From bgholami at aretexeng.com Mon Aug 3 23:28:13 2015 From: bgholami at aretexeng.com (Behnood Gholami) Date: Mon, 3 Aug 2015 23:28:13 -0400 Subject: Connectionists: Job Posting: Research Scientist or Engineer, Machine Learning Message-ID: *Research Engineer/Scientist, Machine Learning* *AreteX Engineering ? New York, NY* AreteX Engineering, a medical technology startup company accelerating the use of information technology in healthcare, has an immediate opening for a Research Engineer/Scientist in its office located in New York City, SoHo district. AreteX is a former resident of the Harvard Innovation Lab (ilab) and a current resident of the NYU Incubator. The company has received grants from the Department of Defense and the National Science Foundation. The position involves developing machine learning algorithms for innovative biomedical technologies involving physiological signal processing and big data. We are looking for a self-motivated, highly talented individual with an excellent background in machine learning (statistical learning theory). The successful candidate will work closely with a team of physicians, nurses, engineers, and scientists in designing new clinical decision support systems. Candidates with experience in the analysis of experimental data derived from---but not limited to---auditory/visual/cross-sensory psychophysical, EEG, ECG, and galvanic-skin conductance, data would be given a higher priority. *Minimum Requirements:* - MS or PhD in computer science, electrical engineering, biomedical engineering, applied mathematics, or a similar discipline. - Expertise and innovation in methods, theory, and application of machine learning and data mining with a broad understanding of methodological approaches and proficiency in practice. - Expert abilities to work with new data sets regardless of prior exposure to current topic. - Strong interest in research and learning new technologies. - Proficient at writing technical papers/reports/presentations. - Experience with Python. - Familiarity with large data sets, cloud-based development and deployment, open source practices and frameworks is a plus. - Applicants must be U.S. citizens, U.S. nationals or U.S. permanent residents. *Responsibilities* - Collaborate with a team of machine learning, control engineering, and signal processing researchers. - Provide technical expertise to address supervised and unsupervised learning problems in an applied research environment. - Develop and deploy modern machine learning and statistical methods (CART and Random Forests, deep learning, clustering and classification algorithms, Bayesian models, neural networks, support vector machines, and probabilistic graphical models) for finding patterns and models from physiological data. *Preferred Qualifications:* - Prior expertise and exposure using non-invasive human physiological measures such as EEG, ECG, galvanic-skin conductance, or other categorically similar methodologies. - Prior experience in feature extraction from physiological signals. - Experience working with quantitative methods of neural data analysis. - Experience with speech, audio, or video technologies. Send your cover letter and CV to info at aretexeng.com. -- -- Behnood Gholami, Ph.D. Chief Executive Officer AreteX Engineering 137 Varick St., 2nd Floor New York, NY 10013 Phone: (347) 774-1617 -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Tue Aug 4 16:30:37 2015 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 04 Aug 2015 16:30:37 -0400 Subject: Connectionists: Workshop on parallel computing resource for modeling and brain image analysis Message-ID: <55C120ED.6010703@yale.edu> What: Using the Neuroscience Gateway Portal for Parallel Simulations A Satellite Symposium at the 2015 Society for Neuroscience Meeting Where: Lodation to be announced in downtown Chicago, IL When: 9 AM - Noon on Saturday, October 17, 2015 Speakers to include: Amit Majumdar, Subha Sivagnanam, and Padraig Gleeson Registration deadline: Friday, October 2, 2015 This workshop is for neuroscientists who need to use parallel supercomputers for large modeling projects, or analysis and visualization of brain imaging data. With support from NSF, we have been developing the Neuroscience Gateway Portal (NSG) http://www.nsgportal.org/, which * provides free CPU time on NSF-supported high performance computing resources * has a browser-based interface that simplifies the tasks of uploading models, specifying job parameters, monitoring job status, and storing and retrieving output data * already has many widely-used simulatiors optimally installed and configured, including NEST, Pynn, Brian, GENESIS3, NEURON and MOOSE. Also available is the FreeSurfer suite of tools for analyzing and visualizing structural and functional brain imaging data. The workshop will combine didactic presentations by NSG's developers, discussions with experienced users, and hands on instruction in how to use the portal. Come find out how the NSG can be useful in your own research! For more information and the online registration form see http://www.neuron.yale.edu/neuron/static/courses/nsg2014/nsg2014.html --Ted From R.Borisyuk at plymouth.ac.uk Mon Aug 3 06:22:05 2015 From: R.Borisyuk at plymouth.ac.uk (Roman Borisyuk) Date: Mon, 3 Aug 2015 10:22:05 +0000 Subject: Connectionists: =?windows-1252?q?PhD_Studentships_=96_Centre_for_?= =?windows-1252?q?Robotics_and_Neural_Systems_=28CRNS=29=2C_Plymouth_Unive?= =?windows-1252?q?rsity=2C_UK?= Message-ID: <7C21808200B7BB4EBAE3C051E15772F6010FAE63@TIS103.uopnet.plymouth.ac.uk> PhD Studentships ? Centre for Robotics and Neural Systems (CRNS), Plymouth University, UK Following on the exceptional performance of Plymouth University in the UK Research Excellence Framework 2014, the university is now advertising the availability of 50 PhD studentships for study commencing in 2015/16. Of these studentships, at least two will be allocated to research projects and supervisors of the Centre for Robotics and Neural Systems (CRNS), within the Faculty of Science and Engineering. The first studentship can cover any topic within the CRNS research areas: * Cognitive and Humanoid Robotics * Computational Neuroscience * Artificial Intelligence The second studentship will focus on Autonomous Systems, possibly with relevance to unmanned marine systems, and will be in collaboration with the School of Marine Science and Engineering: For more details on the CRNS research projects, interests and supervisors, see: https://www1.plymouth.ac.uk/research/crns/Pages/default.aspx For general information on the studentships and application procedure, see: https://www.plymouth.ac.uk/student-life/your-studies/the-graduate-school/fully-funded-phd-studentships We recommend that in the application form and cover letter you specify a research topic and preferred supervisor. You are also encouraged to contact the individual supervisors before applying, for informal discussion. The application deadline is 15 September 2015 Roman Borisyuk, DSc, PhD Professor of Computational Neuroscience School of Computing and Mathematics University of Plymouth A224, Portland Sq Plymouth, PL4 8AA UK Phone: +44 (0) 1752 584949 E-mail: RBorisyuk at plymouth.ac.uk ________________________________ [http://www.plymouth.ac.uk/images/email_footer.gif] This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form. -------------- next part -------------- An HTML attachment was scrubbed... URL: From j.v.stone at sheffield.ac.uk Tue Aug 4 04:45:07 2015 From: j.v.stone at sheffield.ac.uk (James Stone) Date: Tue, 04 Aug 2015 09:45:07 +0100 Subject: Connectionists: Book: Bayes' Rule With MatLab Message-ID: <55C07B93.3020204@sheffield.ac.uk> I'd like to announce the publication of this book: Bayes' Rule With MatLab A Tutorial Introduction to Bayesian Analysis by JV Stone Reviews, synopsis, and table of contents can be found here: http://jim-stone.staff.shef.ac.uk/BookBayes2012/BayesRuleBookMain.html regards, Dr Jim Stone University of Sheffield, UK. http://jim-stone.staff.shef.ac.uk/BookBayes2012/books_by_jv_stone/index.html From n.lepora at bristol.ac.uk Wed Aug 5 11:47:02 2015 From: n.lepora at bristol.ac.uk (Nathan Lepora) Date: Wed, 5 Aug 2015 16:47:02 +0100 Subject: Connectionists: PhD studentship in Tactile Robotics / Superresolution (University of Bristol) Message-ID: PhD Position in Tactile Robotics / Superresolution University of Bristol and Bristol Robotics Laboratory, UK. Applications are invited for a 3.5 year funded PhD Studentship at the University of Bristol and Bristol Robotics Laboratory, UK. Funding is available for outstanding UK candidates, at a tax-free stipend of ?14,057 (2015-2016) per year. Further details can be found at http://www.bristol.ac.uk/engineering/graduate/pg-open/funding/epsrcdta.html The studentship is to undertake research on a recently awarded EPSRC grant on 'Tactile superresolution sensing': http://gow.epsrc.ac.uk/NGBOViewGrant.aspx?GrantRef=EP/M02993X/1 Further background on the research can be found on the PI's website (www.lepora.com) and in the paper: N. Lepora et al. Tactile superresolution and biomimetic hyperacuity. IEEE Transactions on Robotics 31(3), 605-618, 2015. http://dx.doi.org/10.1109/TRO.2015.2414135. The student will work closely with the PI (Dr Lepora) and a postdoctoral Research Associate funded by the grant, and will join two other PhD students working on related projects in tactile robotics. The Studentship is available from now and will remain open for applications until the position is filled. Suitable applicants should initially contact N. Lepora (n.lepora at bristol.ac.uk) enclosing a copy of their CV and a short paragraph of why they are interested in the Scholarship. **Please note that this studentship is available ONLY to UK citizens, or EU citizens resident in the UK for at least 3 years.** -- Dr N Lepora Website: http://www.lepora.com Lecturer in Engineering Mathematics http://www.bristol.ac.uk/engineering/people/nathan-f-lepora Program Director (UoB) for the MSc in Robotics http://www.bristol.ac.uk/engineering/interdisciplinary/robotics/ Department of Engineering Mathematics Merchant Venturers School of Engineering University of Bristol BS8 1UB From mehdi.khamassi at isir.upmc.fr Fri Aug 7 11:32:57 2015 From: mehdi.khamassi at isir.upmc.fr (Mehdi Khamassi) Date: Fri, 07 Aug 2015 17:32:57 +0200 Subject: Connectionists: =?utf-8?q?2nd_call_for_posters/registration=3A_Or?= =?utf-8?q?bitofrontal_Cortex_and_Cognition_in_the_City_of_Lights=2C_Sept_?= =?utf-8?q?30_=E2=80=93_Oct_2=2C_2015_=40_Paris=2C_France?= In-Reply-To: <5ecefa4796ef1d5fd97dc57dced51505@mailhost.isir.upmc.fr> References: <5ecefa4796ef1d5fd97dc57dced51505@mailhost.isir.upmc.fr> Message-ID: <55C4CFA9.3060309@isir.upmc.fr> [Please accept our apologies if you get multiple copies of this message] Dear colleagues, The "Orbitofrontal Cortex and Cognition in the City of Lights" meeting will take place in Paris, France, on Sept 30th - Oct 2nd 2015. Confirmed speakers are: Tim Behrens, Yogita Chudasama, Howard Eichenbaum, Lesley Fellows, Jay Gottfried, Shannon Gourley, Christina Gremel, Ben Hayden, Patricia Janak, Thorsten Kahnt, Daeyeol Lee, Elisabeth Murray, Yael Niv, John O'Doherty, Camillo Padoa-Schioppa, Mathias Pessiglione, Angela Roberts, Peter Rudebeck, Matthew Rushworth, Geoffrey Schoenbaum, Wolfram Schultz, Matthew Shapiro, Philippe Tobler, Jonathan Wallis, Catharine Winstanley. The deadlines for poster submission and registration (via the website: http://ofc2015.isir.upmc.fr) have both been extended to September 6^th . Please circulate widely and encourage your colleagues and team members to attend. ------------------------------------------------------------------------------------------------ ORBITOFRONTAL CORTEX AND COGNITION IN THE CITY OF LIGHTS (OFC 2015) Sept 30-Oct 2, 2015, Paris, France Institut du Cerveau et de la Moelle Epini?re, H?pital La Piti? Salp?tri?re, Paris, France. & Universit? Pierre et Marie Curie, Paris, France. http://ofc2015.isir.upmc.fr ------------------------------------------------------------------------------------------------ PRESENTATION: The Third Quadrennial Meeting on Orbitofrontal Cortex Function which will take place in Paris, France, on Sept 30th ? Oct 2nd 2015 at the Institut du Cerveau et de la Moelle Epini?re, Paris, France. The objective of this three day meeting is to bring together researchers with a deep interest in the role of the orbitofrontal cortex in supporting cognition (behavior, learning, decision-making) across species. The meeting is the third, following up on similar meetings in 2007 and 2011. As such, it is intended to focus specifically on new ideas and research that has influenced the field over the past 4 years and that appear likely to lead the way into the next 4 years. The meeting consists of both invited talks and poster sessions. The invited talks are loosely organized into six different sessions that are titled to reflect the various stages of processing underlying cognition. Talks will be relatively short with ample time for questions and discussion after each talk and sub-group of talks. Poster sessions will be interspersed to allow participants to interact and present their own unique findings of relevance to advancing our understanding of this fascinating brain region. CONFIRMED SPEAKERS: Tim Behrens (Oxford University, UK) Yogita Chudasama (McGill University, Canada) Howard Eichenbaum (Boston University, USA) Lesley Fellows (McGill University, Canada) Jay Gottfried (Northwestern University, USA) Shannon Gourley (Emory University, USA) Christina Gremel (UCSD, USA) Ben Hayden (University of Rochester, USA) Patricia Janak (John Hopkins, USA) Thorsten Kahnt (Northwestern University, USA) Daeyeol Lee (Yale University, USA) Elisabeth Murray (NIMH, USA) Yael Niv (Princeton University, USA) John O'Doherty (Caltech, USA) Camillo Padoa-Schioppa (Washington Univ. St Louis, USA) Mathias Pessiglione (INSERM-ICM, France) Angela Roberts (Cambridge University, UK) Peter Rudebeck (Mount Sinai School, USA) Matthew Rushworth (Oxford University, UK) Geoffrey Schoenbaum (NIDA-NIH, USA) Wolfram Schultz (Cambridge University, UK) Matthew Shapiro (Mount Sinai School, USA) Philippe Tobler (University of Zurich, Switzerland) Jonathan Wallis (University of California at Berkeley, USA) Catharine Winstanley (University of British Columbia, Canada) IMPORTANT DATES: September 6, 2015 Deadline for Poster Submission September 6, 2015 Deadline for Registration Sept 30-Oct 2, 2015 Symposium Venue ORGANIZING COMMITTEE: Jay Gottfried (Northwestern University, USA) Mehdi Khamassi (CNRS / UPMC, Paris, France) Elisabeth Murray (NIMH, USA) Mathias Pessiglione (INSERM / ICM, France) Geoffrey Schoenbaum (NIDA-NIH, USA) CONTACT INFORMATION : Website, registration, poster submission and detailed program: http://ofc2015.isir.upmc.fr Contact: ofc2015 [ at ] isir.upmc.fr / ofc2015-registration at isir.upmc.fr -- Mehdi Khamassi, PhD Researcher (CNRS) Institut des Syst?mes Intelligents et de Robotique (UMR7222) CNRS - Universit? Pierre et Marie Curie Pyramide, Tour 55 - Bo?te courrier 173 4 place Jussieu, 75252 Paris Cedex 05, France tel: + 33 1 44 27 28 85 fax: +33 1 44 27 51 45 cell: +33 6 50 76 44 92 http://people.isir.upmc.fr/khamassi -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.herbster at cs.ucl.ac.uk Mon Aug 10 13:43:51 2015 From: m.herbster at cs.ucl.ac.uk (Mark Herbster) Date: Mon, 10 Aug 2015 18:43:51 +0100 Subject: Connectionists: PhD Studentship in Quantum Machine Learning Message-ID: <0A9831B5-3844-4B0E-A78A-20DAE94ADAE2@cs.ucl.ac.uk> PhD Studentship in Quantum Machine Learning University College London Department of Computer Science A fully funded PhD studentship is available for UK students. It will suit students with a strong background in mathematics, physics, or theoretical computer science. The aim of this PhD position is to design and analyse efficient algorithms for quantum machine learning. We are interested in both algorithms that may be implemented with currently envisioned quantum computing devices as well as the efficient implementation on classical computers of quantum-inspired algorithms. A common framework for machine learning is regularised risk minimisation. The idea is that given a dataset we should select a hypothesis which trades off ?fit to the data? and ?complexity? of the hypothesis. Standard examples of regularisers for linear prediction include the 2-norm, 1-norm and maximum entropy. A number of machine learning problems may be framed as ?matrix learning? - these include for example collaborative filtering, metric learning, and multi-task learning. A popular approach to these problems is the use of spectral matrix regularisers, where the regulariser may be expressed as a function of singular values of the matrix predictor. The project goal is to develop quantum approaches to spectral regularisation. Practically, we will be concerned with the application of matrix learning to scheduling and network transport problems. This project will be jointly supervised by Mark Herbster, Massimiliano Pontil, and Simone Severini. Please see https://www.prism.ucl.ac.uk/#!/?project=140 for further details. Regards, Mark Herbster From liam at stat.columbia.edu Wed Aug 12 11:11:04 2015 From: liam at stat.columbia.edu (Liam Paninski) Date: Wed, 12 Aug 2015 11:11:04 -0400 Subject: Connectionists: desperately seeking neural data scientists Message-ID: Hi all (apologies for the cross-post) - we have multiple postdoctoral positions open in statistical neuroscience and machine learning. Full details here: http://grossmancenter.columbia.edu/postdoc.html, and copied below. Please share with anyone who might be interested. L Postdoctoral positions in statistical neuroscience and machine learning Multiple postdoctoral positions are available immediately in Columbia University's Grossman Center for the Statistics of the Mind, a new center focusing on the intersection of neuroscience, machine learning, and statistics. The Grossman Center bridges Columbia's Statistics and Neuroscience departments, and is closely integrated with the Center for Theoretical Neuroscience. The Grossman Center is part of Columbia's larger, growing initiatives in neuroscience and data sciences, all located in New York City. The principal appointments will be in the Statistics department, in the research groups of Liam Paninski and/or John Cunningham, with ample opportunities for interaction with an exceptional group of experimental and theoretical collaborators, including M. Churchland, L. Abbott, D. Blei, R. Yuste, R. Bruno, T. Jessell, K. Miller, E. Hillman, E.J. Chichilnisky, E. Simoncelli, K. Shenoy, M. Ahrens, and more. Requirements: Qualifications include primarily a strong research portfolio in computational neuroscience, statistical neuroscience, machine learning, or a related field. Backgrounds in analyzing large neural datasets, modeling complex neural systems, and cutting-edge machine learning will be particularly valuable. These positions are highly quantitative and highly interdisciplinary; applicants should have a PhD in Electrical Engineering, Statistics, Machine Learning, Physics, Applied Mathematics, or Computational Neuroscience. Appointment: The initial appointments will be for one year, and are renewable. Salaries will be set based on experience and skills. Applicants should send email to "grossman at stat dot columbia dot edu" providing: 1. a one-page description of past research experience 2. a one-page description of future research interests and goals 3. a resume of educational and research experience, including publications 4. names of at least two people that could provide letters of reference All materials should be in pdf or plain text. Applications will be reviewed as they arrive until the positions are filled; interested candidates are encouraged to express their interest early. Due to demand, we may not be able to reply to all applications. -------------- next part -------------- An HTML attachment was scrubbed... URL: From vembarasanv at um.edu.my Tue Aug 11 05:54:33 2015 From: vembarasanv at um.edu.my (Vembarasan Vaitheeswaran) Date: Tue, 11 Aug 2015 17:54:33 +0800 Subject: Connectionists: CFPs: Special Session on Computer and Deep Vision in 19th Asia Pacific Symposium on IES 2015 - reg Message-ID: **We apologize if you received multiple copies** Due to numerous requests, the submission deadline has one final extension until *August 15, 2015 !!!* The final deadline for papers submission is fast approaching. Dear Professors/Researchers/Friends, We are organizing the "Special Session on Computer and Deep Vision" in conjunction with the 19th Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES-2015), to be held in Bangkok from 22-25 November 2015. Special Session Theme: Vision has always played an essential role in everyday human activities. In the past, images were, today they are, and in the future they will continue to be important information carriers. Recent advances in digital imaging and computer hardware technology have led to an explosion in the use of computer vision in a variety of scientific and engineering applications. These applications often arise from the interactions between fundamental scientific research and development of new and high-standard technologies. This symposium aims to provide an opportunity for researchers to describe scientific achievements and long-term research challenges, point to new research directions, or brave perspectives that pave the way to innovation. Subjects of interest are video and image processing, and aspects of related disciplines (such as machine learning, computer graphics, biological vision, mathematics) which illuminate the state of the art in video and image processing. Topics for contributions include, but not limited to, the following research areas: - Motion Estimation - Biometrics - Video Surveillance - Deep Learning - Image Processing - Pattern Recognition - Bio-medical Image Important dates: *Paper Submission Deadline Extended: August 15, 2015 *** Notification of Acceptance: September 1, 2015 Camera-ready Deadline: September 15, 2015 Conference dates: 22-25, November 2015 Confirmed Speakers: Keynote Speakers: - Professor Tan Kay Chen, National University of Singapore, Singapore - Professor Irwin King, The Chinese University of Hong Kong, Hong Kong - Professor Chidchanok Lursinsap, Chulalongkorn University, Thailand Plenary Speaker: - Professor Akira Namatame, National Defense Academy, Japan Paper Submission: Submit your paper via the following site using your EasyChair login information: https://www.easychair.org/conferences/?conf=ies2015 NOTICE: In submission page in the site, you must to choose a track from a list. For general session papers, IES 2015 should be chosen. For invited session papers, their invited session must be selected. All manuscripts submitted should be full papers and prepared according to the Springer conference paper templates (Click here ). The manuscript text should be in one-column page format. The length of the manuscripts prepared with the given template is 10 to 12 pages, up to 15 pages. All submissions will be checked by VeriGuide for originality. The IES 2015 proceedings will be published in Proceedings in Adaptation, Learning and Optimization (PALO), a Springer-Verlag book series. More information of PALO can be found at http://www.springer.com/series/13543 Selected papers from IES 2015 will be invited to extend and publish in Special Issues of SCI/SCIE/Scopus-indexed international journals. Accepted papers will be considered for the Best Paper Awards and the Best Student Paper Awards, which will be presented during the banquet. Special Session Organizers: Dr. Vembarasan Vaitheeswaran, University of Malaya, Malaysia Dr. Jonathan Chan, King Mongkut?s University of Technology Thonburi, Thailand Dr. Weng Kin Lai, Tunku Abdul Rahman University College, Malaysia Dr. Chee Seng Chan, University of Malaya, Malaysia For more information, please contact us at inns at sit.kmutt.ac.th or Special Session Chairs at vembarasanv at um.edu.my(Dr. V. Vembarasan); cs.chan at um.edu.my (Dr. Chan Chee Seng) ? -- *With Regards,Dr. Vembarasan Vaitheeswaran,?HIR Postdoctoral FellowDepartment of Artificial Intelligence,Faculty of Computer Science and Information Technology,University of Malaya,50603 Kuala Lumpur, MalaysiaMobile Number: +6-010-9462382 <%2B6-010-9462382>E-mail: vembarasanv at um.edu.my ; dr.v.vembarasan at ieee.org Website: https://sites.google.com/site/vembarasanv/ * -- " PENAFIAN: E-mel ini dan apa-apa fail yang dikepilkan bersamanya ("Mesej") adalah ditujukan hanya untuk kegunaan penerima(-penerima) yang termaklum di atas dan mungkin mengandungi maklumat sulit. Anda dengan ini dimaklumkan bahawa mengambil apa jua tindakan bersandarkan kepada, membuat penilaian, mengulang hantar, menghebah, mengedar, mencetak, atau menyalin Mesej ini atau sebahagian daripadanya oleh sesiapa selain daripada penerima(-penerima) yang termaklum di atas adalah dilarang. Jika anda telah menerima Mesej ini kerana kesilapan, anda mesti menghapuskan Mesej ini dengan segera dan memaklumkan kepada penghantar Mesej ini menerusi balasan e-mel. Pendapat-pendapat, rumusan-rumusan, dan sebarang maklumat lain di dalam Mesej ini yang tidak berkait dengan urusan rasmi Universiti Malaya adalah difahami sebagai bukan dikeluar atau diperakui oleh mana-mana pihak yang disebut. DISCLAIMER: This e-mail and any files transmitted with it ("Message") is intended only for the use of the recipient(s) named above and may contain confidential information. You are hereby notified that the taking of any action in reliance upon, or any review, retransmission, dissemination, distribution, printing or copying of this Message or any part thereof by anyone other than the intended recipient(s) is strictly prohibited. If you have received this Message in error, you should delete this Message immediately and advise the sender by return