-mail: thomas.shultz at mcgill.ca http://www.psych.mcgill.ca/perpg/fac/shultz/personal/default.htm Phone: 514 398-6139 Fax: 514 398-4896 ----------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080930/2e936d66/attachment-0001.html