From dirk.jancke at rub.de Wed Sep 1 12:19:20 2010 From: dirk.jancke at rub.de (dirk jancke) Date: 1 Sep 2010 18:19:20 +0200 Subject: Connectionists: Postdoc position - Optical Imaging of Visual Cortical Plasticity Message-ID: <4C7E7D08.2040309@rub.de> In the framework of the newly established DFG Sonderforschungsbereich 874 "Integration and Representation of Sensory Processes" at the Ruhr-University Bochum, Germany, we are seeking a postdoctorate researcher for project A2 "Stability and Plasticity of Activity and Specificity Maps in Early Visual Cortex". Our group uses cutting-edge voltage-sensitive dye (VSDI) and intrinsic optical imaging approaches in combination with electrophysiology to characterize network activation dynamics and plastic reorganization processes in cortical primary visual areas. The Ruhr-University Bochum is home to a vibrant research community in neuroscience with many laboratories focusing on all aspects of neuroscience research. The SFB 874 hosts in total 13 projects, realized in close collaboration between theoretical neuroscientists and experimenters. Successful candidates should have a PhD in the field of neuroscience, expertise in electrophysiology in vivo, and good programming skills applicable to complex data recordings, analysis and mathematical concepts. The willingness to work within integrative frameworks is highly desirable. The position (full-time, E13 TV-L) is presently available for 3 years. Application process will remain open until the position is filled. To apply please send a statement of research interests and a complete CV and names (incl. contact info) of two possible references. Contact: Dr. Dirk Jancke Bernstein Group for Computational Neuroscience Institut f?r Neuroinformatik, ND 04/584 Ruhr-University Bochum D-44780 Bochum Germany email: jancke at neurobiologie.rub.de for further information see: http://homepage.ruhr-uni-bochum.de/Dirk.Jancke The Ruhr-University Bochum is committed to equal opportunity in employment and gender equality in its working environment. To increase gender distribution in all job categories and at all levels, we strongly encourage applications from qualified women. Female applicants will be given preferential consideration when their level of qualification, competence and professional achievements equals that of male candidates, unless arguments based on the personal background of a male co-applicant prevail. Applications from appropriately qualified handicapped persons are also encouraged. From p.husbands at sussex.ac.uk Fri Sep 3 08:38:12 2010 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Fri, 3 Sep 2010 13:38:12 +0100 Subject: Connectionists: Sussex Workshop on Synthetic Neuroethology 9-10 Sept Message-ID: Sussex Workshop on Synthetic Neuroethology Sept. 9-10 Synthetic Neuroethology refers to the use of computational and robotic models in the study of the neural mechanisms underlying the generation of behaviour in animals. This one and a half day workshop brings together researchers involved in this and related fields in order to review progress and debate prospects. The program is outlined below. All the talks will be in Silverstone 309. For talk and poster abstract see http://www.cogs.susx.ac.uk/users/philh/snworkshop.htm LAST MINUTE SUBMISSIONS OF POSTERS MAY STILL BE ACCEPTED - if you wish to submit one please email synthneuro at sussex.ac.uk Thursday 9th Sept. (Silverstone 309) 1230-1330 arrival and lunch 13.30 Tony Prescott (Sheffield University) "Understanding the brain through active touch sensing in rats and robots" 14:15 Thomas Nowotny (University of Sussex) "Spiking Neuronal Network Model of Unsupervised Olfactory Learning on Graphical Processing Units" 15:00 coffee 15:30 Roland Baddeley (Bristol University)"Constraints on representations from the statistics of our visual world" 16:15 Joseph Ayers (Northeastern University, US)"Controlling Biomimetic Robots with Electronic Nervous Systems" 17:00 Poster Spotlights 1715 onwards: Wine and POSTERS (in Pev 3c07 - the InQbate space) Friday 10th September (Silverstone 309) 0900-0930 coffee 09:30 Neil Burgess (UCL) "Neural mechanisms of spatial cognition" 10:15 Barbara Webb (Edinburgh University) "Mechanisms of insect behaviour" 11:00 coffee 11:30 Paul Graham (Sussex) TBA 12:00 Bart Baddeley (Sussex) "Parsimonious route learning strategies in ants: A possible role for observed scanning behaviours" 12:45 Richard Mann (Uppsala University) "Prediction of Homing Pigeon Flight Paths using Gaussian Processes" 1330 Lunch 14:30 Volker Duerr (Bielefeld University) "Embodied motion intelligence: a dialogue between insects and robots" 15:15 Owen Holland (Sussex) "Modelling the modeller: towards a human-like robot with action-oriented imagination." 16:00 END Fees and REGISTRATION In order to contribute towards costs a small fee will be charged for attendance at the workshop. Students: 20 GB pounds, non-students: 40 GB pounds. Registered attendees will be provided with lunch and refreshments on both days. To register follow the instruction on the workshop website http://www.cogs.susx.ac.uk/users/philh/snworkshop.htm Contact information: synthneuro at sussex.ac.uk Local organisation: Bart Baddeley, Paul Graham, Phil Husbands, Andy Philippides (Centre for Computational Neuroscience and Robotics) From large at ccs.fau.edu Fri Sep 3 15:54:53 2010 From: large at ccs.fau.edu (Edward Large) Date: Fri, 3 Sep 2010 15:54:53 -0400 Subject: Connectionists: postdoctoral position at the Music Dynamics Laboratory Message-ID: <524867AB-33FE-4AD9-A6E6-401570F565FE@ccs.fau.edu> A postdoctoral position is now available in the Music Dynamics Laboratory at Florida Atlantic University. Research at MDL focuses on auditory cognitive neuroscience and music cognition, with an emphasis on theoretical modeling of neural and psychological processes. This NSF-funded position involves the development of neurodynamic models of tonal cognition in music. Individuals with experience in music psychology, music theory, auditory neuroscience, signal processing, music technology, neural networks, dynamical systems or related areas are encouraged to apply. An initial appointment will be made for two years with a possibility of extension based on the availability of funding. Salary will be determined according to NIH scale. Please send a copy of your vita and a cover letter emphasizing relevant experience and training to large at ccs.fau.edu. Include the names and contact information of three individuals who can serve as references, and indicate when you would be available to start. Funding for the position will begin in January, 2011. Additional information about the Music Dynamics Laboratory can be found at http:www.ccs.fau.edu/~large. Edward Large Associate Professor of Complex Systems and Brain Sciences Florida Atlantic University www.ccs.fau.edu/~large tel: 561.297.0106 fax: 561.297.3634 -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100903/3b43e071/attachment.html From erik at tnb.ua.ac.be Mon Sep 6 05:41:05 2010 From: erik at tnb.ua.ac.be (Erik De Schutter) Date: Mon, 6 Sep 2010 18:41:05 +0900 Subject: Connectionists: Call for proposals to host the annual Computational Neuroscience (CNS) Meetings in 2012 and 2013 Message-ID: <89AEB007-73CD-4970-92A4-A66AE0DF299C@tnb.ua.ac.be> After the successful CNS*2010 meeting in San Antonio, OCNS (http://www.cnsorg.org) hereby requests proposals from candidate local organizers to organize CNS meetings in 2012 (North America) and in 2013 (Europe). The CNS*2011 meeting will be held in Stockholm, Sweden July 23-28. Groups or individuals interested in organizing CNS meetings should send in a proposal with consideration of the on-line information (http://www.cnsorg.org/meetings/future_hosts/) using the on-line template provided as a guide. The OCNS board, executive and program committee members will select/discuss the different proposals, contact the potential local organizers for more information if necessary and come to a timely agreement between OCNS and potential local organizers. Proposals should be emailed to OCNS president at president at cnsorg.org no later than November 7, 2010. Considering the tight deadline incomplete proposals will be considered. Decisions are expected to be conveyed to potential organizers by begin 2011. Erik De Schutter OCNS President From knorman at princeton.edu Wed Sep 8 20:37:17 2010 From: knorman at princeton.edu (Kenneth Norman) Date: Wed, 8 Sep 2010 20:37:17 -0400 Subject: Connectionists: Postdoctoral position: Unified models of text, functional MRI, and human memory Message-ID: <908A295A-DB5A-4DC9-A592-801FBC68F972@princeton.edu> David Blei (Computer Science, Princeton University) and Ken Norman (Psychology, Princeton University) are looking for a postdoctoral researcher for an exciting project at the intersection of statistical machine learning and neuroscience. This is a one year (renewable) position. The position involves developing models and algorithms to help us explain human memory data. Specifically, we will be developing new hierarchical Bayesian models for simultaneously analyzing brain imaging data, corpus statistics, and behavioral data. The ideal candidate will be comfortable with a subset of the following: - hierarchical Bayesian modeling and posterior inference - topic modeling - brain imaging data - massive data sets - human memory research He or she will be an active participant in both Ken Norman's lab and David Blei's research group, collaborating closely with both faculty and their graduate students. For related work, see "A Bayesian analysis of dynamics in free recall" (NIPS, 2009), which can be found here: http://www.cs.princeton.edu/~blei/papers/SocherGershmanPerotteSederbergBleiNorman2009.pdf A PhD in Computer Science, Statistics, Engineering, Neuroscience, Psychology, Cognitive Science, or other related field is required. Applications should include a cover letter, a CV, one or two representative publications, and two letters of reference. To apply, please visit the website https://jobs.princeton.edu(Requisition #1000680) and create an online application. Princeton University is an equal opportunity employer and complies with applicable EEO and affirmative action regulations. -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100908/3dbc5418/attachment.html From wsenn at cns.unibe.ch Sun Sep 12 17:45:30 2010 From: wsenn at cns.unibe.ch (Walter Senn) Date: Sun, 12 Sep 2010 23:45:30 +0200 Subject: Connectionists: Biological Cybernetics (open access): vol 103, issue 4: Table of Content Message-ID: <4C8D49FA.3050204@cns.unibe.ch> Biological Cybernetics: vol 103, issue 4 --- Table of Content All open access!! Original papers: "Behavioral analysis of differential hebbian learning in closed-loop systems" Tomas Kulvicius, Christoph Kolodziejski, Minija Tamosiunaite, Bernd Porr & Florentin W?rg?tter http://www.springerlink.com/content/y0txgm6522001l67/ "Stochastic modeling of the neuronal activity in the subthalamic nucleus and model parameter identification from Parkinson patient data" Ishita Basu, Daniel Graupe, Daniela Tuninetti & Konstantin V. Slavin http://www.springerlink.com/content/y5187x01v0664012/ "Compact internal representation of dynamic situations: neural network implementing the causality principle" Jos? Antonio Villacorta-Atienza, Manuel G. Velarde & Valeri A. Makarov http://www.springerlink.com/content/f822261k8lp646l3/ "Path planning versus cue responding: a bio-inspired model of switching between navigation strategies" Laurent Doll?, Denis Sheynikhovich, Beno?t Girard, Ricardo Chavarriaga & Agn?s Guillot http://www.springerlink.com/content/t453579818r7ul17/ Review: "Modeling discrete and rhythmic movements through motor primitives: a review" Sarah Degallier & Auke Ijspeert http://www.springerlink.com/content/x7n0355642074wx0/ ---- Biological Cybernetics, all issues: http://www.springerlink.com/content/100465/ From Randy.OReilly at Colorado.EDU Tue Sep 14 00:23:57 2010 From: Randy.OReilly at Colorado.EDU (Randall Charles O'Reilly) Date: Mon, 13 Sep 2010 22:23:57 -0600 Subject: Connectionists: Senior C++ Software Developer for Cognitive Neuroscience Simulation System Message-ID: Senior C++ Software Developer for Cognitive Neuroscience Simulation System eCortex, Inc., based in Boulder, Colorado, is seeking an experienced C++ software engineer to be a key contributor to the Emergent neural network simulation environment (http://grey.colorado.edu/emergent). eCortex licenses this technology from the University of Colorado, Boulder, and collaborates closely with its Computational Cognitive Neuroscience laboratory. Emergent has been under development for over 15 years, and is used in the CCN lab and many others across the world to help understand how the brain secretes mind. It enables psychology experiments on simulated networks of neurons constructed according to neuroscience data, and embodied in virtual robots that interact with virtual environments. This software plays a central role in several large funded research projects, and the goal of the position is to implement new features as required for these projects, in addition to adding general improvements to the system overall. An example of one major project of interest is GPU acceleration