e-mail. Opinions, conclusions and other information in this Message that do not relate to the official business of University of Malaya shall be understood as neither given nor endorsed by any of the forementioned. " -------------- next part -------------- An HTML attachment was scrubbed... URL: From jkrichma at uci.edu Mon Aug 10 13:35:01 2015 From: jkrichma at uci.edu (Jeff Krichmar) Date: Mon, 10 Aug 2015 10:35:01 -0700 Subject: Connectionists: Importance of Lateral Connections in the Parietal Cortex for Generating Motor Plans Message-ID: <0930ADFF-35E9-4E04-86CF-D3BA80D61F8A@uci.edu> Dear Connectionists, I would like to draw your attention to our recent publication on a model of Parietal Cortex and a methodology to construct neurobiologically plausible architectures. I think it might be of interest to many of you. Asher, D.E., Oros, N., and Krichmar, J.L. (2015). The Importance of Lateral Connections in the Parietal Cortex for Generating Motor Plans. PLoS ONE 10, e0134669. http://www.plosone.org/article/citationList.action?articleURI=info%3Adoi%2F10.1371/journal.pone.0134669 Substantial evidence has highlighted the significant role of associative brain areas, such as the posterior parietal cortex (PPC) in transforming multimodal sensory information into motor plans. However, little is known about how different sensory information, which can have different delays or be absent, combines to produce a motor plan, such as executing a reaching movement. To address these issues, we constructed four biologically plausible network architectures to simulate PPC: 1) feedforward from sensory input to the PPC to a motor output area, 2) feedforward with the addition of an efference copy from the motor area, 3) feedforward with the addition of lateral or recurrent connectivity across PPC neurons, and 4) feedforward plus efference copy, and lateral connections. Using an evolutionary strategy, the connectivity of these network architectures was evolved to execute visually guided movements, where the target stimulus provided visual input for the entirety of each trial. The models were then tested on a memory guided motor task, where the visual target disappeared after a short duration. Sensory input to the neural networks had sensory delays consistent with results from monkey studies. We found that lateral connections within the PPC resulted in smoother movements and were necessary for accurate movements in the absence of visual input. The addition of lateral connections resulted in velocity profiles consistent with those observed in human and non-human primate visually guided studies of reaching, and allowed for smooth, rapid, and accurate movements under all conditions. In contrast, Feedforward or Feedback architectures were insufficient to overcome these challenges. Our results suggest that intrinsic lateral connections are critical for executing accurate, smooth motor plans. Best regards, Jeff Krichmar Department of Cognitive Sciences 2328 Social & Behavioral Sciences Gateway University of California, Irvine Irvine, CA 92697-5100 jkrichma at uci.edu http://www.socsci.uci.edu/~jkrichma From M.deKamps at leeds.ac.uk Tue Aug 11 05:09:54 2015 From: M.deKamps at leeds.ac.uk (Marc de Kamps) Date: Tue, 11 Aug 2015 09:09:54 +0000 Subject: Connectionists: PhD scholarships in Applied Computing in Biology, Medicine and Health Message-ID: PhD scholarships in Applied Computing in Biology, Medicine and Health School of Computing, University of Leeds, UK Closing date for applications: 30 August 2015 The School of Computing, at the University of Leeds, ranked in the top 10 for research impact in the UK Research Excellence Framework REF2014, is offering up to five fully funded UK/EU PhD scholarships. This is an exciting opportunity for prospective UK/EU PhD students to engage in world class research from theoretical foundations of computer science through to highly applied computational modelling and systems engineering. Each scholarship covers fees, stipend and research training support. The scholarships are fully supported by School and the EPSRC (Engineering and Physical Science Research Council); however, requests for part-funding will also be considered where the balance is covered from elsewhere. We welcome applications within the research theme of Applied Computing in Biology, Medicine and Health: Our cross-disciplinary and highly collaborative research involves expertise spanning computer vision, data mining and visual analytics methods for Big Data, scientific computation, secure systems architectures, computational biology/neuroscience and bio-robotics. Topics include: Computational Neuroscience: development of cutting edge neuro-informatics frameworks; modelling dynamics of neural circuits and systems as part of the Human Brain Project; modelling adaptive sensory-motor control and biomechanics of animal behaviour; bio-robotic applications; Computational and Systems Biology: in-silico modelling of biological systems, from molecular and cellular dynamics to whole tissues, within basic biomedical research and as a pre-screening tool to accelerate the development of novel therapeutic products; Biomedical Image Analysis: development of novel image analysis techniques for computer assisted diagnosis, bio-mechanical modelling and surgical planning and training. Medical and Health Informatics: advanced process, text and data mining and novel visualization tools for analysing electronic health records, in the new ?15m Leeds Institute for Data Analytics (LIDA). How to apply: Formal applications for research degree study should be made on-line through www.leeds.ac.uk/info/125187/applying_for_research_degrees Please state clearly on the funding section of the application form that you wish to be considered for scholarship 'PhD scholarship Computing (FAO Dr Raymond Kwan)'. Additional information: If English is not your first language, then candidates must also meet the University's English language requirements. Academic requirement: UK 2.1 Bachelor (or equivalent) and/or MSc with merit Web: http://www.engineering.leeds.ac.uk/computing/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From huajin.tang at gmail.com Sat Aug 8 05:06:40 2015 From: huajin.tang at gmail.com (Huajin Tang) Date: Sat, 8 Aug 2015 17:06:40 +0800 Subject: Connectionists: Call for 2016 IEEE CIS Winter Schools Proposals Message-ID: Call for 2016 IEEE CIS Winter Schools Proposals *Important Dates:* - Eligible period: *1 December 2015 to 31 March 2016* - Deadline for submitting the proposal: *15 September 2015* - Notification of the outcome of the review process: *01 October 2015* You are encouraged to submit a proposal to hold a CIS winter school in Computational Intelligence from *Dec 2015 to Mar 2016*. If the proposal is approved, and upon request, CIS will provide a financial contribution to support the initiative. The amount of the financial support from CIS depends on the available budget, the number of financed proposals and the soundness of the school budget. The CIS Summer schools subcommittee will review received proposals based on the following criteria: 1. The quality of the proposed technical program and topic balance; 2. The length of the school; 3. The geographical balance of the proposals. In writing your proposal, please address the following aspects: 1. Aim and target. 2. Courses and lecturers. 3. Tentative program. 4. Local organizer(s). 5. Registration and accommodation. 6. School budget, financial sponsor(s) and requested co-finance from CIS. The main organizer must be a CIS member. A template is provided for your reference. Further details can be found at the website: http://cis.ieee.org/summer-schools.html. Please submit your proposal by the deadline to the Summer Schools Subcommittee Chair, Dr. Huajin Tang, at huajin.tang at ieee.org. -------------- next part -------------- An HTML attachment was scrubbed... URL: From friedhelm.schwenker at uni-ulm.de Mon Aug 10 16:24:43 2015 From: friedhelm.schwenker at uni-ulm.de (Dr. Schwenker) Date: Mon, 10 Aug 2015 22:24:43 +0200 Subject: Connectionists: PhD position in computer vision project at Ulm University (Germany) Message-ID: <55C9088B.4070701@uni-ulm.de> Applications are invited for one full-time position (in a funded project) for a period of 3 years, in the Institute of Neural Information Processing in the Faculty of Engineering, Computer Science, and Psychology at Ulm University, Germany. * RESEARCH TOPIC "Visual motion detection for behavior analysis". The vision and perception science research group (Prof. Heiko Neumann) has a job opening to work in the project \"SenseEmotion - Multisensory recognition of pain and emotion for elderly people"\ funded by the German Federal Ministry of Research and Education (BMBF). The topic focuses on the analysis of motion and stereo from multiple event-based and frame-based cameras. The input fusion aims at combining high temporal resolution event-based representations with high spatial resolution feature representations available at a slower frame rate. Visual features are used to analyze articulated motion patterns of subjects and pose information for detecting pain and abnormal spatio-temporal patterns and behavior in indoor scenes. It is expected that the candidate succeeds a PhD project within the project work. We are looking for talented and highly motivated computer scientists (or people with a related background, see REQUIREMENTS) interested in the development of novel computer vision algorithms and learning mechanisms to achieve robust high-performance analysis of complex articulated motions. The initial appointment is for 12 months, renewable for the rest of the project duration. A start date at the earliest disposal is preferred. Salary is according to the level TV-L E13. * CANDIDATE REQUIREMENTS ? training in computer science, electrical engineering, physics, math, or related discipline; ? he/she has a strong background and already experience in computer vision and/or machine learning (in vision); camera calibration and 3D stereo reconstruction; ? excellent programming skills are required (C/C++/Matlab/Python); ? communicative skills are required within a collaborative project with several research groups being involved, self-initiated interaction with other team members and the transfer algorithms and software integration into an overall system are required; ? writing skills are mandatory for generating project reports and deliverables as well as writing manuscripts to be submitted for publication. * RESEARCH GROUP Information about the research group can be found at http://www.uni-ulm.de/in/neuroinformatik/mitarbeiter/h-neumann.html (link to private homepage). * HOW TO APPLY? Please send your applications (in one file in pdf format) by email to heiko.neumann at uni-ulm.de. The application should include a brief statement of interests, a curriculum vitae, two letters of reference, a list of publications (if already available), and contact details (postal mailing address, email address, skype address). Applicants are encouraged to apply as soon as possible as the position will be filled as soon as a suitable applicant is found. From publicity at ecmlpkdd2015.org Tue Aug 11 18:20:47 2015 From: publicity at ecmlpkdd2015.org (ECMLPKDD 2015) Date: Tue, 11 Aug 2015 23:20:47 +0100 Subject: Connectionists: ECMLPKDD 2015: GREAT PROGRAM with reduced late fee until August 15 Message-ID: <55CA753F.3050509@ecmlpkdd2015.org> * **Apologies for cross-postings*** Time is running out for the reduced late fee of ECMLPKDD 2015 until August 15 (three days from now)! Register to attend our excellent program and meet the spectacular Porto city, the Best European Destination in 2012 and 2014, by the European Consumers Choice . Register here: http://www.ecmlpkdd2015.org/attending/registratio n The program of ECMLPKDD 2015 is now complete and it is great! - More than 450 participants confirmed so far! - We are proud to confirm the participation of prominent guest speakers (http://www.ecmlpkdd2015.org/program/invited-speakers). - Our scientific track features papers selected from a very large number of submissions. Some of these papers will be in special issues of the Machine Learning Journal and Data Mining and Knowledge Discovery. - The program will include an industrial track with selected papers from industry. - There is a Demo session where participants can take a look at machine learning and data mining in action. - We present selected Nectar papers from sister conferences. - You will have a chance to get in touch with our top-tier sponsors for information or to find yourself an exciting job as a data scientist. - Best paper awards will be announced. - Daily social events for networking, food and wine tasting. - And last but not least: to see Porto, one of the best places to visit these days (and perhaps go to the Douro Valley and the surroundings of Porto). More details about the ECMLPKDD 2015 program are available in: http://www.ecmlpkdd2015.org/program/program-calendar Below you can find a word cloud generated from the papers accepted in the ECMLPKDD 2015. Hope to see you in Porto, the Best European Destination in 2012 and 2014, by the European Consumers Choice . More about Porto:http://www.ecmlpkdd2015.org/gallery/about-porto PS: please disregard this message if you're already registered in ECMLPKDD 2015 The organization of the ECMLPKDD 2015 * -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: IQ83b3W52lb9cI3T5b1IswnSOEj2MS8E6fvXlC5ju9LzCDTopYlfGlXbx8CVhgP4lDcgQtFs52-MLjstEWdCqI9XDOMc0dBZpzNRtqTlnsVC7ehxIQwAjJQu_aY6YG9FC4XNoQ Type: image/jpeg Size: 123665 bytes Desc: not available URL: From Thomas_Serre at brown.edu Mon Aug 10 06:53:45 2015 From: Thomas_Serre at brown.edu (Thomas Serre) Date: Mon, 10 Aug 2015 10:53:45 +0000 Subject: Connectionists: =?utf-8?q?Postdoc_position_in_machine_vision_?= =?utf-8?q?=E2=80=93_Serre_lab=2C_Brown_University_=28Providence=2C?= =?utf-8?q?_RI=29?= Message-ID: The computational vision research group, headed by Dr. Thomas Serre at Brown University, has an opening for a postdoctoral fellow to work on the automated analysis of behavior. In particular, we are looking for a computer scientist interested in the development of computer vision algorithms to automate the video analysis of behavioral data with a range of applications from the study of bird cognition in the wild to rodents in their home cage to people in their homes. Candidates are expected to have a solid background in modern computer vision and machine learning methods. An interest in biology and applications of computer vision to the biological sciences would also be a strong plus but this is not a requirement for the position. The initial appointment is for 12 months, renewable for another year, and potentially longer depending on funding. The start date is negotiable though an early start is strongly preferred. Salary is commensurate with experience and is competitive. Representative recent work related to the project: H. Jhuang, E. Garrote, X. Yu, V. Khilnani, T. Poggio and A. Steele and T. Serre. Automated home-cage behavioral phenotyping of mice. In: Nature Communications 1(1), doi:10.1038/ncomms1064, 2010 H. Kuehne, A. Arlsan & T. Serre. The language of actions: Recovering the syntax and semantics of goal-directed human activities. In: Proceedings of 2014 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2014), IEEE Computer Society Press, Columbus, Ohio, 2014 Research group: Our research group is located within the Department of Cognitive Linguistic & Psychological sciences at Brown University. We maintain strong ties with the computer science, engineering and applied math departments as part of the Brain Institute. Through Brown?s Center for Computation and Visualization (https://www.ccv.brown.edu), our group has access to a state-of-the-art computing facility with includes over 300K GPU cores and over 500 Teraflops of GPU computing power. Information about Dr. Serre and his research group can be found at http://serre-lab.clps.brown.edu. Requirements: Applicants are expected to have finished, or be about to finish their Ph.D. degrees. They must have a strong background in computer vision and/or machine learning, with a track record of relevant publications at top venues (such as NIPS, CVPR, ICCV, ICML or ECCV). Excellent programming skills are required (C/C++/Matlab/Python). Programming experience in CUDA and/or parallel computing would be a strong plus. Application: Please send your applications by email to thomas_serre at correct_university_name.edu where correct_university_name should be replaced by ?brown'. Please include a brief statement of interests, a curriculum vita, a list of publications and contact details for 2-3 letters of reference (no letters required at this stage). There is no deadline for the application but applicants are encouraged to apply as soon as possible as the position will be filled as soon as a suitable applicant is found. -------------- next part -------------- An HTML attachment was scrubbed... URL: From Hugo.Larochelle at USherbrooke.ca Wed Aug 12 17:59:57 2015 From: Hugo.Larochelle at USherbrooke.ca (Hugo Larochelle) Date: Wed, 12 Aug 2015 21:59:57 +0000 Subject: Connectionists: Workshop on Describing and Understanding Video and The Large Scale Movie Description Challenge (LSMDC) Message-ID: We would like to invite you to participate in the workshop on Describing and Understanding Video, which will be organized in conjunction with ICCV 2015, Santiago, Chile, as well as to take part in our Large Scale Movie Description Challenge (LSMDC). ================================================================= Call for papers and challenge participation Automatically describing open-domain videos using rich natural sentences is among the most challenging tasks of computer vision, natural language processing and machine learning. To stimulate research on this topic, we propose the Describing and Understanding Videos Workshop & LSMDC Challenge, which features a unified version of the recently published large-scale movie datasets (M-VAD and MPII-MD). These datasets have been built using Audio Descriptions (AD) / Descriptive Video Service (DVS) resources for the visually impaired, which are transcribed and aligned to the video. The goal of this workshop is thus to bring together researchers working on diverse topics in computer vision and natural language processing in order to obtain a better understanding of the existing challenges and new research directions of open-domain video description with natural sentences. We invite submissions on topics pertaining to the subject, including: ? Generating descriptions for videos. ? Generating Audio Descriptions for movies. ? Using textual descriptions as weak supervision for video understanding. ? Using dialogs and/or audio for video understanding. ? Understanding plots. ? Recognizing characters in TV series / movies. ? Novel tasks with Audio Descriptions / DVS dataset. LSMDC Challenge A unified challenge based on the M-VAD and MPII-MD datasets is put in place. We will provide a blind test set (i.e. without descriptions). Winners will be selected based on a human evaluation of submissions to the challenge. Additional automatic evaluation scripts will be made available for development. We host two challenges: ? Text generation using single video clip. ? Text generation using single video clip as well as its surrounding context (i.e. video clips, ground truth descriptions, character names, dialogues). Important Dates Paper submission early deadline: October 1st Paper submission final deadline: November 16th Notification of paper acceptance: within 2 weeks after each deadline Challenge submission opens: September 16th Challenge submission deadline: November 16th Workshop: half day, on one of these days: 11, 12, 17 or 18th of December Contact: lsmdc2015 at gmail.com Website: https://sites.google.com/site/describingmovies Best, Organizers Anna Rohrbach? Max Planck Institute for Informatics Atousa Torabi? Universit? de Montr?al Marcus Rohrbach ICSI and UC Berkeley Christopher Pal ?cole Polytechnique de Montr?al Hugo Larochelle Universit? de Sherbrooke Aaron Courville? Universit? de Montr?al Bernt Schiele? Max Planck Institute for Informatics From fmschleif at googlemail.com Fri Aug 14 03:34:07 2015 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Fri, 14 Aug 2015 09:34:07 +0200 Subject: Connectionists: Early call - special session - 'Indefinite proximity learning' (ESANN'16) Message-ID: Call for Papers Special Session on 'Indefinite proximity learning' 27-29 April 2016, Bruges, Belgium http://www.dice.ucl.ac.be/esann AIMS AND SCOPE Today real life data are often not given as vectorial data, but by means of proximities (similarities or dissimilarities) only, calculated by an appropriate proximity function. The pairwise proximity matrix may be a symmetric positive semidefinite matrix - and hence a kernel matrix but can be much more generic. Often the underlying data may not exist in a vector space and the proximity function violates metric properties, leading to indefinite, potentially asymmetric proximity matrices, which can not directly be processed by classical machine learning algorithms - like kernel machines. We can find these settings in various domains like the analysis of text documents - using e.g. the compression distance, the comparison of biological sequence data - with domain specific alignment measures, shape retrieval problems in robotics using the inner distance, the representation of structured data like graphs or trees and many other applications. The recent technological developments, also in the context of big data, allow the generation of very large data sets. If the data are represented by non-metric proximities the processing becomes particular challenging, because many classical mathematical models require metric properties. Dedicated processing strategies for non-metric proximity data (indefinite proximities, non-positive kernels, dissimilarity data) are of wide interest and the subject of this special session. TOPICS We encourage submission of papers on novel methods for (pre-) processing of non-metric kernels, structured data or in the field of non-metric dissimilarity learning by means of computational intelligence and machine learning approaches, including but not limited to: - data analysis and pattern recognition approaches for (indefinite) proximity data, structured data and dissimilarity learning - clustering, classification, regression, embedding approaches for indefinite data - approaches in the line of matrix completion, collaborative filtering, reduction techniques for non-standard data - low rank matrix approaches - valid for indefinite proximities - vector space embedding - metric nearness and correction approaches - large scale proximity matrix analysis and handling - quality and error measures for indefinite data representations - applications with indefinite proximity data IMPORTANT DATES Paper submission deadline : 20 November 2015 Notification of acceptance : 31 January 2016 The ESANN 2014 conference : 27-29 April 2016 SPECIAL SESSION ORGANIZERS: Frank-Michael Schleif, University of Birmingham, Birmingham, UK and University of Appl. Sc. Mittweida, Germany Peter Tino, University of Birmingham, Birmingham, UK Yingyu Liang, Princeton University, USA -- ------------------------------------------------------- PD Dr. rer. nat. habil. Frank-Michael Schleif School of Computer Science The University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom - email: fschleif at techfak.uni-bielefeld.de http://promos-science.blogspot.de/ ------------------------------------------------------- From D.Zambrano at cwi.nl Fri Aug 14 07:14:42 2015 From: D.Zambrano at cwi.nl (Davide Zambrano) Date: Fri, 14 Aug 2015 11:14:42 -0000 Subject: Connectionists: Deep Learning and Continuous Time Computing - Track at SAC 2016 - Second Call for Papers Message-ID: Dear all, This is a Second Call for Paper to join our track at SAC 2016. The deadline for the submission of papers and SRC research abstract is September 11, 2015. Apologies for cross posting. Best regards. ????????????????????????????????????? ACM Symposium on Applied Computing (SAC) 2016 The 31st Annual ACM Symposium on Applied Computing in Pisa, Italy, April 3 ? 8, 2016. (webpage : http://www.acm.org/conferences/sac/sac2016/ ) Deep Learning and Continuous-Time Computing (webpage : http://event.cwi.nl/sac2016/ ) ????????????????????????????????????? SAC 2016: For the past thirsty years, the ACM Symposium on Applied Computing has been a primary gathering forum for applied computer scientists, computer engineers, software engineers, and application developers from around the world. SAC 2016 is sponsored by the ACM Special Interest Group on Applied Computing (SIGAPP), and will be hosted by the University of Pisa and Scuola Superiore Sant?Anna University, Italy. Artificial Intelligence (AI) is one of the objectives of Machine Learning: how to create computers capable of intelligent behavior. Deep Learning in artificial neural networks represents a remarkable step toward this direction. Current state-of-the-art AI in the form of deep neural networks has recently demonstrated breakthrough performance in various AI-cognitive tasks, from image and speech recognition to natural language generation and playing ATARI games. However, in real-world applications like video processing or robot control, a deep neural network has then to be updated continuously, causing a high computational load. Specialized acceleration hardware is being developed for deep learning in continuous-time environments. In addition, or alternatively, Spiking Neural Networks (SNNs) represent another possible solution for efficient continuous-time representation and computing in deep neural networks. This Track aims to consolidate the current state-of-the-art in deep learning, continuous-time computing, spiking neural networks and related acceleration hardware tools (such as GPUs, SpiNNaker or Neuromorphic Silicon systems) showing recent and future progresses of this rising and growing research field. ????????????????????????????????????? Topics of interests: Deep learning Continuous-time learning Spiking Neural Networks Asynchronous computation Large scale parallel simulations and computing Neuromorphic computing ????????????????????????????????????? Important Dates are published on the Conference? or Track? webpages. ????????????????????????????????????? Track Program Committee: Sander Bohte, CWI Amsterdam (NL) (Track Chair ? email to s.m.bohte at cwi.nl ) Davide Zambrano, CWI Amsterdam (NL) (Track Chair ? email to d.zambrano at cwi.nl ) Thomas Nowotny, University of Sussex (UK) Stephen Furber, University of Manchester (UK) Karl Tuyls, University of Liverpool (UK) Shih-Chii Liu, University of Zurich/ETH Zurich (CH) Robert Babuska, Delft University of Technology (NL) Andre Gruning, University of Surrey (UK) Max Welling, University of Amsterdam (NL) Narayan Srinavasa, HRL Laboratories LLC (USA) Eleni Vasilaki, University of Sheffield (UK) Giacomo Indiveri, University of Zurich/ETH Zurich, (CH) ????????????????????????????????????? Important notice: Paper registration is required, allowing the inclusion of the paper, poster, or SRC abstract in the conference proceedings. An author or a proxy attending SAC MUST present the paper. This is a requirement for including the work in the ACM/IEEE digital library. No-show of registered papers, posters, and SRC abstracts will result in excluding them from the ACM/IEEE digital library. ????????????????????????????????????? ? Dr. Davide Zambrano PostDoc at CWI, Amsterdam (NL) MSc in Biomedical Eng. - PhD in Biorobotics D.Zambrano at cwi.nl Centrum Wiskunde & Informatica (CWI) Science Park, 123 1098 XG - Amsterdam -------------- next part -------------- An HTML attachment was scrubbed... URL: From ahu at cs.stir.ac.uk Sun Aug 16 11:39:30 2015 From: ahu at cs.stir.ac.uk (Dr Amir Hussain) Date: Sun, 16 Aug 2015 18:39:30 +0300 Subject: Connectionists: Call for Papers: 7th International Conference on Brain Inspired Cognitive Systems (BICS), 11-13 Dec 2015, Hefei, China Message-ID: BICS'2015 Call for Papers (with journal ONLY conference proceedings - see details below!) With apologies for any cross-postings, please help circulate this CFP to friends and colleagues. Thank you in advance. BICS'2015 CFP website: http://www.cs.stir.ac.uk/events/bics2015/cfp_e.html (ALL papers accepted (after a rigorous peer-review process) for presentation at the Conference will be published in the leading ISI-SCI indexed Springer journal: Cognitive Computation (http://springer.com/12559) as a multi-part Special Issue! - for more details, see the conference website, and below) Introduction to BICS'2015: The seventh 2015 International Conference on Brain Inspired Cognitive Systems (BICS 2015) will be held on December 11-13, 2015, in Hefei, Anhui, China, as a sequel of BICS 2004 - 2013. The first BICS 2004 was held in Stirling, Scotland, UK and the last BICS 2013 was held in Beijing, China, 9-13 June 2013 (http://www.conference123.org/bics2013/). The aim of BICS 2015 is to provide a high-level international forum for scientists, engineers, and educators to present the state-of-the-art of brain inspired cognitive systems research and applications in diverse fields. The conference will feature plenary lectures given by world renowned scholars, regular sessions with broad coverage, and special sessions focusing on popular and timely topics. Proceedings Information: BICS 2015 will be unique in that there will be no conference proceedings. ALL accepted papers will be published (following a rigorous peer review process) in the leading ISI-SCI indexed Springer journal: Cognitive Computation (http://springer.com/12559), as a multi-part Special Issue. Conference Location The conference will be held in Anhui University in Hefei, China. Hefei, formerly known as Hofei, Luzhou, or Luchow, is the capital and largest city of Anhui Province in Eastern China. Hefei Xinqiao International Airport provides scheduled passenger service to major airports in China and international cities as well. Hefei plays an important role in scientific research in China. It has seven national laboratories, second only to Beijing. We would be delighted to welcome you to Hefei in December. For more details on the venue, including travel information, see: http://www.cs.stir.ac.uk/events/bics2015/venue_e.html Important Dates Full paper submission: 15 September 2015 First notification: 31 October 2015 Conference Dates: 11-13 December 2015 Revised/final manuscripts due: 31 December 2015 BICS'2015 Issue Publication Date: early 2016 Paper Submission: All prospective authors are invited to submit full-length papers (10-15 pages maximum) through the online Springer submission system (selecting the BICS2015 Special Issue), with a covering letter indicating the paper is being submitted for BICS'2015 (hhttp://www.editorialmanager.com/cogn/ ) - please indicate the relevant BICS Symposium name (see topics list on the Conference website). The submission of a paper implies that the paper is original and has not been submitted under review or copyright protected elsewhere. The authors of accepted papers will have an opportunity to revise their papers. If the paper is accepted, at least one of the authors listed on the paper (or his/her representative) must attend the conference and present the paper. On behalf of: BICS'2015 General co-Chairs: Professor Amir Hussain (University of Stirling, Scotland, UK) and Professor Bin Luo (Anhui University, China) and BICS'2015 Organizing Committee ( http://www.cs.stir.ac.uk/events/bics2015/committee_e.html ) For any enquiries, please email: ahu at cs.stir.ac.uk or luobin at ahu.edu.cn -- The University is ranked in the QS World Rankings of the top 5% of universities in the world (QS World University Rankings, 2014) The University of Stirling is a charity registered in Scotland, number SC 011159. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Mon Aug 17 10:48:20 2015 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 17 Aug 2015 10:48:20 -0400 Subject: Connectionists: High performance computing workshop at SFN 2015 Annual Meeting Message-ID: <55D1F434.7020704@yale.edu> What: This workshop is intended for neuroscientists who are engaged in computationally intensive tasks such as large modeling projects or analysis of neuroimaging data. With support from NSF, we are developing and expanding the Neuroscience Gateway Portal (NSG, http://www.nsgportal.org/), which eliminates most administrative and technical barriers involved in using high performance computing (HPC) resources. NSG offers free computing time and has a simple user interface so you can focus on productive research. Software currently installed includes the Freesurfer Software Suite, the Virtual Brain Empirical Data Pipeline (Schirner et al., 2015), and simulators such as Brian, MOOSE, GENESIS3, NEST, NEURON, and PyNN. This workshop will combine didactic presentations by NSG's developers, discussions with experienced users, and hands on instruction in how to use the portal. Where: Downtown Chicago, site TBA. When: 9AM - Noon on Saturday, October 17, 2015. Speakers: Amit Majumdar, Subha Sivagnanam, Padraig Gleeson, Simon Rothmeier, Ted Carnevale Registration deadline: Friday, October 2, 2015 For more information see http://www.neuron.yale.edu/neuron/static/courses/nsg2015/nsg2015.html or contact Ted Carnevale [ted dot carnevale at yale dot edu] or Amit Majumdar [majumdar at sdsc dot edu] References: Schirner, M., Rothmeier, S., Jirsa, V.K., McIntosh, A.R., Ritter, P.. An automated pipeline for constructing personalized virtual brains from multimodal neuroimaging data. Neuroimage 117:343-357, 2015. From pfeiffer at ini.phys.ethz.ch Mon Aug 17 12:55:44 2015 From: pfeiffer at ini.phys.ethz.ch (Michael Pfeiffer) Date: Mon, 17 Aug 2015 18:55:44 +0200 Subject: Connectionists: MSc program in Neural Systems and Computation - University of Zurich and ETH Zurich Message-ID: <55D21210.2040502@ini.phys.ethz.ch> We are inviting applications for the MSc program in Neural Systems and Computation, an interdisciplinary program offered as a Joint Master Program by the University of Zurich and ETH Zurich, Switzerland. The program offers a theoretical and laboratory training in neural computation and systems neuroscience. It offers hands-on knowledge of data gathering, analysis and scientific presentation. Students join an international and interdisciplinary research community with expertise in neuroinformatics, advanced experimental techniques and neuromorphic engineering. Further information can be found on our homepage http://www.nsc.uzh.ch. We offer a specialized full-time Masters program open to students with a Bachelor?s degree in the following disciplines: neurosciences, information technology, electrical engineering, biology, physics, computer sciences, chemistry, mathematics, and mechanical/chemical/control engineering. The core courses (all offered in English) provide a common foundation for students with different educational backgrounds, and cover the following: 1. Systems Neurosciences 2. Neural Computation and Theoretical Neuroscience 3. Neurotechnologies and Neuromorphic Engineering The application deadline for students starting in Spring Semester 2016 is *September 15th 2015*. Details about the application process and required documents can be found here: http://www.nsc.uzh.ch/?page_id=10 Mentors of the program are Richard Hahnloser, Kevan Martin, Daniel Kiper, Giacomo Indiveri, Ruedi Stoop, Tobi Delbruck, Shih-Chii Liu, Klaas Enno Stephan, Fritjof Helmchen, Jean-Pascal Pfister, Fatih Yanik, Michael Pfeiffer, Matthew Cook, Valerio Mante, Arko Ghosh, and Wolfger von der Behrens. The program is affiliated with the Mathematics and Natural Sciences Faculty (MNF) at the University of Zurich (UZH) and the Information Technology and Electrical Engineering Department (D-ITET) of the ETH Zurich. All applications are handled by the University of Zurich. Application documents should be sent by email to nsc at ini.uzh.ch. Best regards, Michael Pfeiffer -- ========================================= Dr. Michael Pfeiffer Postdoc, Program coordinator NSC Institute of Neuroinformatics University of Zurich and ETH Zurich Winterthurerstrasse 190 CH-8057 Zurich, Switzerland Tel. +41 44 635 30 45 Fax +41 44 635 30 53 pfeiffer (at) ini.phys.ethz.ch http://www.ini.uzh.ch/~pfeiffer/ ========================================= -------------- next part -------------- An HTML attachment was scrubbed... URL: From manuel.lopes at inria.fr Tue Aug 18 06:38:07 2015 From: manuel.lopes at inria.fr (Manuel Lopes) Date: Tue, 18 Aug 2015 12:38:07 +0200 (CEST) Subject: Connectionists: Phd or Post-Doc Robot Learning positions at INRIA Bordeaux In-Reply-To: <1068145341.504221.1300101764739.JavaMail.root@zmbs3.inria.fr> Message-ID: <1868445647.11734658.1439894287638.JavaMail.zimbra@inria.fr> To all interested, We are seeking applications for phd students (3years) and/or postdocs (2.5years) in the area of artificial intelligence and robot learning at Inria. Our interests are in developing machines that are able to learn novel skills and capable of natural and robust interaction with people. We focus our research on intelligent exploration techniques, robot learning and automatic learning of representation for artificial intelligence. One position is open to work in an international research project (with partners from Canada, Sweden, Spain, Belgium and France). The candidates will be involved in research in the areas of deep learning of action and state representations, and interactive machine learning. The candidates must have strong mathematical competences, experience in machine learning and programming proficiency (e.g. C/C++, Matlab, Python or Java). Knowledge of deep learning and/or experience with real robots is a plus. Inria is a highly reputed french national center for computer science and automation. It has more than 3000 researchers and is distributed among 8 centers. These positions are for the Flowers Team at Inria Bordeaux Sud-Ouest and will involve travelling for collaborating with the project partners. Bordeaux is a growing city with a wonderful natural landscape, a very active city life and with a booming economy. Is has a very privileged location: 3h from Paris, 2h from Toulose, 30 minutes from the sea and 2hours from the Pyreness mountains. It has very good travel connections with fast trains and international flights including low-cost companies. Interested candidates should send a detailed CV, and email addresses of three references to Manuel Lopes at manuel.lopes at inria.fr . Review of applications will continue until the position is filled. Desired starting date is 1 of November 2015. http://flowers.inria.fr http://3rdhandrobot.eu/ http://www.inria.fr http://www.bordeaux.fr/ --------------------------------------------------------------- Manuel Lopes - Researcher flowers.inria.fr/mlopes FLOWERS team Phone: +33524574179 INRIA Bordeaux Sud-Ouest, Bat. A29 351 Cours de la Lib?ration 33405 Talence, Cedex, France --------------------------------------------------------------- From Pavis at iit.it Tue Aug 18 11:33:06 2015 From: Pavis at iit.it (Pavis) Date: Tue, 18 Aug 2015 15:33:06 +0000 Subject: Connectionists: Postdoctoral position in Computer Vision, Machine Learning and Pattern Recognition BC:71372 Message-ID: <0E09F354EB71FC40A4D51EE54D8A9C883B55C084@IITMXWGE015.iit.local> Postdoctoral position in Computer Vision, Machine Learning and Pattern Recognition BC:71372 Fondazione Istituto Italiano di Tecnologia - IIT - was founded with the objective of promocting Italy?s technological development and further education in science and technology. In this sense, IIT?s scientific program is based in the combination of basic scientific research and development of technical applications, a major inspirational principle. Researchareas cover scientific topics of high innovative content, representing the most advanced frontiers of modern technology, with wide application possibilities in various fields ranging from medicine to industry, from computer science to robotics, life sciencesand nanobiotechnology. PAVIS department at Istituto Italiano di Tecnologia (IIT) (http://www.iit.it/pavis) is looking for a highly qualified researcher with a strong background in Computer Vision, Pattern Recognition and Machine Learning, with particular emphasis on recognition, video analysis, behavior understanding and prediction. As the activities may be carried out in collaboration with other research units inside IIT, previous multidisciplinary experience is an added value which will be duly considered. The main mission of PAVIS (Pattern Analysis and Computer Vision) is to design and develop innovative video surveillance systems, characterized by the use of highly-functional smart sensors and advanced video analytics features. PAVIS also plays an active role in supporting the other research units inside IIT providing providing scientists in Neuroscience, Nanophysics and other IIT departments/centers with ad hoc solutions. To this end, the group is involved in activities concerning computer vision and pattern recognition, machine learning, multimodal data analysis and sensor fusion, and embedded computer vision systems. The lab will pursue this goal by working collaboratively and in cooperation with external private and public partners. In particular, this call aims at consolidating PAVIS expertise in one or more of the following research areas: ? Analysis of static and dynamic scenes. ? Recognition (objects, scenes, actions, events, etc.). ? Behavior Analysis & Activity Recognition (individuals, groups, crowd). ? Prediction of intentions. ? And, from the methodological point of view, in one or more of the following subjects: Graphical Models, Topic Models, Deep Learning, Representation/Feature Learning, Transfer Learning, Domain Adaptation, Sparse Learning, and Statistical and Probabilistic Models in general. Candidates to this position have a Ph.D. in computer vision, machine learning or related areas. Research experience and qualification in computer vision and pattern recognition/machine learning are clearly a must and evidence of top quality research on the above specified areas in the form of published papers in top conferences/journals and/or patents is mandatory. Experience in the preparation and management of research proposals (EU, US, national) and a few years of postdoc experience, either in academia or industrial lab, will also be duly considered. The scientist is expected to publish his/her research results in leading international journals and conferences. She/he is also expected to contribute to the set-up of new project proposals, participate in funding activities,supervising PhD candidates and collaborate with other scientists, also with different (neuroscience) expertise. Salary will be commensurate to qualification and experience and in line with international standard. Working location: Genova, Italy. Further details and informal enquires can be made by email to pavis at iit.it quoting PAVIS-PD 71372 as reference number. Completed application forms along with a curriculum listing all publications (possibly including pdf of your most representative publications), and a research statement describing your previous research experience and outlining its relevance to the above topics should be sent by email to pavis at iit.it, quoting PAVIS-PD 71372as reference number. Please also indicate 2 independent references inside the CV or the email. This call will remain open and applications will be reviewed until the position is filled but for full consideration please apply by September 20th, 2015. In order to comply with Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), the candidate is kindly asked to give his/her consent to allow Istituto Italiano di Tecnologia to process his/her personal data. We inform you that the information you provide will be solely used for the purpose of evaluating and selecting candidates in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, with its headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper-based means, observing the rules on the protection of personal data, including those relating to the security of data, and they will not be communicated to thirds. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Holder. Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in the workforce. Further details and informal enquires can be made by email to pavis at iit.it quoting PAVIS-PD 71092 as reference number. Completed application forms along with a curriculum listing all publications (possibly including pdfs of your most representative publications) and a research statement describing your previous research experience and outlining its relevance to the above topics should be sent by email to pavis at iit.it, PAVIS-PD 71092 as reference number. Please also indicate 2 independent references inside the CV or in the email. This call will remain open and applications will be reviewed until the position is filled but for full consideration please apply by September 11th, 2015. In order to comply with Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), the candidate is kindly asked to give his/her consent to allow Istituto Italiano di Tecnologia to process his/her personal data. We inform you that the information you provide will be solely used for the purpose of evaluating and selecting candidates in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, with its headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper-based means, observing the rules on the protection of personal data, including those relating to the security of data, and they will not be communicated to thirds. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Holder. Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in the workforce. -------------- next part -------------- An HTML attachment was scrubbed... URL: From Pavis at iit.it Tue Aug 18 11:34:00 2015 From: Pavis at iit.it (Pavis) Date: Tue, 18 Aug 2015 15:34:00 +0000 Subject: Connectionists: Postdoctoral position in Computer Vision, Machine Learning and Pattern Recognition BC:71092 Message-ID: <0E09F354EB71FC40A4D51EE54D8A9C883B55C095@IITMXWGE015.iit.local> Postdoctoral position in Computer Vision, Machine Learning and Pattern Recognition BC:71092 Fondazione Istituto Italiano di Tecnologia - IIT - was founded with the objective of promoting Italy?s technological development and further education in science and technology. In this sense, IIT?s scientific program is based on the combination of basic scientific research and development of technical applications, a major inspirational principle. Research areas cover scientific topics of high innovative content, representing the most advanced frontiers of modern technology with wide application possibilities in various fields ranging from medicine to industry, from computer science to robotics, life sciences and nanobiotechnology. PAVIS department at Istituto Italiano di Tecnologia (IIT) (http://www.iit.it/pavis) is looking for a highly qualified researcher with a strong background in Computer Vision, Pattern Recognition and Machine Learning, with particular emphasis on video analysis for behavior understanding and prediction while also addressing neural correlates. As the activities will be carried out in collaboration with other neuroscience units in IIT, previous multidisciplinary experience is an added value which will be duly considered. The main mission of PAVIS (Pattern Analysis and Computer Vision) is to design and develop innovative video surveillance systems, characterized by the use of highly-functional smart sensors and advanced video analytics features. PAVIS also playsan active role in supporting the other research units inside IIT providing scientists in Neuroscience, Nanophysics and other departments/centers with ad hoc solutions. To this end, the group is involved in activities concerning computer vision and pattern recognition, machine learning, multimodal data analysis and sensor fusion and embedded computer vision systems. The lab will pursue this goal by working collaboratively and in cooperation with external private and public partners. In particular, this call aims at consolidating PAVIS expertise in one or more of the following research areas: ? Analysis of static and dynamic scenes. ? Analysis of MRI and other neuroimaging data (possibly). ? Behavior Analysis & Activity Recognition (individuals, groups, crowd). ? Prediction of intentions. ? And, from the methodological point of view, in one or more of the following subjects: Graphical Models, Topic Models, Deep Learning, Representation/Feature Learning, Transfer Learning, Domain Adaptation, Sparse Learning, and Statistical and Probabilistic Models in general. Candidates to this position have a Ph.D. in computer vision, machine learning or related areas. Research experience and qualification in computer vision and pattern recognition/machine learning are clearly a must and evidence of top quality research on the above specified areas in the form of published papers in top conferences/journals and/or patents is mandatory. Experience in the preparation and management of research proposals (EU, US, national) and a few years of postdoc experience, either in academia or industrial lab, will also be duly considered. The scientist is expected to publish his/her research results in leading international journals and conferences. She/he is also expected to contribute to the set-up of new project proposals, participate in funding activities, supervising PhD candidates and collaborate with other scientists, also with different (neuroscience) expertise. Salary will be commensurate to qualification and experience and in line with international standard. Working location: Genova, Italy. Further details and informal enquires can be made by email to pavis at iit.it quoting PAVIS-PD 71092 as reference number. Completed application forms along with a curriculum listing all publications (possibly including pdfs of your most representative publications) and a research statement describing your previous research experience and outlining its relevance to the above topics should be sent by email to pavis at iit.it, PAVIS-PD 71092 as reference number. Please also indicate 2 independent references inside the CV or in the email. This call will remain open and applications will be reviewed until the position is filled but for full consideration please apply by September 11th, 2015. In order to comply with Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), the candidate is kindly asked to give his/her consent to allow Istituto Italiano di Tecnologia to process his/her personal data. We inform you that the information you provide will be solely used for the purpose of evaluating and selecting candidates in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, with its headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper-based means, observing the rules on the protection of personal data, including those relating to the security of data, and they will not be communicated to thirds. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Holder. Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in the workforce. -------------- next part -------------- An HTML attachment was scrubbed... URL: From Pavis at iit.it Tue Aug 18 11:29:06 2015 From: Pavis at iit.it (Pavis) Date: Tue, 18 Aug 2015 15:29:06 +0000 Subject: Connectionists: Postdoctoral position in Pattern Recognition, Machine Learning and Computer Vision for the analysis of retinal electrophysiology in response to visual stimulation, with specific expertise in deep learning and sparse learning BC: 71326 - 71327 Message-ID: <0E09F354EB71FC40A4D51EE54D8A9C883B55C078@IITMXWGE015.iit.local> Postdoctoral position in Pattern Recognition, Machine Learning and Computer Vision for the analysis of retinal electrophysiology in response to visual stimulation, with specific expertise in deep learning and sparse learning BC: 71326 - 71327 Fondazione Istituto Italiano di Tecnologia ? IIT ? was established by the Italian government to promote technological development and training in the scientific and technological field. Toward this end, IIT is implementing a detailed scientific program, which comprises integration across fundamental research and application. IIT?s research endeavour focuses on high-tech and innovation, representing the forefront of technology with possible application from medicine to industry, computer science, robotics, life sciences and nano-biotechnologies. One postdoctoral position in Computer Vision, Pattern Recognition and Machine Learning is available in the department of Pattern Analysis and Computer Vision (PAVIS) at the Istituto Italiano di Tecnologia (IIT) ,Genova, Italy. PAVIS department has consolidated expertise in image processing, computer vision, pattern recognition and machine learning and aims at studying and designing intelligent systems for the analysis and understanding of real-world problems. PAVIS focuses in particular on activities related, but not limited, to surveillance and security, biomedical imaging, and bioinformatics. Project Description The research position is funded by the European project ?RENVISION - Retina-inspired ENcoding for advanced VISION tasks? (http://www.renvision-fp7.eu/). The overall aim of the project is to achieve a comprehensive understanding of how the retina encodes complex visual scenes, and to use such insights to develop new computational models of retina and toapply them to high-level computer vision tasks, such as scene categorization and action recognition. The project is highly interdisciplinary, including neuro-engineering, electrophysiology, high-resolution microscopy imaging, computational modelling, data analysis, machine learning and computer vision. RENVISION is funded by the European Commission FP7 Future Emerging Technologies programme, under contract n. 600847. Description of the research The candidate will design novel methodologies and algorithms based on pattern recognition and machine learning techniques, aiming at analysing electrophysiological recordings in response to visual stimulation of retina. The main objective of the research is the discovery/determination of representative and/or discriminative features in retina coding allowing for high-level vision tasks, such as scene categorization and action recognition. To this purpose, deep learning, sparse and dictionary learning approaches are to be considered. Experience and Qualifications We are seeking a self-motivated individual with the ability to take day-to-day responsibility for the progress of the proposed work. The ideal candidate will have a PhD in Computer Science, Mathematics, Electronic Engineering or a closely-related discipline, with competences on machine learning/pattern recognition/computer vision, coupled with a keen interest in neuroscience and biological data processing and analysis. Expertise in deep learning, compressive sensing, and/or dictionary learning is in general preferred. Experience in spiking networks or retinal function will be appreciated while not being a discriminating factor. A strong programming skill is required. Annual salary will depend on research experience and qualification. Closing Date The initial deadline for applications is September 7th , 2015, however please note that the search will continue until appropriate candidates have been identified. How to apply Completed application forms along with a curriculum listing all publications (possibly including pdfs of the most representative ones), names of 2 referees and a research statement (describing previous research experience and outlining its relevance to the above topics) should be sent by email to Prof. Vittorio Murino vittorio.murino at iit.it or Diego Sona diego.sona at iit.it, quoting PAVIS-PD 71327 ? 71326 as reference number. For informal enquiries please write to Prof. Vittorio Murino vittorio.murino at iit.it or Diego Sona diego.sona at iit.it. In order to comply with Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), the candidate is kindly asked to give his/her consent to allow Istituto Italiano di Tecnologia to process his/her personal data. We inform you that the information you provide will be solely used for the purpose of evaluating and selecting candidates in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, with its headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper-based means, observing the rules on the protection of personal data, including those relating to the security of data, and they will not be communicated to thirds. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Holder. Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in its workforce From tbrown at research.baycrest.org Tue Aug 18 11:57:57 2015 From: tbrown at research.baycrest.org (Tanya Brown) Date: Tue, 18 Aug 2015 11:57:57 -0400 Subject: Connectionists: The Virtual Brain Node #3 Workshop - REGISTRATION NOW OPEN Message-ID: *?* *NODE#3* : Training Workshop Chicago, IL - SfN 2015 Conference *October 16, 2015* www.thevirtualbrain.org/node3 In this workshop we will explain the fundamental principles of full brain network modelling using the open source neuroinformatics platform *The Virtual Brain (TVB)*. This simulation environment enables the biologically realistic modelling of network dynamics using Connectome-based approaches across different brain scales. Configurable brain network models generate macroscopic neuroimaging signals including functional MRI (fMRI), intracranial and stereotactic EEG, surface EEG and MEG for single subjects. Researchers from different backgrounds can benefit from an integrative software platform including a supporting framework for data management (generation, organization, storage, integration and sharing) and a simulation core written in Python. The architecture of TVB supports interaction with MATLAB packages, for example, the well-known Brain Connectivity Toolbox. *Workshop Goals:* to create a conceptual and technical understanding of the various network modelling approaches in TVB; familiarization with TVB graphical user interface, Python and Matlab programming environment and data formats. *Workshop Format: * lectures and hands-on tutorials - *space is limited** ================================================================== *For more details and registration, please visit our website : * *http://www.thevirtualbrain.org/node3 * ================================================================== *Important Dates:* - August 10, 2015 ? Registration Open - *space is limited** - October 9, 2015 ? Registration Closed - October 16, 2015 ? TVB NODE#2 Training Workshop *Location:* Hyatt Regency Chicago Downtown Hotel 151 East Wacker Drive Chicago, IL, 60601, USA *Note: This is a Society for Neuroscience (SfN) 2015 conference official satellite event.* With our best regards, *The TVB Team * -- *Tanya Brown* Program Manager - The Virtual Brain Rotman Research Institute at Baycrest 416-785-2500 x 2782 tbrown at research.baycrest.org -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: tvb_node3_mailbanner.png Type: image/png Size: 9973 bytes Desc: not available URL: From M.Herbster at cs.ucl.ac.uk Tue Aug 18 13:48:51 2015 From: M.Herbster at cs.ucl.ac.uk (Mark Herbster) Date: Tue, 18 Aug 2015 18:48:51 +0100 Subject: Connectionists: PhD Studentship in Quantum Machine Learning Message-ID: PhD Studentship in Quantum Machine Learning University College London Department of Computer Science A fully funded PhD studentship is available for UK students. It will suit students with a strong background in mathematics, physics, or theoretical computer science. The aim of this PhD position is to design and analyse efficient algorithms for quantum machine learning. We are interested in both algorithms that may be implemented with currently envisioned quantum computing devices as well as the efficient implementation on classical computers of quantum-inspired algorithms. A common framework for machine learning is regularised risk minimisation. The idea is that given a dataset we should select a hypothesis which trades off ?fit to the data? and ?complexity? of the hypothesis. Standard examples of regularisers for linear prediction include the 2-norm, 1-norm and maximum entropy. A number of machine learning problems may be framed as ?matrix learning? - these include for example collaborative filtering, metric learning, and multi-task learning. A popular approach to these problems is the use of spectral matrix regularisers, where the regulariser may be expressed as a function of singular values of the matrix predictor. The project goal is to develop quantum approaches to spectral regularisation. Practically, we will be concerned with the application of matrix learning to scheduling and network transport problems. This project will be jointly supervised by Mark Herbster, Massimiliano Pontil, and Simone Severini. Please see https://www.prism.ucl.ac.uk/#!/?project=140 for further details. Regards, Mark Herbster From gerrywolff65 at gmail.com Wed Aug 19 08:51:11 2015 From: gerrywolff65 at gmail.com (Gerry Wolff) Date: Wed, 19 Aug 2015 13:51:11 +0100 Subject: Connectionists: The SP theory of intelligence: distinctive features and advantages Message-ID: As some people will know, I have been engaged in a long-term project to simplify and integrate observations and concepts across artificial intelligence, mainstream computing, mathematics, and human perception and cognition (http://www.cognitionresearch.org/sp.htm). I?ve been reluctant to make comparisons with other research in AI and related areas, mainly because of differences in what people are trying to achieve. But now I have drafted a paper, intended for publication, that may be downloaded via this link: The SP theory of intelligence: distinctive features and advantages (PDF, http://bit.ly/1WDRbJv). As its name suggests, the paper describes what distinguishes the SP theory from other AI-related research, and why, in many cases, the SP theory has advantages compared with other approaches to AI. One of the biggest sections is about advantages of the SP system compared with deep learning in neural networks. I?m aware that there are likely to be objections to some of the things I have said. But this is only a draft paper and I would very much like to hear objections, or any other comments or suggestions, so that I can make corrections and changes to the paper, as necessary. If you would be willing to look at the paper and send me your comments or suggestions, please let me know fairly soon, in advance of when you send the comments. I will of course acknowledge all contributions of that kind. Many thanks, Gerry Wolff -- Dr Gerry Wolff PhD CEng MIEEE Cognition Research jgw [AT] cognitionresearch.org, +44 (0) 1248 712962, +44 (0) 7746 290775, Skype: gerry.wolff, Web: www.cognitionresearch.org . -------------- next part -------------- An HTML attachment was scrubbed... URL: From Rufin.Vogels at med.kuleuven.be Wed Aug 19 10:10:56 2015 From: Rufin.Vogels at med.kuleuven.be (Rufin Vogels) Date: Wed, 19 Aug 2015 14:10:56 +0000 Subject: Connectionists: ph.d position on deep learning networks applied to neuroscience Message-ID: <6ADFA371A5E9B641B6E0AD6367CD613746B780C5@ICTS-S-MBX11.luna.kuleuven.be> The division of Neurophysiology, KU Leuven, Belgium, has a research (ph.d.) position available to apply deep learning networks (also known as convolutional neural networks) to investigate information processing in the visual cortex. The applicant should have a mathematical, computer science or engineering background and have fluent English language skills (speaking and writing). Expertise in artificial neural networks and machine learning is a plus. Candidates should contact Rufin Vogels (rufin.vogels at med.kuleuven.be). -------------- next part -------------- An HTML attachment was scrubbed... URL: From friedhelm.schwenker at uni-ulm.de Thu Aug 20 17:14:49 2015 From: friedhelm.schwenker at uni-ulm.de (Dr. Schwenker) Date: Thu, 20 Aug 2015 23:14:49 +0200 Subject: Connectionists: Assistant researcher position at Ulm University (Germany) Message-ID: <55D64349.5010000@uni-ulm.de> Assistant researcher position at Ulm University (Germany) Applications are invited for a full-time doctoral or postdoctoral position in the vision and perception science research group (Prof. Heiko Neumann), depending on the candidate's academic record. The position includes regular teaching assistance in the computer science undergraduate and graduate program of the faculty (wissenschaftlicher Mitarbeiter). Salary is according to the level TV-L E13. The duration is for a maximum of six years. The candidate should fit into the main research focus areas of developing biologically inspired canonical circuit models for sensory processing (particularly in vision), the analysis of such dynamical systems, and the mapping of computational principles onto neuromorphic hardware. This considers new event-based sensor technologies and neuromorphic algorithms for developing brain-inspired computing mechanisms and their applications. Biologically inspired learning mechanisms utilising correlation learning and reinforcement learning to self-organise sparse representations for behavioural control will be developed as well. The regular teaching duties include supervision of courses in computer vision at the basic and advanced level in the Bachelor and Masters program of Computer Science and Media-Informatics. Within the MSc. program Cognitive Systems supervised lectures relate to topics in autonomous learning, dynamical systems, and human psychophysics. ** IDEAL CANDIDATE ? training in computer science, math, electrical engineering, physics, or related discipline; ? he/she has a strong background and already experience in computer vision and/or machine learning (in vision); computational modelling; (machine) learning in systems; ? excellent programming skills are required (e.g., Java/C/C++/Matlab/Python); ** HOW TO APPLY? Please send your applications (in one file in pdf format) by email to heiko.neumann at uni-ulm.de The application should include a ? brief statement of interest, ? a curriculum vitae, ? two letters of reference, ? a list of publications (if already available), and ? contact details (postal mailing address, email, skype address) Applicants are encouraged to apply as soon as possible as the position will be filled as soon as a suitable applicant is found. ** RESEARCH GROUP Information about the research group can be found athttp://www.uni-ulm.de/in/neuroinformatik/mitarbeiter/h-neumann.html (link to private homepage). From fernando at tsc.uc3m.es Wed Aug 19 21:16:33 2015 From: fernando at tsc.uc3m.es (Fernando Perez-Cruz) Date: Wed, 19 Aug 2015 21:16:33 -0400 Subject: Connectionists: AISTATS 2016 Message-ID: <8EC1038D-34DA-4C29-8CAC-1D1420DDB5A2@tsc.uc3m.es> Call for Papers: AISTATS 2016 http://aistats.org/ Cadiz, Spain, May 9 - 11, 2016 The 19th International Conference on Artificial Intelligence and Statistics will be held in Cadiz, Spain, from May 9-11 2016. We invite submissions of papers on all topics related to machine learning and statistics for the conference proceedings. The submission of papers and the management of the paper reviewing process for the main conference will be electronic. Submission site: https://cmt.research.microsoft.com/AISTATS2016/ Submission deadline: October 9th, 2015, 23:59 Universal Time. Detailed formatting and submission instructions: http://aistats.org/submit.php Solicited topics include, but are not limited to: * Models and estimation: graphical models, causality, Gaussian processes, approximate inference, kernel methods, nonparametric models, statistical and computational learning theory, manifolds and embedding, sparsity and compressed sensing, ... * Classification, regression, density estimation, unsupervised and semi-supervised learning, clustering, topic models, ... * Structured prediction, relational learning, logic and probability * Reinforcement learning, planning, control * Game theory, no-regret learning, multi-agent systems * Algorithms and architectures for high-performance computation in AI and statistics * Applications of AI and statistics Papers may be at most 8 pages long, excluding references and supplementary material. All submissions must be anonymized and must follow the formatting guidelines in the template, otherwise they will automatically be rejected. Note also the dual submission policy detailed in the instructions. Main Conference Paper Dates Paper submissions due: 23:59 UTC Oct 9, 2015 Author response period: Nov 16, 2015 - Nov 23, 2015 Author notification: Dec 20, 2015 Organization General chair: Fernando Perez Cruz Program chairs: Arthur Gretton, Christian Robert -------------- next part -------------- An HTML attachment was scrubbed... URL: From h.glotin at gmail.com Thu Aug 20 20:21:01 2015 From: h.glotin at gmail.com (Herve Glotin) Date: Thu, 20 Aug 2015 18:21:01 -0600 Subject: Connectionists: PhD pos.: Deep Learning for Speech / Bioacoustic Recognition Message-ID: 'PhD student position: Deep Learning for Speech / Bioacoustic Recognition' ( extended deadline application: august 31st. please forward to whom it may concern ) DYNI / academic LSIS lab is seeking a PhD student in Toulon, France, to investigate deep learning for efficient bioacoustic representations, applied to human speech, bird and whales sound classification. Evaluations will be conducted on international benchmarks. Since 2012, DYNI heads the SABIOD consortium ( http://sabiod.org ) on Scaled Acoustic Biodiversity, joining several international teams expert in machine learning, signal processing and bioacoustics. DYNI chaired several workshops on machine learning meetings bioacoustics at ICML 2013, 2014, NIPS 2013, ICDM 2015. Toulon campus provides scientific facilities and is located in the Provence C?te d'Azur. LSIS lab actually gathers 200 researchers professors & PhD students in computer science and signal analysis & pattern recognition. Applicants should have a strong background in machine learning (maths, statistics, computer science) & a genuine interest in understanding neural computation in perceptual intelligence. Prior exposure to neural computation and machine learning & programming skills is advantageous. Applicants with interest in combining machine learning, feature learning & signal processing are encouraged to apply. The starting date of the 100% government grant (MRT) is October or at last December. The full grant lasts at least 3 years (french Phd program lasts usually 3 years). Application materials should include a CV (university grades, honors / awards, brief statement of research interests, contact details of 2 referees), + 1 or 2 work samples, anything that is genuinely the own work of the applicant (e.g. thesis, computer code, web site demo, research manuscript / essay). For informal inquiries, please contact: Dr. Joseph Razik, Pr. Herv? Glotin and Dr. S?bastien Paris : razik at univ-tln.fr, h.glotin at gmail.com, sebastien.paris at lsis.org Submit your application (a single .PDF) by august 31st to: phd.application.dyni at gmail.com Sincerely, Herve' et coll. -- H. Glotin, Pr - http://glotin.univ-tln.fr - glotin at univ-tln.fr Institut Univ. de France (IUF), UMR CNRS LSIS, Univ. Toulon (UTLN) Head of Scaled Acoustic Biodiversity (http://sabiod.org) & DYNI projects From jkrichma at uci.edu Fri Aug 21 12:35:46 2015 From: jkrichma at uci.edu (Jeff Krichmar) Date: Fri, 21 Aug 2015 09:35:46 -0700 Subject: Connectionists: Chaired Professors in Mathematical Psychology/Cognitive Sciences at UC Irvine Message-ID: <2345D0F2-6294-44E7-B4A6-39D53B0026DA@uci.edu> Dear Connectionists, The following job posting may be of interest to many of you. ---------- University of California, Irvine Chaired Professors in Mathematical Psychology/Cognitive Sciences The Department of Cognitive Sciences (www.cogsci.uci.edu) at the University of California, Irvine (UCI) invites applications for faculty positions associated with the Falmagne Endowed Chairs in Mathematical Psychology/Cognitive Sciences. Applicants should have an exemplary track record of implementing innovative mathematical approaches to important questions in psychology or cognitive science. We are especially interested in candidates at the advanced Associate or Full Professor level whose research focus is in either human cognition or visual perception, and related areas of specialization. Information about the Falmagne Endowed Chairs can be found at: http://www.cogsci.uci.edu/falmagnechairs.php. The online application includes: A cover letter, CV, research and teaching statements, 3 major publications, and contact information for 3-5 referees. Interested candidates can apply for the position at: https://recruit.ap.uci.edu/apply/JPF03041. Application review will commence on December 1, 2015 and continue until filled. The University of California, Irvine is an Equal Opportunity/Affirmative Action Employer advancing inclusive excellence. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, protected veteran status, or other protected categories covered by the UC nondiscrimination policy. ---------- Jeff Krichmar Department of Cognitive Sciences 2328 Social & Behavioral Sciences Gateway University of California, Irvine Irvine, CA 92697-5100 jkrichma at uci.edu http://www.socsci.uci.edu/~jkrichma From Kai.Puolamaki at ttl.fi Fri Aug 21 08:48:46 2015 From: Kai.Puolamaki at ttl.fi (=?utf-8?B?UHVvbGFtw6RraSBLYWk=?=) Date: Fri, 21 Aug 2015 12:48:46 +0000 Subject: Connectionists: Postdoc position in computational data analysis at Brain Work Research Centre @FIOH (DL 15 Sep) Message-ID: <1440161327609.70597@ttl.fi> Summary: Postdoctoral researcher position in computational data analysis at Brain Work Research Centre at the Finnish Institute of Occupational Health, Helsinki. DL 15 Sep. See http://goo.gl/sCKmH6 * * * The Brain Work Research Centre (BWRC) at the Finnish Institute of Occupational Health (FIOH) is seeking for a SPECIALIST RESEARCH SCIENTIST (postdoctoral researcher) in computational data analysis. Your task is to develop methods for explorative data analysis. The work is part of the Human-guided data analysis project, funded by the Academy of Finland. The project studies the use of constrained randomisation methods that enable efficient interaction with state-of-the-art data mining and machine learning algorithms. In your work you will have access to real-world data sets related to health and occupational settings and you will collaborate with experts, e.g., in cognition at FIOH. In addition to research work, you are expected to participate in the supervision of junior researchers related to your research topic. We require a doctoral degree in computer science or other suitable discipline, as well as an excellent track record in one or several fields of computer science. The applicant must have a good working knowledge of statistics as well as of design and analysis of algorithms. We require good communication skills in written and spoken English. Expertise in one or more of the following is considered an advantage: - Deep knowledge of statistics and of design and analysis algorithms - Good programming skills - Knowledge of human cognition - HCI - Multidisciplinary collaboration We reserve the right to hire a doctoral student instead, if there is an outstanding candidate who otherwise satisfies the requirements but does not yet have a doctoral degree. The position is for a fixed term of 2-4 years - upon agreement, with a four month probation period. The location of work is in Meilahti, Helsinki. Interested? Please fill in and submit an electronic application form at latest on 15 September 2015 at http://goo.gl/sCKmH6 Additional information: Kai Puolam?ki, Docent, PhD, Director, Brain Work Research Centre, kai.puolamaki at ttl.fi, +358 30 474 2445 Antti Ukkonen, PhD, Specialist Research Scientist, antti.ukkonen at ttl.fi, +358 30 474 9424 Matti Gr?hn, PhD, Team Leader, matti.grohn at ttl.fi, +358 30 474 2687 The Brain Work Research Centre has a web site at www.ttl.fi/bwrc The Finnish Institute of Occupational Health has a web site at www.ttl.fi You can find the full call text at http://goo.gl/sCKmH6 -- Kai Puolam?ki, Docent, PhD. Director, Brain?Work Research Centre, Finnish Institute of Occupational Health. PO Box 40, 00251 Helsinki, Finland. Phone: +358 43 8250726 Email: kai.puolamaki at ttl.fi FIOH web site: http://www.ttl.fi/ Research homepage: http://www.iki.fi/kaip/ From DCLu at mednet.ucla.edu Sat Aug 22 00:42:35 2015 From: DCLu at mednet.ucla.edu (Lu, Daniel C. M.D., Ph.D. (Neurosurgery)) Date: Sat, 22 Aug 2015 04:42:35 +0000 Subject: Connectionists: UCLA Post-Doctoral Engineering Fellowship Message-ID: Dear Connectionists, Please kindly post this job listing. Thank you. Post-Doctoral Engineering Fellowship at UCLA A full-time, post-doctoral fellowship is immediately available in the laboratory of Dr. Daniel Lu, UCLA Department of Neurosurgery, to study the neural networks within the spinal cord and leverage this understanding to facilitate recovery of motor function after spinal cord injury (SCI). Qualified candidate must have strong background in the scientific method, data analysis, signal processing, and statistics; training in bio-engineering and computational biology. The candidate will be working with an inter-disciplinary team of researchers from molecular biology, physiology, and engineering to test therapeutic interventions and impact on motor function in human and animals. Specific to the candidate, s/he will analyze the kinematic and neurophysiological data to assess intervention efficacy, engineer and devise tools or computational methods to finely assess motor improvements. Fluency in programming and coding in MatLab to analyze large volume of data is a must. We are seeking independent, motivated individual with excellent organizational, interpersonal, and communication skills. Interested applicant should send a CV that includes the names and contact information of three references to the following address: Daniel Lu, MD PhD Department of Neurosurgery University of California, Los Angeles 300 Stein Plaza, Ste. 536 Los Angeles, CA 90095-6901 DCLu at mednet.ucla.edu ________________________________ IMPORTANT WARNING: This email (and any attachments) is only intended for the use of the person or entity to which it is addressed, and may contain information that is privileged and confidential. You, the recipient, are obligated to maintain it in a safe, secure and confidential manner. Unauthorized redisclosure or failure to maintain confidentiality may subject you to federal and state penalties. If you are not the intended recipient, please immediately notify us by return email, and delete this message from your computer. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ranzato at fb.com Fri Aug 21 12:56:17 2015 From: ranzato at fb.com (Marc'Aurelio Ranzato) Date: Fri, 21 Aug 2015 16:56:17 +0000 Subject: Connectionists: First Deep Learning Symposium at NIPS 2015 In-Reply-To: References: Message-ID: First Deep Learning Symposium at the 29th Annual Conference on Neural Information Processing Systems (NIPS 2015) December 10, 2015, Montreal, Canada https://sites.google.com/site/nips2015deeplearnings/ Program Committee nomination deadline: Friday, August 28, 2015 Overview Deep Learning algorithms attempt to discover good representations, at multiple levels of abstraction. Deep Learning is a topic of broad interest, both to researchers who develop new algorithms and theories, as well as to the rapidly growing number of practitioners who apply these algorithms to a wider range of applications, from vision and speech processing, to natural language understanding, neuroscience, health, etc. There has been very rapid and impressive progress in this area in recent years, in terms of both algorithms and applications, but many challenges remain. This symposium aims at bringing together researchers in Deep Learning and related areas to discuss the new advances, the challenges we face, and to brainstorm about new solutions and directions. Format A selected group of leading experts in the field -- the Program Committee (PC) members (see the list at https://sites.google.com/site/nips2015deeplearnings/home/pc-members ) -- will recommend papers to present at the event. There is no usual submission/review process, but PCs members will make their recommendations based on papers they have recently read. In order to let the broader research community and authors contribute with links to paper URLs and comments to papers, we have set up a recommendation website at https://recommend-papers.org . The PCs recommendation deadline is: Friday, August 28, 2015 (although the recommendation website will remain open for comments and contributions even after this date to benefit the PCs in their subsequent discussion to determine the final presenter list, and even after the Symposium date for the benefit of the whole community). For more information, please visit: https://sites.google.com/site/nips2015deeplearnings/ The Deep Learning Symposium Organizers at NIPS 2015, Yoshua Bengio, Marc?Aurelio Ranzato, Honglak Lee, Max Welling, Andrew Ng -------------- next part -------------- An HTML attachment was scrubbed... URL: From ahu at cs.stir.ac.uk Fri Aug 21 15:36:40 2015 From: ahu at cs.stir.ac.uk (Dr Amir Hussain) Date: Fri, 21 Aug 2015 22:36:40 +0300 Subject: Connectionists: Increased Impact Factor (2014/15) and Table of Contents Alert: Cognitive Computation journal (Springer Neuroscience, USA): Vol.7, No.4 / Aug 2015 Issue Message-ID: Dear Colleagues: (with advance apologies for any cross-postings) We are delighted to announce the publication of Volume 7, No.4 / Aug 2015 Issue, of Springer's Cognitive Computation journal - www.springer.com/12559 ================================================================ Important News: Increased Impact Factor & Six bi-monthly Journal Issues from 2015! ================================================================ As you will know, Cognitive Computation was selected for coverage in Thomson Reuter?s products and services in 2011. Beginning with V.1 (1) 2009, this publication is now indexed and abstracted in: ? Science Citation Index Expanded (also known as SciSearch?) ? Journal Citation Reports/Science Edition ? Current Contents?/Engineering Computing and Technology ? Neuroscience Citation Index? Cognitive Computation received its first Impact Factor (IF) of 1.0 in 2011 The IF for 2014 has increased to 1.44 (Thomson Reuters Journal Citation Reports? 2014) Many congratulations to the editors, reviewers and authors! Want to be part of the growing success? Visit the journal homepage (http:// springer.com/12559) for instructions on submitting your research. ================================= Quarterly to Bi-monthly Issues, from 2015!! ================================= Due to continuously growing number of high quality submissions, the number of Issues has increased from four (quarterly Issues) to six (bi-monthly Issues) each year, starting Feb 2015! ================================================================= The August 2015 Issue comprises an invited paper by Alessandro Vinciarelli and Anna Esposito, et al. titled: Open Challenges in Modelling, Analysis and Synthesis of Human Behaviour in Human?Human and Human?Machine Interactions. This is followed by six regular papers. The full listing of published articles (Table of Contents) for this August 2015 Issue can be viewed here (and also at the end of this message, followed by an overview of the previous Issues/Archive listings): http://link.springer.com/journal/12559/7/4/ A list of the journal's most downloaded articles (which can always be read for FREE) can be found here: http://www.springer .com/biomed/neuroscience/journal/12559?hideChart=1#realtime Other 'Online First' published articles not yet in a print issue can be viewed here: http://www.springerlink.com/content/121361/?Content+Status=Accepted All previous Volumes and Issues of the journal can be viewed here: http://link.springer.com/journal/volumesAndIssues/12559 ============================================ Reminder: Cognitive Computation "LinkedIn" Group: ============================================ To further strengthen the bonds amongst the interdisciplinary audience of Cognitive Computation, we have set-up a "Cognitive Computation LinkedIn group", which has over 800 members already! We warmly invite you to join us at: http://www.linkedin.com/groups?gid=3155048 For further information on the journal and to sign up for electronic "Table of Contents alerts" please visit the Cognitive Computation homepage: http://www.springer.com/12559 or follow us on Twitter at: http://twitter.com/CognComput for the latest On-line First Issues. For any questions with regards to LinkedIn and/or Twitter, please contact Springer's Publishing Editor: Marleen Moore: Marleen.Moore at springer.com Finally, we would like to invite you to submit short or regular papers describing original research or timely review of important areas - our aim is to peer review all papers within approximately six-eight weeks of receipt. We also welcome relevant high quality proposals for Special Issues - four are already planned for 2015-16 (including for the 7th international BICS'2015 Conference at Hefei, China, 11-13 Dec 2015, see: http://cs.stir.ac.uk/events/bics2015 - for CFPs of other Special Issues, see: http://www.springer.com/biomed/neuroscience/journal/12559?detailsPage=press ) With our very best wishes to all aspiring readers and authors of Cognitive Computation, Professor Amir Hussain, PhD (Editor-in-Chief: Cognitive Computation) E-mail: ahu at cs.stir.ac.uk (University of Stirling, Scotland, UK) Professor Igor Aleksander, PhD (Honorary Editor-in-Chief: Cognitive Computation) (Imperial College, London, UK) http://www.springer.com/12559 NEW: Open Access Springer/BMC journal: Big Data Analytics ( http://www.bdataanalytics.com/) - Now accepting submissions! NEW: Springer Series on Socio-Affective Computing: http://www.springer.com/series/13199 Also consider your work for related Book Series: SpringerBriefs on Cognitive Computation: http://www.springer.com/series/10374 ------------------------------------------------------------------------------------------------- ???????????Table of Contents Alert -- Cognitive Computation Vol 7 No 4, August 2015 -------------------------------------------------------------------------------------------------- Open Challenges in Modelling, Analysis and Synthesis of Human Behaviour in Human?Human and Human?Machine Interactions Alessandro Vinciarelli, Anna Esposito, Elisabeth Andr?, Francesca Bonin, Mohamed Chetouani, Jeffrey F. Cohn, Marco Cristani, Ferdinand Fuhrmann, Elmer Gilmartin, Zakia Hammal, Dirk Heylen, Rene Kaiser, Maria Koutsombogera, Alexandros Potamianos, Steve Renals, Giuseppe Riccardi and Albert Ali Salah http://link.springer.com/article/10.1007/s12559-015-9326-z Towards Autonomous Robots Via an Incremental Clustering and Associative Learning Architecture Matthias U. Keysermann, Patr?cia A. Vargas http://link.springer.com/article/10.1007/s12559-014-9311-y Visual Attention Model Based Vehicle Target Detection in Synthetic Aperture Radar Images: A Novel Approach Fei Gao, Ye Zhang, Jun Wang, Jinping Sun, Erfu Yang, Amir Hussain http://link.springer.com/article/10.1007/s12559-014-9312-x Correlation Coefficients of Hesitant Fuzzy Sets and Their Application Based on Fuzzy Measures Fanyong Meng, Xiaohong Chen http://link.springer.com/article/10.1007/s12559-014-9313-9 An Arterial Traffic Signal Control System Based on a Novel Intersections Model and Improved Hill Climbing Algorithm Fuyang Chen, Li Wang, Bin Jiang, Changyun Wen http://link.springer.com/article/10.1007/s12559-014-9314-8 Convergence Analysis of a New Self Organizing Map Based Optimization (SOMO) Algorithm Atlas Khan, Li Zheng Xue, Wu Wei, YanPeng Qu, Amir Hussain, Ricardo Z. N. Vencio http://link.springer.com/article/10.1007/s12559-014-9315-7 Concept-Level Sentiment Analysis with Dependency-Based Semantic Parsing: A Novel Approach Basant Agarwal, Soujanya Poria, Namita Mittal, Alexander Gelbukh, Amir Hussain http://link.springer.com/article/10.1007/s12559-014-9316-6 -------------------------------------------------------- Previous Issues/Archive: Overview: -------------------------------------------------------- All previous Volumes and Issues can be viewed here: http://link.springer.com/journal/volumesAndIssues/12559 Alternatively, the full listing of the Inaugural Vol. 1, No. 1 / March 2009, can be viewed here (which included invited authoritative reviews by leading researchers in their areas - including keynote papers from London University's John Taylor, Igor Aleksander and Stanford University's James McClelland, and invited papers from Ron Sun, Pentti Haikonen, Geoff Underwood, Kevin Gurney, Claudius Gross, Anil Seth and Tom Ziemke): http://www.springerlink.com/content/1866-9956/1/1/ The full listing of Vol. 1, No. 2 / June 2009, can be viewed here (which included invited reviews and original research contributions from leading researchers, including Rodney Douglas, Giacomo Indiveri, Jurgen Schmidhuber, Thomas Wennekers, Pentti Kanerva and Friedemann Pulvermuller): http://www.springerlink.com/content/1866-9956/1/2/ The full listing of Vol.1, No. 3 / Sep 2009, can be viewed here: http://www.springerlink.com/content/1866-9956/1/3/ The full listing of Vol. 1, No. 4 / Dec 2009, can be viewed here: http://www.springerlink.com/content/1866-9956/1/4/ The full listing of Vol.2, No. 1 / March 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/1/ The full listing of Vol.2, No. 2 / June 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/2/ The full listing of Vol.2, No. 3 / Aug 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/3/ The full listing of Vol.2, No. 4 / Dec 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/4/ The full listing of Vol.3, No.1 / Mar 2011 (Special Issue on: Saliency, Attention, Active Visual Search and Picture Scanning, edited by John Taylor and Vassilis Cutsuridis), can be viewed here: http://www.springerlink.com/content/1866-9956/3/1/ The Guest Editorial can be viewed here: http://www.springerlink.com/content/hu2245056415633l/ The full listing of Vol.3, No.2 / June 2011 can be viewed here: http://www.springerlink.com/content/1866-9956/3/2/ The full listing of Vol. 3, No. 3 / Sep 2011 (Special Issue on: Cognitive Behavioural Systems, Guest Edited by: Anna Esposito, Alessandro Vinciarelli, Simon Haykin, Amir Hussain and Marcos Faundez-Zanuy), can be viewed here: http://www.springerlink.com/content/1866-9956/3/3/ The Guest Editorial for the special issue can be viewed here: http://www.springerlink.com/content/h4718567520t2h84/ The full listing of Vol. 3, No. 4 / Dec 2011 can be viewed here: http://www.springerlink.com/content/1866-9956/3/4/ The full listing of Vol. 4, No.1 / Mar 2012 can be viewed here: http://www.springerlink.com/content/1866-9956/4/1/ The full listing of Vol. 4, No.2 / June 2012 can be viewed here: http://www.springerlink.com/content/1866-9956/4/2/ The full listing of Vol. 4, No.3 / Sep 2012 (Special Issue on: Computational Creativity, Intelligence and Autonomy, Edited by: J. Mark Bishop and Yasemin J. Erden) can be viewed here: http://www.springerlink.com/content/1866-9956/4/3/ The full listing of Vol. 4, No.4 / Dec 2012 (Special Issue titled: "Cognitive & Emotional Information Processing", Edited by: Stefano Squartini, Bj?rn Schuller and Amir Hussain, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/4/4/page/1 The full listing of Vol. 5, No.1 / March 2013 Special Issue titled: Computational Intelligence and Applications Guest Editors: Zhigang Zeng & Haibo He, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/5/1/page/1 The full listing of Vol. 5, No.2 / June 2013 Special Issue titled: Advances on Brain Inspired Computing, Guest Editors: Stefano Squartini, Sanqing Hu & Qingshan Liu, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/5/2/page/1 The full listing of Vol. 5, No.3 / Sep 2013 Special Issue titled: In Memory of John G Taylor: A Polymath Scholar, Guest Editors: Vassilis Cutsuridis & Amir Hussain, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/5/3/page/1 The full listing of Vol. 5, No.4 / Dec 2013, which includes regular papers (including an invited paper by Professor Ron Sun, Rensselaer Polytechnic Institute, USA, titled: Moral Judgment, Human Motivation, and Neural Networks), and a Special Issue titled: Advanced Cognitive Systems Based on Nonlinear Analysis. Guest Editors: Carlos M. Travieso and Jes?s B. Alonso, can be viewed here: http://link.springer.com/journal/12559/5/4/page/1 The full listing of Vol. 6, No.1 / Mar 2014, can be viewed here: http://link.springer.com/journal/12559/6/1/page/1 The full listing of Vol. 6, No.2 / June 2014, can be viewed here: http://link.springer.com/journal/12559/6/2/page/1 The full listing of Vol. 6, No.3 / Sep 2014, can be viewed here: http://link.springer.com/journal/12559/6/3/page/1 The full listing of Vol. 6, No.4 / Dec 2014 (Special Issue on Modeling emotion, behaviour and context in socially believable robots and ICT interfaces, Guest Editors: Anna Esposito, Leopoldina Fortunati, and Giuseppe Lugano) can be viewed here: http://link.springer.com/journal/12559/6/4/page/1 The full listing of Vol. 7, No.1 / Feb 2015 can be viewed here: http://link.springer.com/journal/12559/7/1/ (with the first six papers part of a Special Issue on "Neural Signal Processing", Guest Edited by: Jordi Sole?-Casals, Francois-Benoit Vialatte, Justin Dauwels. The Guest Editorial titled: "Alternative Techniques of Neural Signal Processing in Neuroengineering" is available (for free download) here: http://link.springer.com/article/10.1007/s12559-015-9317-0) The full listing of Vol. 7, No. 2 / April 2015, can be viewed here: http://link.springer.com/journal/12559/7/2/ This comprises a Special Issue on "Sentic Computing", Guest Edited by: E. Cambria and A. Hussain. The Guest Editorial titled: "Sentic Computing" is available (for free download) here: http://link.springer.com/article/10.1007/s12559-015-9325-0 The full listing of Vol. 7, No. 3 / June 2015, can be viewed here: http://link.springer.com/journal/12559/7/3/ ________________________________ -- The University is ranked in the QS World Rankings of the top 5% of universities in the world (QS World University Rankings, 2014) The University of Stirling is a charity registered in Scotland, number SC 011159. -------------- next part -------------- An HTML attachment was scrubbed... URL: From antonior at ffclrp.usp.br Sun Aug 23 17:12:34 2015 From: antonior at ffclrp.usp.br (Antonio C. Roque) Date: Sun, 23 Aug 2015 18:12:34 -0300 Subject: Connectionists: LASCON 2016 - VI Latin American School on Computational Neuroscience (Call for applications) Message-ID: **** Apologies for cross-posting **** VI Latin American School on Computational Neuroscience - LASCON 2016 January 3 - 29, 2016, Sao Paulo, Brazil http://sisne.org/lascon APPLICATION DEADLINE: September 6 2015 SECOND ANNOUNCEMENT Dear Colleagues, Following the success of the previous editions of LASCON (Latin American School on Computational Neuroscience), I am pleased to announce the 6th LASCON, which will take place between January 3 - 29 2016 at the NeuroMat Center in the University of Sao Paulo, Sao Paulo, Brazil. LASCON aims at introducing young researchers and graduate and advanced undergraduate students to the use of computational and mathematical methods for modeling neurons and neural networks. These models will be taught via a combination of theoretical lectures and hands-on tutorials with the use of the programs like neuroConstruct, NEURON, NEST, Brian, the Virtual Brain and Matlab. Students will have to work on small research projects (to be done in groups of two), which they will present orally at the end of the school. The following lecturers will be in charge of theoretical classes and tutorials: Arnd Roth, University College, London, UK Benjamin Lindner, Humboldt-Universitaet zu Berlin, Berlin, Germany Boris Marin, University College, London, UK Christophe Pouzat, Universite Paris Descartes, Paris, France Demian Battaglia, Aix-Marseille Universite, Marseille, France German Mato, Centro Atomico Bariloche, San Carlos de Bariloche, RN, Argentina Hannah Bos, Forschungszentrum Juelich, Juelich, Germany Jannis Schuecker, Forschungszentrum Juelich, Juelich, Germany John Murray, Yale University, New Haven, CT, USA Marco Huertas, University of Texas Medical School, Houston, TX, USA Volker Steuber, University of Hertfordshire, Hatfield, UK William Lytton, State University of New York, New York, NY, USA There will also be some invited lectures. The current list of invited lecturers is: Andre Kohn, Universidade de Sao Paulo, Sao Paulo, SP, Brazil Antonio Galves, Universidade de Sao Paulo, Sao Paulo, SP, Brazil Cesar Renno-Costa, Universidade Federal do Rio Grande do Norte, Natal, RN, Brazil Fabio Simoes de Souza, Universidade Federal do ABC, Santo Andre, SP, Brazil Julian Tejada, Universidade Federal de Sergipe, Aracaju, SE, Brazil Leonardo Maia, Universidade de Sao Paulo, Sao Carlos, SC, Brazil Marco Idiart, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil Marcelo Reyes, Universidade Federal do ABC, Santo Andre, SP, Brazil Mauro Copelli, Universidade Federal de Pernambuco, Recife, PE Sakyasingha Dasgupta, RIKEN Brain Science Institute, Wako, Japan Sergio Neuenschwander, Universidade Federal do Rio Grande do Norte, Natal, RN, Brazil The number of students is limited to 20 and applications should be made electronically via the application form in the school's web page ( http://sisne.org/?page_id=253&lang=en). Applicants are also requested to submit a detailed CV (in English) and to provide two letters of recommendation. The application deadline is September 6 2015 (until midnight, US Pacific time). There is no registration fee for the school. Costs for accommodation will be covered by the school organization. Travel costs have to be covered by the students. Sao Paulo is the major transportation hub in South America, so it is possible to fly from basically anywhere in the world to it. In the selection procedure, priority will be given to Latin-American students, but students from other parts of the world are encouraged to apply as well. LASCON 2016 is an activity of the FAPESP Center for Neuromathematics (NeuroMat -http://neuromat.numec.prp.usp.br) and is jointly organized by the University of Sao Paulo and the Federal University of ABC. I am looking forward to see you in Sao Paulo. Best regards, A. Roque LASCON Director -- Dr. Antonio C. Roque Professor Associado Departamento de Fisica FFCLRP, Universidade de Sao Paulo 14040-901 Ribeirao Preto-SP Brazil - Brasil E-mails: antonior at ffclrp.usp.br aroquesilva at gmail.com URL: www.sisne.org Tels: +55 16 3315-3768 (sala/office); +55 16 3315-3859 (lab) FAX: +55 16 3315-4887 -------------- next part -------------- An HTML attachment was scrubbed... URL: From pascal.fua at epfl.ch Mon Aug 24 11:24:42 2015 From: pascal.fua at epfl.ch (Pascal Fua) Date: Mon, 24 Aug 2015 17:24:42 +0200 Subject: Connectionists: Post-doctoral Position in Computer Vision at EPFL Message-ID: <55DB373A.9070007@epfl.ch> EPFL's Computer Vision Laboratory (http://cvlab.epfl.ch/) has an opening for a post-doctoral fellow in the field of Microscopy. The position is initially offered for 1 year and can be extended for up to 4 years total. Description: The work will be performed in collaboration with EPFL's Centre for Electron Microscopy (http://cime.epfl.ch/) and will involve developing Computer-Vision techniques for automated detection of dislocations and other defects in crystals seen in Transmission Electron Microscopy. Position: The Computer Vision Laboratory offers a creative international environment, a possibility to conduct competitive research on a global scale and involvement in teaching. There will be ample opportunities to cooperate with some of the best groups in Europe and elsewhere. The centre for electron microscopy is a world leading center for scanning and transmission electron microscopy and develops innovative techniques for image acquisition. EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers away from the city of Geneva. Salaries for post-doctoral fellows start from CHF 81,400 per year, the precise amount to be determined by EPFL's department of human resources. Education: Applicants are expected to have finished, or be about to finish their Ph.D. degrees, to have a strong background in Computer Vision and Biomedical Imaging, and to have a track record of publications in top conferences and journals. Strong programming skills (C or C++) are a plus. Good communication skills and ability to work in a multidisciplinary environment are important. French language skills are not required, English is mandatory. Application: Applications must be sent by email to Ms. Gisclon (josiane.gisclon at epfl.ch). They must contain a statement of interest, a CV, a list of publications, and the names of three references. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From terry at salk.edu Mon Aug 24 18:23:38 2015 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 24 Aug 2015 15:23:38 -0700 Subject: Connectionists: NEURAL COMPUTATION - September 1, 2015 In-Reply-To: Message-ID: Neural Computation - Volume 27, Number 9 - September 1, 2015 Available online for download now: http://www.mitpressjournals.org/toc/neco/27/9 ----- Article Extracting Low-dimensional Latent Structure From Time Series in the Presence of Delays Karthik C. Lakshmanan, Patrick T Sadtler, Elizabeth C Tyler-Kabara, Aaron P Batista, and Byron M. Yu Note Is First-Order Vector Autoregressive Model Optimal for fMRI Data? Chee-Ming Ting, Abd-Krim Seghouane, Muhammad Usman Khalid, and Sh-Hussain Salleh Letters A Novel Reconstruction Framework for Time Encoded Signals with Integrate-and-fire Neurons Dorian Florescu, Daniel Coca Online Direct Density-Ratio Estimation Applied to Inlier-based Outlier Detection Marthinus Christoffel du Plessis, Hiroaki Shiino, and Masashi Sugiyama Relations Among Some Low Rank Subspace Recovery Models Hongyang Zhang, Zhouchen Lin, Chao Zhang, and Junbin Gao A Fast Algorithm for Learning Overcomplete Dictionary for Sparse Representation Based on Proximal Operators Zhenni Li, Shuxue Ding, and Yujie Li Fusion of Scores in a Detection Context Based on Alpha Integration Antonio Soriano, Luis Vergara, Bouziane Ahmed, and Addisson Salazar ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp SUBSCRIPTIONS - 2015 - VOLUME 27 - 12 ISSUES Student/Retired $75 Individual $134 Institution $1,075 MIT Press Journals, One Rogers Street, Cambridge, MA 02142-1209 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-cs at mit.edu ------------ From Hugo.Larochelle at USherbrooke.ca Tue Aug 25 12:29:28 2015 From: Hugo.Larochelle at USherbrooke.ca (Hugo Larochelle) Date: Tue, 25 Aug 2015 16:29:28 +0000 Subject: Connectionists: CfP: ICLR 2016 - Conference Track Message-ID: <366CF53E-5A03-4E05-A1A6-9FC7309BAF24@usherbrooke.ca> ------------------------------------------------------------------- 4th International Conference on Learning Representations (ICLR 2016) ------------------------------------------------------------------- Website: http://www.iclr.cc/ Submission deadline for title and abstract: November 12th, 2015 Submission deadline for arXiv paper ID: November 19th, 2015 Location: Caribe Hilton, San Juan, Puerto Rico, May 2-4, 2016 Overview -------- It is well understood that the performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. The rapidly developing field of representation learning is concerned with questions surrounding how we can best learn meaningful and useful representations of data. We take a broad view of the field, and include in it topics such as deep learning and feature learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization. Despite the importance of representation learning to machine learning and to application areas such as vision, speech, audio and NLP, there was no venue for researchers who share a common interest in this topic. The goal of ICLR has been to help fill this void. A non-exhaustive list of relevant topics: - unsupervised, semi-supervised, and supervised representation learning - metric learning and kernel learning - dimensionality expansion - sparse modeling - hierarchical models - optimization for representation learning - learning representations of outputs or states - implementation issues, parallelization, software platforms, hardware - applications in vision, audio, speech, natural language processing, robotics, neuroscience, or any other field The program will include keynote presentations from invited speakers, oral presentations, and posters. As usual, ICLR will feature two tracks: a Conference Track and a Workshop Track. However, this year, conference and workshop submissions will be reviewed separately, in two different periods. This call for paper is thus only for conference contributions. Workshop submissions will be received a few months before the conference and be subject to a lighter review. A future call for papers will be sent with more details on the Workshop Track. Also, the reviewing period for conference submissions will be separated into two short rounds (normally 2 reviews in the first round, 1 review in the second round). The first round will run as usual. The second round reviews, however, in addition to evaluating the submissions, will be required to include comments on the content of the first round reviews. By asking for such comments, we hope to ensure a minimum of discussion for every paper, and favour interactions that might either identify factual errors early or reveal a clearer consensus. Note that some of the submitted papers that are not accepted to the Conference Track will be invited to be presented under the Workshop Track. ICLR Submission Instructions ---------------------------- 1. By November 12th, authors are asked to enter in openreview.net the title, abstract and author list for their paper. 2. Then, as soon as possible, authors must post on arXiv their submission: http://arxiv.org . 3. Finally, by November 19th, authors must update their submission in openreview.net with the arXiv ID of their paper. Note that there can be up to 3 days of delay between sending a manuscript on arXiv and receiving your arXiv ID. It is thus important to post your submission on arXiv early. Note also that you can always update your submission on arXiv later on, anytime during the review process. Submissions without an arXiv ID after November 19th will be automatically removed from openreview.net. For more information on paper preparation, including style files and the URL for the openreview ICLR 2016 website, please see http://www.iclr.cc/doku.php?id=iclr2016:main Submission deadline: November 12th for title and abstract, November 19th for arXiv ID. Notes: i. Regarding the conference submission's 6-9 page limits, these are really meant as guidelines and will not be strictly enforced. For example, figures should not be shrunk to illegible size to fit within the page limit. However, in order to ensure a reasonable workload for our reviewers, papers that go beyond the 9 pages should be formatted to include a 9 page submission, with supplementary material appended at the end of the manuscript and clearly marked as an appendix, which will be optionally reviewed. ii. Paper revisions will be permitted, and in fact are encouraged, in response to comments from and discussions with the reviewers (see "An Open Reviewing Paradigm" below). An Open Reviewing Paradigm -------------------------- 1. Submissions to ICLR are posted on arXiv prior to being submitted to the conference. 2. Authors submit their paper to either the ICLR conference track or workshop track via the openreview.net ICLR 2016 website. 3. After the authors have submitted their papers via openreview.net, the ICLR program committee designates anonymous reviewers as usual. 4. The submitted reviews are published without the name of the reviewer, but with an indication that they are the designated reviews. 5. Anyone can openly (non-anonymously) write and publish comments on the paper. Anyone can ask the program chairs for permission to become an anonymous designated reviewer (open bidding). The program chairs have ultimate control over the publication of each anonymous review. Open commenters will have to use their real names. 6. Authors can post comments in response to reviews and comments. They can revise the paper as many times as they want, possibly citing some of the reviews. Reviewers are expected to revise their reviews in light of paper revisions. 7. The review calendar includes a generous amount of time for discussion between the authors, anonymous reviewers, and open commentators. The goal is to improve the quality of the final submissions. 8. The ICLR program and area chairs will consider all submitted papers, comments, and reviews and will decide which papers are to be presented in the conference track, which will be invited to be presented in the workshop track, and which will not appear at ICLR. 9. Papers that are presented in the workshop track or are not accepted will be considered non-archival, and may be submitted elsewhere (modified or not), although the ICLR site will maintain the reviews, the comments, and the links to the arXiv versions. Organizers ---------- Yoshua Bengio, Universit? de Montreal, General Chair Yann LeCun, New York University and Facebook, General Chair Hugo Larochelle, Twitter and Universit? de Sherbrooke, Senior Program Chair Brian Kingsbury, IBM Watson Group, Program Chair Samy Bengio, Google, Program Chair Contact ------- The organizers can be contacted at iclr2016.programchairs at gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From axel.hutt at inria.fr Tue Aug 25 17:55:35 2015 From: axel.hutt at inria.fr (Axel Hutt) Date: Tue, 25 Aug 2015 23:55:35 +0200 (CEST) Subject: Connectionists: Slides for the Tutorial at the CNS 2015 in Prague on Neural Mass and Neural Field Models In-Reply-To: <901214987.11784488.1440539660217.JavaMail.zimbra@inria.fr> Message-ID: <872698039.11784608.1440539735912.JavaMail.zimbra@inria.fr> Dear all, for the Tutorial "Neural Mass and Neural Field Models" at the Computational Neuroscience Conference 2015 in Prague, the presentation files are available now, please see http://www.geocities.ws/digitalbath/CNSTutorial_2015.html The speakers were: 09:00 - 10:30 : Introduction to Neural Fields (Axel Hutt) 10:45 - 12:15 : Nonlinear and Stochastic Analysis of Neural Fields Equations (Jeremie Lefebvre) 13:15 - 14:45 : Tutorial introduction to mean-field modelling of general anaesthesia (Alistair Steyn-Ross) 15:00 - 16:30 : Neural fields, a cognitive approach: attention, plasticity and decision (Nicolas Rougier) Best Axel -- PD Axel Hutt Directeur de Recherche INRIA CR Nancy - Grand Est Equipe NEUROSYS (Head) 615, rue du Jardin Botanique 54603 Villers-les-Nancy Cedex France http://www.loria.fr/~huttaxel From ELM_Xposed at Safe-mail.net Wed Aug 26 10:46:04 2015 From: ELM_Xposed at Safe-mail.net (ELM Xposed) Date: Wed, 26 Aug 2015 10:46:04 -0400 Subject: Connectionists: Homepage on the Origins of the Extreme Learning Machine (ELM) Message-ID: The Extreme Learning Machine (ELM) is one of the hottest connectionist model at the present. With annotated PDF files at http://elmorigin.wix.com/originofelm , you can easily verify the following facts within 10 to 20 minutes: 1. The kernel (or constrained-optimization-based) version of ELM (ELM-Kernel, Huang 2012) is identical to kernel ridge regression (for regression and single-output classification, Saunders ICML 1998, as well as the LS-SVM with zero bias; for multiclass multi-output classification, An CVPR 2007). 2. ELM-SLFN (the single-layer feedforward network version of the ELM, Huang IJCNN 2004) is identical to the randomized neural network (RNN, with omission of bias, Schmidt 1992) and another simultaneous work, i.e., the random vector functional link (RVFL, with omission of direct input-output links, Pao 1994). 3. ELM-RBF (Huang ICARCV 2004) is identical to the randomized RBF neural network (Broomhead-Lowe 1988, with a performance-degrading randomization of RBF radii or impact factors). From schurgerlab at gmail.com Wed Aug 26 07:29:02 2015 From: schurgerlab at gmail.com (Schurger Lab) Date: Wed, 26 Aug 2015 13:29:02 +0200 Subject: Connectionists: Interdisciplinary post-doctoral position in cognitive neuroscience Message-ID: Brain-behavior forecasting: Neural antecedents of spontaneous self-initiated movement and the forecasting of behavior from brain activity Interdisciplinary post-doctoral position in cognitive neuroscience Starting date: Spring 2016 or Fall 2016 Duration: 2 years (renewable for one additional year) The French Institute of Health and Medical Research (INSERM) invites applications for a post-doctoral position in the Cognitive Neuroimaging Group, at the NeuroSpin Research Center near Paris, France, as part of the research team of Dr. Aaron Schurger. The Schurger lab focuses on understanding how decisions are made and actions initiated spontaneously, without an external sensory cue, and how time series of neural activity (now) can be used to forecast behavior (seconds or minutes from now). We pursue this research using a combination of behavioral experiments, neuroimaging, computational modeling, time-series analyses, and machine learning techniques. We are particularly interested in attracting applicants from meteorology, macroeconomics, machine learning, statistics and other disciplines that involve a mastery of time series analysis, statistical learning, forecasting, and/or forecast verification. Applicants should have a obtained a PhD in a relevant discipline prior to the starting date, and should have strong skills in at least some of the following areas: computer programming (MatLab, Python, C, C++), statistics, signal processing, computational, mathematical, and/or neural network modeling, statistical learning / machine learning / mutivariate pattern classification, time series analysis, forecasting. Resources available at NeuroSpin include Siemens 3T and 7T MRI scanners; high-density EEG (EGI Inc.); Elekta NeuroMag 306-channel MEG (allowing for the simultaneous recording of EEG); eye tracking (available for MRI, MEG, and behavioral experiments); an in-house team of experts in signal processing and statistical learning; a dedicated staff handling subject recruitment, scheduling, and payment; various Nespresso devices; and proximity to Paris. The salary is competitive, being aligned with that offered by Marie Curie fellowships. Applicants should send a CV, letter of motivation (max 2 pages), and a list of three references via e-mail to schurgerlab at gmail.com. Review of applicants will begin immediately, and will continue until the positions are filled. The NeuroSpin Research Center is located on the campus of the CEA-Saclay, near Orsay, about 18 km southwest of Paris. For more information on the NeuroSpin Research Center and the Cognitive Neuroimaging Group: http://www-centre-saclay.cea.fr/fr/Visite-guidee-de-NeuroSpin http://meg-france.in2p3.fr/_lesCentres/Neurospin_en.php http://www-dsv.cea.fr/en/institutes/institute-of-biomedical-imaging-i2bm/departments/neurospin-neurospin http://www.unicog.org/pm/pmwiki.php ----------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From neurogirl at hotmail.com Wed Aug 26 18:16:21 2015 From: neurogirl at hotmail.com (neuro girl) Date: Thu, 27 Aug 2015 00:16:21 +0200 Subject: Connectionists: Registration and Abstract submission Brain States Conference Message-ID: Dear All, Registration and abstract submission are now open! Brain States: Characterization and Neuromodulation by DBS November 11-13, 2015 in Cologne, Germany. Interdisciplinary contributions to the study of brain mechanics have greatly advanced our theories of the neurodynamic operations employed by the brain. Although the brain exhibits continuous ongoing activity, variation in the spatiotemporal patterns of activation observed across different brain regions during rest versus active processing provides valuable information about functional connectivity and strategies for information processing. This conference will explore the most up-to-date theories of normal brain function and how these processes may be altered to produce pathological states. Furthermore, it will explore the models and methods used to describe the proposed neural strategies subserving these different brain states. Our list of confirmed speakers include: Hagai Bergman (Hebrew University of Jerusalem) Peter Brown (University of Oxford) Stephan Chabardes (University Hospital Grenoble) Alain Destexhe (CNRS) Emad N. Eskandar (Massachusetts General Hospital-Harvard Medical School) John J. Foxe (Albert Einstein College of Medicine) Marc Goodfellow (University of Exeter) Anthony A. Grace (University of Pittsburgh) Rowshanak Hashemiyoon (University Hospital of Cologne) Jens Haueisen (Technische Universit?t Ilmenau) Viktor Jirsa (Aix-Marseille Universit? /CNRS) Jens Kuhn (University Hospital Cologne) Fernando Lopes da Silva (University of Amsterdam) Andres Lozano (University of Toronto) Cameron McIntyre (Case Western Reserve University) Christoph M. Michel (University of Geneva) Bart Nuttin (KU Leuven) Urs Ribary (Simon Fraser University) G?nter Schiepek (Paracelsus Medical University) Wolf Singer (Max Planck Institute for Brain Research) Dimitri van de Ville (University of Geneva) Veerle Visser-Vandewalle (University Hospital of Cologne) J?rgen Voges (Otto-von-Guericke-University Magdeburg) We are intentionally limiting attendance in order to ensure a collegial atmosphere with excellent discussion. More information can be found on these websites http://bit.ly/1JVElkf and https://dbs.veomed.net/. Please find attached the poster with the announcement. Distribution is welcome and appreciated. Hope to see you in Cologne! With kind regards, Row Hashemiyoon Rowshanak Hashemiyoon, PhD Chief, Behavioral Neurophysiology and Computational Neuroscience Klinik f?r Stereotaxie und Funktionelle Neurochirurgie Universit?tsklinikum K?ln Kerpener Str. 62 D - koeln 50937 http://www.uk-koeln.de/de/stereotaxie -------------- next part -------------- A non-text attachment was scrubbed... Name: Poster_Brain-States final.pdf Type: application/pdf Size: 397092 bytes Desc: not available URL: From paul.zhutovsky at gmail.com Thu Aug 27 02:53:44 2015 From: paul.zhutovsky at gmail.com (Paul Zhutovsky) Date: Thu, 27 Aug 2015 08:53:44 +0200 Subject: Connectionists: PhD Position in Deep Learning & Visual Neuroscience Message-ID: Hi there, we at EyeQuant, a visual neuroscience / machine learning startup based in Berlin have teamed up with a Marie Curie training network to offer a fully salaried PhD candidate position at the rapidly advancing intersection of Deep Learning, Computer Vision and Visual Neuroscience, starting as soon as possible. This is a really unique opportunity to obtain a PhD through a prestigious programme while working with and at a successful technology software startup, enabling you to simultaneously advance your career prospects both inside and outside of academia. Your supervisor and PI will be neuroscientist and EyeQuant co-founder Prof. Dr. Peter K?nig, who is the Director of the Institute of Cognitive Science and Head of the Neurobiopsychology Lab at the University of Osnabr?ck, Germany. You will be based in EyeQuant?s Berlin HQ, with regular trips to our Lab in Osnabr?ck. You can find more details and next steps here: http://www.eyequant.com/#!/jobs Please note that in order to be eligible for the MARIE SK?ODOWSKA-CURIE grant, you must not have carried out your main research activity for more than 12 months in Germany in the previous 36 months. -------------- next part -------------- An HTML attachment was scrubbed... URL: From cassio at idsia.ch Thu Aug 27 04:49:53 2015 From: cassio at idsia.ch (Cassio P. de Campos) Date: Thu, 27 Aug 2015 09:49:53 +0100 Subject: Connectionists: CFP IJAR Special issue on Statistical and Computational methods for genomics and integrative genomics Message-ID: CALL FOR PAPERS International Journal of Approximate Reasoning Special issue on Statistical and Computational methods for genomics and integrative genomics http://www.journals.elsevier.com/international-journal-of-approximate-reasoning/call-for-papers/special-issue-on-statistical-and-computational-methods-for-g/ Background and Scope: In the last decade, the advent of microarray and next-generation sequencing technologies has created the need of statistical and computational methodologies specifically developed for dealing with these types of data and novel biomedical research goals. Genomic data measure quantities (such as, gene-expression, copy number, genotype, methylation) at several thousands or millions of positions along the genome, resulting in an enormous amount of information from which to extract the relevant content. They are usually noisy and subject to uncertainties due to non-biological variations, which must be taken into account during the modelling and inferential processes. Many other issues arise when the field of application regards the study of complex genetic diseases, since patients can be highly heterogeneous and several different lesions may alter the same biological pathway. Moreover, the number of patients is usually small with respect to the number of variables, which brings another facet to the problem. Approaches that try to overcome all these difficulties rely on biological assumptions and integrate established knowledge and multiple types of data. Data integration may comprise not only different genomic data, but also clinical and other patient information. Combining all this information by an accurate biological and statistical modelling may allow us to achieve reliable biomedical discoveries. Inferential and computational issues must be also considered, as data have very high dimension and computational resources are limited. Papers are sought on theoretical and practical considerations involving statistical and computational approaches to address problems and data from the biomedical domain. General methodological and algorithmic developments are also welcome as long as they have a clear applicability to the biomedical domain. If unsure about the fit of your intended paper or for any additional information, please do not hesitate to contact the guest editors. Important Dates: Deadline for expression of interest to submit a paper (suggested): September 15, 2015. Deadline for first submission: October 15, 2015 Reviews available: December, 2015 Expected online publication: April, 2016 Submission and Review Process: Authors should prepare their papers according to the Guide for Authors of the International Journal of Approximate Reasoning (http://ees.elsevier.com/ija/). All submissions must be made electronically through the Elsevier's EES submission system at http://ees.elsevier.com/ija/ with the Article Type 'SI: Statistical genomics'. All papers will be peer-reviewed following the IJAR review guidelines. Guest Editors: Paola M.V. Rancoita University Centre for Statistics for the Biomedical Sciences Vita-Salute San Raffaele University, Italy http://www.unisr.it/persona.asp?id=8888&linguacv=english Cassio P. de Campos School of Electronics, Electrical Engineering and Computer Science Queen's University Belfast, UK http://www.cs.qub.ac.uk/~c.decampos/ From shakir.mohamed at gmail.com Thu Aug 27 04:32:19 2015 From: shakir.mohamed at gmail.com (Shakir Mohamed) Date: Thu, 27 Aug 2015 09:32:19 +0100 Subject: Connectionists: NIPS 2015 Workshop on Advances in Approximate Bayesian Inference Message-ID: Call for Participation We invite researchers in machine learning and statistics to participate in the: NIPS 2015 Workshop on Advances in Approximate Bayesian Inference 11 December 2015, Montreal, Canada www.approximateinference.org Submission deadline: 2 October 2015 1. Call for Participation We invite researchers to submit their recent work on the development, analysis, or application of approximate Bayesian inference. A submission should take the form of an extended abstract of 2-4 pages in PDF format using the NIPS style. Author names do not need to be anonymized and references may extend as far as needed beyond the 4 page upper limit. If authors' research has previously appeared in a journal, workshop, or conference (including the NIPS 2015 conference), their workshop submission should extend that previous work. Submissions may include a supplement/appendix, but reviewers are not responsible for reading any supplementary material. Submissions will be accepted either as contributed talks or poster presentations. Extended abstracts should be submitted by 2 October; see website for submission details. Final versions of the extended abstract are due by 1 December, and will be posted on the workshop website. 2. Workshop Overview The ever-increasing size of data sets has resulted in an immense effort in Bayesian statistics to develop more expressive probabilistic models. Inference remains a challenge and limits the use of these models in large-scale scientific and industrial applications. Thus we must resort to approximate inference, which is computationally efficient on massive and streaming data?without compromising on the complexity of these models. This workshop aims to bring together researchers and practitioners in order to discuss recent advances in approximate inference; we also aim to discuss the methodological and foundational issues in such techniques in order to consider future improvements. The resurgence of interest in approximate inference has furthered development in many techniques: for example, scalability, black box techniques, and dependency in variational inference; divide and conquer techniques in expectation propagation; dimensionality reduction using random projections; and stochastic variants of Laplace approximation-based methods. Despite this interest, there remain significant trade-offs in speed, accuracy, generalizability, and learned model complexity. In this workshop, we will discuss how to rigorously characterize these tradeoffs, as well as how they might be made more favourable. Moreover, we will address the issues of its adoption in scientific communities which could benefit from advice on their practical usage and the development of relevant software packages. This workshop is motivated by, and in some ways a successor to, the NIPS 2014 workshop on Advances in Variational Inference. It is supported by the International Society of Bayesian Analysis (ISBA) and Adobe Creative Technologies Laboratory. 