of the core simulation code. The ideal candidate will have at least 5 years of experience developing large, complex software systems in C++ or a similar object-oriented language. Knowledge of and concern for high-quality coding standards in the software engineering process is important, as is the ability to work independently. A generalist development skill-set is preferred, as the work will range from GUI to core simulation enhancements. Familiarity with the toolkits used in Emergent is a plus (Qt, Coin3D, ODE). Experience in neural networks, neuroscience, computer simulation, and/or cognitive psychology is helpful but not required; however, interest in and enthusiasm for this field is essential. The position is funded through an initial one-year federal government subcontract, with options for an additional 2.5 years. eCortex will be seeking additional sources of support to make this a permanent full-time position. Some advantages of the position include: flexible hours, a casual academic-like work environment, and the opportunity to make important contributions to figuring out one of the greatest mysteries in the universe: the brain. Salary will be competitive with industry positions and based on experience. eCortex is committed to equal employment opportunity. If interested, please email a resume to David.Jilk at e-cortex.com. - Randy ---- Dr. Randall C. O'Reilly Professor, Department of Psychology and Neuroscience University of Colorado Boulder 345 UCB, Boulder, CO 80309-0345 303-492-0054 Fax: 303-492-2967 http://psych.colorado.edu/~oreilly From wachtler at biologie.uni-muenchen.de Wed Sep 15 12:09:06 2010 From: wachtler at biologie.uni-muenchen.de (Thomas Wachtler) Date: Wed, 15 Sep 2010 18:09:06 +0200 (CEST) Subject: Connectionists: Postdoc Position: Computational modeling and electrophysiology of early visual processing Message-ID: A postdoctoral position is available at the Bernstein Center for Computational Neuroscience Munich (www.bccn-munich.de), for a research project at Ludwig-Maximilians-Universitaet Munich in a collaboration of the laboratories of Thomas Wachtler and Tim Gollisch. The research will involve a combination of computational modeling of early visual processing and experimental recordings of neural activity in the vertebrate retina, to investigate signal processing in the visual system and its role in the learning of invariant representations. The position is available immediately and is for two years initially, with possibility of extension. Salary is according to German salary scale TVL-13. Applicants should hold a doctoral degree in neuroscience, physics, computer science or a related field. Experience with computational modeling and/or electrophysiology is required, as well as a strong interest in combining these approaches. Applications including CV, letter of motivation, and names of referees, should be sent to Thomas Wachtler . -- Thomas Wachtler Department Biologie II Ludwig-Maximilians-Universit?t M?nchen Grosshaderner Str. 2 82152 Planegg-Martinsried Germany Tel: +49 89 2180 74810 Fax: +49 89 2180 74803 From terry at salk.edu Thu Sep 16 11:34:12 2010 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 16 Sep 2010 08:34:12 -0700 Subject: Connectionists: NEURAL COMPUTATION - October, 2010 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 22, Number 10 - October 1, 2010 ARTICLE Discrete Time Rescaling Theorem: Determining Goodness of Fit for Discrete Time Statistical Models of Neural Spiking Robert Haslinger, Gordon Pipa, and Emery Brown LETTERS Convergence and Stability of Quantized Hopfield Networks Operating in a Fully Parallel Mode Daniel Calabuig, Jose F. Monserrat, and Nar?is Cardona Probability of Repeating Patterns in Simultaneous Neural Data Anne C. Smith, Vinh Kha Nguyen, Mattias P Karlsson, Loren M Frank, and Peter Smith Recording from Two Neurons: Second-Order Stimulus Reconstruction from Spike Trains and Population Coding N. M. Fernandes, B. D. L. Pinto, L. O. B. Almeida, J. F. W. Slaets, and R. Köle On a Stochastic Leaky Integrate-and-Fire Neuronal Model A. Buonocore, L. Caputo, E. Pirozzi, and L.M. Ricciardi Neuronal Population Decoding Explains the Change in Signal Detection Sensitivity Caused by Task-Irrelevant Perceptual Bias Satohiro Tajima, Hiromasa Takemura, Ikuya Murakami, and Masato Okada Spiking Neural P Systems with Weights Jun Wang, Hendrik Jan Hoogeboom, Linqiang Pan, Gheorghe Paun and Mario J. Perez-Jimenez A New Bidimensional Neural Field Model with Heterogeneous Connection Topology Mouhamad Jradeh Convergence Analysis of Three Classes of Split-Complex Gradient Algorithms for Complex-Valued Recurrent Neural Networks Dongpo Xu, Huisheng Zhang, and Lijun Liu Large-Margin Classification in Infinite Neural Networks Youngmin Cho, and Lawrence K. Saul The MEE Principle in Data Classification: A Perceptron-Based Analysis Luis M. Silva, J. Marques de Sa and Luis A. Alexandre ----- ON-LINE - http://www.mitpressjournals.org/loi/neco SUBSCRIPTIONS - 2010 - VOLUME 22 - 12 ISSUES USA Others Electronic only Student/Retired $65 $128 $60 Individual $115 $178 $107 Institution $962 $1,025 $860 Canada: Add 5% GST to USA prices 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 tt at cs.dal.ca Thu Sep 16 11:57:37 2010 From: tt at cs.dal.ca (Thomas Trappenberg) Date: Thu, 16 Sep 2010 12:57:37 -0300 Subject: Connectionists: Demonstration programs for Computational Neuroscience Classes Message-ID: Dear Colleagues, Thanks to the efforts of my student Leah Brown, I am pleased to provide some demonstration programs for spiking networks, a point attractor networks, and a dynamic neural field model with graphical user interfaces. The programs are mainly a graphical user interface for the programs of my book Fundamentals of Computational Neuroscience, 2nd edition, published this year by Oxford University Press. At this time, these programs have to be executed in Matllab, but some standalone versions will soon follow. The programs can be downloaded at http://web.cs.dal.ca/~tt/fundamentals/programs/MatlabGUIs *List of programs: * * * *Spiking_Models.m* is a GUI which simulates several different models of spiking neuron models (Hodgkin-Huxley, Wilson, Izhikevich, Integrate-and-fire) and a simple conductance-based ion channel model. Requires file *wilson_ode.m*. *DynamicNeuralFieldModel.m * is a GUI of the program dnf.m in the textook. Requires file *rnn_ode.m*. * * *Attractor_Network.m *is a MATLAB copy of the windows program HebbHop ( http://web.cs.dal.ca/~tt/HebbHop/HebbHop02.zip) that demonstrate a point attractor network. This is not part of the textbook, but I often use it in my classes. Requires file *pattern1.mat*. All programs require the associated .fig files. Regards, Thomas Trappenberg Dalhousie University, Canada -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100916/6d20f30b/attachment-0001.html From joern.anemueller at uni-oldenburg.de Mon Sep 13 03:59:25 2010 From: joern.anemueller at uni-oldenburg.de (=?iso-8859-1?Q?J=F6rn_Anem=FCller?=) Date: Mon, 13 Sep 2010 09:59:25 +0200 Subject: Connectionists: =?windows-1252?q?PhD_position_in_Oldenburg=2C_Ger?= =?windows-1252?q?many=2C_=94Model_Based_Blind_Source_Separation_for_Audit?= =?windows-1252?q?ory_Scene_Analysis=93?= Message-ID: <6B6D5897-942B-4E52-B880-B4AAB1991248@uni-oldenburg.de> The project ?Model Based Blind Source Separation for Auditory Scene Analysis? within the transregional collaborative research center ?The Active Auditory System? (SFB/TRR 31, www.sfb-trr31.uni-oldenburg.de) offers a position for a Physicist, applied Mathematician, Electrical Engineer or Computer Scientist at the Ph.D. student level. Salary and social benefits will conform to the provisions of the Collective Agreement for the Lower Saxony Civil Service (TV-L, E13 50 %). The appointment is until June 2013 with further extension subject to project renewal. The ideal candidate will be highly qualified in quantitative approaches from machine learning and statistical signal processing. She or he will have a keen interest in auditory neuroscience and psychophysics. Experience in scientific programming and excellent English are essential. The position is located within the Medical Physics Unit of the Dept. of Physics, University of Oldenburg, Germany, see www.medi.uni-oldenburg.de. The successful candidate will work in the Statistical Signal Models Group, which conducts research to build statistical signal processing and machine learning models for speech and audio applications, and collaborate with the Psycho-acoustic Models Group. The transregional collaborative research center ?The Active Auditory System? (SFB/Transregio ?Das aktive Geh?r?) jointly operated by research groups at the University of Oldenburg, University of Magdeburg and the Leibniz Institute for Neurobiology at Magdeburg studies the mechanisms of auditory scene analysis and their application to health and technology. Pursued numerical and experimental approaches include signal processing and psychoacoustic modeling for speech and audio analysis, EEG, MEG and fMRI analysis and in vivo recording in the auditory pathway. The University of Oldenburg strives to increase the percentage of female employees in the field of science and encourages applications from female candidates. Handicapped applicants will be given preference in case of equal qualifications. For further inquiries, please contact Dr. J?rn Anem?ller, Dept. of Physics, University of Oldenburg, 26111 Oldenburg, Germany, joern.anemueller at uni-oldenburg.de. Applications received until 17th September 2010 will be given full consideration. Applications should include a curriculum vitae, copies of degree certificates, writing samples/copies (e.g. thesis, scientific papers), and names and addresses of two referees. Applications should be submitted electronically via e-mail (quoting the reference code B6/2010) to sfb-tr31 at uni-oldenburg.de as a single file in portable document format (PDF) and should be addressed to SFB/TRR 31 ?Das aktive Geh?r?, ? Gesch?ftsstelle ? Carl von Ossietzky Universit?t Oldenburg, Fakult?t V, IBU D-26111 Oldenburg, Germany, e-mail: sfb-tr31 at uni-oldenburg.de From ASAHTan at ntu.edu.sg Fri Sep 17 04:13:47 2010 From: ASAHTan at ntu.edu.sg (Tan Ah Hwee (Assoc Prof)) Date: Fri, 17 Sep 2010 16:13:47 +0800 Subject: Connectionists: Invitation for Submission to the Special Issue of ACM TIST Journal on Brain-Inspired Cognitive Agents Message-ID: <629B8F547581594A9B9760E372AA15771624B98C90@EXCHANGE32.staff.main.ntu.edu.sg> Dear Colleagues We are currently preparing a special issue on Brain-Inspired Cognitive Agents for the ACM Transactions on Intelligent Systems and Technology (ACM TIST) and we would like to invite you to contribute a paper based on your recent research work. The deadline for the paper submission is 31 December 2010, which we hope allows sufficient time for writing. Further information on submission and schedule can be found in the ACM TIST home page (http://tist.acm.org/) and the call for the papers attached here. We look forward to receiving your contribution soon. Thank you very much. Best regards Ah-Hwee Tan and Wlodzislaw Duch [cid:image001.gif at 01CB567D.FCBDD0B0] Ah-Hwee TAN (Dr) | Associate Professor and Head, Division of Information Systems | School of Computer Engineering | Nanyang Technological University Block N4, Level 2, Section A, Room 26, Nanyang Avenue, Singapore 639798 Tel: (65) 6790-4326 GMT+8h | Fax: (65) 6792-6559 | Email: asahtan at ntu.edu.sg | Web: www.ntu.edu.sg/home/asahtan ________________________________ CONFIDENTIALITY: This email is intended solely for the person(s) named and may be confidential and/or privileged. If you are not the intended recipient, please delete it, notify us and do not copy, use, or disclose its content. Thank you. Towards A Sustainable Earth: Print Only When Necessary -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100917/4da00efc/attachment-0001.html -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.gif Type: image/gif Size: 5563 bytes Desc: image001.gif Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100917/4da00efc/image001-0001.gif -------------- next part -------------- A non-text attachment was scrubbed... Name: TIST-SI-BICA-10 cfp.pdf Type: application/pdf Size: 50172 bytes Desc: TIST-SI-BICA-10 cfp.pdf Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100917/4da00efc/TIST-SI-BICA-10cfp-0001.pdf From jose at psychology.rutgers.edu Sat Sep 18 19:55:31 2010 From: jose at psychology.rutgers.edu (Stephen =?ISO-8859-1?Q?Jos=E9?= Hanson) Date: Sat, 18 Sep 2010 19:55:31 -0400 Subject: Connectionists: POSTDOC--COMPUTATIONAL IMAGING --NEW IMAGING CENTER Message-ID: <1284854131.1638.29.camel@max> We have received a new NSF-MRI award for an Imaging Center. We are looking for a computational neuroimaging postdoc interested in MVPA and graph modeling of brain imaging data. Please see ad. -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100918/538c11d9/attachment-0001.html -------------- next part -------------- A non-text attachment was scrubbed... Name: signature2010.png Type: image/png Size: 24455 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100918/538c11d9/signature2010-0001.png -------------- next part -------------- A non-text attachment was scrubbed... Name: postdoc-rumba.pdf Type: application/pdf Size: 74192 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100918/538c11d9/postdoc-rumba-0001.pdf From brian.mingus at Colorado.EDU Mon Sep 20 16:24:50 2010 From: brian.mingus at Colorado.EDU (Brian J Mingus) Date: Mon, 20 Sep 2010 14:24:50 -0600 Subject: Connectionists: NIPS 2010 workshop announcements Message-ID: Dear colleagues, Below you can find a compilation of the NIPS 2010 announcements that have been sent to the Connectionists mailing list. If more NIPS-related announcements arrive I will send another compilation on October 15th, so if you are planning an announcement please send it to the list before that time. The following announcements are included here. You may wish to paste the title into the Ctrl+f find function of your browser. - NIPS 2010 Registration Open - Deep Learning and Unsupervised Feature Learning - Discrete Optimization in Machine Learning -- Structures, Algorithms and Applications (DISCML) - Optimization for Machine Learning - Numerical Mathematics Challenges in Machine Learning - Machine Learning for Assistive Technologies - Challenges of Data Visualization - Tensors, Kernels, and Machine Learning - Transfer Learning Via Rich Generative Models - Coarse-to-Fine Learning and Inference - New Directions in Multiple Kernel Learning - Predictive Models in Personalized Medicine - New Problems and Methods in Computational Biology Brian Mingus Connectionists moderator Graduate student Computational Cognitive Neuroscience Lab University of Colorado at Boulder ---------- Forwarded message ---------- From: Chris Hiestand To: connectionists at cs.cmu.edu Date: Wed, 8 Sep 2010 14:22:43 -0700 Subject: NIPS 2010 Registration Open NIPS 2010 Registration for the Tutorials and Conference Sessions in Vancouver and the Workshops in Whistler is now open: https://nips.cc/Register/ Please note: early registration pricing ends after November 6. For planning purposes, we'd tremendously appreciate if you participate in a survey about the 2011 NIPS conference in Spain: https://nips.cc/Surveys/survey.php?id=8 For students or Post Docs seeking financial support, both travel support applications and volunteer applications are now open: http://nips.cc/ConferenceInformation/TravelSupport http://nips.cc/ConferenceInformation/Volunteering The demonstrations proposal deadline is approaching: September 20, 2010 23:59 PDT http://nips.cc/Conferences/2010/CallForDemonstrations We look forward to seeing you in Vancouver and Whistler! ---------- Forwarded message ---------- From: Honglak Lee To: connectionists at cs.cmu.edu Date: Thu, 16 Sep 2010 22:23:31 -0400 Subject: CFP: NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning Dear colleagues, This is a call for participation in the: Deep Learning and Unsupervised Feature Learning Workshop in conjunction with 24th Annual Conference on Neural Information Processing Systems (NIPS 2010) December 10 or 11, 2010 Whistler, BC, Canada (This is a one-day workshop, and the date will be determined soon.) http://deeplearningworkshopnips2010.wordpress.com/ Overview ------------------------------------ In recent years, there has been a lot of interest in algorithms that learn feature hierarchies from unlabeled data. Deep learning methods such as deep belief networks, sparse coding-based methods, convolutional networks, and deep Boltzmann machines, have shown promise and have already been successfully applied to a variety of tasks in computer vision, audio processing, natural language processing, information retrieval, and robotics. In this workshop, we will bring together researchers who are interested in deep learning and unsupervised feature learning, review the recent technical progress, discuss the challenges, and identify promising future research directions. The workshop invites paper submissions that will be either presented as oral or in poster format. Through invited talks, panel discussions and presentations by the participants, this workshop attempts to address some of the more controversial topics in deep learning today, such as whether hierarchical systems are more powerful, and what principles should guide the design of objective functions used to train these models. Panel discussions will be led by the members of the organizing committee as well as by prominent representatives of the vision and neuro-science communities. The goal of this workshop is two-fold. First, we want to identify the next big challenges and propose research directions for the deep learning community. Second, we want to bridge the gap between researchers working on different (but related) fields, to leverage their expertise, and to encourage the exchange of ideas with all the other members of the NIPS community. Dates ------------------------------------ - Submission deadline: October 15, 2010 - Acceptance notification: November 5, 2010 - Workshop date: December 10 or 11, 2010 (This is a one-day workshop, and the date will be determined soon.) A tentative schedule is available at: http://deeplearningworkshopnips2010.wordpress.com/schedule. Submissions ------------------------------------ We solicit submissions of unpublished research papers. Papers must have at most 8 pages and must satisfy the formatting instructions of the NIPS 2010 call for papers. Style files are available at http://nips.cc/PaperInformation/StyleFiles. Please note that the reviewing is double blind, and make sure to submit your papers anonymously. Papers should be submitted through https://cmt.research.microsoft.com/DLUFL2010/ no later than 23:59 EST, Friday, October 15, 2010. We encourage submissions on the following and related topics: * unsupervised feature learning algorithms * deep learning algorithms * semi-supervised and transfer learning algorithms * inference and optimization * theoretical foundations of unsupervised learning * theoretical foundations of deep learning * applications of deep learning and unsupervised feature learning The best papers will be awarded by an oral presentation, all other papers will have a poster presentation accompanied by a short spotlight presentation. Organizers ------------------------------------ * Honglak Lee ? University of Michigan * Marc?Aurelio Ranzato ? University of Toronto * Yoshua Bengio ? University of Montreal * Geoff Hinton ? University of Toronto * Yann LeCun ? New York University * Andrew Y. Ng ? Stanford University ---------- Forwarded message ---------- From: Andreas Krause To: connectionists at cs.cmu.edu Date: Sun, 29 Aug 2010 14:07:54 -0700 Subject: CFP: NIPS 2010 Workshop on Discrete Optimization in Machine Learning -- Structures, Algorithms and Applications (DISCML) =============================================== Call for Papers Discrete Optimization in Machine Learning Structures, Algorithms and Applications Workshop at the 24th Annual Conference on Neural Information Processing Systems (NIPS 2010) http://www.discml.cc Submission Deadline: Friday October 29, 2010 =============================================== - We apologize for multiple postings - Solving optimization problems with ultimately discretely solutions is becoming increasingly important in machine learning: At the core of statistical machine learning is to infer conclusions from data, and when the variables underlying the data are discrete, both the tasks of inferring the model from data, as well as performing predictions using the estimated model are discrete optimization problems. This workshop aims at exploring discrete structures relevant to machine learning and techniques relevant to solving discrete learning problems. In addition to studying discrete structures and algorithms, this year's workshop will put a particular emphasis on novel applications of discrete optimization in machine learning. We would like to encourage high quality submissions of short papers relevant to the workshop topics. Accepted papers will be presented as spotlight talks and posters. Of particular interest are new algorithms with theoretical guarantees, as well as applications of discrete optimization to machine learning problems in areas such as the following: Combinatorial algorithms - Submodular & supermodular optimization - Discrete convex analysis - Pseudo-boolean optimization - Randomized / approximation algorithms Continuous relaxations - Sparse approximation & compressive sensing - Regularization techniques - Structured sparsity models Applications - Graphical model inference & structure learning - Clustering - Feature selection, active learning & experimental design - Structured prediction - Novel discrete optimization problems in ML Submission deadline: October 29, 2010 Length & Format: max. 6 pages NIPS 2010 format Time & Location: December 11 2010, Whistler, Canada Submission instructions: Email to submit at discml.cc Organizers: Andreas Krause (California Institute of Technology), Pradeep Ravikumar (University of Texas, Austin), Jeff A. Bilmes (University of Washington), Stefanie Jegelka (Max Planck Institute for Biological Cybernetics in Tuebingen, Germany) ---------- Forwarded message ---------- From: Suvrit Sra To: connectionists at cs.cmu.edu Date: Mon, 13 Sep 2010 14:24:26 +0200 Subject: CFP: OPT 2010, 3rd International (NIPS) Workshop on Optimization for Machine Learning *** Sorry if you have already received this call for participation ** Dear colleagues, This is a call for participation in OPT 2010, The 3rd International Workshop on Optimization for Machine Learning, a Neural Information Processing Systems (NIPS 2010) Workshop. Date: Dec. 10, 2010. Location: Whistler, Canada http://opt.kyb.tuebingen.mpg.de *Deadline for submissions: 24th Oct., 2010 *Submission URL: http://www.easychair.org/conferences/?conf=opt2010 The detailed CFP follows. ------------------------------------------------------------------------------ OPT 2010 3rd International Workshop on Optimization for Machine Learning NIPS*2010 Workshop December 10th, 2010, Whistler, Canada URL: http://opt.kyb.tuebingen.mpg.de/ ------------------------------------------------------------------------------ Abstract -------- Optimization is a well-established, mature discipline. But the way we use this discipline is undergoing a rapid transformation: the advent of modern data intensive applications in statistics, scientific computing, or data mining and machine learning, is forcing us to drop theoretically powerful methods in favor of simpler but more scalable ones. This changeover exhibits itself most starkly in machine learning, where we have to often process massive datasets; this necessitates not only reliance on large-scale optimization techniques, but also the need to develop methods "tuned" to the specific needs of machine learning problems. Background and Objectives ------------------------- We build on OPT*2008 and 2009, the forerunners to this workshop that happened as a part of NIPS workshops. Beyond that significant precedent, there have been several other related workshops such as the "Mathematical Programming in Machine Learning / Data Mining" series (2005 to 2007) and the BigML NIPS 2007 workshop. Our workshop has the following major aims: * Provide a platform for increasing the interaction between researchers from optimization, operations research, statistics, scientific computing, and machine learning; * Identify key problems and challenges that lie at the intersection of optimization and ML; * Narrow the gap between optimization and ML, to help reduce rediscovery, and thereby accelerate new advances. Call for Participation ---------------------- This year we invite two types of submissions to the workshop: (i) contributed talks and/or posters (ii) open problems For the latter, we request the authors to prepare a few slides that clearly present, motivate, and explain an important open problem --- the main aim here is to foster active discussion. The topics of interest for the open problem session are the same as those for regular submissions; please see below for details. In addition to open problems, we invite high quality submissions for presentation as talks or poster presentations during the workshop. We are especially interested in participants who can contribute theory / algorithms, applications, or implementations with a machine learning focus on the following topics: Topics ------ * Stochastic, Parallel and Online Optimization, - Large-scale learning, massive data sets - Distributed algorithms - Optimization on massively parallel architectures - Optimization using GPUs, Streaming algorithms - Decomposition for large-scale, message-passing and online learning - Stochastic approximation - Randomized algorithms * Algorithms and Techniques (application oriented) - Global and Lipschitz optimization - Algorithms for non-smooth optimization - Linear and higher-order relaxations - Polyhedral combinatorics applications to ML problems * Non-Convex Optimization, - Non-convex quadratic programming, including binary QPs - Convex Concave Decompositions, D.C. Programming, EM - Training of deep architectures and large hidden variable models - Approximation Algorithms * Optimization with Sparsity constraints - Combinatorial methods for L0 norm minimization - L1, Lasso, Group Lasso, sparse PCA, sparse Gaussians - Rank minimization methods - Feature and subspace selection * Combinatorial Optimization - Optimization in Graphical Models - Structure learning - MAP estimation in continuous and discrete random fields - Clustering and graph-partitioning - Semi-supervised and multiple-instance learning Important Dates --------------- * Deadline for submission of papers: 24st October 2010 * Notification of acceptance: 12th November 2010 * Final version of submission: 20th November 2010 * Workshop date: 10th December 2010 Please note that at least one author of each accepted paper must be available to present the paper at the workshop. Further details regarding the submission process are available at the workshop homepage (style files, page limits, etc.) Workshop -------- The workshop will be a one-day event with a morning and afternoon session. In addition to a lunch break, long coffee breaks will be offered both in the morning and afternoon. A new session on open problems is proposed for spurring active discussion and interaction amongst the participants. A key aim of this session will be on establishing areas and problems of interest to the community. Invited Speakers ---------------- * Yurii Nesterov -- Catholic University of Louvain * Laurent El Ghaoui -- University of California, Berkeley * Mark Schmidt -- University of British Columbia Workshop Organizers ------------------- * Suvrit Sra, Max Planck Institute for Biological Cybernetics * Sebastian Nowozin, Microsoft Research, Cambridge, UK * Stephen Wright, University of Wisconsin, Madison ------------------------------------------------------------------------------ ---------- Forwarded message ---------- From: Suvrit Sra To: connectionists at cs.cmu.edu Date: Mon, 13 Sep 2010 14:23:25 +0200 Subject: CFP: NUMML 2010, NIPS Workshop on Numerical Mathematics Challenges in Machine Learning Dear colleagues, *** Sorry if you have already received this call for participation ** This is a call for participation in the: Neural Information Processing Systems (NIPS 2010) Workshop on Numerical Mathematical Challenges in Machine Learning Dec. 11, 2010. Whistler, Canada http://numml.kyb.tuebingen.mpg.de *Deadline for submissions: 21st Oct., 2010 *Submit by email to: suvadmin at googlemail.com The detailed CFP follows. -------------------------------------------------------------------------------------------------- NUMML 2010 Numerical Mathematical Challenges in Machine Learning NIPS*2010 Workshop December 11th, 2010, Whistler, Canada URL: http://numml.kyb.tuebingen.mpg.de/ -------------------------------------------------------------------------------------------------- Call for Contributions ------------------------------ We invite high-quality submissions for presentation as posters at the workshop. The poster session will be designed along the lines of the poster session for the main NIPS conference. There will probably be a spotlight session (2 min./poster), although this depends on scheduling details not finalized yet. In any case, authors are encouraged (and should be motivated) to use the poster session as a means to obtain valuable feedback from experts present at the workshop (see "Invited Speakers" below). Submissions should be in the form of an extended abstract, paper (limited to 8 pages), or poster. Work must be original, not published or in submission elsewhere (a possible exception are publications at venues unknown to machine learning researchers, please state such details with your submission). Authors should make an effort to motivate why the work fits the goals of the workshop (see below) and should be of interest to the audience. Merely resubmitting a submission rejected at the main conference, without adding such motivation, is strongly discouraged. Important Dates ------------------------ * Deadline for submission: 21st October 2010 * Notification of acceptance: 27th October 2010 * Workshop date: 11th December 2010 Submission: ----------------- Please email your submissions to: suvadmin at googlemail.com NOTE: --------- At least one author of each accepted submission must attend to present the poster/potential spotlight at the workshop. Further details regarding the submission process are available from the workshop homepage. What follows is a synopsis about workshop goals, invited speakers, expected audience. This information can also be obtained from the workshop homepage. ----------------------------------------------------------------------------------------------------------------- Abstract ------------ Most machine learning (ML) methods are based on numerical mathematics (NM) concepts, from differential equation solvers over dense matrix factorizations to iterative linear system and eigen-solvers. As long as problems are of moderate size, NM routines can be invoked in a black-box fashion. However, for a growing number of real-world ML applications, this separation is insufficient and turns out to be a severe limit on further progress. The increasing complexity of real-world ML problems must be met with layered approaches, where algorithms are long-running and reliable components rather than stand-alone tools tuned individually to each task at hand. Constructing and justifying dependable reductions requires at least some awareness about NM issues. With more and more basic learning problems being solved sufficiently well on the level of prototypes, to advance towards real-world practice the following key properties must be ensured: scalability, reliability, and numerical robustness. Unfortunately, these points are widely ignored by many ML researchers, preventing applicability of ML algorithms and code to complex problems and limiting the practical scope of ML as a whole. Goals, Potential Impact ---------------------------------- Our workshop addresses the abovementioned concerns and limitations. By inviting numerical mathematics researchers with interest in *both* numerical methodology *and* real problems in applications close to machine learning, we will probe realistic routes out of the prototyping sandbox. Our aim is to strengthen dialog between NM and ML. While speakers will be encouraged to provide specific high-level examples of interest to ML and to point out accessible software, we will also initiate discussions about how to best bridge gaps between ML requirements and NM interfaces and terminology; the ultimate goal would be to figure out how at least some of NM's high standards of reliability might be transferred to ML problems. The workshop will reinforce the community's awakening attention towards critical issues of numerical scalability and robustness in algorithm design and implementation. Further progress on most real-world ML problems is conditional on good numerical practices, understanding basic robustness and reliability issues, and a wider, more informed integration of good numerical software. As most real-world applications come with reliability and scalability requirements that are by and large ignored by most current ML methodology, the impact of pointing out tractable ways for improvement is substantial. General Topics of Interest ------------------------------------- A basic example for the NM-ML interface is the linear model (or Gaussian Markov random field), a major building block behind sparse estimation, Kalman smoothing, Gaussian process methods, variational approximate inference, classification, ranking, and point process estimation. Linear model computations reduce to solving large linear systems, eigenvector approximations, and matrix factorizations with low-rank updates. For very large problems, randomized or online algorithms become attractive, as do multi-level strategies. Additional examples include analyzing global properties of very large graphs arising in social, biological, or information transmissing networks, or robust filtering as a backbone for adaptive exploration and control. We welcome and seek contributions on the following subtopics (although we do not limit ourselves to these): A) Large to huge-scale numerical algorithms for ML applications * Eigenvector approximations: Specialized variants of the Lanczos algorithm, randomized algorithms. Application examples are: - The linear model (covariance estimation); - Spectral clustering, graph Laplacian methods, - PCA, scalable graph analysis (social networks), - Matrix completion (consumer-preference prediction) * Randomized algorithms for low-rank matrix approximations * Parallel and distributed algorithms * Online and streaming numerical algorithms B) Solving large linear systems: * Iterative solvers * Preconditioners, especially those based on model/problems structure which arise in ML applications * Multi-grid / multi-level methods * Exact solvers for very sparse matrices Application examples are: - Linear models / Gaussian MRF (mean computations), - Nonlinear optimization methods (trust-region, Newton steps, IRLS) C) Numerical linear algebra packages relevant to ML * LAPACK, BLAS, GotoBLAS, MKL, UMFPACK, PETSc, MPI D) Exploiting matrix/model structure, fast matrix-vector multiplication * Matrix decompositions/approximations * Multi-pole methods * Nonuniform FFT, local convolutions E) How can numerical methods be improved using ML technology? * Reordering strategies for sparse decompositions * Preconditioning based on model structure * Distributed parallel computing Target audience: Our workshop is targeted towards practitioners from NIPS, but is of interest to numerical linear algebra researchers as well. Workshop -------------- The workshop will feature talks (tutorial style, as well as technical) on topics relevant to the workshop. Because the explicit purpose of our workshop is to foster cross-fertilization between the NM and ML communities, we also plan to hold a discussion session, which we will help to structure by raising concrete questions based on the topics and concerns outlined above. To further bolster active participation, we will set aside time for poster and spotlight presentations, which will offer participants a chance to get feedback about their work. Invited Speakers ------------------------ Inderjit Dhillon University of Texas, Austin Dan Kushnir Yale University Michael Mahoney Stanford University Richard Szeliski Microsoft Research Alan Willsky Massachusetts Institute of Technology Workshop URL --------------------- http://numml.kyb.tuebingen.mpg.de Workshop Organizers ------------------------------ Suvrit Sra Max Planck Institute for Biological Cybernetics, Tuebingen Matthias W. Seeger Max Planck Institute for Informatics and Saarland University, Saarbruecken Inderjit Dhillon University of Texas at Austin, Austin, TX ------------------------------------------------------------------------------ ---------- Forwarded message ---------- From: jesse hoey To: connectionists Date: Wed, 8 Sep 2010 11:14:12 -0400 Subject: CFP: NIPS 2010 Workshop on Machine Learning for Assistive Technologies ###################################################################### FIRST CALL FOR CONTRIBUTIONS Machine Learning for Assistive Technologies a workshop in conjunction with 24th Annual Conference on Neural Information Processing Systems (NIPS 2010) December 10 2010 Whistler, BC, Canada http://www.cs.uwaterloo.ca/~jhoey/mlat-nips2010 Deadline for Submissions: Wednesday, October 20, 2010 Notification of Decision: Wednesday, November 3, 2010 ##################################################################### Overview: This workshop will expose the research area of assistive technology to machine learning specialists, will provide a forum for machine learning researchers and medical/industrial practitioners to brainstorm about the main challenges, and will lead to developments of new research ideas and directions in which machine learning approaches are applied to complex assistive technology problems. The workshop will discuss important open questions aimed at the next five years of research in a number of key areas, for example 1) What are the main bottlenecks that are currently holding back complex assistive technologies from being widely deployed/used? The argument to be presented and discussed at the workshop is that the application of adaptivity and machine learning is one of these bottlenecks. However, other viewpoints will be presented and discussed. 2) Do assistive technologies need some new type of machine learning? Are there any new machine learning problems or is it mostly a matter of adapting existing machine learning techniques to assistive technologies? A key challenge for assistive technologies is the detection of novel or changing patterns of behavior. Are existing novelty detection, feature selection and unsupervised learning techniques sufficient to handle this challenge? 3) What are the bottlenecks for the scaling of machine learning techniques for the assistive technology domain? More precisely, how can ML algorithms scale to large domains both in terms of state, action and observation spaces, and in terms of temporal extent? Unsupervised learning, feature selection, distributivity, and hierarchy are obvious choices. However, user adaptability and customizability, the appropriate integration of prior knowledge, and the rapid and inexpensive deployment of large sensor networks (including cameras) also play a significant role. Workshop Format --------------- Participants will be machine learning specialists with an interest in expanding their research profile into the area of assistive technology, existing researchers in AT, practitioners in occupational therapy with an interest in machine learning, and technology developers with an interest in further developing their application area into this novel field of research. The main focus of the workshop will be on discussions and brainstorming sessions of breakout groups with the explicit goal of identifying demands from the field of AT, and ML related research topics that will help to overcome current bottlenecks for successful AT approaches. The workshop will consist of invited talks from two perspectives (medical/industrial and academic/research) to be given by experts from the field. Participants of the workshop will be asked to submit short or long papers. Accepted papers will briefly be presented orally in short (spotlight) sessions. Accompanying posters will be displayed throughout the whole workshop. The workshop will then define breakout discussion topics, and will allocate participants to groups for brainstorming sessions, closing with presentations and discussions. Significant time will be allocated to these breakout discussions and the presentations of their findings. Invited Talks ------------- Prasad Tadepalli, Oregon State University will speak from the machine learning perspective Other invited speakers to be confirmed soon. Submissions: ------------------- We welcome the following types of papers: 1. 6-8 page research papers that describe research in machine learning as applied to assistive technology 2. 6-8 page research papers that describe studies of assistive technology, emphasising the role (or potential role) of learning. 3. 2 page position statements or research abstacts from academia or industry describing particular approaches or research techniques and tools Accepted papers will be presented as posters. Exceptional work will be considered for oral presentation. All submissions should adhere to NIPS format (http://nips.cc/PaperInformation/StyleFiles). Please email your submissions to: mlat.nips2010 at gmail.com Deadline for Submissions: Wednesday, October 20, 2010 Notification of Decision: Wednesday, November 3, 2010 Organizers: ----------- Jesse Hoey, University of Waterloo, jhoey at cs.uwaterloo.ca Pascal Poupart, University of Waterloo, ppoupart at cs.uwaterloo.ca Thomas Plotz, Newcastle University, t.ploetz at ncl.ac.uk We look forward to receiving your submissions! Jesse, Pascal and Thomas -- Jesse Hoey David R. Cheriton School of Computer Science University of Waterloo 200 University Avenue West Waterloo, Ontario N2L 3G1 CANADA tel: +15198884567x37744 email: jhoey at cs.uwaterloo.ca ---------- Forwarded message ---------- From: Laurens van der Maaten To: Date: Tue, 31 Aug 2010 11:00:49 -0700 Subject: NIPS 2010 Workshop on Challenges of Data Visualization -- Apologies if you receive multiple copies of this announcement -- -- Please forward to anyone who might be interested -- ###################################################################### CALL FOR PAPERS Challenges of Data Visualization a workshop in conjunction with 24th Annual Conference on Neural Information Processing Systems (NIPS 2010) December 10 or 11, 2010 Whistler, BC, Canada http://cseweb.ucsd.edu/~lvdmaaten/workshops/nips2010 Submission deadline: October 22, 2010 Acceptance notification: November 5, 2010 ##################################################################### Overview: --------------------------------- The increasing amount and complexity of electronic data sets turns visualization into a key technology to provide an intuitive interface to the information. Unsupervised learning has developed powerful techniques for, e.g., manifold learning, dimensionality reduction, collaborative filtering, and topic modeling. However, the field has so far not fully appreciated the problems that data analysts seeking to apply unsupervised learning to information visualization are facing such as heterogeneous and context dependent objectives or streaming and distributed data with different credibility. Moreover, the unsupervised learning field has hitherto failed to develop human-in-the-loop approaches to data visualization, even though such approaches including, e.g., user relevance feedback are necessary to arrive at valid and interesting results. As a consequence, a number of challenges arise in the context of data visualization which cannot be solved by classical methods in the field: - Methods have to deal with modern data formats and data sets: How can the technologies be adapted to deal with streaming and probably non i.i.d. data sets? How can specific data formats be visualized appropriately such as spatio-temporal data, spectral data, data characterized by a general probably non-metric dissimilarity measure, etc.? How can we deal with heterogeneous data and different credibility? How can the dissimilarity measure be adapted to emphasize the aspects which are relevant for visualization? - Available techniques for specific tasks should be combined in a canonic way: How can unsupervised learning techniques be combined to construct good visualizations? For instance, how can we effectively combine techniques for clustering, collaborative filtering, and topic modeling with dimensionality reduction to construct scatter plots that reveal the similarity between groups of data, movies, or documents? How can we arrive at context dependent visualization? - Visualization techniques should be accompanied by theoretical guarantees: What are reasonable mathematical specifications of data visualization to shape this inherently ill-posed problem? Can this be controlled by the user in an efficient way? How can visualization be evaluated? What are reasonable benchmarks? What are reasonable evaluation measures? - Visualization techniques should be ready to use for users outside the field: Which methods are suited to users outside the field? How can the necessity be avoided to set specific technical parameters by hand or choose from different possible mathematical algorithms by hand? Can this necessity be substituted by intuitive interactive mechanisms which can be used by non-experts? The goal of the workshop is to identify the state-of-the-art with respect to these challenges and to discuss possibilities to meet these demands with modern techniques. The workshop will consist of invited tutorial talks, presentations of new research in a poster session, and panel discussions to identify the current state-of-the-art and future perspectives. Registration will be open to all NIPS 2010 Workshop attendees. Submissions: --------------------------------- We solicit submissions for an oral or poster presentation that report new (unpublished) research results or ongoing research. Submissions can be up to 4 pages long. It is allowed to use additional pages for visualizations (i.e., it is acceptable to have additional pages with images). Papers should be formatted in NIPS 2010 format (LaTeX style files are available on the conference website). Papers must be in English and must be submitted as PDF files. If accepted, submissions will be published on the workshop website. Papers should be submitted electronically no later than 23:59 Pacific Standard time, Friday, October 22, 2010. The submission website will be announced soon. At least one author of each accepted submission will be expected to attend and present their findings at the workshop. We encourage submissions connected to the following non-exhaustive list of topics: - Visualization methods for streaming data sets - Visualization of structures and heterogeneous objects - Visualization of multiple modalities and non-metric data - Back-projection methods - Parameterless models for data visualization - Evaluation measures of data visualization - Innovative combination of different machine learning tools for data visualization - Novel benchmarks for data visualization Dates: --------------------------------- - Submission deadline: October 22, 2010 - Acceptance notification: November 5, 2010 - Workshop date: December 10 or 11, 2010 Organizers: --------------------------------- - Barbara Hammer, TU Clausthal - Laurens van der Maaten, UC San Diego / Delft University of Technology - Fei Sha, University of Southern California - Alex Smola, Yahoo! Research / Australian National University ---------- Forwarded message ---------- From: Marco Signoretto To: connectionists at cs.cmu.edu Date: Mon, 13 Sep 2010 22:20:31 +0200 Subject: NIPS 2010 Workshop: Tensors, Kernels, and Machine Learning - Call for Contributions ======================================================================= NIPS2010 Workshop Tensors, Kernels, and Machine Learning Friday December 10th, Whistler, BC http://csmr.ca.sandia.gov/~dfgleic/tkml2010 ----------------------------------------------------------------------- Submission deadline: September 30th, 2010 Notification deadline: October 11th, 2010 ----------------------------------------------------------------------- Tensors are a generalization of vectors and matrices to high dimensions. The goal of this workshop is to explore the links between tensors, kernel methods, and machine learning. We expect that many problems in, for example, machine learning and kernel methods can benefit from being expressing as tensor problems; conversely, the tensor community may learn from the estimation techniques commonly used in information processing and from some of the kernel extensions to nonlinear models. Moreover, some of the techniques in kernel methods might enable kernel based multi-linear models of tensors. This workshop is appropriate for anyone who wishes to learn more about tensor methods and/or share their machine learning or kernel techniques with the tensor community; conversely, we invite contributions from tensor experts seeking to use tensors for problems in machine learning and information processing. Please see http://csmr.ca.sandia.gov/~dfgleic/tkml2010for more information about submissions. ORGANIZERS Andreas Argyriou (Toyota Institute of Technology), David F. Gleich (Sandia), Tamara G. Kolda (Sandia), Vicente Malave (UC San Diego), Marco Signoretto (KU Leuven), Johan Suykens (KU Leuven) ======================================================================= -- Marco Signoretto, Office Nr. 04.11 ESAT - SCD - SISTA, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 LEUVEN - HEVERLEE (BELGIUM) Email : Marco.Signoretto at esat.kuleuven.be Phone: +32 16 328657 ---------- Forwarded message ---------- From: Ruslan Salakhutdinov To: connectionists at cs.cmu.edu Date: Wed, 25 Aug 2010 17:04:23 -0400 (EDT) Subject: NIPS 2010 workshop on Transfer Learning Via Rich Generative Models -- Apologies if you receive multiple copies of this announcement -- ------------------------------------------------------------ CALL FOR CONTRIBUTIONS NIPS 2010 workshop on Transfer Learning Via Rich Generative Models. Whistler, BC, Canada, December, 2010 http://www.mit.edu/~rsalakhu/workshop_nips2010/index.html Important Dates: ---------------- Deadline for submissions: October 20, 2009 Notification of acceptance: October 27, 2009 Overview: ---------------- Intelligent systems must be capable of transferring previously-learned abstract knowledge to new concepts, given only a small or noisy set of examples. This transfer of higher order information to new learning tasks lies at the core of many problems in the fields of computer vision, cognitive science, machine learning, speech perception and natural language processing. Over the last decade, there has been considerable progress in developing cross-task transfer (e.g., multi-task learning and semi-supervised learning) using both discriminative and generative approaches. However, many existing learning systems today can not cope with new tasks for which they have not been specifically trained. Even when applied to related tasks, trained systems often display unstable behavior. More recently, researchers have begun developing new approaches to building rich generative models that are capable of extracting useful, high-level structured representations from high-dimensional input. The learned representations have been shown to give promising results for solving a multitude of novel learning tasks, even though these tasks may be unknown when the generative model is being trained. Although there has been recent progress, existing computational models are still far from being able to represent, identify and learn the wide variety of possible patterns and structure in real-world data. The goal of this workshop is to catalyze the growing community of researchers working on learning rich generative models, assess the current state of the field, discuss key challenges, and identify future promising directions of investigation. (More detailed background information is available at the workshop website, http://www.mit.edu/~rsalakhu/workshop_nips2010/index.html ) Submission Instructions: ------------------------ We invite submission of extended abstracts to the workshop. Extended abstracts should be 2-4 pages and adhere to the NIPS style ( http://nips.cc/PaperInformation/StyleFiles). Submissions should include the title, authors' names, institutions and email addresses and should be sent in PDF or PS file format by email to gentrans-nips2010 at cs.toronto.edu Submissions will be reviewed by the organizing committee on the basis of relevance, significance, technical quality, and clarity. Selected submissions may be accepted either as an oral presentation or as a poster presentation: there will be a limited number of oral presentations. We encourage submissions with a particular emphasis on: 1. Learning structured representations: How can machines extract invariant representations from a large supply of high-dimensional highly-structured unlabeled data? How can these representations be used to learn many different concepts (e.g., visual object categories) and expand on them without disrupting previously-learned concepts? How can these representations be used in multiple applications? 2. Transfer Learning: How can previously-learned representations help learning new tasks so that less labeled supervision is needed? How can this facilitate knowledge representation for transfer learning tasks? 3. One-shot learning: Can we develop rich generative models that are capable of efficiently leveraging background knowledge in order to learn novel categories based on a single or a few training example? Are there models suitable for deep transfer, or generalizing across domains, when presented with few examples? 4. Deep learning: Recently, there has been notable progress in learning deep probabilistic generative models, including Deep Belief Networks, Deep Boltzmann Machines, deep nonparametric Bayesian models, that contain many layers of hidden variables. Can these models be extended to transfer learning tasks as well as learning new concepts with only one or few examples? Can we use representations learned by the deep models as an input to more structured hierarchical Bayesian models? 5. Scalability and success in real-world applications: How well do existing transfer learning models scale to large-scale problems including problems in computer vision, natural language processing, and speech perception? How well do these algorithms perform when applied to modeling high-dimensional real-world distributions (e.g. the distribution of natural images)? Organizers ---------- Ruslan Salakhutdinov, MIT Ryan Adams, University of Toronto Josh Tenenbaum, MIT Zoubin Ghahramani, University of Cambridge Tom Griffiths, University of California, Berkeley. ---------- Forwarded message ---------- From: Ben Taskar To: connectionists at cs.cmu.edu Date: Thu, 26 Aug 2010 07:30:59 -0400 Subject: Call for papers: NIPS 2010 Workshop on Coarse-to-Fine Learning and Inference Apologies for multiple copies of this announcement. ###################################################################### CALL FOR PAPERS Coarse-to-Fine Learning and Inference a workshop in conjunction with 24th Annual Conference on Neural Information Processing Systems (NIPS 2010) December 10 or 11, 2010 Whistler, BC, Canada http://learning.cis.upenn.edu/coarse2fine/ Deadline for Submissions: Friday, October 29, 2010 Notification of Decision: Monday, November 8, 2010 ##################################################################### Overview The bottleneck in many complex prediction problems is the prohibitive cost of inference or search at test time. Examples include structured problems such as object detection and segmentation, natural language parsing and translation, as well as standard classification with kernelized or costly features or a very large number of classes. These problems present a fundamental trade-off between approximation error (bias) and inference or search error due to computational constraints as we consider models of increasing complexity. This trade-off is much less understood than the traditional approximation/estimation (bias/variance) trade-off but is constantly encountered in machine learning applications. The primary aim of this workshop is to formally explore this trade-off and to unify a variety of recent approaches, which can be broadly described as "coarse-to-fine" methods, that explicitly learn to control this trade-off. Unlike approximate inference algorithms, coarse-to-fine methods typically involve exact inference in a coarsened or reduced output space that is then iteratively refined. They have been used with great success in specific applications in computer vision (e.g., face detection) and natural language processing (e.g., parsing, machine translation). However, coarse-to-fine methods have not been studied and formalized as a general machine learning problem. Thus many natural theoretical and empirical questions have remained un-posed; e.g., when will such methods succeed, what is the fundamental theory linking these applications, and what formal guarantees can be found? A significant portion of the workshop will be given over to discussion, in the form of two organized panel discussions and a small poster session. We have taken care to invite speakers who come from each of the research areas mentioned above, and we intend to similarly ensure that the panels are comprised of speakers from multiple communities. We anticipate that this workshop will lead to new research directions in the analysis and development of coarse-to-fine and other methods that address the bias/computation trade-off, including the establishment of several benchmark problems to allow easier entry by researchers who are not domain experts into this area. Call for Participation We invite submission of workshop papers that discuss ongoing or completed work in machine learning, computer vision, and natural language processing and addressing large-scale prediction problems where inference cost is a major bottleneck. Furthermore, because the "coarse-to-fine" label is broadly interpreted across many different fields, we also invite any submission that involves learning to address the bias/computation trade-off or that provides new theoretical insight into this problem. A workshop paper should be no more than six pages in the standard NIPS format. Authorship should not be blind. Please submit a paper by emailing it in Postscript or PDF format to coarse2fineNIPS2010 at gmail.com. We anticipate accepting six such papers for poster presentations, some of which will also receive an oral presentation. Please only submit an article if at least one of the authors will be able to attend the workshop and present the work. * Please use NIPS template and style files. No more than 6 pages, authorship not blind. * Submit to coarse2fineNIPS2010 at gmail.com by October 29. Important Dates: * Friday, October 29 -- Paper submission deadline * Monday, November 8 -- Notification of acceptance Organizers: Ben Taskar taskar at cis.upenn.edu University of Pennsylvania David Weiss djweiss at cis.upenn.edu University of Pennsylvania Ben Sapp bensapp at cis.upenn.edu University of Pennsylvania Slav Petrov petrov at cs.berkeley.edu Google Research, New York ---------- Forwarded message ---------- From: Marius Kloft To: connectionists at cs.cmu.edu Date: Wed, 01 Sep 2010 23:18:39 -0700 Subject: NIPS 2010 Workshop: New Directions in Multiple Kernel Learning - Call for Contributions ========================================================================= CALL FOR PAPERS New Directions in Multiple Kernel Learning NIPS 2010 Workshop, Whistler, British Columbia, Canada http://doc.ml.tu-berlin.de/mkl_workshop -- Submission Deadline: October 18, 2010 -- ========================================================================= Research on Multiple Kernel Learning (MKL) has matured to the point where efficient systems can be applied out of the box to various application domains. In contrast to last year's workshop, which evaluated the achievements of MKL in the past decade, this workshop looks beyond the standard setting and investigates new directions for MKL. In particular, we focus on two topics: 1. There are three research areas, which are closely related, but have traditionally been treated separately: learning the kernel, learning distance metrics, and learning the covariance function of a Gaussian process. We therefore would like to bring together researchers from these areas to find a unifying view, explore connections, and exchange ideas. 2. We ask for novel contributions that take new directions, propose innovative approaches, and take unconventional views. This includes research, which goes beyond the limited classical sum-of-kernels setup, finds new ways of combining kernels, or applies MKL in more complex settings. The workshop will include: * A brief introduction talk * 4 invited keynote talks on new views and directions in MKL * 4 talks by authors of contributed papers * A poster session of contributed papers, and a poster-spotlight session * A discussion panel The organizing committee is seeking short research papers for presentation at the workshop. The committee will select several submitted papers for 15-minute talks and poster presentations. The accepted papers will be published on the workshop web site. We plan to publish proceedings of this workshop in a special issue of an appropriate journal. We will submit a proposal for such an issue to the Journal of Machine Learning Research. Amongst others, we encourage submissions in the following areas: * New views on MKL, e.g., from the perspectives of metric learning, Gaussian processes, learning with similarity functions, etc. * New approaches to MKL, in particular, kernel parameterizations different than convex combinations and new objective functions * Sparse vs. non-sparse regularization in similarity learning * Use of MKL in unsupervised, semi-supervised, multi-task, and transfer learning * MKL with structured input/output * Innovative applications SUBMISSION GUIDELINES Submissions should be written as extended abstracts, no longer than 4 pages in the NIPS latex style. Style files and formatting instructions can be found at http://nips.cc/PaperInformation/StyleFiles. The extended abstract may be accompanied by an unlimited appendix and other supplementary material, with the understanding that anything beyond 4 pages may be ignored by the program committee. Please send your submission by email to ml-newtrendsinmkl at lists.tu-berlin.de before October 18. Notifications will be given on Nov 2. Topics that were recently published or presented elsewhere are allowed, provided that the extended abstract mentions this explicitly. ORGANIZERS: Marius Kloft (UC Berkeley), Ulrich Rueckert (UC Berkeley), Cheng Soon Ong (ETH Zuerich), Alain Rakotomamonjy (University of Rouen), Soeren Sonnenburg (TU Berlin/Max Planck FML), Francis Bach (ENS/INRIA) WORKSHOP HOMEPAGE: http://doc.ml.tu-berlin.de/mkl_workshop ---------- Forwarded message ---------- From: "Yu, Shipeng (H USA)" To: Date: Thu, 26 Aug 2010 15:43:48 -0400 Subject: NIPS-2010 workshop on Predictive Models in Personalized Medicine -- Apologies if you receive multiple copies of this announcement -- ------------------------------------------------------------ CALL FOR CONTRIBUTIONS NIPS 2010 workshop on Predictive Models in Personalized Medicine Whistler, BC, Canada, December, 2010 http://sites.google.com/site/personalmedmodels/ Important Dates: ---------------- Deadline for submissions: October 8, 2010 Notification of acceptance: November 12, 2010 Background: ---------------- Recently there has been a paradigm shift from evidence based medicine to personalized medicine. Earlier optimal therapy selection based on populations e.g. If a patient belonged to a homogenous category such as T2 stage, node negative, non-metastatic, non-small cell lung cancer, the best treatment was selected on clinical trials for the various medications on the same population. Historically, treatment is identical for all members of this patient cohort. While this approach was developed to utilize the statistical power of significantly large sample of a relatively homogeneous group of patients, it ignores the heterogeneity of the individuals within the cohort. This is slowly being replaced by personalized predictive models utilize all available information from each patient (exams, demographics, imaging, lab, genomic etc.) to identify optimal therapy in an individualized manner. This approach improves outcomes because it exploits more detailed patient information to reduce uncertainty in predicting patient outcomes as a function of treatment. This finds applications in preventive care, diagnosis, therapy selection and monitoring. For example, a) predicting patients at risk of developing hypertension and preventing manifestation ahead of time with appropriate intervention (medications, diet, lifestyle changes etc.); b) improving the early detection of cancer in asymptomatic patient; c) selecting the optimal chemotherapy/radiation dosage or other therapy parameters based on patient characteristics. Chemotherapy is expensive with terrible side effects and often only works for less than 50% of the patients treated with it. Identifying the right subset of patients that can benefit from it reduces the costs and improves efficacy of the treatment. d) predicting patient response to a given medication or/and treatment: Often the outcomes of therapy manifest too late e.g. outcomes of chemo-radiation therapy in patients with non-small cell lung cancer may take many months to manifest. By monitoring surrogate markers, one may be able to predict poor outcomes early on and modify the therapy plan. Also by predicting patient response and adequate dosage for a given medication , undesirable possible drugs adverse side effects can be avoided. A good example of this is the recent work from the International Warfarin Pharmacogenetics Consortium (see references) on estimation of the Warfarin Dose with Clinical and Pharmacogenetic Data. Goal: ---------------- The purpose of this cross-discipline workshop is to bring together machine learning and healthcare researchers interested in problems and applications of predictive models in the field of personalized medicine. The goal of the workshop will be to bridge the gap between the theory of predictive models and the applications and needs of the healthcare community. There will be exchange of ideas, identification of important and challenging applications and discovery of possible synergies. Ideally this will spur discussion and collaboration between the two disciplines and result in collaborative grant submissions. The emphasis will be on the mathematical and engineering aspects of predictive models and how it relates to practical medical problems. Although, predictive modeling for healthcare has been explored by biostatisticians for several decades, this workshop focuses on substantially different needs and problems that are better addressed by modern machine learning technologies. For example, how should we organize clinical trials to validate the clinical utility of predictive models for personalized therapy selection? This workshop does not focus on issues of basic science; rather, we focus on predictive models that combine all available patient data (including imaging, pathology, lab, genomics etc.) to impact point of care decision making. Topics of Interest: ---------------- We would like to encourage submissions on any of (but not limited to) the following topics: ** Applications - Personalized Medicine (individualized or sub-population based) - Preventive Medicine - Therapy Selection - Precision Diagnostics (Disease Sub-typing, Precise Diagnosis) - Companion Diagnostics and Therapeutics - Patient Risk Assessment (for incidence of disease) - Integrated Diagnostics combining modalities like imaging, genomics and in-vitro diagnostics. ** Algorithms/Theory - Dealing with missing data (e.g. data not missing at random) - Inductive transfer for reducing sample sizes - Feature Selection - Classification - Survival Analysis - Data Challenges (Noise, other pre-processing) - Statistical Methods for validating personalized predictive models (e.g. Clinical Trials) Submission Instructions: ------------------------ We call for paper contribution of up to 8 pages to the workshop using NIPS style. Accepted papers will be either presented as a talk or poster (with poster spotlight). They will also be available in an online proceedings that will be made available prior to the workshop. Extended versions of some accepted papers will also be invited for inclusion in an edited book on the same topic as the workshop. Papers should be emailed to the organizers at personalmedmodels.nips10 at gmail.com. Please indicate your preference for oral or poster presentation. Organizers ---------- Faisal Farooq, Siemens Medical Solutions USA, Inc. Balaji Krishnapuram, Siemens Medical Solutions USA, Inc. Romer Rosales, Siemens Medical Solutions USA, Inc. Glenn Fung, Siemens Medical Solutions USA, Inc. Shipeng Yu, Siemens Medical Solutions USA, Inc. Jude Shavlik, University of Wisconsin at Madison ---------------------------------------------------------------------------- This message and any included attachments are from Siemens Medical Solutions and are intended only for the addressee(s). The information contained herein may include trade secrets or privileged or otherwise confidential information. Unauthorized review, forwarding, printing, copying, distributing, or using such information is strictly prohibited and may be unlawful. If you received this message in error, or have reason to believe you are not authorized to receive it, please promptly delete this message and notify the sender by e-mail with a copy to Central.SecurityOffice at siemens.com Thank you ---------- Forwarded message ---------- From: Yanjun Qi To: connectionists at cs.cmu.edu, Connectionists-Request at cs.cmu.edu Date: Fri, 17 Sep 2010 17:48:54 -0400 Subject: [NIPS 2010 MLCB workshop ] Call for contributions - New Problems and Methods in Computational Biology ---------- Call for contributions New Problems and Methods in Computational Biology http://www.mlcb.org A workshop at the Twenty-Third Annual Conference on Neural Information Processing Systems (NIPS 2010) Whistler, BC, Canada, December 10 or 11, 2010. Deadline for submission of extended abstracts: Oct 25, 2010, 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), high-content phenotypic screening data, 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, semi-supervised approaches, feature selection and other techniques applied to relevant bioinformatics problems would all be appropriate for the workshop. SUBMISSION INSTRUCTIONS Researchers interested in contributing should upload an extended abstract of 4 pages in PDF format to the MLCB submission web site http://www.easychair.org/conferences/?conf=mlcb2010 by Oct 25, 2010, 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 pt) and margins (1 in). 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 http://www.mlcb.org/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, we intent to make presentations 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 Gunnar R?tsch, Friedrich Miescher Laboratory of the Max Planck Society Tomer Hertz, Fred Hutchinson Cancer Research Center Yanjun Qi, Machine Learning Department, NEC Research Jean-Philippe Vert, Mines ParisTech, Institut Curie PROGRAM COMMITTEE Mathieu Blanchette, McGill University Gal Chechik, Google Research Florence d'Alche-Buc, Universit? d'Evry-Val d'Essonne, Genopole, Eleazar Eskin, UC Los Angeles, Brendan Frey (University of Toronto) Alexander Hartemink (Duke University) David Heckerman, Microsoft Research , Michael I. Jordan, UC Berkeley , Christina Leslie, Memorial Sloan-Kettering Cancer Research Center, Michal Linial, The Hebrew University of Jerusalem , Quaid Morris, University of Toronto, Klaus-Robert M?ller, Fraunhofer FIRST , William Stafford Noble, Department of Genome Sciences, University of Washington Dana Pe'er, Columbia University , Uwe Ohler, Duke University , Alexander Schliep, Rutgers University, Koji Tsuda, Computational Biology Research Center Alexander Zien, LIFE Biosystems -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100920/2368af0c/attachment-0001.html From wermter at informatik.uni-hamburg.de Tue Sep 21 13:02:20 2010 From: wermter at informatik.uni-hamburg.de (Stefan Wermter) Date: Tue, 21 Sep 2010 19:02:20 +0200 Subject: Connectionists: research associate : adaptive ambient robotics Message-ID: <4C98E51C.3060907@informatik.uni-hamburg.de> UNIVERSITY OF HAMBURG, Department: Informatics Institute: Research Group for Knowledge Technology Open Position: Research Associate Cognitive Ambient Robotics The University has a 75% FTE (29.25 hours/week) open position for a research associate (wissenschaftliche/r Mitarbeiter/in) salary group 13 TV-L with a starting date of as soon as possible for the project KSERA. This contract is valid until 31.1.2013. The university intends to increase the number of women amongst its academic personnel and encourages qualified women to apply. In compliance with the Hamburg Equal Opportunity Law, preference will be given to qualified female applicants. Area(s) of Responsibility: The research area is intelligent systems and artificial intelligence, in particular socially assistive robots and ambient intelligence. This includes the integration of an ambient environment with new adaptive humanoid robots. A system architecture, robot navigation and human robot interaction modules for the robotic device will be developed including methods from neural networks, statistics and symbolic AI. Requirements: Academic degree in one of the above academic subject areas qualifying the holder to carry out the above-mentioned responsibilities. In particular, at least an MSc or equivalent in Artificial Intelligence, Computer Science or Robotics/Engineering with a focus on Intelligent Systems is required. Excellent programming skills (C++, Python etc) are needed and a background in robotics, neural networks, machine learning or sensor technology would be an advantage for the position. The post involves traveling within Europe. We are also looking for very good English communication skills and teamwork. Preference will be given to disabled applicants with equal qualifications. Responsibilities: The research associate?s duties include academic service for the following project: KSERA (Knowledgeable Service Robots for Aging). Outside of these tasks the research associate has the opportunity to further his/her academic education, in particular through the work towards a doctoral dissertation. Results obtained by the associate through project work may be used for the dissertation. Applications (application letter, curriculum vitae, certificates etc.) are to be submitted electronically by 31st Oct 2010 to Ms Elke Brodtrueck, brodtrueck at informatik.uni-hamburg.de . Interviews are expected to begin from November until the position is filled. For more information see http://www.informatik.uni-hamburg.de/WTM/ and http://ksera.ieis.tue.nl/ . For queries please contact Prof. Dr. Stefan Wermter, Head of Know-ledge Technology at wermter at informatik.uni-hamburg.de . Please forward to interested staff/ postgraduate students. best wishes Stefan Wermter *********************************************** Professor Dr. Stefan Wermter Head of Knowledge Technology Department of Informatics University of Hamburg Vogt Koelln Str. 30 22527 Hamburg, Germany Secretary: +49 40 42883 2433 Phone: +49 40 42883 2434 Fax : +49 40 42883 2515 Email: wermter (at) informatik.uni-hamburg.de http://www.informatik.uni-hamburg.de/~wermter/ http://www.informatik.uni-hamburg.de/WTM/ *********************************************** From rm at cs.tu-berlin.de Tue Sep 21 22:02:13 2010 From: rm at cs.tu-berlin.de (Robert Martin) Date: Wed, 22 Sep 2010 04:02:13 +0200 Subject: Connectionists: Call for applications: Doctoral Program in Machine Learning and Computational Neuroscience Message-ID: <4C9963A5.10100@cs.tu-berlin.de> The Bernstein Center for Computational Neuroscience (BCCN) Berlin and the TU Berlin invite applications for *7 Fellowships* of the Research Training Group ?Sensory Computation in Neural Systems? (GRK 1589/1). Doctoral candidates will develop computational methods for the study of sensory computations, focusing on time and dynamics, and apply these in experiments. To this end, the training group brings machine learning and engineering together with neural and cognitive modeling as well as experimental approaches. Each student will be supervised by two investigators with complementary expertise and will be associated with the Bernstein Center for Computational Neuroscience Berlin, http://www.bccn-berlin.de/, a well-known research center dedicated to the theoretical study of neural processing. Candidates are expected to hold a Masters degree (or equivalent) in a relevant subject (e.g., neuroscience, cognitive science, computer science, physics, etc.) and have the required advanced mathematical background. All applications received until November 15, 2010, are assured full consideration. Successful candidates will be invited for a short presentation and an interview, expected to take place in January 2011. Later applications may be considered if places are still available. The fellowships of approximately 1500 ?/month will be granted for up to three years. For further information concerning the program and the application procedure, see http://www.bccn-berlin.de/Graduate+Programs/Doctoral+Program/ or e-mail graduateprograms at bccn-berlin.de . -- Robert Martin, PhD Bernstein Center for Computational Neuroscience (BCCN) Berlin Philippstr. 13, Haus 6, 10115 Berlin, Germany From thomas.wennekers at plymouth.ac.uk Wed Sep 22 13:29:45 2010 From: thomas.wennekers at plymouth.ac.uk (Thomas Wennekers) Date: Wed, 22 Sep 2010 18:29:45 +0100 Subject: Connectionists: Associate Professor / Professor Post in Robotic and Neural Systems Message-ID: <201009221829.45498.thomas.wennekers@plymouth.ac.uk> Associate Professor (Reader) / Professor in Robotics and Neural Systems Faculty of Science and Technology School of Computing and Mathematics Centre for Robotics and Neural Systems Ref: A1905 Salary ?45155 to ?59089 pa ? Grade 9 / Senior Manager Scale The Centre for Robotics and Neural Systems is inviting applicants for a post of Professor or Associate Professor (Reader) in one, or more, of the fields of computational neuroscience, cognitive robotics, and computational intelligence. You will be working in a large inter-disciplinary research team at the Centre for Robotics and Neural Systems and the School of Computing and Mathematics. This new post is part of the university?s strategic investment in research, following the success of the centre at the latest Research Assessment Exercise (RAE2008). You must have a strong track record of research at world leading and/or international excellence level, including publications in the leading journals in the field. A sustainable track record of grant income, leadership of research laboratory/group, and evidence of research impact and peer esteem at international excellence level is also essential. The offer of a full Professor, or an Associate Professor (Reader), post will be commensurate to the track record of the candidate. Recruitment and selection will be based on individual merit, however, we should particularly like to encourage applications from women, black and minority ethnic people who are under-represented in the Faculty of Science and Technology. For more information on the centre please visit http://www.tech.plym.ac.uk/SoCCE/CRNS/ For an informal discussion, please contact Professor Angelo Cangelosi on 01752 586217 or email angelo.cangelosi at plymouth.ac.uk although applications must be made in accordance with the details shown. Closing date: 12 noon, Friday 22 October 2010 For further information see http://www.plymouth.ac.uk/pages/view.asp?page=33347 From dayan at gatsby.ucl.ac.uk Sat Sep 25 17:43:13 2010 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Sat, 25 Sep 2010 22:43:13 +0100 Subject: Connectionists: job openings @ UCL Message-ID: <20100925214312.GC422@gatsby.ucl.ac.uk> I am posting this announcement on behalf of Kate Jeffery (UCL): Call for Expressions of Interest: UCL Cognitive, Perceptual and Brain Sciences The UCL Cognitive, Perceptual and Brain Sciences (CPB) Research Department, within the Division of Psychology and Language Sciences, is planning the future appointment of at least two and likely more academic posts (at Lecturer, Senior Lecturer, Reader or Professor level) to complement existing strengths. For one post the emphasis is on multimodal communication, with ideal candidates having research interests that include sign language/deafness research. For a second post, the emphasis is on Decision and Cognitive Sciences. However, we would also encourage other candidates with an excellent record of internationally renowned research in other areas represented within the department (including computational and animal neuroscience) to express their interest in the posts. UCL CPB offers a top research and teaching environment with research covering behavioural neuroscience, perceptual and cognitive sciences and cognitive neuroscience. Members of the department are directly involved in the activities of a number of research centres, including the Deafness, Cognition and Language (DCAL) centre, the Institute of Behavioural Neuroscience (IBN), the Birkbeck/UCL Centre for Neuroimaging (BUCNI) and the Centre for Mathematics and Physics in the Life Sciences and Experimental Biology (CoMPLEX). They further contribute to the Institute of Cognitive Neuroscience (ICN) and the Wellcome Department of Imaging Neuroscience. Research facilities available to members of staff comprise state-of-the-art equipment for most types of behavioural research including a multimodal communication laboratory, animal housing facility, MRI scanner and TMS facilities. At this stage, we invite informal expression of interest (including a CV and statement of research interests) which should be directed to Kate Jeffery by email at k.jeffery at ucl.ac.uk before October 20 2010. From dglanzma at mail.nih.gov Mon Sep 27 12:07:15 2010 From: dglanzma at mail.nih.gov (Glanzman, Dennis (NIH/NIMH) [E]) Date: Mon, 27 Sep 2010 12:07:15 -0400 Subject: Connectionists: FINAL CALL FOR POSTERS - 18th Annual Dynamical Neuroscience Meeting Message-ID: <87A69598824B3D4EBF14080B3F0906BE031C66A82B@NIHMLBX12.nih.gov> FINAL CALL FOR POSTERS 18th Annual Dynamical Neuroscience Satellite Symposium The Resting Brain: Not At Rest! Preceding the 40th Annual Meeting of the Society for Neuroscience Thursday and Friday, November 11-12, 2010 Manchester Grand Hyatt Hotel, San Diego, CA The theme of this year's meeting emphasizes the role of endogenous, ongoing activity (and noise) in determining behavior. The concept of "the brain at rest" has received much current interest as technologies have evolved which allow measuring electrical and physiological activity during periods when the subject is not engaged in pursuing any active physical or cognitive activities. In addition to being active at rest, the brain continuously monitors both internal and external environments, processes information, and alters its activity enabling it to orchestrate specific behaviours regard-less of ongoing tasks. As an example, considerable recent research activity has been devoted to examining how the phase of ongoing EEG oscillations influence ensuing perception or motor activities. Other areas focus on how correlations of activity across brain regions during rest are related to memory for recent experiences. Resting state functional connectivity shows characteristic changes in various psychiatric and neurological disorders, and a better understanding of the relationship between brain state and its induced activity due to task demands would broaden our understanding of how alterations in this relationship may be relevant to these illnesses. Submission Deadline Poster abstracts must be received by C.O.B. on October 15, 2010 to ensure that they will appear in the printed programme booklet. You will need to register for the meeting to submit a poster. Invited Speakers Kwabena Boahen, Lila Davachi, Michael Fee, Michael Hasselmo Eugene Izhikevich, Vinod Menon, Earl Miller, Tirin Moore, Yuval Nir Sheila Nirenberg, Patricio O'Donnell, Marcus Raichle and Matthew Wilson Keynote Address Winner of the 3rd Annual Swartz Prize in Computational Neuroscience Symposium Organizers Jonathan Victor, Weill Cornell Medical College, and Dennis Glanzman, NIMH/NIH For logistical information please contact Nakia Wilson, The Dixon Group, Inc., (202)-281-2825, nwilson at dixongroup.com For programmatic information, please contact Dennis Glanzman, NIMH/NIH, (301) 443-1576, glanzman at nih.gov To register for the meeting and submit a poster, please use this website: http://neuro.dgimeetings.com -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20100927/d2c14483/attachment-0001.html From Randy.OReilly at Colorado.EDU Tue Sep 28 04:12:18 2010 From: Randy.OReilly at Colorado.EDU (Randall Charles O'Reilly) Date: Tue, 28 Sep 2010 02:12:18 -0600 Subject: Connectionists: Software Developer for Computational Brain Modeling Message-ID: The Computational Cognitive Neuroscience lab at the University of Colorado Boulder (http://grey.colorado.edu/CompCogNeuro/index.php/CCNLab) and eCortex, Inc are seeking Computational Modelers who will construct, program, train, test, and support complex models of brain areas and functions. This is not a software development position, but the ability and patience to program complex software applications has proven to be an excellent indicator of success in computational modeling. Consequently, we are seeking motivated individuals with at least a bachelor?s degree in Computer Science and two years of industry experience developing software that is more complex than a web GUI. Any pertinent experience or coursework in AI, computer simulation, neural networks, neuroscience, and/or cognitive science is a plus, but there will be supervision and expertise available on these domain-specific aspects of the role, and we will train you on the relevant software (emergent neural network simulation software http://grey.colorado.edu/emergent, and other relevant tools including MATLAB, Python, and R). Interest in and enthusiasm for this field is essential. The positions are funded through various research projects, and the time commitment is initially for 1 year, with renewal opportunities for subsequent years. Some advantages of the position include: flexible hours, a casual academic-like work environment, and the opportunity to make important contributions to figuring out one of the greatest mysteries in the universe: the brain. Salary will be competitive with industry positions and based on experience. The University of Colorado is committed to diversity and equality in education and employment, and eCortex is committed to equal employment opportunity. Please email a resume and cover letter to Randy.OReilly at colorado.edu. - Randy ---- Dr. Randall C. O'Reilly Professor, Department of Psychology and Neuroscience University of Colorado Boulder 345 UCB, Boulder, CO 80309-0345 303-492-0054 Fax: 303-492-2967 http://psych.colorado.edu/~oreilly From kmtn at atr.jp Thu Sep 30 04:02:28 2010 From: kmtn at atr.jp (Yukiyasu Kamitani) Date: Thu, 30 Sep 2010 17:02:28 +0900 Subject: Connectionists: CfP: Workshop on Pattern Recognition in NeuroImaging Message-ID: Dear Colleagues, please accept our apologies for multiple postings. * CALL FOR PAPERS * International Workshop on Pattern Recognition in Neuroimaging (PRNI 2011) Seoul, Korea, May 16-18, 2011 http://brain.korea.ac.kr/prni2011 Pattern recognition and machine learning techniques provide a new way to analyze complex and huge brain imaging datasets. Many challenges are also present in other applications of pattern recognition, such as non-stationary distributions, model regularisation, high-dimensional time series, or causality modeling. Following the success of the first Workshop on Brain Decoding (Istanbul, 2010), this three-day workshop aims at providing an opportunity for discussing recent advances in methods and applications, while trying to narrow the gap between imaging modalities. A subfield where discussion is of special interest is that of real-time methods, as they are at the confluence of modalities (EEG/fMRI) and at the forefront of machine learning research (incremental learning, non-i.i.d. data). Interpretability of classification and regression machines is also critical to increasing interactions between methods and application-oriented researchers, and is of particular interest for this workshop. Several travel scholarships will be available for Ph.D. students and post-docs, and will be awarded competitively based on reviewer scores of the papers. Keynote speakers will include Stephen Strother (University of Toronto, Canada) Stephen LaConte (Baylor College of Medicine, USA) SCOPE The workshop welcomes original contributions using relevant modalities (e.g. functional/structural MRI, EEG, ECoG, MEG) including the following areas: * Data representation Voxel / channel / feature selection Linear and non-linear dimensionality reduction Sparse time-course representations Interpretability and validation * High-dimensional learning Regularisation Transfer learning Multimodal / ensemble classification Incremental / online learning and adaptation * Applications Cognitive, affective, and social neurosciences Man-machine interfaces Clinical applications SUBMISSION AND PROCEEDINGS Authors should prepare full 4-pages papers (double-column, IEEE style). Extended abstract are not accepted. The review process will be double-blind. Proceedings will be published by IEEE Computer Science Society in electronic format. They will be permantently available on the IEEExplore and IEEE CS Digital Library online repositories, and indexed in IEE INSPEC, EI Compendex (Elsevier), Thomson ISI, and others. DATES AND DEADLINES Full paper submission: December 1st, 2010 Acceptance notification: January 15th, 2011 Travel scholarship notification: January 15th, 2011 Camera-ready paper: February 15th, 2011 Workshop: May 16-18, 2011 PROGRAMME COMMITTEE R. Abugharbieh (U. of British Columbia, CA) T. Adali (U. of Maryland, Baltimore County, USA) J. Ashburner (UCL, UK) B. Blankertz (TU Berlin, DE) M. Brammer (King's College London, UK) V. Calhoun (Yale, USA) C. Chu (NIH, USA) T. Ethofer (U. T(IC<(Bbingen, DE) C. Gaser (U. Jena, DE) P. Golland (MIT, USA) L. Grosenick (Stanford, USA) G. Hamarneh (Simon Fraser U., CA) D. Hardoon (Inst. for Infocomm Research, SG) T. Jiang (Chinese Academy of Sciences, CN) K. Kryszczuk (IBM Research, CH) G. Langs (MIT, USA) F. Lotte (A*STAR, SG) A. Marquand (UCL, UK) J. Meynet (Bestofmedia Group, FR) J. Sato (Federal U. of ABC, BR) S. Schwartz (U. of Geneva, CH) N. Schuff (UCSF, USA) B. Thirion (Neurospin, FR) P. Vemuri (Mayo Clinic, USA) P. Vuilleumier (U. of Geneva, CH) M. Van Hulle (K.U. Leuven, BE) ORGANISING COMMITTEE General Chairs: S.-W Lee (Korea University, KR), C. Davatzikos (U. of Pennsylvania, USA), D. Van De Ville (EPFL/U. of Geneva, CH) Program Chairs: J. Richiardi (EPFL/U. of Geneva, CH), J. Mour(IC#(Bo-Miranda (UCL/King's College, UK), Y. Kamitani (ATR, JP) Tutorial Chair: F. Pereira (Princeton U., USA) Local Arrangements Chair: J.-H. Lee (Korea University, KR) Publication Chair: C. Wallraven (Korea University, KR) Finance Chair: J. Kwag (Korea University, KR) Registration Chair: S.-P. Kim (Korea University, KR)