3. Speakers and Panelists Invited Speakers John Cunningham (Columbia University) Emily Fox (University of Washington) Rajesh Ranganath (Princeton University) James Hensman (University of Sheffield) Andrea Montanari (Stanford University) Panel: "Tricks of the Trade" Matt Hoffman (Adobe Research) Danilo Rezende (Google DeepMind) David Duvenaud (Harvard University) Alp Kucukelbir (Columbia University) Stephan Mandt (Columbia University) Panel: "On the Foundations and Future of Approximate Inference" Max Welling (University of Amsterdam) Yee Whye Teh (University of Oxford) Andrew Gelman (Columbia University) Steve MacEachern (Ohio State University) Manfred Opper (Technische Universit?t Berlin) 4. Key Dates Paper submission: 2 October 2015 Travel award application deadline: 2 October 2015 Acceptance notification: 23 October 2015 Travel award notification: 30 October 2015 Notification of type of presentation: 5 November 2015 Final paper submission: 1 December 2015 Workshop: 11 December 2015 Workshop Organizers Dustin Tran (Harvard University) Tamara Broderick (MIT) Shakir Mohamed (Google DeepMind) Alp Kucukelbir (Columbia University) Stephan Mandt (Columbia University) James McInerney (Columbia University) Matt Hoffman (Adobe Research) David Blei (Columbia University) Neil Lawrence (University of Sheffield) -------------- next part -------------- An HTML attachment was scrubbed... URL: From v.steuber at herts.ac.uk Fri Aug 28 06:11:05 2015 From: v.steuber at herts.ac.uk (Steuber, Volker) Date: Fri, 28 Aug 2015 11:11:05 +0100 Subject: Connectionists: Senior lectureship in computer science (machine learning / biocomputation) In-Reply-To: <18EF08266D889C41A14D1099C7102CE2C9C4D860D6@UH-MAILSTOR.herts.ac.uk> References: <18EF08266D889C41A14D1099C7102CE2BDFC6EC5F0@UH-MAILSTOR.herts.ac.uk>, <18EF08266D889C41A14D1099C7102CE2C9C4D860D6@UH-MAILSTOR.herts.ac.uk> Message-ID: <18EF08266D889C41A14D1099C7102CE2C9C6381819@UH-MAILSTOR.herts.ac.uk> Senior Lecturer in Computer Science School of Computer Science University of Hertfordshire Hatfield, Hertfordshire UK Salary: ?37,394 to ?47,328 per annum depending on skills and experience FTE: Full time position Duration of contract: Permanent Closing date: 10 September 2015 Applications are invited for a post of Senior Lecturer in the School of Computer Science at the University of Hertfordshire. The successful candidate will be expected to contribute to the School's teaching and curriculum development activities, and to strengthen its research activities. We are looking to recruit specifically computer scientists with specialist interests in data science or machine learning related to biocomputation (including computational neuroscience), with the flexibility to teach across mainstream topics in computer science. The School has an international reputation for teaching and research, with 58 academic staff, 20 adjunct lecturer staff, and 65 research students and postdoctoral research staff. With a history going back to 1958, the School teaches one of the largest cohorts of undergraduate students in the UK, and also delivers a thriving online computer science degree programme. The University of Hertfordshire is situated in Hatfield, in the green belt just north of London. The person appointed will be expected to contribute to learning and teaching relevant to core computer science topics, participate in curriculum review and development, design and develop new modules, and supervise student projects at all levels. The appointee will strengthen the research culture in the School by pursuing research as part of a larger research team, seeking external funding, publishing papers, supervising research students, and participating in commercial activity as appropriate. Preference will be given to candidates who can contribute to teaching and research in databases or machine learning. You must hold a PhD (or equivalent) in a relevant subject, possess excellent communication skills in English and the ability to teach at undergraduate and postgraduate level. It is desirable that candidates have a track record of publication, external research funding, collaboration across disciplines, experience of different types of assessment and higher education quality assurance. They should also have the ability to play a role in the routine running of the School of Computer Science. The University is required to meet UKVI visa regulations. Applicants who do not currently have the right to work in the UK will have to satisfy UKVI regulations before they can be appointed. Application should be made through http://www.herts.ac.uk/contact-us/jobs-and-vacancies/academic-vacancies (reference 012476). For informal enquiries contact Prof William Clocksin (Dean of School, w.clocksin at herts.ac.uk) or Dr Volker Steuber (Head of the Biocomputation Research Group, v.steuber at herts.ac.uk). From poirazi at imbb.forth.gr Thu Aug 27 12:24:09 2015 From: poirazi at imbb.forth.gr (Yiota Poirazi) Date: Thu, 27 Aug 2015 19:24:09 +0300 Subject: Connectionists: Postdoctoral position in dendritic modelling, Poirazi lab, Crete Message-ID: Can you please post this job opening in my lab to the list? Thank you! Yiota Poirazi ----------------------------------------- 1-2 Postdoctoral positions funded by the* ERC Starting Grant dEMORY *will be available as of* October 1st 2015* (the start date is flexible) at IMBB-FORTH in Crete, in the lab of Dr. *Panayiota Poirazi*. *Indicative application deadline: September 25th, 2015 (applications will be continuously screened until the positions are filled).* ? Available for 2 years, with a *yearly *salary of 30,000-36,000 ? (with benefits), depending on experience and career stage. ? *Requirements: *Expertise in computational neuroscience, preferably in compartmental modeling and neural/dendritic computations. *THE PROJECT: Dissecting the Role of Dendrites in Memory* While memory is a function that has attracted the interest of the scientific community for several years, little is known about the rules underlying memory formation in the brain. Until recently, the single neuron was considered the main processing unit of the brain and memories were believed to be stored exclusively through plasticity modifications that take place in the synapses, the connecting sites between neurons. Over the last decade however, emerging evidence suggests that the neuron is no longer the key processing unit of the brain. The dendrites of individual neurons, which were thought as merely passive devices that allow neuronal communication, are currently the no 1 candidate for this role. The goal of this work is to characterize the role of dendrites in learning and memory processes so as to formulate a unifying theory regarding their contribution in memory formation across brain regions and abstraction levels. This will be achieved via the development of computational models that start at the single cell level and expand to the microcircuit and the network level, while varying in their degree of biophysical detail. Models will express a distinct memory function, specific to the region they belong to: the hippocampus the prefrontal cortex or the amygdala. By manipulating the biophysical, anatomical and plasticity properties of dendrites and tracking the effect on memory, the project aims to infer the key rules by which these thin structures shape mnemonic processes. These rules will then form the basis for deducing theoretical abstractions of trainable neurons with dendrites. The project has been running since 2012 and has already produced a number of outcomes which can be found at the following web sites: *www.demory.gr* *, * *www.dendrites.gr* *IMBB-FORTH* The Foundation for Research and Technology-Hellas (FORTH) is one of the top European Research Centers. It has ranked 1st in terms of high impact publications in Greece and 12th in the number of FP7 grants in Europe. It should be noted that since the establishment of the ERC grant scheme in 2007, a total of 39 awards have been made to scientists working in Greek Institutions and 11 of them are located in Institutes of FORTH. The Institute of Molecular Biology and Biotechnology (IMBB) at FORTH is the top Biological Institute in Greece, in terms of high quality personnel, publications, infrastructure and competitive grants. IMBB-FORTH is located in Heraklion, one of the most ancient and historical Greek cities, on the picturesque island of Crete. Crete, the homeland of major artists, such as El Greco and Nikos Kazantzakis, impressively combines the outstanding geophysical variety (forests, mountains, gorges, and beaches) with its rich history of thousands of years, resulting in the well-known Cretan culture and cuisine. *THE POIRAZI LAB* The Computational Biology Laboratory at IMBB-FORTH performs research that is at the forefront of Computational Neuroscience. The work of Dr. Poirazi led to several high impact publications, some of which have shaped the field of dendritic computations. Her work received prestigious awards, including the EMBO Young Investigator Award in 2005, 2 Marie Curie Fellowships, a scientist-of-the year award in Greece in 2012, a European Research Council (ERC) starting grant in 2012, a nomination by EMBO to AcademiaNet?portal for outstanding female scientists in Europe (2013), and the "Manolis Christofides" Young Cypriot Investigator award in 2014. She is named Young Scientist of the World Economic Forum for its Annual Meeting of the New Champions in 2014 and 2015. She is a member of the Young Academy of Europe since 2015 and currently the Chair of the FENS-KAVLI Network of Excellence whose aim is to promote Neuroscience research and science policy in Europe and beyond. *TO APPLY:* Candidates that match the required profile will be continuously interviewed until the positions are filled. Candidates should send a *resume and two (2) reference letters* to *poirazi[at]imbb.forth.gr *. If possible, recommendations should be sent by the referees. -- Panayiota Poirazi, Ph.D. Research Director Computational Biology Laboratory Institute of Molecular Biology and Biotechnology (IMBB) Foundation of Research and Technology-Hellas (FORTH) Vassilika Vouton, P.O.Box 1385, GR 70013, Heraklion, Crete GREECE Tel: +30 2810 391139 Fax: +30 2810 391101 ?mail: poirazi at imbb.forth.gr Lab site: www.dendrites.gr Chair, FENS-Kavli Network of Excellence -------------- next part -------------- An HTML attachment was scrubbed... URL: From martin.pyka at gmail.com Fri Aug 28 09:23:34 2015 From: martin.pyka at gmail.com (Martin Pyka) Date: Fri, 28 Aug 2015 15:23:34 +0200 Subject: Connectionists: Dendritic Trees with MST-Dendrite Message-ID: <55E060D6.1090508@gmail.com> Here is a new tool that some of you might find interesting: MST-Dendrites is an addon for Blender to create realistic dendritic trees in 3D and to distribute them on large network morphologies. The algorithm is a Python implementation of this method Cuntz H, Forstner F, Borst A, H?usser M (2010). One rule to grow them all: A general theory of neuronal branching and its practical application. PLoS Comput Biol 6(8): e1000877." This is the Github repository: https://github.com/pherbers/MST-Dendrites.git And here is a video showcasing the tool https://www.youtube.com/watch?v=18Us4noy6z8 Best, Martin From biaswatchneuro at gmail.com Fri Aug 28 21:10:21 2015 From: biaswatchneuro at gmail.com (Bias Watch) Date: Fri, 28 Aug 2015 21:10:21 -0400 Subject: Connectionists: Registration and Abstract submission Brain States Conference In-Reply-To: <0B58716A-E49C-4627-88AC-BEE16D8F90B4@princeton.edu> References: <0B58716A-E49C-4627-88AC-BEE16D8F90B4@princeton.edu> Message-ID: Brain States: Characterization and Neuromodulation by DBS Organizers: Rowshanak Hashemiyoon, Veerle Visser-Vandewalle Invited speaker gender ratio: 0 Females / 22 Males Estimated* base rate of females in the field: 20% BiasWatchNeuro rating: 0 out of 3 *Method of estimation: NIH RePORTER with text keyword ?DBS?, count number of female first PIs in first 25 results for more information: www.biaswatchneuro.com > From: neuro girl > > Subject: Connectionists: Registration and Abstract submission Brain > States Conference > > Date: August 26, 2015 6:16:21 PM EDT > > To: Connectionists List > > > > Dear All, > > > > Registration and abstract submission are now open! > > > > Brain States: Characterization and Neuromodulation by DBS > > November 11-13, 2015 in Cologne, Germany. > > > > Interdisciplinary contributions to the study of brain mechanics have > greatly advanced our theories of the neurodynamic operations employed by > the brain. Although the brain exhibits continuous ongoing activity, > variation in the spatiotemporal patterns of activation observed across > different brain regions during rest versus active processing provides > valuable information about functional connectivity and strategies for > information processing. > > > > This conference will explore the most up-to-date theories of normal > brain function and how these processes may be altered to produce > pathological states. Furthermore, it will explore the models and methods > used to describe the proposed neural strategies subserving these different > brain states. > > > > Our list of confirmed speakers include: > > Hagai Bergman (Hebrew University of Jerusalem) > > Peter Brown (University of Oxford) > > Stephan Chabardes (University Hospital Grenoble) > > Alain Destexhe (CNRS) > > Emad N. Eskandar (Massachusetts General Hospital-Harvard Medical School) > > John J. Foxe (Albert Einstein College of Medicine) > > Marc Goodfellow (University of Exeter) > > Anthony A. Grace (University of Pittsburgh) > > Rowshanak Hashemiyoon (University Hospital of Cologne) > > Jens Haueisen (Technische Universit?t Ilmenau) > > Viktor Jirsa (Aix-Marseille Universit? /CNRS) > > Jens Kuhn (University Hospital Cologne) > > Fernando Lopes da Silva (University of Amsterdam) > > Andres Lozano (University of Toronto) > > Cameron McIntyre (Case Western Reserve University) > > Christoph M. Michel (University of Geneva) > > Bart Nuttin (KU Leuven) > > Urs Ribary (Simon Fraser University) > > G?nter Schiepek (Paracelsus Medical University) > > Wolf Singer (Max Planck Institute for Brain Research) > > Dimitri van de Ville (University of Geneva) > > Veerle Visser-Vandewalle (University Hospital of Cologne) > > J?rgen Voges (Otto-von-Guericke-University Magdeburg) > > We are intentionally limiting attendance in order to ensure a collegial > atmosphere with excellent discussion. > > > > More information can be found on these websites http://bit.ly/1JVElkf > and https://dbs.veomed.net/. > > > > Please find attached the poster with the announcement. Distribution is > welcome and appreciated. > > > > Hope to see you in Cologne! > > > > > > With kind regards, > > Row Hashemiyoon > > > > Rowshanak Hashemiyoon, PhD > > Chief, Behavioral Neurophysiology and Computational Neuroscience > > Klinik f?r Stereotaxie und Funktionelle Neurochirurgie > > Universit?tsklinikum K?ln > > Kerpener Str. 62 > > D - koeln 50937 > > http://www.uk-koeln.de/de/stereotaxie > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From wduch at is.umk.pl Fri Aug 28 12:39:29 2015 From: wduch at is.umk.pl (=?iso-8859-2?Q?W=B3odzis=B3aw_Duch?=) Date: Fri, 28 Aug 2015 18:39:29 +0200 Subject: Connectionists: Paper: Memetics and Neural Models of Conspiracy Theories Message-ID: <00e901d0e1b0$20b28b10$6217a130$@is.umk.pl> Memetics and Neural Models of Conspiracy Theories Conspiracy theories, or in general seriously distorted beliefs, are widespread. How and why are they formed in the brain is still more a matter of speculation rather than science. In this paper one plausible mechanisms is investigated: rapid freezing of high neuroplasticity (RFHN). Emotional arousal increases neuroplasticity and leads to creation of new pathways spreading neural activation. Using the language of neurodynamics a meme is defined as quasi-stable associative memory attractor state. Depending on the temporal characteristics of the incoming information and the plasticity of the network, memory may self-organize creating memes with large attractor basins, linking many unrelated input patterns. Memes with fake rich associations distort relations between memory states. Simulations of various neural network models trained with competitive Hebbian learning (CHL) on stationary and non-stationary data lead to the same conclusion: short learning with high plasticity followed by rapid decrease of plasticity leads to memes with large attraction basins, distorting input pattern representations in associative memory. Such system-level models may be used to understand creation of distorted beliefs and formation of conspiracy memes, understood as strong attractor states of the neurodynamics. http://arxiv.org/abs/1508.04561 Regards, W?odzis?aw Duch ____________________ Google W. Duch -------------- next part -------------- An HTML attachment was scrubbed... URL: From tbesold at uni-osnabrueck.de Sat Aug 29 13:44:22 2015 From: tbesold at uni-osnabrueck.de (Tarek R. Besold) Date: Sat, 29 Aug 2015 19:44:22 +0200 Subject: Connectionists: 1st CfP: Cognitive Computation @ NIPS 2015 - Integrating Neural and Symbolic Approaches Message-ID: **************************************************** * Cognitive Computation: * * Integrating Neural and Symbolic Approaches * * (CoCo @ NIPS 2015) * **************************************************** Workshop at NIPS 2015, Montreal, Canada December 11 & 12, 2015 == WORKSHOP WEBPAGE == http://www.neural-symbolic.org/CoCo2015/ == MISSION STATEMENT == While early work on knowledge representation and inference was primarily symbolic, the corresponding approaches subsequently fell out of favor, and were largely supplanted by connectionist methods. In this workshop, we will work to close the gap between the two paradigms, and aim to formulate a new unified approach that is inspired by our current understanding of human cognitive processing. This is important to help improve our understanding of Neural Information Processing and build better Machine Learning systems, including the reuse of knowledge learned in one application domain in analogous domains. The workshop brings together world leaders in the fields of neural computation, logic and artificial intelligence, natural language understanding, cognitive science, and computational neuroscience. Over the two workshop days, their invited lectures will be complemented with presentations based on contributed papers (following an open call for papers) and a poster session, giving ample opportunity to interact and discuss the different perspectives and emerging approaches. The workshop targets a single broad theme of general interest to the vast majority of the NIPS community, namely the study of translations between neural models and knowledge representation for the purpose of achieving an effective integration of learning and reasoning. Neural-symbolic computing is now an established topic of wider interest to NIPS with topics that are relevant to almost everyone studying neural information processing. == KEYWORDS == The following list gives some (but by far not all) relevant keywords for the CoCo @ NIPS 2015 workshop: - neural-symbolic computing; - language processing; - cognitive agents; - multimodal learning; - deep networks; - symbol manipulation; - variable binding; - integration of learning and reasoning. == INVITED SPEAKERS == - Antoine Bordes, Facebook AI Research. - Rina Dechter, UC Irvine. - Ramanathan V. Guha, Google Inc. - Geoffrey E. Hinton, University of Toronto and Google Inc. - Gary F. Marcus, NYU and Geometric Intelligence. - Stephen H. Muggleton, Imperial College London. - Daniel L. Silver, Acadia University. - Paul Smolensky, Johns Hopkins University. - Josh Tenenbaum, Massachusetts Institute of Technology. - Greg Wayne, Deep Mind, Google Inc. - Michael Witbrock, Cycorp Inc. == CALL FOR PAPERS == The workshop intends to bring together researchers and world leaders in the fields of neural-symbolic integration, neural computation, logic and artificial intelligence, natural language understanding, cognitive science, and computational neuroscience. We intend to create an atmosphere of exchange of ideas, providing a forum for the presentation and discussion of the key topics related to neural-symbolic integration. We expect the workshop to become a source of future collaboration between researchers interested in neural-symbolic integration. After a short introduction by the organizers to neural-symbolic computing in the relevant fields of artificial intelligence, theoretical computer science, cognitive science, neuroinformatics and computational neuroscience, the symposium will proceed with talks by the invited speakers and additional presentations based on submission from the community. Additionally, in order to further increase the opportunities for community participation, poster sessions will be included in the program. Speakers will be encouraged to keep their talks accessible and centered on the main arguments of their perspective on the topic, leaving time for questions and discussion. We invite submission of papers dealing with topics related to the research questions discussed in the workshop. The reported work can range from theoretical/foundational research to reports on applications and/or implemented systems. We explicitly also encourage the submission of more controversial papers which can serve as basis for open discussions during the event. Possible topics of interest include but are (by far!) not limited to: - The representation of symbolic knowledge by connectionist systems; - Neural Learning theory; - Integration of logic and probabilities, e.g., in neural networks, but also more generally; - Structured learning and relational learning in neural networks; - Logical reasoning carried out by neural networks; - Integrated neural-symbolic approaches; - Extraction of symbolic knowledge from trained neural networks; - Integrated neural-symbolic reasoning; - Neural-symbolic cognitive models; - Biologically-inspired neural-symbolic integration; - Applications in robotics, simulation, fraud prevention, natural language processing, semantic web, software engineering, fault diagnosis, bioinformatics, visual intelligence, etc. = Submission instructions = - Submissions have to be made via EasyChair (https://easychair.org/conferences/?conf=coconips2015) before the paper submission deadline indicated below. - Submissions are limited to at most eight pages, an additional ninth page containing only cited references is allowed. Still, also shorter papers are expressly welcomed. - Submissions have to use the NIPS 2015 submission format (see http://nips.cc/Conferences/2015/PaperInformation/StyleFiles). - Reviewing will be single-blind, i.e., you are free to indicate your name etc. on the paper. (Still, this is not an obligation.) Please note that at least one author of each accepted paper must register for the event and be available to present the paper at the workshop. =Publication= Accepted papers will be published in official workshop proceedings (which will be distributed during the workshop) and will be made available from this webpage. Authors of the best papers will be invited to submit a revised and extended version of their papers to a journal special issue after the workshop. == IMPORTANT DATES == - Deadline for paper submission: October 03, 2015 - Notification of paper acceptance: October 17, 2015 - Camera-ready paper due: November 9, 2015 - Workshop date: December 11/12, 2015 - NIPS 2015 main conference: December 7-10, 2015 == ADMISSION == The workshop is open to anybody, please register via NIPS 2015 (http://nips.cc). == WORKSHOP ORGANIZERS == - Tarek R. Besold (Institute of Cognitive Science, University of Osnabrueck, Germany) - Artur d'Avila Garcez (City University London, UK) - Gary F. Marcus (New York University, U.S.A.) - Risto Miikulainen (University of Texas at Austin, U.S.A.) == ADDITIONAL INFORMATION == - General questions concerning the workshop should be addressed to Tarek R. Besold at Tarek(dot)Besold(at)uni(hyphen)osnabrueck(dot)de. - This workshop is conceptually related to the series of International Workshops on Neural-Symbolic Learning and Reasoning (NeSy). If interested, have a look at http://www.neural-symbolic.org - Please also feel free to join the neural-symbolic integration mailing list for announcements and discussions - it's a low traffic mailing list. If interested, register at http://maillists.city.ac.uk/mailman/listinfo/nesy. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tarek R. Besold Institute of Cognitive Science University of Osnabr?ck (Germany) tarek.besold at uni-osnabrueck.de https://sites.google.com/site/tarekbesold/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From biaswatchneuro at gmail.com Sat Aug 29 22:21:23 2015 From: biaswatchneuro at gmail.com (Bias Watch) Date: Sat, 29 Aug 2015 22:21:23 -0400 Subject: Connectionists: 1st CfP: Cognitive Computation @ NIPS 2015 - Integrating Neural and Symbolic Approaches In-Reply-To: References: Message-ID: Cognitive Computation @ NIPS 2015 - Integrating Neural and Symbolic Approaches Organizers: Tarek R. Besold, Artur d'Avila Garcez, Gary F. Marcus, Risto Miikkulainen Invited speaker gender ratio: 1 Female / 10 Males Estimated* base rate of females in the field: 36% BiasWatchNeuro rating: 0 out of 3 *Method of estimation: NIH RePORTER search with text keywords "neural-symbolic integration" or "neural computation" or "logic and artificial intelligence" or "natural language understanding" or "cognitive science" or "computational neuroscience"; count number of female first PIs in first 25 results for more information: www.biaswatchneuro.com On Sat, Aug 29, 2015 at 1:44 PM, Tarek R. Besold wrote: > **************************************************** > * Cognitive Computation: * > * Integrating Neural and Symbolic Approaches * > * (CoCo @ NIPS 2015) * > **************************************************** > > Workshop at NIPS 2015, Montreal, Canada > December 11 & 12, 2015 > > > > == WORKSHOP WEBPAGE == > > http://www.neural-symbolic.org/CoCo2015/ > > > > == MISSION STATEMENT == > > While early work on knowledge representation and inference was primarily > symbolic, the corresponding approaches subsequently fell out of favor, and > were largely supplanted by connectionist methods. In this workshop, we will > work to close the gap between the two paradigms, and aim to formulate a new > unified approach that is inspired by our current understanding of human > cognitive processing. This is important to help improve our understanding > of Neural Information Processing and build better Machine Learning systems, > including the reuse of knowledge learned in one application domain in > analogous domains. > > The workshop brings together world leaders in the fields of neural > computation, logic and artificial intelligence, natural language > understanding, cognitive science, and computational neuroscience. Over the > two workshop days, their invited lectures will be complemented with > presentations based on contributed papers (following an open call for > papers) and a poster session, giving ample opportunity to interact and > discuss the different perspectives and emerging approaches. > > The workshop targets a single broad theme of general interest to the vast > majority of the NIPS community, namely the study of translations between > neural models and knowledge representation for the purpose of achieving an > effective integration of learning and reasoning. Neural-symbolic computing > is now an established topic of wider interest to NIPS with topics that are > relevant to almost everyone studying neural information processing. > > > == KEYWORDS == > > The following list gives some (but by far not all) relevant keywords for > the CoCo @ NIPS 2015 workshop: > - neural-symbolic computing; > - language processing; > - cognitive agents; > - multimodal learning; > - deep networks; > - symbol manipulation; > - variable binding; > - integration of learning and reasoning. > > > > == INVITED SPEAKERS == > > - Antoine Bordes, Facebook AI Research. > - Rina Dechter, UC Irvine. > - Ramanathan V. Guha, Google Inc. > - Geoffrey E. Hinton, University of Toronto and Google Inc. > - Gary F. Marcus, NYU and Geometric Intelligence. > - Stephen H. Muggleton, Imperial College London. > - Daniel L. Silver, Acadia University. > - Paul Smolensky, Johns Hopkins University. > - Josh Tenenbaum, Massachusetts Institute of Technology. > - Greg Wayne, Deep Mind, Google Inc. > - Michael Witbrock, Cycorp Inc. > > > > == CALL FOR PAPERS == > > The workshop intends to bring together researchers and world leaders in > the fields of neural-symbolic integration, neural computation, logic and > artificial intelligence, natural language understanding, cognitive science, > and computational neuroscience. We intend to create an atmosphere of > exchange of ideas, providing a forum for the presentation and discussion of > the key topics related to neural-symbolic integration. We expect the > workshop to become a source of future collaboration between researchers > interested in neural-symbolic integration. > > After a short introduction by the organizers to neural-symbolic computing > in the relevant fields of artificial intelligence, theoretical computer > science, cognitive science, neuroinformatics and computational > neuroscience, the symposium will proceed with talks by the invited speakers > and additional presentations based on submission from the community. > Additionally, in order to further increase the opportunities for community > participation, poster sessions will be included in the program. > > > Speakers will be encouraged to keep their talks accessible and centered on > the main arguments of their perspective on the topic, leaving time for > questions and discussion. > > We invite submission of papers dealing with topics related to the research > questions discussed in the workshop. The reported work can range from > theoretical/foundational research to reports on applications and/or > implemented systems. We explicitly also encourage the submission of more > controversial papers which can serve as basis for open discussions during > the event. > > Possible topics of interest include but are (by far!) not limited to: > - The representation of symbolic knowledge by connectionist systems; > - Neural Learning theory; > - Integration of logic and probabilities, e.g., in neural networks, but > also more generally; > - Structured learning and relational learning in neural networks; > - Logical reasoning carried out by neural networks; > - Integrated neural-symbolic approaches; > - Extraction of symbolic knowledge from trained neural networks; > - Integrated neural-symbolic reasoning; > - Neural-symbolic cognitive models; > - Biologically-inspired neural-symbolic integration; > - Applications in robotics, simulation, fraud prevention, natural language > processing, semantic web, software engineering, fault diagnosis, > bioinformatics, visual intelligence, etc. > > > = Submission instructions = > > - Submissions have to be made via EasyChair ( > https://easychair.org/conferences/?conf=coconips2015) before the paper > submission deadline indicated below. > - Submissions are limited to at most eight pages, an additional ninth page > containing only cited references is allowed. Still, also shorter papers are > expressly welcomed. > - Submissions have to use the NIPS 2015 submission format (see > http://nips.cc/Conferences/2015/PaperInformation/StyleFiles). > - Reviewing will be single-blind, i.e., you are free to indicate your name > etc. on the paper. (Still, this is not an obligation.) > > Please note that at least one author of each accepted paper must register > for the event and be available to present the paper at the workshop. > > > =Publication= > > Accepted papers will be published in official workshop proceedings (which > will be distributed during the workshop) and will be made available from > this webpage. > Authors of the best papers will be invited to submit a revised and > extended version of their papers to a journal special issue after the > workshop. > > > > == IMPORTANT DATES == > > - Deadline for paper submission: October 03, 2015 > - Notification of paper acceptance: October 17, 2015 > - Camera-ready paper due: November 9, 2015 > - Workshop date: December 11/12, 2015 > - NIPS 2015 main conference: December 7-10, 2015 > > > > == ADMISSION == > > The workshop is open to anybody, please register via NIPS 2015 ( > http://nips.cc). > > > > == WORKSHOP ORGANIZERS == > > - Tarek R. Besold (Institute of Cognitive Science, University of > Osnabrueck, Germany) > - Artur d'Avila Garcez (City University London, UK) > - Gary F. Marcus (New York University, U.S.A.) > - Risto Miikulainen (University of Texas at Austin, U.S.A.) > > > > == ADDITIONAL INFORMATION == > > - General questions concerning the workshop should be addressed to Tarek > R. Besold at Tarek(dot)Besold(at)uni(hyphen)osnabrueck(dot)de. > - This workshop is conceptually related to the series of International > Workshops on Neural-Symbolic Learning and Reasoning (NeSy). If interested, > have a look at http://www.neural-symbolic.org > - Please also feel free to join the neural-symbolic integration mailing > list for announcements and discussions - it's a low traffic mailing list. > If interested, register at > http://maillists.city.ac.uk/mailman/listinfo/nesy. > > > > ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ > > Tarek R. Besold > Institute of Cognitive Science > University of Osnabr?ck (Germany) > tarek.besold at uni-osnabrueck.de > https://sites.google.com/site/tarekbesold/ > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From alexei at bicasymposium.com Mon Aug 31 00:49:34 2015 From: alexei at bicasymposium.com (Alexei Samsonovich) Date: Mon, 31 Aug 2015 00:49:34 -0400 Subject: Connectionists: Biologically Inspired Cognitive Architectures - call for papers, abstracts, and talks Message-ID: Greetings! We are soliciting submissions to three upcoming BICA events (abstract-only OK for a talk, all accepted papers will be published in Elsevier journals BICA (acquires a Thomson Reuters JCR Impact Factor, www.elsevier.com/locate/bica) and Procedia Computer Science (www.journals.elsevier.com/procedia-computer-science/), both indexed in Web of Science and Scopus): (1) BICA 2015: Lyon, France, Nov 6-8 (http://liris.cnrs.fr/bica2015/) - still accepting! (2) Fierces on BICA 2016: Moscow, April 22-24 (http://school.bicasociety.org/) - submit a title, abstract, paper or tutorial proposal (3) BICA 2016: New School, Manhattan, New York, July 6-9 (http://bicasociety.org/meetings/2016), email alexei at bicasociety.org to express an interest Cheers, -Alexei P.S. The scope of each event is much broader than biologically inspired cognitive architectures and includes all hot topics in cognitive, computer and neurosciences (please see individual pages). -- Alexei V. Samsonovich Editor-in-Chief, Biologically Inspired Cognitive Architectures Research Assistant Professor, Krasnow Institute for Advanced Study, George Mason University at Fairfax, VA -------------- next part -------------- An HTML attachment was scrubbed... URL: From h.jaeger at jacobs-university.de Mon Aug 31 05:06:46 2015 From: h.jaeger at jacobs-university.de (Herbert Jaeger) Date: Mon, 31 Aug 2015 11:06:46 +0200 Subject: Connectionists: Postdoc/PhD Position in Recurrent Neural Network Architectures In-Reply-To: <4E397C49.8090907@jacobs-university.de> References: <4E397C49.8090907@jacobs-university.de> Message-ID: <55E41926.2020302@jacobs-university.de> The department of Computer Science at Jacobs University Bremen (http://www.jacobs-university.de) announces a POSTDOC / PHD RESEARCH POSITION IN MACHINE LEARNING / NEURAL NETWORKS / INTELLIGENT AGENT ARCHITECTURES (full-time, very competitive salary, 3 years, start December 1, 2015 or later) the MINDS research group of Herbert Jaeger (http://minds.jacobs-university.de). The position is created in the European Horizon 2020 integrated project "Neural Computing Architectures in Advanced Monolithic 3D-VLSI Nano-Technologies" (NeuRAM3). The project aim of NeuRAM3 is to design and fabricate a large-scale, highly configurable neuromorphic microchip. Based on spiking, recurrent neural dynamics, the microchip is similar in some ways to IBM's recent TrueNorth neurochip (http://www.research.ibm.com/articles/brain-chip.shtml). However, our project aims significantly further than TrueNorth, and IBM is one of the consortium partners. In particular, novel 3-dimensional chip manufacturing technologies will enable a much more complex and much more flexibly configurable on-chip neural architecture. Within this setting, the MINDS group develops *neural learning algorithms and architectures* which are tailored to the novel opportunities afforded by a 3-dimensional, spiking microchip. This line of research will be carried out in close collaboration with a consortium partner from computational neuroscience (Institute of Neuroinformatics, University Zurich and ETH Zurich). Currently in machine learning approaches of deep learning are attracting much attention. In several ways the research in the MINDS group is *complementary to deep learning*. The latter is grounded in high-precision gradient descent methods for training and can devour extremely large training datasets to learn extremely complex tasks. The price paid is very long training times and a lack of online adaptability. In contrast, *we aim for very fast (even instantaneous) learning, online adaptability and extensibility, robustness against noise and computations with low numerical accuracy*. Such properties will be crucial for the algorithms running on next-generation chipsets for mobile devices ? and they are also crucial for biological neural systems. The background philosophy of this research is framed by reservoir computing (http://minds.jacobs-university.de/ESNresearch) and conceptors (http://minds.jacobs-university.de/conceptors). Eligible candidates must have a mindset inclined toward mathematical modeling, fluency in English, plus a solid background in at least one of the following areas: ? dynamical systems theory, ? signal processing and control, ? machine learning, ? computational neuroscience, ? intelligent agent architectures. Details about the position and the NeuRAM3 project will be gladly supplied by Herbert Jaeger (h.jaeger at jacobs-university.de) upon request. Please submit applications by email to Herbert Jaeger. Applicants passing an initial screening will be asked to supply two letters of reference. Applications will be processed as long as the job announmcent is posted online at http://minds.jacobs-university.de/jobs. *Jacobs University Bremen* is Germany's only private university with a full range of academic programs from the natural and social sciences and engineering. Its student body is one of the most international conceivable: more than 100 nations are joined on our beautiful campus. Within its young history of only a little more than 10 years, Jacobs University has climbed to the top in many disciplines in Germany's most important university ranking (http://www.che-ranking.de/cms/?getObject=613&getLang=en). The language on campus is English. ------------------------------------------------------------------ Dr. Herbert Jaeger Professor of Computational Science Jacobs University Bremen gGmbH Campus Ring 28759 Bremen, Germany Phone (+49) 421 200 3215 Fax (+49) 421 200 49 3215 email h.jaeger at jacobs-university.de http://minds.jacobs-university.de ------------------------------------------------------------------ From dwang at cse.ohio-state.edu Sun Aug 30 12:02:31 2015 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Sun, 30 Aug 2015 12:02:31 -0400 Subject: Connectionists: NEURAL NETWORKS, Sept. 2015 Message-ID: <55E32917.1040300@cse.ohio-state.edu> Neural Networks - Volume 69, Sept. 2015 http://www.journals.elsevier.com/neural-networks Many regression algorithms, one unified model: A review Freek Stulp, Olivier Sigaud Asymptotic accuracy of Bayesian estimation for a single latent variable Keisuke Yamazaki Improving nonlinear modeling capabilities of functional link adaptive filters Danilo Comminiello, Michele Scarpiniti, Simone Scardapane, Raffaele Parisi, Aurelio Uncini L1-norm locally linear representation regularization multi-source adaptation learning Jianwen Tao, Shiting Wen, Wenjun Hu A new robust model of one-class classification by interval-valued training data using the triangular kernel Lev V. Utkin, Anatoly I. Chekh Locality preserving score for joint feature weights learning Hui Yan, Jian Yang Accuracy of latent-variable estimation in Bayesian semi-supervised learning Keisuke Yamazaki Finite-time synchronization for memristor-based neural networks with time-varying delays Abdujelil Abdurahman, Haijun Jiang, Zhidong Teng Convergence analysis of an augmented algorithm for fully complex-valued neural networks Dongpo Xu, Huisheng Zhang, Danilo P. Mandic Finite-time boundedness and stabilization of uncertain switched neural networks with time-varying delay Yuanyuan Wu, Jinde Cao, Abdulaziz Alofi, Abdullah AL-Mazrooei, Ahmed Elaiw Real-time human action classification using a dynamic neural model Zhibin Yu, Minho Lee Optimized face recognition algorithm using radial basis function neural networks and its practical applications Sung-Hoon Yoo, Sung-Kwun Oh, Witold Pedrycz From gquon at UCDAVIS.EDU Mon Aug 31 02:07:29 2015 From: gquon at UCDAVIS.EDU (Gerald Quon) Date: Mon, 31 Aug 2015 06:07:29 +0000 Subject: Connectionists: NIPS 2015 workshop on Machine Learning in Computational Biology Message-ID: NIPS 2015 workshop on Machine Learning in Computational Biology ---------- Call for contributions Workshop on Machine Learning in Computational Biology http://www.mlcb.org A workshop at the Twenty-Ninth Annual Conference on Neural Information Processing Systems (NIPS 2015) Montreal, QC, Canada, December 12, 2015. Important dates: Oct 4, 2015 : Deadline for submission of extended abstracts Oct 22, 2015: Acceptance notification Dec 12, 2015: Workshop date WORKSHOP DESCRIPTION The field of computational biology has seen dramatic growth over the past few years. A wide range of high-throughput technologies developed in the last decade now enable us to measure parts of a biological system at various resolutions?at the genome, epigenome, transcriptome, and proteome levels. These technologies are now being used to collect data for an ever-increasingly diverse set of problems, ranging from classical problems such as predicting differentially regulated genes between time points and predicting subcellular localization of RNA and proteins, to models that explore complex mechanistic hypotheses bridging the gap between genetics and disease, population genetics and transcriptional regulation. Fully realizing the scientific and clinical potential of these data requires developing novel supervised and unsupervised learning methods that are scalable, can accommodate heterogeneity, are robust to systematic noise and confounding factors, and provide mechanistic insights. The goals of this workshop are to i) present emerging problems and innovative machine learning techniques in computational biology, and ii) generate discussion on how to best model the intricacies of biological data and synthesize and interpret results in light of the current work in the field. We will invite several rising leaders from the biology/bioinformatics community who will present current research problems in computational biology and lead these discussions based on their own research and experiences. We will also have the usual rigorous screening of contributed talks on novel learning approaches 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 established alternatives. Kernel methods, graphical models, feature selection, non-parametric models and other techniques applied to relevant bioinformatics problems would all be appropriate for the workshop. We are particularly keen on considering contributions related to the prediction of functions from genotypes and that target data generated from novel technologies such as gene editing and single cell genomics, though we will consider all submissions that highlight applications of machine learning into computational biology. The targeted audience are people with interest in learning and applications to relevant problems from the life sciences, including NIPS participants without any existing research link to computational biology. SUBMISSION INSTRUCTIONS Researchers interested in contributing should upload an extended abstract of 4 pages in PDF format to the MLCB submission web site https://easychair.org/conferences/?conf=mlcb2015 by Oct 4, 2015, 11:59pm (time zone of your choice). 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). *Submissions should be suitably anonymized and meet the requirements for double-blind reviewing.* 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/. 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. Send any questions to mlcb2015 at easychair.org. INVITED SPEAKERS Dana Pe?er (Associate Professor of Biology and Systems Biology, Columbia University) Matthew Stephens (Professor of Statistics and Human Genetics, University of Chicago) ORGANIZERS Nicolo Fusi (Microsoft Research) Anna Goldenberg (University of Toronto) Sara Mostafavi (UBC) Gerald Quon (UC Davis) Oliver Stegle (EMBL-EBI) -------------- next part -------------- An HTML attachment was scrubbed... URL: From simone.seeger at zi-mannheim.de Mon Aug 31 05:04:07 2015 From: simone.seeger at zi-mannheim.de (Seeger, Simone) Date: Mon, 31 Aug 2015 09:04:07 +0000 Subject: Connectionists: Bernstein Conference 2015: Late registration ends on Friday! Message-ID: <68B5BBF569FEF84891D3AAB4D3141E45A7DA3676@ZIMAIL1.Zi.local> BERNSTEIN CONFERENCE 2015 in Heidelberg Late registration ends on Friday, September 4, 2015! Please register here. *************************************************************************** Satellite Workshops September 14, 2015 Main Conference September 15-17, 2015 *************************************************************************** The Bernstein Conference has become the largest annual Computational Neuroscience Conference in Europe and now regularly attracts more than 500 international participants. This year, the Conference is organized by the Bernstein Center Heidelberg-Mannheim and will take place in Heidelberg on September 15-17, 2015. In addition, there will be a series of pre-conference satellite workshops on September 14, 2015. The Bernstein Conference is a single-track conference, covering all aspects of Computational Neuroscience and Neurotechnology, and sessions for poster presentations are an integral part of the conference. The Bernstein conference will also feature a series of satellite workshops on September 14, 2015. The goal is to provide an informal forum for the discussion of timely research questions and challenges. For more information on the conference, please visit: http://www.bernstein-conference.de CONFERENCE DATE AND VENUE: Satellite Workshops September 14, 2015 Main Conference September 15-17, 2015 Venue: Neue Universit?t, Grabengasse 3-5, 69117 Heidelberg, Germany PHD STUDENT EVENT: September 17-18, 2015 ORGANIZING COMMITTEE: Peter Bastian Andreas Draguhn Daniel Durstewitz Martin Gerchen Joachim Hass Elke Jochum Peter Kirsch Andreas Meyer-Lindenberg Christoph Schuster Simone Seeger We look forward to seeing you in Heidelberg in September! *** Simone Seeger, M.A. Administration Bernstein Center for Computational Neuroscience Zentralinstitut f?r Seelische Gesundheit Postfach 12 21 20, 68072 Mannheim J5, 68159 Mannheim Telefon: 0621/1703-1326 oder 06221/54-8310 Fax: 0621/1703-2915 E-Mail: Simone.Seeger at zi-mannheim.de Internet: http://www.bccn-heidelberg-mannheim.de -------------- next part -------------- An HTML attachment was scrubbed... URL: From andreas.wichert at tecnico.ulisboa.pt Mon Aug 31 08:08:36 2015 From: andreas.wichert at tecnico.ulisboa.pt (Andrzej Wichert) Date: Mon, 31 Aug 2015 13:08:36 +0100 Subject: Connectionists: New Book Message-ID: <82D74B6F-656D-4B91-8EE6-501838EE04FF@tecnico.ulisboa.pt> Dear All, I recently published a book, it deals with DFT, Wavelet transform, feature extraction, (SIFT), fractals, high dimensional indexing, neural networks, deep learning, so maybe it is of some interest to you. It is called "Intelligent Big Multimedia Databases? and was published by World Scientific, http://www.worldscientific.com/worldscibooks/10.1142/9665 Best Wishes, Andreas Wichert --------------------------------------------------------------------------------------------------- Prof. Auxiliar Andreas Wichert http://web.tecnico.ulisboa.pt/~andreas.wichert/ Instituto Superior T?cnico - Universidade de Lisboa Campus IST-Taguspark Avenida Professor Cavaco Silva Phone: +351 214233231 2780-990 Porto Salvo, Portugal -------------- next part -------------- An HTML attachment was scrubbed... URL: From aaron.clauset at colorado.edu Mon Aug 31 22:43:19 2015 From: aaron.clauset at colorado.edu (Aaron Clauset) Date: Tue, 1 Sep 2015 02:43:19 +0000 Subject: Connectionists: CFP: NIPS Workshop on Networks in the Social and Information Sciences Message-ID: <0B243DE4-1DF8-4ACE-B627-334FC7C77F95@colorado.edu> ############################################################# CALL FOR PAPERS NIPS workshop on Networks in the Social and Information Sciences 12 December 2015, Montreal, Canada http://tinyurl.com/NetworksNIPS2015 Submission Deadline : Monday, 2 November 2015 ############################################################# Description ---------------------- This workshop aims to bring together a diverse and cross-disciplinary set of researchers to discuss recent advances and future directions for developing new network methods in statistics and machine learning. In particular, we are interested in ? network methods that learn the patterns of interaction, flow of information, or propagation of effects in social and information systems, ? empirical studies, particularly attempts to bridge observational methods and causal inference, and studies that combine learning, networks, and computational social science, ? research that unifies the study of both structure and content in rich network datasets. While this research field is broad and diverse, there are emerging signs of convergence. For example, in the study of information diffusion, social media and social network researchers are beginning to use rigorous tools to distinguish effects driven by social influence, homophily, or external processes -- subjects historically of intense interest amongst statisticians and social scientists. Similarly, there is a growing statistics literature developing learning approaches to study topics popularized earlier within the physics community, including clustering in graphs, network evolution, and random-graph models. Finally, learning methods are increasingly used in highly complex application domains, such as large-scale knowledge graph construction and use, and massive social networks like Facebook and LinkedIn. These applications are stimulating new scientific and practical questions that often cut across disciplinary boundaries. Invited speakers (confirmed) ---------------------- Deepak Awargal (LinkedIn) Emily Fox (Washington U) Jon Kleinberg (Cornell U) Hanna Wallach (Microsoft Research) Format and Submissions ---------------------- This is a 1-day workshop. The program will feature 4 invited talks, poster spotlights and a poster session, and a panel discussion. We welcome the following types of papers: ? Research papers that introduce new models or apply established models to novel domains, ? Research papers that explore theoretical and computational issues, or ? Position papers that discuss shortcomings and desiderata of current approaches, or propose new directions for future research. Submissions will be lightly peer-reviewed. We encourage authors to emphasize the role of learning and its relevance to the application domains at hand. In addition, we hope to identify current successes in the area, and will therefore consider papers that apply previously proposed models to novel domains and data sets. Submissions should be 4?-?8 pages long, non-anonymized, and otherwise adhere to NIPS format. *** Submission Deadline : Monday, November 2, 2015 *** Decision Notification : Thursday, November 5, 2015 Submissions will be accepted via : https://easychair.org/conferences/?conf=nipsnetworks2015 ISBA Travel Awards ---------------------- The workshop is endorsed by the International Society for Bayesian Analysis (ISBA). The organizers have been invited to nominate graduate students or junior researchers (up to five years after graduation) who will be presenting at the workshop for ISBA Travel Awards. Two such awards will be granted (across all NIPS workshops endorsed by the ISBA), offering up to 700 USD in support. To be considered for an ISBA Travel Award, submissions must be submitted early, by ** October 12, 2015. ** Organizers ---------------------- Edo Airoldi, Harvard University David Choi, Carnegie Mellon University Aaron Clauset, University of Colorado, Boulder Panos Toulis, Harvard University Johan Ugander, Microsoft Research From gershman at fas.harvard.edu Mon Aug 31 21:34:03 2015 From: gershman at fas.harvard.edu (Sam Gershman) Date: Mon, 31 Aug 2015 21:34:03 -0400 Subject: Connectionists: Call for abstracts: Bounded optimality and rational metareasoning workshop @ NIPS Message-ID: We are pleased to announce a NIPS workshop on bounded optimality and rational metareasoning, which will take place in Montreal, Canada, December 11, 2015. This workshop brings together computer scientists working on bounded optimality and metareasoning with psychologists and neuroscientists reverse-engineering the computational principles that make the human brain incredibly resource-efficient. The goal of this workshop is to synthesize these different perspectives on bounded optimality, to promote interdisciplinary interactions and cross-fertilization, and to identify directions for future research. We invite abstract submissions, due October 28: https://sites.google.com/site/boundedoptimalityworkshop/call-for-abstracts Tentative schedule: https://sites.google.com/site/boundedoptimalityworkshop/home Sam Gershman Department of Psychology and Center for Brain Science Harvard University http://gershmanlab.webfactional.com/index.html -------------- next part -------------- An HTML attachment was scrubbed... URL: