From osporns at indiana.edu Sun Sep 1 11:03:01 2013 From: osporns at indiana.edu (Olaf Sporns) Date: Sun, 01 Sep 2013 11:03:01 -0400 Subject: Connectionists: Computational Neuroscience Faculty Position Message-ID: <52235725.2060200@indiana.edu> COMPUTATIONAL NEUROSCIENCE FACULTY POSITION, INDIANA UNIVERSITY: The Department of Psychological and Brain Sciences at Indiana University ? Bloomington seeks to fill a faculty position at the level of Assistant Professor (tenure-track) to begin August 2014. Applicants for this position must have a doctorate, a strong record of publication, and the potential for research funding. The applicant's research should focus on theoretical and computational approaches to understand neurobiological processes at any one or several levels of organization, ranging from individual neurons to circuits to systems interactions. Problem areas include models of complex brain networks, neural coding, learning and plasticity, development, dynamic brain activity, or relations between brain and behavior. Candidates with an integrated research program combining computational modeling and empirical neuroscience research are strongly encouraged to apply. The department is highly integrative, and we would be especially interested in researchers whose interests complement existing strengths in cognitive neuroscience, social neuroscience, cellular and systems neuroscience, cognitive science, network science, developmental psychology, and clinical psychology. Teaching responsibilities will include courses at the graduate and undergraduate levels. Interested candidates should review the application requirements and submit their applications at: http://indiana.peopleadmin.com/postings/350. Questions regarding the position or application process can be directed to: Dr. William P. Hetrick, Ph.D., Professor and Chair, Department of Psychology and Brain Sciences, psychair at indiana.edu with ?Computational Neuroscience Search? in the subject line. Review of all applications will begin on November 1, 2013 and will continue until the position is filled. Indiana University is an Affirmative Action/Equal Opportunity employer. The Department is committed to increasing faculty diversity and welcomes applications from women and underrepresented ethnic, racial, and cultural groups, sexual minorities, and from people with disabilities. Information about the department and the university is available at http://psych.indiana.edu/opportunities.php -- Olaf Sporns, PhD Department of Psychological and Brain Sciences Programs in Neuroscience and Cognitive Science Indiana University Bloomington, IN 47405 From matthew.blaschko at tuebingen.mpg.de Sun Sep 1 08:09:37 2013 From: matthew.blaschko at tuebingen.mpg.de (Matthew Blaschko) Date: Sun, 01 Sep 2013 14:09:37 +0200 Subject: Connectionists: Fully funded PhD position - Paris Message-ID: Fully funded PhD position in Machine Learning (Structured prediction) for fMRI analysis in our team Institute: INRIA and Ecole Centrale Paris. Founding member of the University of Paris Saclay. Collaboration with Neurospin http://www-centre-saclay.cea.fr/fr/NeuroSpin Location: Chatenay-Malabry, Paris region (25 minutes to city center by public transport) Eligibility Criteria: Masters + very good maths background + awesome programming skills and at least one good publication. if interested or any query: email matthew.blaschko at inria.fr with a CV and statement of purpose Matthew Blaschko http://pages.saclay.inria.fr/matthew.blaschko/ From passerini at disi.unitn.it Mon Sep 2 04:00:33 2013 From: passerini at disi.unitn.it (andrea passerini) Date: Mon, 2 Sep 2013 10:00:33 +0200 Subject: Connectionists: CALL FOR PAPERS NIPS 2013 Workshop on Constructive Machine Learning Message-ID: <11472AA1-FCBE-46E2-9C70-8B21B66C8EB3@disi.unitn.it> Dear Colleagues, it is our pleasure to invite submissions to the *NIPS 2013 Workshop on Constructive Machine Learning* 9 or 10 December 2013 (to be determined) Lake Tahoe, Nevada, USA http://www.kdml-bonn.de/cml/ cml.nips2013 at gmail.com Detailed information is below. Do not hesitate to contact us for further information. Best Regards, Andrea Passerini, Roman Garnett, and Thomas G?rtner --- *Overview* In many real-world applications, machine learning algorithms are employed as a tool in a "constructive process". These processes are similar to the general knowledge-discovery process but have a more specific goal: the construction of one-or-more domain elements with particular properties. The most common use of machine learning algorithms in this context is to predict the properties of candidate domain elements. In this workshop we want to bring together domain experts employing machine learning tools in constructive processes and machine learners investigating novel approaches or theories concerning constructive processes as a whole. The concerned machine learning approaches are typically interactive (e.g., online- or active-learning algorithms) and have to deal with huge, relational in- and/or output spaces. Many of the applications of constructive machine learning are primarily considered in their respective application domain research area but are hardly present at machine learning conferences. By bringing together domain experts and machine learners working on constructive ML, we hope to bridge this gap between the communities. --- *Contributions* We welcome contributions on both theory and applications related to constructive machine-learning problems. We also welcome submissions containing previously published content in fields related to machine learning, especially descriptions of real-world problems and applications. Topics of interest (though not exhaustive) include: Theory: * Active approaches for structured output learning * Transfer and multi-task learning of generative models * Active search and online optimization in relational domains * Learning with constraints * Integrating learning and search Applications: * De novo drug design * Generation of art (e.g., music composition) * Synthetic biology * Construction of game levels * Generation of novel food recipes * Creation of music playlists, travel itineraries, etc. We welcome work-in-progress contributions, position papers, as well as papers discussing potential research directions. Submission of previously published work or work under review is allowed. However, preference will be given to novel work or work that was not yet presented elsewhere. All double submissions must be clearly declared as such! Submissions will be reviewed on the basis of relevance, significance, technical quality, and clarity. All accepted papers will be presented as posters and among them a few will be selected for the oral presentation. Submissions should be in the NIPS 2013 format, with a maximum of 4 pages (excluding references). Accepted papers will be made available online at the workshop website, but the workshop proceedings can be considered non-archival. Submissions need not be anonymous. All papers should be submitted as pdf via email to cml.nips2013 at gmail.com. --- *Important dates* Submission deadline (tentative): October 9th, 2013 Acceptance decisions (tentative): October 23th, 2013 --- *Invited speakers* Ross King (University of Manchester, confirmed) Bob Keller (Harvey Mudd College, confirmed) Doug Turnbull (Ithaca College, confirmed) Josh Tenenbaum (MIT, tentative) --- *Organizers* Andrea Passerini (University of Trento) Roman Garnett (University of Bonn) Thomas G?rtner (University of Bonn and Fraunhofer IAIS) ------------------------------------------------------ Andrea Passerini Dipartimento di Ingegneria e Scienza dell'Informazione Universita' degli Studi di Trento Via Sommarive 5 38100, Povo di Trento - Italy http://www.disi.unitn.it/~passerini Phone: +39 0461 28 5224 Fax: +39 0461 88 3935 email: passerini at disi.unitn.it ----------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From marc-oliver.gewaltig at epfl.ch Mon Sep 2 07:50:36 2013 From: marc-oliver.gewaltig at epfl.ch (Gewaltig Marc-Oliver) Date: Mon, 2 Sep 2013 11:50:36 +0000 Subject: Connectionists: Full time position: Software Architect Neurorobotics at EPFL Message-ID: Dear colleagues, The EU FET Flagship Human Brain Project seeks a talented Software Architect/Engineer (C++) to strengthen its Neurorobotics team. Please find the details at: http://emploi.epfl.ch/page-96228-en.html Description Specific responsibilities include : * Develop design and specification for a distributed, performance optimized C++ middleware to connect various neural simulators with physics based robotics and environment simulations and visualizations * Refactor large C++ parallel tools and libraries targeting multiple platforms. * Direct collaboration with BBP scientific and software development teams as well as external collaborators Essential skills and experience required : * Expert knowledge in modern C++ software design/implementation * Extensive experience using UNIX/Linux operating systems * Experience in software development targeting multiple operating systems and architectures. * Very good familiarity in software development life-cycle, such as versioning (git), debugging, workflows, testing, QA * Demonstrable expertise in distributed and/or parallel computing - MPI especially * Good team player and fluent English in speech and writing * Willingness to travel Preferred : * Experience with real-time systems/robotics/simulation environments * Game engine development experience * Experience in Python, the scientific software stack (numpy, scipy, ?), and wrapping technologies (Boost.Python, Cython) Profile : * Bachelors or Masters degree in computer science, physics or equivalent * Successful development track record making significant contributions to software projects * Experience with software design and maintenance of medium-scale projects What we offer : * An internationally visible and rising project in simulation-based research in neuroscience using supercomputers and neuromorphic hardware * A young, dynamic, inter-disciplinary, and international working environment Start date : 01.10.2013. Deadline for application: position open until filled Duration of contract : 1 year, renewable Activity rate : 100% Applicants should submit a cover letter and a detailed CV in PDF format only, with file name ?Surname_positon applied_Cover letter? and ?Surname_positon applied_CV? electronically tojobs.bbp at epfl.ch. Please use the position title in the ?subject? field. SV-lp 10.07.13 http://emploi.epfl.ch/page-96228-en.html best wishes Marc-Oliver Gewaltig ---- EPFL- BLUE BRAIN PROJECT Quartier de l?innovation B?timent J ? 3?me ?tage CH-1015 Lausanne - Switzerland Tel: +41 21 693 1866 http://people.epfl.ch/marc-oliver.gewaltig http://www.nest-initiative.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From maggini at dii.unisi.it Mon Sep 2 06:25:02 2013 From: maggini at dii.unisi.it (maggini at dii.unisi.it) Date: Mon, 2 Sep 2013 12:25:02 +0200 Subject: Connectionists: Open PhD Position at the University of Siena on Artificial Vision Message-ID: <1902d32f69a34fb71da256512fb4211d.squirrel@www.dii.unisi.it> (Apologies for cross-posting) Open PhD Position at the University of Siena Research topics: a three year PhD position on computer vision is open at the Department of Information Engineering and Mathematics, University of Siena, Italy. The position is related to the project "Learning to See like Children", that aims at constructing a web service based on intelligent agents to emulate human-like vision skills. The research will focus on never-end machine learning processes based on continuous streams. Like for children, in addition to such a natural visual interaction, the agents are expected to interact with humans so as to receive supervision of objects and actions, and to acquire background knowledge on the visual environment. Please, don't hesitate to contact us for additional details on the project. We can open you the access to a site where you can find plenty of information on the project. Qualifications: Master's degree at the time of the formalization of the contract in one of the following (or related) disciplines: computer science, computer or information engineering, mathematics, physics. Knowledge in the fields of artificial intelligence, machine learning and computer vision are appreciated, but do not represent the main qualification. We are mostly looking for truly open-minded students willing to join a project which departs clearly from the current computer vision research guidelines and frontiers. Working environment: We are an interdisciplinary team of researchers with backgrounds in artificial intelligence, machine learning, and computer vision. The research will be carried in a pleasant working atmosphere at the AI-lab of the University of Siena in close connection with the TEV (TEchnologies of Vision) http://tev.fbk.eu/ of Fondazione Bruno Kessler (Trento, Italy). We offer: The student will receive a fellowship during the three years of the PhD program. Details for the formal application: http://www.unisi.it/sites/default/files/allegatiparagrafo/Ingegneria_avviso_ING.pdf Deadline: September 20th, 2013. Contact: Prof. Marco Gori marco at dii.unisi.it Prof. Marco Maggini maggini at dii.unisi.it From doya at oist.jp Tue Sep 3 09:25:54 2013 From: doya at oist.jp (Kenji Doya) Date: Tue, 3 Sep 2013 13:25:54 +0000 Subject: Connectionists: International Symposium on Prediction and Decision Making, Kyoto Message-ID: We are pleased to announce a symposium in beautiful Kyoto in Autumn: ************************************************ International Symposium on Prediction and Decision Making Date: October 13th - 14th (Sun-Mon), 2013 Venue: Shiran Kaikan, Kyoto University Speakers: Kenji Doya (Okinawa Institute of Science and Technology) Fumino Fujiyama (Doshisha University) Takatoshi Hikida (Kyoto University) Masaki Isoda(Kansai Medical University) Adam Kepecs (Cold Spring Harbor Laboratory) Yutaka Komura (AIST) Daeyeol Lee (Yale University) Hitoshi Okamoto (Riken Brain Science Institute) Hiroyuki Nakahara (Riken Brain Science Institute) Paul Philips (University of Washington) Masamichi Sakagami (Tamagwa University) Geoffrey Schoenbaum (NIDA) Daphna Shohamy (Columbia University) Karl Sigmund (University of Vienna) Hidehiko Takahashi (Kyoto University) Poster Abstract Deadline: SEPTEMBER 10th Registration Deadline: SEPTEMBER 20th Please register (free) from the web page: http://www.decisions.jp/english/symposium/application.html Sponsor: MEXT Scientific Research on Innovative Areas "Prediction and Decision Making" http://www.decisions.jp/english/ ---- Kenji Doya Neural Computation Unit, Okinawa Institute of Science and Technology 1919-1 Tancha, Onna, Okinawa 904-0495, Japan Phone: +81-98-966-8594; Fax: +81-98-966-2891 https://groups.oist.jp/ncu From mjose.escobar at gmail.com Tue Sep 3 14:44:26 2013 From: mjose.escobar at gmail.com (Maria Jose Escobar) Date: Tue, 3 Sep 2013 14:44:26 -0400 Subject: Connectionists: REMINDER: LACONEU2014 Call for Applications Message-ID: ----------------------------------------------------------------------- We have the pleasure to invite Graduate and Undergraduate students to participate in: ----------------------------------------------------------------------- LACONEU 2014 III Latin American Summer School in Computational Neuroscience and Biomedical Analysis Special Topic: Computational Neuroscience / Network Neurodynamics / Basal Ganglia and Motivated Learning January 13th-31st, 2014 Valpara?so - CHILE http://www.laconeu.cl ----------------------------------------------------------------------- The principal aims of LACONEU 2014 Summer School are to disseminate and to develop Computational Neuroscience in Latin America, gathering researchers and students with common interests in the beautiful and historical city of Valparaiso, in Chile. LACONEU 2014 expects to foster a collaborative exchange between the attendees, researchers and students, based on fundamental theoretical and practical knowledge, and thus, to help the establishment of strong, long-term collaborations. The proficiencies and expertise of the Faculty participants represent an unique opportunity for this research area in Latin America. For this version of LACONEU 2014 we propose a Summer School of three entire weeks combining lectures and student projects. Each week is focused on a different topic: Week1: Computational Neuroscience Week2: Network Neurodynamics Week3: Basal Ganglia and Motivated Learning. CONFIRMED SPEAKERS - Pascal Mamassian (Universit? Paris Descartes, France) - Fred Wolf (Max Planck Institute, Germany) - Olivier Marre (Institute de la Vision, France) - Romain Brette (Institute Universitaire de France, France) - Tom?s P?rez-Arcle (Computational Biology Lab, Chile) - Helmuth Grubmueller (Max Planck Institute, Germany) - Jason Kerr (Max Planck Institute, Germany) - Moritz Helmstaedter (Max Planck Institute, Germany) - David Hansel (Interdisciplinary Center of Neural Computation, Israel) - Robert Gutig (Max Planck Institute, Germany) - Bruno Cessac (INRIA, France) - Francoise Dellu-Hagedorn (Universit? de Bordeaux, France) - Arthur Leblois (Institute National de Sciences Biologiques, France) - Nicolas Rougier (INRIA & Institute of Neurodegenerative Diseases, France) - Andr? Garenne (Institute of Neurodegenerative Diseases, France) - Thomas Boraud (Universit? de Bordeaux, France) - Adrian Palacios (CINV, Chile) - Maria-Jose Escobar (UTFSM, Chile) - Patricio Orio (CINV, Chile) - Fr?deric Alexandre (INRIA & Institute of Neurodegenerative Diseases, France) - Thierry Vi?ville (INRIA, France) IMPORTANT DATES - Call for Applications: July 19th, 2013 - Application submission deadline: September 19th, 2013 (visit the webpage to see the details) - Acceptance notification: September 30th, 2013 TRAVEL GRANTS ARE AVAILABLE FOR LATIN AMERICAN STUDENTS Looking forward to see you in January! -------------- next part -------------- An HTML attachment was scrubbed... URL: From samuel.kaski at aalto.fi Tue Sep 3 16:04:22 2013 From: samuel.kaski at aalto.fi (Kaski Samuel) Date: Tue, 3 Sep 2013 20:04:22 +0000 Subject: Connectionists: Postdoctoral positions in Computer Science in Helsinki, Finland Message-ID: <9874A714-1844-4890-8496-5FB64DAEEE02@aalto.fi> [Includes neuroinformatics / machine learning for neuroscience. -Sami] POSTDOCTORAL POSITIONS IN COMPUTER SCIENCE IN HELSINKI, FINLAND Application deadline Sept 30, 2013, 3:00 p.m. EEST Topics include: Algorithms, Bioinformatics, Human-Computer Interaction, Information retrieval, Logic, Machine Learning, Networks, Statistical Data Analysis, etc. http://www.hiit.fi/postdoc-call-2013 Jobs are available at: Helsinki Institute for Information Technology HIIT, Aalto Univ and Univ Helsinki; Dept Computer Science, Univ Helsinki; Dept Information and Computer Science, Aalto Univ; Dept Computer Science and Engineering, Aalto Univ; Dept Mathematics and Statistics, Univ Helsinki. Why Helsinki? The collaborating Aalto University and University of Helsinki form a leading hub of computer science and modelling. Helsinki region is a safe, pleasant and attractive place to live in, with well-functioning services such as public transport etc. Finland has a comprehensive social security and health care system, including exceptionally good parental leaves, and children's day care services. Positions are offered in: Algorithm engineering (String Algorithms group) Algorithmic bioinformatics (Genome-Scale Algorithmics group) Automated reasoning and search, especially propositional logic (Computational Logic group) Computational astrophysics and/or data analysis (Computational Methods and Data Analysis for Astrophysics group) Computational biology and statistical methods in bioinformatics (Computational Systems Biology group) Computational creativity and data mining (Discovery group) Dynamic and large-scale networked systems (Data Communications Software group) Intelligent multimodal information access (Content-Based Image and Information Retrieval Group) Machine learning and neuroscience (Statistical Machine Learning group) Machine learning for structured data (Kernel Machines, Pattern Analysis and Computational Biology group) Machine learning methods for infectious disease epidemiology (Bayesian Statistics Group) Probabilistic modeling and machine learning (Complex Systems Computation group) Statistical machine learning (Statistical Machine Learning group) Analysing ubiquitous sensor data (HIIT-Wide Focus Area) Interactive visualization (HIIT-Wide Focus Area) Affective computing and BCI (HIIT-Wide Focus Area) Intelligent user interfaces and/or recommender systems (HIIT-Wide Focus Area) Information retrieval (HIIT-Wide Focus Area) Machine learning and data analysis, especially information retrieval, HCI, text and context data (HIIT-Wide Focus Area) Probabilistic modeling and data analysis for bioinformatics (HIIT-Wide Focus Area) From ted.carnevale at yale.edu Tue Sep 3 19:42:31 2013 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 03 Sep 2013 19:42:31 -0400 Subject: Connectionists: Satellite symposium: Using the NSG Portal for Parallel Simulation Message-ID: <522673E7.10103@yale.edu> What: Using the Neuroscience Gateway Portal for Parallel Simulations A Satellite Symposium at the 2013 Society for Neuroscience Meeting Where: Downtown San Diego, CA, just a short walk from the convention center When: 9 AM - Noon on Saturday, Nov. 9, 2013 Speakers: A. Majumdar, S. Sivagnanam, K. Yoshimoto, and T. Carnevale Registration deadline: Friday, October 25, 2013 Do you have a large scale modeling project that exceeds the speed or capacity of your local hardware? Have you tried to use high performance computing (HPC) resources at your own institution, but found the process too difficult because of administrative or technical barriers? If yes, this workshop is for you. In a single morning session, you will learn how to use the Neuroscience Gateway Portal (NSG) http://www.nsgportal.org/ which is designed for neuroscientists who need to use HPC resources for large modeling projects. It simplifies every aspect of the process, from getting allocations of free CPU time to uploading your model, launching and monotoring jobs, and downloading results. The NSG already has several parallel simulators installed, including Brian, MOOSE, NEST, NEURON, PGENESIS and PyNN. Space is limited, so sign up quickly. See http://www.neuron.yale.edu/neuron/static/courses/nsg2013/nsg2013.html for further details and the registration form. Supported by NSF From K.Tsaneva-Atanasova at bristol.ac.uk Wed Sep 4 15:29:43 2013 From: K.Tsaneva-Atanasova at bristol.ac.uk (K Tsaneva-Atanasova) Date: Wed, 4 Sep 2013 20:29:43 +0100 Subject: Connectionists: Associate Research Fellow position - mathematical modelling and analysis of human social interactions Message-ID: *Associate Research Fellow position available immediately for 25 months.* > Based in the College of Engineering, Mathematics and Physical Sciences at > the University of Exeter, you will undertake research into mathematical > modelling and analysis of human social interactions. This is an exciting > opportunity to contribute to a joint venture between movement scientists > from Montpellier 1 University in France, computer science experts from the > DFKI centre (Germany), mathematicians from the University of Exeter and > Bristol (UK), roboticists from the Ecole Polytechnique F?d?rale de Lausanne > (CH), as well as clinicians, psychologists and psychiatrists from the > Academic Hospital of Montpellier (CHRU, FR). This position is funded by > European Union FP7 research project *AlterEgo: Enhancing social > interactions using information technology*. The objective of AlterEgo is > the creation of an interactive cognitive architecture (ICA), implementable > in various artificial agents, allowing a continuous interaction with > socially deficient humans. The final aim of the proposal is to produce a > new robotic-based clinical method able to enhance social interaction of > patients suffering from social disorders. > > > > You will have an excellent background in mathematics, physics and/or > engineering, and should be committed to applying their research to make > real artificial agents? systems interacting with people in challenging > circumstances. You are expected to produce reliable mathematical models and > numerical algorithms that i) allow real-time adaptation of the coupled > human-artificial agent dynamics and ii) integrate all parts of the > interactive cognitive architecture together. The successful applicant will > be able to present information on research progress and outcomes, > communicate complex information, orally, in writing and electronically and > prepare proposals and applications to external bodies. > > Applicants will possess a relevant PhD and be able to demonstrate > sufficient knowledge in the discipline and of research methods and > techniques to work within established research programmes, including > mathematical modelling and numerical bifurcation analysis. > > The closing date for applications is *20 September 2013*. > > > > *The salary range is ?24,766 up to ?26,476 per annum, depending on > qualifications and experience**.* > > *HOW TO APPLY FOR THIS POSITION:** * > > *Please send your completed application and equal opportunities form > along with your CV, covering letter and the details of three referees, to > Dr Krasimira Tsaneva-Atanasova,** **email:** * > K.Tsaneva-Atanasova at exeter.ac.uk*, tel:** **01392 723615** **quoting the > reference number P45548 in any correspondence.* > > *To download the application and equal opportunities form please follow > the below links:* > > *http://www.admin.ex.ac.uk/personnel/jobs/app_form.rtf* > > *http://www.admin.ex.ac.uk/personnel/jobs/EO_form.rtf* > * > * > -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Wed Sep 4 21:23:23 2013 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 04 Sep 2013 18:23:23 -0700 Subject: Connectionists: NEURAL COMPUTATION - October 1, 2013 In-Reply-To: Message-ID: Neural Computation - Contents -- Volume 25, Number 10 - October 1, 2013 Available online for download now: http://www.mitpressjournals.org/toc/neco/25/10 Article Scaling Laws of Associative Memory Retrieval Sandro Romani, Itai Pinkoviezky, Alon Rubin, and Misha Tsodyks Letters Effect of Phase Response Curve Skewness on Synchronization of Electrically Coupled Neuronal Oscillators Ramana Dodla, Charles J Wilson Spike-Timing-Dependent Construction Toby Lightheart, Steven Grainger, and Tien-Fu Lu Computer Modeling of Mild Axonal Injury: Implications for Axonal Signal Transmission Vladislav Volman, Laurel J Ng A Principled Dimension Reduction Method for the Population Density Approach to Modeling Networks of Neurons With Synaptic Dynamics Cheng Ly Discriminative Learning of Propagation and Spatial Pattern for Motor Imagery EEG Analysis Xinyang Li, Haihong Zhang, Cuntai Guan, Sim-Heng Ong, Kai Keng Ang, and Yaozhang Pan Density-Difference Estimation Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus Christoffel du Plessis, Song Liu, and Ichiro Takeuchi Block Clustering Based on Difference of Convex Functions (DC) Programming and DC Algorithms Hoai Minh Le, Hoai An Le Thi, Tao Pham Dinh, and Van Ngai Huynh ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp SUBSCRIPTIONS - 2013 - VOLUME 25 - 12 ISSUES USA Others Electronic Only Student/Retired $70 $193 $65 Individual $124 $187 $115 Institution $1,035 $1,098 $926 Canada: Add 5% GST MIT Press Journals, 238 Main Street, Suite 500, Cambridge, MA 02142-9902 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ------------ From sala038 at aucklanduni.ac.nz Wed Sep 4 21:13:57 2013 From: sala038 at aucklanduni.ac.nz (shafiq burki) Date: Thu, 5 Sep 2013 13:13:57 +1200 Subject: Connectionists: CALL FOR CHAPTER : Biologically-Inspired Techniques for Knowledge Discovery and Data Mining Message-ID: CALL FOR CHAPTER Full Chapter Submission Deadline: Sep 30, 2013 (No Further Extensions) Biologically-Inspired Techniques for Knowledge Discovery and Data Mining Advances in Data Mining and Database Management (ADMDM) Book Series A book edited by Dr. Shafiq Alam, Dr. Yun Sing Koh, and Prof. Gillian Dobbie University of Auckland, New Zealand Website: https://conference.fos.auckland.ac.nz/bdm/biokdd/index.html To be published by IGI Global: http://bit.ly/13tKOjc -- Kind Regards, Shafiq Alam Postdoctoral Research Fellow, Department of Computer Science, University of Auckland, New Zealand. *http://www.cs.auckland.ac.nz/research/groups/kmg/shafiq.html* -------------- next part -------------- An HTML attachment was scrubbed... URL: From Jean-Philippe.Vert at mines-paristech.fr Thu Sep 5 06:41:47 2013 From: Jean-Philippe.Vert at mines-paristech.fr (Jean-Philippe Vert) Date: Thu, 05 Sep 2013 12:41:47 +0200 Subject: Connectionists: NIPS 2013 workshop on Machine Learning in Computational Biology Message-ID: <20130905124147.68687dr238jxgykg@webmail.sif.mines-paristech.fr> NIPS 2013 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-Seventh Annual Conference on Neural Information Processing Systems (NIPS 2013) Lake Tahoe, Nevada, USA, December 9 or 10, 2013. Important dates: Oct 22, 2013 : Deadline for submission of extended abstracts Nov 4, 2013: Acceptance notification Dec 9 or 10, 2013: Workshop date WORKSHOP DESCRIPTION The field of computational biology has seen dramatic growth over the past few years, in terms of newly available data, new scientific questions and new challenges for learning and inference. In particular, biological data is often relationally structured and highly diverse, and thus requires combining multiple weak evidence from heterogeneous sources. These sources include sequenced genomes of a variety of organisms, gene expression data from multiple technologies, protein sequence and 3D structural data, protein interaction data, gene ontology and pathway databases, genetic variation data (such as SNPs), high-content phenotypic screening data, and an enormous amount of text data in the biological and medical literature. New types of scientific and clinical problems require novel supervised and unsupervised learning approaches that can use these growing resources. Furthermore, next generation sequencing technologies are yielding terabyte scale data sets that require novel algorithmic solutions. The workshop will host presentations of emerging problems and machine learning techniques in computational biology. We encourage contributions describing either progress on new bioinformatics problems or work on established problems using methods that are substantially different from standard approaches. Kernel methods, graphical models, semi-supervised approaches, feature selection and other techniques applied to relevant bioinformatics problems would all be appropriate for the workshop. SUBMISSION INSTRUCTIONS Researchers interested in contributing should upload an extended abstract of 4 pages in PDF format to the MLCB submission web site http://www.easychair.org/conferences/?conf=mlcb2013 by Oct 22, 2013, 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. INVITED SPEAKERS Jonathan Pritchard (Stanford) Samuel Kaski (HIIT) ORGANIZERS Anna Goldenberg (University of Toronto) Sara Mostafavi (Stanford) Oliver Stegle (EMBL) Jean-Philippe Vert (Mines ParisTech, Institut Curie) From sameer at cs.umass.edu Wed Sep 4 22:09:57 2013 From: sameer at cs.umass.edu (Sameer Singh) Date: Wed, 4 Sep 2013 22:09:57 -0400 Subject: Connectionists: CFP NIPS Workshop on Big Learning 2013: Advances in Algorithms and Data Management Message-ID: Big Learning 2013: Advances in Algorithms and Data Management *NIPS 2013 Workshop (http://www.biglearn.org)* ORGANIZERS: - *Xinghao Pan* (Berkeley) - *Haijie Gu* (CMU) - *Joseph Gonzalez* (Berkeley) - *Sameer Singh* (UMass Amherst) - *Yucheng Low* (CMU) Submissions are solicited for a one day workshop on December 9th or 10th at Lake Tahoe, Nevada. This workshop will address algorithms, systems, and real-world problem domains related to large-scale machine learning (?Big Learning?). Big Learning has attracted intense interest, with active research spanning diverse fields. In particular, the machine learning and databases have taken distinct approaches by developing new algorithms and data management systems. This workshop will bring together experts across these diverse communities to discuss recent progress, share tools and software, identify pressing new challenges, and to exchange new ideas. Topics of interest include (but are not limited to): - *Scalable Data Systems*: Systems for large-scale parallel or distributed learning; implementations of machine learning models and algorithms in database management systems (DBMS); insights and discussions on properties (availability, scalability, correctness, etc.), strengths, and limitations of databases for Big Learning. - *Big Data*: Methods for managing large, unstructured, and/or streaming data; cleaning, visualization, interactive platforms for data understanding and interpretation; sketching and summarization techniques; sources of large datasets. - *Models & Algorithms*: Machine learning algorithms for parallel, distributed, GPGPUs, or other novel architectures; theoretical analysis; distributed online algorithms; implementation and experimental evaluation; methods for distributed fault tolerance. - *Applications of Big Learning*: Practical application studies and challenges of real-world system building; insights on end-users, common data characteristics (stream or batch); trade-offs between labeling strategies (e.g., curated or crowd-sourced). Submissions should be written as extended abstracts, no longer than 4 pages (excluding references) in the NIPS latex style. Relevant work previously presented in non-machine-learning conferences is strongly encouraged, though submitters should note this in their submission. Submission Deadline: *October 9th, 2013*. Please refer to the website for detailed submission instructions: Guidelines -------------- next part -------------- An HTML attachment was scrubbed... URL: From pelillo at dsi.unive.it Thu Sep 5 02:54:08 2013 From: pelillo at dsi.unive.it (Marcello Pelillo) Date: Thu, 5 Sep 2013 08:54:08 +0200 (CEST) Subject: Connectionists: Last Call for Papers: Special Issue of IEEE TNNLS on "Learning in Non-(geo)metric Spaces" Message-ID: LAST CALL FOR PAPERS IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Special Issue on Learning in Non-(geo)metric Spaces Traditional machine learning and pattern recognition techniques are intimately linked to the notion of feature space. Adopting this view, each object is described in terms of a vector of numerical attributes and is therefore mapped to a point in a Euclidean (geometric) vector space so that the distances between the points reflect the observed (dis)similarities between the respective objects. This kind of representation is attractive because geometric spaces offer powerful analytical as well as computational tools that are simply not available in other representations. However, the geometric approach suffers from a major intrinsic limitation which concerns the representational power of vectorial, feature-based descriptions. In fact, there are numerous application domains where either it is not possible to find satisfactory features or they are inefficient for learning purposes. By departing from vector-space representations one is confronted with the challenging problem of dealing with (dis)similarities that do not necessarily possess the Euclidean behavior or not even obey the requirements of a metric. The lack of (geo)metric (i.e., geometric and/or metric) properties undermines the very foundations of traditional machine learning theories and algorithms, and poses totally new theoretical/computational questions and challenges that the research community is currently trying to address. The goal of the special issue is to consolidate research efforts in this area by soliciting and publishing high-quality papers which, together, will present a clear picture of the state of the art. SCOPE OF THE SPECIAL ISSUE We will encourage submissions of papers addressing theoretical, algorithmic, and practical issues related to the two fundamental questions that arise when abandoning the realm of vectorial, feature-based representations, namely: - how can one obtain suitable similarity information from data representations that are more powerful than, or simply different from, the vectorial? - how can one use similarity information in order to perform learning and classification tasks? Accordingly, topics of interest include (but are not limited to): - Embedding and embeddability - Graph spectra and spectral geometry - Indefinite and structural kernels - Game-theoretic models of pattern recognition and learning - Characterization of non-(geo)metric behavior - Foundational issues - Measures of (geo)metric violations - Learning and combining similarities - Multiple-instance learning - Applications We aim at covering a wide range of problems and perspectives, from supervised to unsupervised learning, from generative to discriminative models, and from theoretical issues to real-world applications. IMPORTANT DATES October 1, 2013 Deadline for manuscript submission April 1, 2014 Notification to authors July 1, 2014 Deadline for submission of revised manuscripts October 1, 2014 Final decision GUEST EDITORS Marcello Pelillo, Ca Foscari University, Venice, Italy (pelillo at dsi.unive.it) Edwin Hancock, University of York, UK (edwin.hancock at york.ac.uk) Xuelong Li, Chinese Academy of Sciences, China (xuelong_li at ieee.org) Vittorio Murino, Istituto Italiano di Tecnologia & University of Verona, Italy (vittorio.murino at iit.it) SUBMISSION INSTRUCTIONS 1. Read the information for authors at: http://cis.ieee.org/publications.html 2. Submit the manuscript by October 1, 2013 at the TNNLS webpage (http://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript has been submitted to the special issue on "Learning in non-(geo)metric spaces." Send also an e-mail to M. Pelillo (pelillo at dsi.unive.it) with subject TNNLS special issue submission to notify the editors of your submission. --- Marcello Pelillo, FIEEE, FIAPR Professor of Computer Science Computer Vision and Pattern Recognition Lab, Director Center for Knowledge, Interaction and Intelligent Systems (KIIS), Director DAIS Ca' Foscari University, Venice Via Torino 155, 30172 Venezia Mestre, Italy Tel: (39) 041 2348.440 Fax: (39) 041 2348.419 E-mail: marcello.pelillo at gmail.com URL: http://www.dsi.unive.it/~pelillo From peter.ljunglof at heatherleaf.se Thu Sep 5 03:40:05 2013 From: peter.ljunglof at heatherleaf.se (=?utf-8?Q?peter_ljungl=C3=B6f?=) Date: Thu, 5 Sep 2013 09:40:05 +0200 Subject: Connectionists: EACL 2014: Call for Software Demonstrations Message-ID: <1CD037F2-78B5-4104-B565-7E3A639BBA32@heatherleaf.se> CALL FOR SOFTWARE DEMONSTRATIONS EACL 2014 The 14th Conference of the European Chapter of the Association for Computational Linguistics Gothenburg, Sweden 26-30 April 2014 http://eacl2014.org/ Demonstrations Chair: Marko Tadi? (University of Zagreb, Faculty of Humanities and Social Sciences) The EACL 2014 Program Committee invites proposals for the Demonstrations Program. This program is primarily to encourage the early exhibition of research prototypes, but interesting mature systems are also eligible. Commercial sales and marketing activities are not appropriate in the Demonstration program. AREAS OF INTEREST We would like to encourage the submission of proposals for demonstrations of software related to any areas of computational linguistics and natural language processing. Areas of interest include, but are not limited to: - Natural language processing systems, including + Dialog systems and interfaces + Machine translation systems and translation aids + Message and narrative understanding systems + Language-oriented information retrieval and information extraction systems - Application systems using embedded language technology components - Reusable components (parsers, generators, taggers, speech recognizers,...) - Software tools for facilitating linguistic research - Software for demonstrating or evaluating computational linguistics research - Aids for teaching computational linguistics concepts. FORMAT FOR SUBMISSION Demo Proposals consist of the following parts, which should all be sent using the EACL 2014 sub-conference submission procedure at https://www.softconf.com/eacl2014/demos/: - An abstract of the technical content to be demonstrated, not to exceed four pages formatted according to the EACL 2014 style guidelines (http://www.eacl2014.org/files/eacl-2014-styles.zip), including title, authors, full contact information, references and acknowledgements. - A detailed description of hardware and software requirements expected to be provided by the local organizer. Demonstrators are encouraged to be flexible in their requirements (possibly with different demos for different logistical situations). Please state what you can bring yourself and what you absolutely must have provided. We will do our best to provide equipment and resources but nothing can be guaranteed at this point beyond space and power. Please contact the demo chair at one of the addresses below for any specific questions. - At least one author of each accepted demo paper must register for and attend the conference, and demonstrate the system during the demo sessions SUBMISSIONS PROCEDURE Proposals should be submitted by 10 January 2014 using the EACL 2014 START web page for Demos: https://www.softconf.com/eacl2014/demos/. Submissions will be evaluated on the basis of their relevance to computational linguistics, innovation, scientific contribution, presentation, and user friendliness, as well as potential logistical constraints. OTHER DETAILS Further details on the the demonstrations sessions will be determined and provided at a later date. IMPORTANT DATES - Demo proposal submissions due: 10 January 2014 - Notification to authors: 1 February 2014 - Camera-ready due: 15 February 2014 - EACL conference dates: 26-30 April 2014 From rsalakhu at cs.toronto.edu Thu Sep 5 11:49:50 2013 From: rsalakhu at cs.toronto.edu (Ruslan Salakhutdinov) Date: Thu, 5 Sep 2013 11:49:50 -0400 (EDT) Subject: Connectionists: Final Call for Demonstrations, NIPS 2013 Message-ID: The Neural Information Processing Systems Conference 2013 http://nips.cc/Conferences/2013/ has a Demonstration Track running in parallel with the evening Poster Sessions, December 5-7, 2013, in Lake Tahoe, Nevada, USA. Demonstration Proposal Deadline: Monday September 16, 2013, 11pm Universal Time (4pm Pacific Daylight Time). http://nips.cc/Conferences/2013/CallForDemonstrations Demonstrations offer a unique opportunity to showcase: ? Hardware technology ? Software systems ? Neuromorphic and biologically-inspired systems ? Robotics or other systems, which are relevant to the technical areas covered by NIPS (see Call for Papers http://nips.cc/Conferences/2013/CallForPapers). Demonstrations must show novel technology and must be run live, preferably with some interactive parts. Unlike poster presentations or slide shows, live action and interaction with the audience are critical elements. Submissions: Submission of demo proposals at the following URL: https://nips.cc/Demonstrators/ You will be asked to fill a questionnaire and describe clearly: ? the technology demonstrated ? the elements of novelty ? the live action part ? the interactive part ? the equipment brought by the demonstrator ? the equipment required at the place of the demo Evaluation Criteria: Submissions will be refereed on the basis of technical quality, novelty, live action, and potential for interaction. Demonstration chair: Russ Salakhutdinov http://nips.cc/Conferences/2013/CallForDemonstrations From miguel.nicolau at ucd.ie Fri Sep 6 13:34:35 2013 From: miguel.nicolau at ucd.ie (Miguel Nicolau) Date: Fri, 6 Sep 2013 18:34:35 +0100 Subject: Connectionists: EuroGP 2014: Second CFP Message-ID: (apologies for cross-posting) ***************************************************************************** EuroGP 2014, 17th European Conference on Genetic Programming 23-25 April 2014, Baeza, Spain www.evostar.org SECOND CALL FOR PAPERS ***************************************************************************** (CFP download: www.evostar.org/flyer/EuroGP2014Flyer.pdf) SUBMISSION DEADLINE: 1 November 2013 EuroGP is the premier annual conference on Genetic Programming, attracting participants from all over the world. High quality papers describing new original research are sought on topics strongly related to the evolution of computer programs, ranging from theoretical work to innovative applications. Topics include but are not limited to: * Innovative applications of GP * Theoretical developments * GP performance and behaviour * Fitness landscape analysis of GP * Algorithms, representations and operators * Real-world applications * Evolutionary design * Evolutionary robotics * Tree-based GP and Linear GP * Graph-based GP and Grammar-based GP * Evolvable hardware * Self-reproducing programs * Multi-population GP * Multi-objective GP * Fast/Parallel GP * Probabilistic GP * Evolution of automata or machine * Software Engineering and GP * Object-oriented GP * Hybrid architectures including GP * Coevolution in GP * Modularity in GP * Semantics in GP * Unconventional evolvable computation * Automatic software maintenance * Evolutionary inductive programming In 2013, the EuroGP acceptance rate was 49% (38% for oral presentations). Accepted papers will be included in the proceedings published by Springer Verlag in the Lecture Notes in Computer Science (LNCS) series. The papers which receive the best reviews will be nominated for the Best Paper Award. EuroGP 2014 will be co-located within the EvoStar event with four related conferences: EvoBIO, EvoCOP, EvoMUSART, and EvoApplications. Website: www.evostar.org/cfpEuroGP.html Facebook: fb.com/evostarconf Twitter: twitter.com/Evostar2014 LinkedIn: www.linkedin.com/groups/EVOstar-1908983 EuroGP programme chairs Miguel Nicolau, University College Dublin, Ireland Krzysztof Krawiec, Poznan University of Technology, Poland -------------- next part -------------- An HTML attachment was scrubbed... URL: From tiago.v.maia at gmail.com Sat Sep 7 10:01:11 2013 From: tiago.v.maia at gmail.com (Tiago Maia) Date: Sat, 7 Sep 2013 15:01:11 +0100 Subject: Connectionists: Postdoctoral fellowships in computational psychiatry and/or translational neuroscience Message-ID: <010101ceabd2$b5e552f0$21aff8d0$@gmail.com> POSTDOCTORAL FELLOWSHIPS IN COMPUTATIONAL PSYCHIATRY AND/OR TRANSLATIONAL NEUROSCIENCE I am looking for postdoctoral fellows to conduct research in my lab at the School of Medicine of the Uiversity of Lisbon (Portugal). There may also be opportunities to spend time at the Department of Psychiatry of Columbia University (USA), where I also have a faculty appointment. Research in my lab focuses on using neurocomputational models, fMRI, and behavioral experimentation to understand the neural bases of cognition and emotion and the disruption of these processes in psychiatric disorders. Additional information, including a list of publications, is available on my web page: http://childpsych.columbia.edu/brainimaging/CV_maia.html An overview of aspects of the lab's approach is given in Maia & Frank (2011, Nature Neuroscience). However, the lab also focuses on several other issues not addressed in that article, so looking at the list of publications on my web page gives a more complete picture of the topics we study. Talented candidates from any background will be considered, but preference will be given to candidates with expertise in one or more of the following areas: computational neuroscience, fMRI, and/or behavioral experimentation. Interested candidates will have opportunities to combine techniques from these three areas. However, candidates interested in only one of these areas are also welcome to apply. There are two funding opportunities: 1. Funding is available immediately for a postdoctoral fellow to work on a project that uses computational models, fMRI, and behavioral experimentation to understand reinforcement learning in Tourette Syndrome. The postdoctoral fellow would also have the opportunity to work on other projects. Initial funding is for one year, but there may be opportunities to extend that period, depending on availability of funds. 2. The Portuguese Foundation for Science and Technology is now accepting applications for postdoctoral fellowships. I would be happy to sponsor the application of strong postdoctoral candidates to pursue research in my lab, in a topic of mutual interest. These fellowships can last up to six years. The nearest deadline for applications for the Portuguese Foundation for Science and Technology is September 19, 2013. The application involves specifying the research to be conducted, so candidates interested in applying for this deadline should contact me as soon as possible. Successful applicants could start their fellowship any time during 2014 (but must have finished their Ph.D. by the end of 2013). Candidates should send a CV and a letter describing their research interests to MaiaT at nyspi.columbia.edu. Reference letters are optional at this stage (but I will probably ask for contact information for two recommenders for candidates who make the shortlist for selection). From peter.ljunglof at heatherleaf.se Mon Sep 9 10:14:37 2013 From: peter.ljunglof at heatherleaf.se (=?utf-8?Q?peter_ljungl=C3=B6f?=) Date: Mon, 9 Sep 2013 16:14:37 +0200 Subject: Connectionists: EACL 2014: Student Research Workshop Message-ID: <33680999-FC31-4CDB-8FFA-97897CADBB51@heatherleaf.se> EACL 2014 STUDENT RESEARCH WORKSHOP The 14th Conference of the European Chapter of the Association for Computational Linguistics Gothenburg, Sweden 26-30 April 2014 http://eacl2014.org/ CALL FOR PAPERS ** Submission deadline: Friday, 22 November 2013; 11:59pm CET ** I. General Invitation for Submissions ------------------------------------- EACL 2014 continues the tradition of providing a forum for student researchers who are investigating various areas related to Computational Linguistics and Natural Language Processing. The workshop provides an excellent opportunity for student participants to present their work and receive valuable feedback from the international research community as well as from selected panelists - experienced researchers who will prepare in-depth comments and questions in advance of the presentation. The workshop's goal is to aid students at multiple stages of their education: from those in the final stages of undergraduate training to those active with graduate thesis research. We invite papers in two separate categories: 1. Thesis/Research Proposals: This category is appropriate for students who wish to get feedback on the progress of their thesis work and broader ideas from the field in order to identify the most promising directions for the remaining thesis work. 2. Research Papers: Most appropriate for students who are new to academic conferences. Papers in this category can describe completed original work or work in progress with preliminary results. Topics relevant to the workshop aim to cover all aspects of Computational Linguistics and Natural Language Processing, including, but not limited to (in alphabetical order): - Cognitive modeling of language processing and psycholinguistics - Dialogue and interactive systems - Discourse, coreference and pragmatics - Evaluation methods - Information retrieval - Language resources - Lexical semantics and ontologies - Machine translation: methods, applications and evaluation - Multilinguality in NLP - NLP applications - NLP and creativity - NLP for low-resource languages - NLP for the Web and social media - Question answering - Semantics - Sentiment analysis, opinion mining and text classification - Spoken language processing - Statistical and Machine Learning methods in NLP - Summarization and generation - Syntax and parsing - Tagging and chunking - Text mining and information extraction - Word segmentation Subject to the availability of established researcher volunteers, each accepted paper will be assigned a mentor, an experienced researcher who will provide feedback on the work to the student at the conference. Details on this service will be provided in the acceptance notification. II. Submission guidelines ------------------------- A) Submission requirements 1. Thesis/Research Proposals may contain previously published work and must include specific research directions. They may also be in the style of a position paper that surveys and critiques existing literature, but must suggest future research directions. Proposals may only have one author, who must be a student. 2. Research Papers must describe original completed work or work in progress. Since the main purpose of presenting at the workshop is to exchange ideas with other researchers and to receive helpful feedback for further development of the work, papers should clearly indicate directions for future research wherever appropriate. The first author of multi-author papers must be a student, but additional co-authors need not be students. Research Papers are eligible for this workshop only if they have not been presented at any other meeting with publicly available published proceedings. Students who have already presented at a past ACL/EACL/NAACL Student Research Workshop may not submit to this track as a first author (though they may still be a co-author, or the first author of a Thesis/Research Proposal). These students are instead encouraged to submit their work to the main conference or to the Thesis Proposal track. During submission, students must clearly indicate whether a paper has been submitted to another conference or workshop. Double submissions to the EACL main conference and the Student Research Workshop are not allowed. One student can only submit one paper to the Research Papers track as the first author. B) Submission procedure Both paper and proposal submissions to the EACL 2014 Student Research Workshop should follow the standard two-column format of the EACL 2014 proceedings and they must be submitted as a PDF file. Authors are strongly recommended to use the style files from the conference web site. The style files are available here: - http://www.eacl2014.org/files/eacl-2014-styles.zip All submissions may consist of up to nine (9) pages of content only. Any number of additional pages containing references is allowed. The reviewing process will be double-blind; therefore, please ensure that the paper does not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity, e.g., "We previously showed (Smith, 1991) ...", should be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ...". Further guidelines are provided in the template style files. References to your own work in thesis proposals should also be anonymized. You may for example write it as "in X (2000) we showed", etc. and do not add your papers in the reference list. Authors should not use other anonymous citations in both research papers and thesis proposals, and should not include any acknowledgments. Papers that do not conform to these requirements will be rejected without review. The deadline for submission is 11:59pm CET on Friday, 22 November 2013. Submission will be electronic using the paper submission web page: - https://www.softconf.com/eacl2014/srw/ Papers will be presented orally or as posters during the main EACL conference as determined by the program committee. Decisions on presentation format will be based on the nature rather than the quality of the work. There will be no distinction in the proceedings between long papers presented orally and as posters. C) Multiple-submission policy Papers that have been or will be submitted to other meetings or publications must indicate this at submission time. Authors of papers accepted for presentation at EACL SRW 2014 must notify the program chairs whether the paper will be presented. All accepted papers must be presented at the workshop in order for them to appear in the proceedings. We will not accept for publication or presentation papers that overlap significantly in content or results with papers that will be (or have been) published elsewhere. Double submissions to the EACL main conference and the Student Research Workshop are not allowed, and the authors must ensure that these submissions do not overlap significantly (> 50%) with each other in content or results. D) Reviewing procedure The reviewing of the papers will be double-blind. Reviewing will be managed by the Student Workshop Co-Chairs and a team of reviewers. Each submission will be matched with a mixed panel of student and senior researchers for review. The final acceptance decision will be based on the results of the review. III. Important dates -------------------- - Submission deadline: 22 November 2013 - Notification of acceptance: 13 January 2014 - Camera-ready submission deadline: 17 February 2014 - Conference dates: 26-30 April 2014 (The workshop will be held during the main conference, in a mode similar to the conference's regular sessions. The exact format will be decided by the workshop co-chairs and conference chairs.) IV. Student Research Workshop Committee --------------------------------------- Student chairs: - Desmond Elliott (University of Edinburgh, UK) - Konstantina Garoufi (University of Potsdam, Germany) - Douwe Kiela (University of Cambridge, UK) - Ivan Vuli? (KU Leuven, Belgium) Faculty advisor: - Sebastian Pad? (University of Stuttgart, Germany) Program committee: - TBA Contact information: - students at eacl.org From grlmc at urv.cat Sat Sep 7 12:11:14 2013 From: grlmc at urv.cat (GRLMC) Date: Sat, 7 Sep 2013 18:11:14 +0200 Subject: Connectionists: TPNC 2013: call for posters Message-ID: <154463DA0CB94E6994F8ECD706988C48@Carlos1> The 2nd International Conference on the Theory and Practice of Natural Computing (TPNC 2013) invites authors to submit poster presentations. TPNC 2013 will be held in C?ceres (Spain) on 3-5 December, 2013. See http://grammars.grlmc.com/tpnc2013/ Poster presentations are intended to enhance informal interactions with the conference participants, at the same time permitting in-depth discussion. TOPICS Authors are encouraged to submit presentations that discuss novel work in progress on: - nature-inspired models of computation, - synthesis of nature by means of computation, - nature-inspired materials, - information processing in nature, - applications of natural computing. Posters do not need to present final research results. Work that may lead to new interesting developments is welcome. KEY DATES Submission deadline: October 20, 2013 Notification of poster acceptance or rejection: October 27, 2013 SUBMISSION Please submit a .pdf abstract through: https://www.easychair.org/conferences/?conf=tpnc2013 It should contain the title, author(s) and affiliation, and should not exceed 500 words. PRESENTATION Posters will be allocated 8 minutes each in the programme for oral presentation. Moreover, they will remain hanging during the whole conference for discussion. PUBLICATION Posters will not appear in the LNCS proceedings volume of TPNC 2013. However, they will be eligible for submission to the post-conference Soft Computing journal special issue. REGISTRATION Authors of accepted posters have to register to the conference. Their registration fare is reduced: 150 Euro (appr. one third of the fare for PhD students). From Michael_Frank at brown.edu Mon Sep 9 20:26:42 2013 From: Michael_Frank at brown.edu (Michael J Frank) Date: Mon, 9 Sep 2013 20:26:42 -0400 Subject: Connectionists: PhD studentships: Computation in Brain and Mind at Brown University Message-ID: Announcing a new multidisciplinary initiative for Computation in Brain and Mind at Brown University, within the Brown Institute for Brain Science. PhD students are encouraged to apply to any of the departments affiliated with the initiative, including Neuroscience, Cognitive, Linguistic and Psychological Sciences, Applied Mathematics, Computer Science and others. The initiative includes a seminar series focused on computation with distinguished lecturers, yearly technical workshops and symposia, and a yearly neural decoding competition. The initiative will also have close links to parallel initiatives at Brown in Human-Robot Interaction, Digital Society (big data), and access to a high performance compute cluster with dedicated cycles for Brain Science. Brown neuroscientists and cognitive scientists rely on computational tools for two core purposes: (i) to develop and refine theories about the fundamental computations of mind and brain, used to guide and interpret experiments; (ii) to develop sophisticated statistical analysis tools for decoding neural data and predicting, for example, spike trains in a given neuronal population based on their spike history and to leverage this predictability for applications such as brain-machine interfaces. Other applications include the use of computational tools to automate the monitoring and analysis of behavioral neuroscience data. Brown has particular expertise in computational approaches to higher order brain function, from perception to cognition, spaning departments of Neuroscience, Cognitive, Linguistic & Psychological Sciences, Applied Mathematics, Computer Science, Neurosurgery, Biostatistics, and Engineering. Most of these faculties cross theory and experiment, but primary foci are listed here: * Core level i* * Computational perception: Theories about how the brain integrates sensory information to give rise to percepts, constrained by biophysics and computational objectives. * Control over action: reinforcement learning, decision making, and cognitive control; application to mental illnesses. * Fundamental questions in neural computation: synaptic plasticity, circuits, networks. *Core level ii* * Neurotechnology: brain-machine interface, advanced neural data analysis. * Automated collection of neuroscience data, e.g. via computer vision and annotation. * These core areas are supported by boundary-pushing development of technical and analytic methods in Computer Science an Applied Mathematics. Core faculty whose research and teaching focus centers around computation in brain and mind include: * James Anderson * Joseph Austerweil * Leon Cooper * Michael Frank * Stuart Geman * Matthew Harrison * James Hays * Sorin Istrail * Stephanie Jones * Benjamin Kimia * Michael Littman * Xi Rossi Luo * Thomas Serre * Erik Sudderth * Wilson Truccolo In addition there are many affiliated faculty who rely on computation in various aspects of their research. See http://compneuro.clps.brown.edu/people/ for a full list. -- Michael J Frank, PhD, Associate Professor Laboratory for Neural Computation and Cognition Brown University http://ski.clps.brown.edu (401)-863-6872 -------------- next part -------------- An HTML attachment was scrubbed... URL: From mr287 at georgetown.edu Mon Sep 9 22:27:17 2013 From: mr287 at georgetown.edu (Maximilian Riesenhuber) Date: Mon, 9 Sep 2013 22:27:17 -0400 Subject: Connectionists: Postdoc position in computational modeling/EEG/fMRI: Shortcuts in the brain's visual hierarchy Message-ID: I have an opening for a postdoctoral fellow, starting immediately, to participate in a new NIH-funded research project that tests the hypothesis that the visual system can increase its processing speed on particular tasks by basing task-relevant decisions on signals that originate from intermediate processing levels, rather than requiring that stimuli are processed by the entire visual hierarchy. This hypothesis will be tested using a tightly integrated multidisciplinary approach consisting of behavioral studies using eye tracking to determine the capabilities of human ultra-rapid object detection, EEG and fMRI studies to determine when and where in the brain object-selective responses occur, and computational modeling studies to determine whether such multilevel object mechanisms can account for human performance levels. Instead of the classic hierarchical model, in which objects can only be coded at the very top of the system, this project will show how ?objects? can be detected by neurons located in early visual areas ? especially when those objects are behaviorally very important and need to be localized accurately ? with fundamental implications for our understanding of the role of early and intermediate visual areas in object detection. The postdoc will receive training in computational modeling, EEG and fMRI. The project is a collaboration between my group at Georgetown University and Simon Thorpe and Jacob Martin at the CerCo in southern France. The project provides funds to travel annually to the CerCo in Toulouse for further training in EEG and visual psychophysics as well as computational modeling. A quantitative background is required. Experience with computational modeling is a strong plus, as is training in biological and/or machine vision. Experience with Mac OS X, Linux, MATLAB, and C++ is helpful. This position is also of interest for PhDs in computer science or engineering with an interest in moving into computational neuroscience. Georgetown University has a vibrant neuroscience community with over fifty labs participating in the Interdisciplinary Program in Neuroscience. Georgetown's scenic campus is located at the edge of Washington, DC, one of the most intellectual and culturally rich cities in the country. Interested candidates should send a CV, a brief (1 page) statement of research interests, representative reprints, and the names and contact information of three references by email to Maximilian Riesenhuber ( mr287 at georgetown.edu). Review of applications will begin immediately, and will continue until the position is filled. Informal inquiries are welcome. -- Maximilian Riesenhuber Lab for Computational Cognitive Neuroscience Department of Neuroscience Georgetown University Medical Center Research Building Room WP-12 3970 Reservoir Rd., NW Washington, DC 20007 phone: 202-687-9198 * fax: 202-784-3562 * email: mr287 at georgetown.edu http://maxlab.neuro.georgetown.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From laszlo at science.upm.ro Tue Sep 10 08:01:31 2013 From: laszlo at science.upm.ro (laszlo at science.upm.ro) Date: Tue, 10 Sep 2013 15:01:31 +0300 Subject: Connectionists: Call for papers: From Natural Computing to Self-organizing Intelligent Complex Systems Message-ID: <20130910150131.15437fxuk8ls7oyj@webmail.upm.ro> ********************* CALL FOR PAPERS ********************* SUBMISSION DUE DATE: 1 November 2013 SPECIAL ISSUE ON: From Natural Computing to Self?organizing Intelligent Complex Systems Journal of Information Technology Research (JITR) http://www.igi?global.com/journal/journal?information?technology?research?jitr/1100 Guest Editor: Barna L?szl? Iantovics, Petru Maior University, Romania Constantin?B?l? Zamfirescu, Lucian Blaga University, Romania Kenneth Revett,The British University, Cairo, Egypt Adrian Gligor, Petru Maior University, Romania INTRODUCTION: Recently a large number of bio?inspired computational methods have been used (also called methods of Natural Computing) to solve computationally hard problems in many domains. These methods have proven to be successful for different types of problems with unknown and uncertain data where the traditional approaches are not so effective. It is estimated that the biological lifethat evolved during millions of years will be a fruitful source of inspiration for the development of newcomputational methods offer in the years to come and they will represent an important researchdirection in the Artificial Intelligence mainstream. OBJECTIVE OF THE SPECIAL ISSUE: From a practical perspective, an essential research direction is represented by the development ofhighly complex systems (usually agent?based) that intelligently solve problems of very high difficulty. Weconsider complex systems composed from a large number of components (agents) capable to makespecialized computations in the problem space. Such developments are usually composed of a very largenumber of computational components, who interact many times nonlinearly, forming as a whole a complex problem solving system. A subclass of complex systems includes the hybrid systems composed from different type of artificial components capable to make computations, and humanspecialists that could interact in different points of decisions during the problems solving. Researchrelated to complex systems address analysis of many aspects such as complexity, self?organization, emergence, intelligence, hybridization and so forth. Many computational complex systems developmentsrequire interdisciplinary approaches, which must include methods developed in different sciences, like sub?domains of the Artificial Intelligence like Natural Computing and Intelligent Agents. A particular subject by interest for this issue is represented by the self?organizing complex systems that use methods of natural computing in different tasks, like: problems solving, self? organizationetc. This issue will centralize some state of the art results in the theme, which we estimate that will remainan important research direction in the near future. RECOMMENDED TOPICS: Topics to be discussed in this special issue include (but are not limited to) the following: ? artificial intelligence ? large?scale and complex systems ? hybrid complex systems ? intelligent systems ? natural computing ? evolutionary systems ? complex systems? modeling ? agents and multi?agent systems ? complex networks ? difficult problem for a human specialist ? difficult problem for a computational system ? complex systems specialized in difficult problems solving ? decision support systems ? problem solving method used by a complex system ? problems that could be solved by a complex system ? large?scale cooperative agent?based systems ? self?organizing system SUBMISSION PROCEDURE: Researchers and practitioners are invited to submit papers for this special theme issue on From NaturalComputing to Self?organizing Intelligent Complex Systems on or before 12 July 2013 . All submissions mustbe original and may not be under review by another publication. INTERESTED AUTHORS SHOULD CONSULTTHE JOURNAL?S GUIDELINES FOR MANUSCRIPT SUBMISSIONS athttp://www.igi?global.com/Files/AuthorEditor/guidelinessubmission.pdf. All submitted papers will bereviewed on a double?blind, peer review basis. Papers must follow APA style for reference citations. Journal of Information Technology Research (JITR) is an official publication of the Information Resources Management Association http://www.igi?global.com/journal/journal?information? technology?research?jitr/1100 Editor?in?Chief: Mehdi Khosrow?Pour Published: Quarterly (both in Print and Electronic form) PUBLISHER: The Journal of Information Technology Research is published by IGI Global (formerly Idea Group Inc.),publisher of the ?Information Science Reference? (formerly Idea Group Reference), ?MedicalInformation Science Reference?, ?Business Science Reference?, and ?Engineering Science Reference?imprints. For additional information regarding the publisher, please visit www.igi?global.com. All submissions should be should be directed to the attention of one of the guest editors: GuestEditors Journal of Information Technology Research (JITR) Barna L?szl? Iantovics, E?mail: laszlo?@?science?[?.?]?upm ?[?.?]?ro Constantin?B?l? Zamfirescu, E?mail: zbc?@?acm ?[?.?]?org KennethRevett, E?mail: ken.revett?@?bue?[?.?]?edu ?[?.?]?eg Adrian Gligor, E?mail:adrian?[?.?]?gligor?@?ing ?[?.?]?upm ?[?.?]?ro From mvladymyrov at ucmerced.edu Tue Sep 10 22:23:45 2013 From: mvladymyrov at ucmerced.edu (Max Vladymyrov) Date: Tue, 10 Sep 2013 19:23:45 -0700 Subject: Connectionists: New code release: Locally Linear Landmarks (LLL) for manifold learning In-Reply-To: <93F80B62-EB02-465F-B714-2D170DCB9D67@ucmerced.edu> References: <93F80B62-EB02-465F-B714-2D170DCB9D67@ucmerced.edu> Message-ID: <86E32031-440E-4469-B571-EC12D8356C08@ucmerced.edu> Dear all, We are pleased to advertise Matlab code for computing Locally Linear Landmarks (LLL) as described in the following paper: M. Vladymyrov and M. A. Carreira-Perpinan: "Locally Linear Landmarks for Large-Scale Manifold Learning", ECML-PKDD 2013, pp. 256-271. https://eng.ucmerced.edu/people/vladymyrov http://faculty.ucmerced.edu/mcarreira-perpinan/papers.html The code computes a fast, approximate solution to Laplacian Eigenmaps and potentially any other spectral method. Laplacian Eigenmaps is a very popular nonlinear dimensionality reduction method. However, it requires computing the trailing eigenvectors of an NxN positive semidefinite matrix, which is expensive with large N. LLL solves a reduced eigenproblem by constructing a new affinity matrix for a subset of landmark points so that the manifold structure is better preserved than with Nystr?m's method. For datasets with millions of points, this results in significant speedups with only a small approximation error. Sincerely, Max Vladymyrov and Miguel A. Carreira-Perpinan From areynolds2 at vcu.edu Wed Sep 11 08:43:14 2013 From: areynolds2 at vcu.edu (Angela M Reynolds) Date: Wed, 11 Sep 2013 08:43:14 -0400 Subject: Connectionists: Conference on nonlinear dynamics - in honor of B. Ermentrout Message-ID: Nonlinear Dynamics and Stochastic Methods:From Neuroscience to Other Biological Applications Conference held in honor of G. Bard Ermentrout's 60th Birthday March 10-12, 2014, University of Pittsburgh Organizers: Rodica Curtu (University of Iowa), Angela Reynolds (Virginia Commonwealth University) Local Committee: Brent Doiron, Jonathan Rubin (University of Pittsburgh) SPEAKERS: Paul Bressloff, Carson Chow, Sharon Crook, Jack Cowan, Jonathan Drover, Leah Edelstein-Keshet, Roberto Fernandez Galan, Pranay Goel, Boris Gutkin, Zachary Kilpatrick, Nancy Kopell, Cheng Ly, Remus Osan, George Oster, John Rinzel, Jonathan Rubin, Daniel Simons, and David Terman REGISTRATION AND SCHEDULE: www.math.uiowa.edu/MathematicalBiologyGroup/conferencePitt2014.htm SPONSORS: Department of Mathematics, University of Pittsburgh Mathematical Biosciences Institute National Science Foundation (pending) CONTACT: rodica-curtu at uiowa.edu or areynolds2 at vcu.edu Virginia Commonwealth University Department of Mathematics and Applied Mathematics Assistant Professor areynolds2 at vcu.edu 804-828-5664 Grace Harris Hall 4176 -------------- next part -------------- An HTML attachment was scrubbed... URL: From elio.tuci at gmail.com Tue Sep 10 11:53:26 2013 From: elio.tuci at gmail.com (Elio Tuci) Date: Tue, 10 Sep 2013 16:53:26 +0100 Subject: Connectionists: 3 years PhD Studentship at Aberystwyth University, Computer Science Department, UK Message-ID: <9ED741AF-C68B-4E08-AC96-B17115B97A61@gmail.com> 3 years PhD Studentship at Aberystwyth University, Computer Science Department Project Description The Intelligent Robotics Group, at Aberystwyth University (UK) has one PhD Studentship available for the academic year starting on 1 October 2013. The studentship is available in the following project: Evolution of Autonomous Road Following Vehicles (Supervisor: Dr Elio Tuci) The project's objective is to design control systems for robotic vehicles required to autonomously navigate (using cameras) poorly delineated roads without straying from the boundaries. The vehicles' controller will be an artificial neural network, synthesized by using evolutionary computation techniques, capable of dynamically (in real time) performing multiple colour model transformations to extract perceptual features that can be reliably used to select the most appropriate motor actions to guide the vehicle on the road. Two versions of the system will be investigated. In the first, the neuro- controller is in charge of both the processing of the visual input and the guidance of the vehicle (by directly controlling the status of the vehicles actuators). In the second, the neuro-controller processes the visual input and contributes to the guidance of the vehicle but it is not fully in charge of it. We will generate two final demonstrators: a vehicle performing road-following in laboratory (controlled) conditions; and a vehicle performing road-following in open environments. The Intelligent Robotics Lab at AU is home to several robots and autonomous vehicles that will be used for the activity of this project. We have 7 Pioneer robots and 10 e-puck robots, all equipped with a vision system that will be used to run laboratory tests. Idris, the 4 wheels drive, 4 wheel steering, electric vehicle and two G-Wiz electric vehicles will be used to run tests in natural environments. Eligibility Applicants should have a high grade Bachelors or Masters Degree in Computer Science, Robotics, Computational Neuroscience, Psychology or related disciplines. The candidates must have good programming skills and a strong motivation for research. Funding The studentship is supported for 3 years and includes full Home/EU tuition fees plus a stipend of ?13,726 per annum. The studentship will only fully fund the applicant who is eligible for Home/EU fees with relevant qualifications. An applicant normally required to cover overseas fees will have to cover the difference between the Home/EU and the overseas tuition fee rates (approximately ?9,790 per annum). For further information on the project or for an informal discussion, please contact Dr Elio Tuci at elt7 at aber.ac.uk. Applications (i.e., a detailed CV) should be sent by email (preferably in PDF format) to (elt7 at aber.ac.uk). Applications will be considered until the position is filled. ======================================================================== Elio Tuci, Lecturer Tel: +44 (0)1970 622537 Department of Computer Science Fax: +44 (0)1970 628536 Llandinam Building Aberystwyth University Aberystwyth Ceredigion SY23 3DB UK ======================================================================== From i.bojak at reading.ac.uk Wed Sep 11 14:30:06 2013 From: i.bojak at reading.ac.uk (Ingo Bojak) Date: Wed, 11 Sep 2013 19:30:06 +0100 Subject: Connectionists: Call for papers: Advances in Neural Population Models and Their Networks Message-ID: <7F3E9D30-79B9-4F69-9E38-1FC4DFF31E40@reading.ac.uk> Dear colleagues, May we draw your attention to an Open Thematic Series ("special issue") in the Springer open access journal EPJ Nonlinear Biomedical Physics: Advances in Neural Population Models and Their Networks This special issue arises from two CNS*13 workshops ("Advances in Neural Mass Modelling" and "Full Brain Network Dynamics - Modelling, Analyses, Experiments", respectively), but welcomes topical submissions from all. Deadline for submissions is 15 November 2013, and will not be moved. The full announcement can be found here as PDF, but is also reproduced below. If you have any questions please feel free to contact us via i.bojak at reading.ac.uk. As (guest) editors, we look forward to receiving your contributions to what promises to be an exciting special issue. Best wishes, Ingo Bojak, Stephan van Gils and Sid Visser Full announcement Neural population models (NPMs) describe the overall behaviour of large ensembles of neurons. Various names have been used for this general approach according to mathematical and conceptual detail: neural mass models, mean field models, neural field models, cortical field theory, etc. Since not all neurons are modelled individually, a distinct advantage of these lumped models is the reduction in dimensionality of both the parameter and variable space, which reduces computation time and makes possible sophisticated mathematical analyses of the model?s behaviour as well as their application to experimental data. Nevertheless, NPMs retain their biological interpretability, allowing researchers to investigate a wide range of brain function in health and disease, as well as the effects of drugs and other extraneous influences. Current non-invasive neuroimaging methods such as EEG, fMRI and MEG measure in various ways the activity of sizable groups of neurons, making their data a natural target for NPMs. Furthermore, thanks to the speed with which NPMs can be evaluated one can computationally match the ability of these modalities to record the activity of entire brains. In combination with rapid experimental progress in determining the large scale connectivity (the connectome), this is leading to novel NPM-based methods for the modelling of partial or even full brain networks. Typically such models are characterized by time delays via signal propagation along connecting fibres with NPMs as network nodes. They promise to make NPMs the tool of choice for neuroimaging analysis in the future. Topics of interest for this thematic series include but are not limited to the following advances in neural population modelling: ? the inclusion of neural mechanisms such as spike rate adaptation or bursting ? the effects of higher order statistics on the dynamics ? the formal and/or computational correspondence between microscopic and macroscopic models ? adapting models for different regions of the brain ? describing pathologies and drug effects ? the development of new analytic tools for these systems ? determining the effects of connectivity on dynamics ? building partial and full brain networks ? studying large scale brain dynamics in health and disease ? addressing cognition through associated brain processes Authors are cordially invited to submit original research papers on novel techniques, theoretical analyses and simulations, as well as applications to experiment and data analysis, of recent developments in neural population models and their networks. Submission Instructions Before submission, authors should carefully read over the ?Instructions for Authors?, which are located at http://www.epjnonlinearbiomedphys.com/authors/instructions. Prospective authors should submit an electronic copy of their complete manuscript through the SpringerOpen submission system at http://www.epjnonlinearbiomedphys.com/manuscript according to the submission schedule. They should choose the section ?Systems Neurosciences and Integrative Brain Research? and then choose the subsection ?Thematic series: Advances in Neural Population Models and Their Networks?. In addition, they should specify the manuscript as a submission to the ?Thematic series on Advances in Neural Population Models and Their Networks? in the cover letter. Submission Schedule Manuscript due: November 15, 2013 Guest Editors Ingo Bojak, School of Systems Engineering, University of Reading, UK and Donders Centre for Neuroscience, Radboud University Nijmegen (Medical Centre), The Netherlands Stephan A. van Gils, Applied Mathematics, University of Twente, The Netherlands Sid Visser, School of Mathematical Sciences, University of Nottingham, UK For any queries please contact Ingo Bojak, i.bojak at reading.ac.uk. -------------- next part -------------- An HTML attachment was scrubbed... URL: From bazhenov at salk.edu Wed Sep 11 14:42:38 2013 From: bazhenov at salk.edu (Maxim Bazhenov) Date: Wed, 11 Sep 2013 11:42:38 -0700 Subject: Connectionists: postdoctoral position: modeling of sleep rhythms and memory consolidation Message-ID: <5230B99E.9030701@salk.edu> Applications are invited for post-doctoral positions in the laboratory of Dr. Maxim Bazhenov at the University of California, Riverside to study role of sleep rhythms in memory and learning. This project involves close collaboration with laboratories of Eric Halgren (UCSD), Terry Sejnowski (Salk), Sydney Cash (Harvard), Jean-Marc Fellous (Univ of Arizona). The ultimate goal of this work is to understand how the interaction among brain areas during different stages of sleep leads to consolidation of memory for recent learning. The successful candidate will be responsible for the design of the anatomically realistic thalamo-cortico-hippocampal models based on existing experimental data. These models will be used to understand network dynamics of brain that are involved in the processes of memory consolidation, as well as guide data analysis and produce novel experimental predictions. Qualified applicants are expected to have experience in computational/theoretical neuroscience and conductance-based neural modeling. Programming experience with C/C++ is required. Knowledge of PYTHON or MATLAB is a plus. The University of California offers excellent benefits. Salary is based on research experience. The initial appointment is for 1 year with a possibility of extension. Applicants should send a brief statement of research interests, a CV and the names of three references to Maxim Bazhenov at maksim.bazhenov at ucr.edu -- Maxim Bazhenov, Ph.D. Professor, Cell Biology and Neuroscience University of California Riverside, CA 92521 Ph: 951-827-4370 http://biocluster.ucr.edu/~mbazhenov/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From fmschleif at googlemail.com Thu Sep 12 05:11:51 2013 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Thu, 12 Sep 2013 11:11:51 +0200 Subject: Connectionists: Special Session about 'Learning of structured and non-standard data' at ESANN 2014 Message-ID: [apologies for multiple posting] Call for Papers - Special Session on 'Learning of structured and non-standard data' 23-25 April 2014, Bruges, Belgium http://www.dice.ucl.ac.be/esann AIMS AND SCOPE Today real life data are often given not in the form of vectorial data but in various formats often without an underlying metric space. Prominent examples are network structured data e.g. from social or communication networks, tree structured data used to represent hierarchical documents or collections thereof. Also the simple relation between objects e.g. by means of score data found in sequence alignments or rating information as obtained in collaborative filtering approaches is of this type. The recent technological developments, also in the context of big data, allow the generation of very complex data sets. Challenges are now in the effective processing of these data, in the light of the pure amount, but also to keep the obtained model informative for subsequent analysis. These data are also often given without an explicit vector space, point relations can be asymmetric, metric properties may not be valid and the available information if often sparse in different representations. Computational intelligence methods have the potential to be used to pre-process, model and to analyze such complex data but new strategies are needed. A very effective way is to employ explicit or implicit knowledge about the data, or the analysis task and to learn an appropriate model from available training data. In other cases the knowledge is used in the design of adaptive analysis algorithms to generate the desired meta information out of the data. Such knowledge may be available by means of appropriate (bio-)physical models, data specific distance measures, auxiliary information associated with the data. or dedicated processing strategies for non-metric data employing infinite kernels or dissimilarity learning approaches. Also novel data encoding techniques and projection methods, employing concepts from randomization algorithm, have been used to obtain compact descriptions of these complex data sets or to identify relevant information. Examples of such data analysis problems are e.g. in the analysis of biological or social networks with a large number of measurements and complex data relations. TOPICS We encourage submission of papers on novel methods for structured data, dissimilarity learning, non-standard data analysis and non-metric data processing by means of computational intelligence and machine learning approaches, including but not limited to: - data analysis and pattern recognition approaches for structured data - dissimilarity learning - methods employing ex- and implicit data knowledge for non-standard data - representation and modeling of heterogeneous, high-dimensional, multi-modal (structured) and/or non-standard data - approaches in the line of matrix completion, collaborative filtering, reduction techniques for non-standard data - large scale network analysis IMPORTANT DATES Paper submission deadline : 29 November 2013 Notification of acceptance : 31 January 2014 Deadline for final papers : 21 February 2014 The ESANN 2014 conference : 23-25 April 2014 SPECIAL SESSION ORGANIZERS: Frank-Michael Schleif, University of Appl. Sc. Mittweida, Germany and University of Birmingham, Birmingham, UK Thomas Villmann, University of Appl. Sc. Mittweida, Germany Peter Tino, University of Birmingham, Birmingham, UK From jlam at bccn-tuebingen.de Thu Sep 12 10:18:52 2013 From: jlam at bccn-tuebingen.de (Judith Lam) Date: Thu, 12 Sep 2013 16:18:52 +0200 Subject: Connectionists: Bernstein Conference 2013 - Program & Registration Message-ID: <5231CD4C.2080509@bccn-tuebingen.de> ************************************************************* Bernstein Conference 2013, T?bingen September 25-27 ************************************************************* Workshops and PhD Symposium are booked out, however online registration for the main conference is still possible through September, 13 (23:59 PDT).(Onsite registration is possible with a service charge of 20.-Euro) Please check here for the program: Workshops September 24-25, 2013 --- http://www.bernstein-conference.de/workshops/ Main Conference September 25-27, 2013 --- http://www.bernstein-conference.de/program/ PhD Symposium September 28, 2013 --- http://www.bernstein-conference.de/phd/phd-schedule/ We look forward to seeing you in Tuebingen! -- Dr. Judith Lam Executive Coordinator Bernstein Center for Computational Neuroscience T?bingen Eberhard Karls University of T?bingen Max Planck Institute for Biological Cybernetics http://www.bccn-tuebingen.de/about-bccn/contact.html Otfried-M?ller-Str. 25, 72076 T?bingen Tel: +49 7071 29 89019 Fax: +49 7071 29 25015 -------------- next part -------------- An HTML attachment was scrubbed... URL: From holger.schwenk at lium.univ-lemans.fr Thu Sep 12 11:24:36 2013 From: holger.schwenk at lium.univ-lemans.fr (Holger Schwenk) Date: Thu, 12 Sep 2013 17:24:36 +0200 Subject: Connectionists: Four Postdoc or PhD positions, neural networks for statistical machine translation (LIUM, France) Message-ID: <5231DCB4.7050907@lium.univ-lemans.fr> Four Postdoc or PhD positions, neural networks for statistical machine translation (LIUM, France) ************ During the last years, there have been several breakthroughs in the use of neural networks for natural language processing, in particular deep learning. The computer science laboratory of the University of Le Mans (LIUM) is working since many years on statistical machine translation (SMT), and we were among the first researchers to successfully use neural networks, namely continuous space language and translation models. We want to substantially increase our research efforts in this area, hoping to achieve a significant advances in SMT. Our goal is to build state-of-the-art large scale SMT systems using neural networks. In this major research effort, we have openings for four postdoc students. Excellent PhD students will be also considered. The candidates are expected to have a very good knowledge of neural networks (feed-forward, recurrent NN, deep learning, etc). Knowledge in statistical machine translation is a plus, but not a necessary condition. Experience with efficient implementations of neural networks on GPU cards is highly appreciated. The positions are immediately available. Initial appointment is for one year, renewable for up to three years. Competitive salaries are available, including health care and other social benefits, travel support, etc. The working language is English or French. LIUM is participating in several international projects, financed by the European Commission, DARPA and the French government. We collaborate with leading research groups in USA and Europe. A large computer cluster is available to support the research (700 CPU cores with a total of 7 TBytes of memory and more than 130 TBytes of RAID disk space). We also own a cluster with 16 Tesla K20 GPU cards, connected by a fast Infiniband network. Le Mans is located in between Paris and the Atlantic ocean. Both can be reached in about 1 hour by high speed train. The Loire valley with many wineries and other attractions is just a short drive away ... Applications should include an CV, a list of publications and the name of two references. We will invite interesting candidates for further discussions. For more information, please contact Holger Schwenk by email: Holger.Schwenk at lium.univ-lemans.fr From mail at jan-peters.net Fri Sep 13 12:47:38 2013 From: mail at jan-peters.net (Jan Peters) Date: Fri, 13 Sep 2013 18:47:38 +0200 Subject: Connectionists: Review Papers on Robotic Reinforcement Learning Message-ID: <85739087-85A7-46A1-8A36-66B6745E1CF0@jan-peters.net> We have recently published several *exhaustive* review papers on Robotic Reinforcement Learning (and highly related issues). 1) A general review on Robotic Reinforcement Learning: Kober, J; Bagnell, D.; Peters, J. (2013). Reinforcement Learning in Robotics: A Survey, International Journal of Robotics Research, 32(11), pp. 1236?1272. http://www.ias.tu-darmstadt.de/uploads/Publications/Kober_IJRR_2013.pdf 2) A review on Policy Search in Robotics: Deisenroth, M.; Neumann, G; Peters, J. (2013). A Survey on Policy Search for Robotics, Foundations and Trends in Robotics, 21, pp. 388?403, doi: 10.1561/2300000021 http://www.ias.tu-darmstadt.de/uploads/Site/EditPublication/PolicySearchReview.pdf 3) A review on the use of models in Robot (Reinforcement) Learning: Nguyen-Tuong, D.; Peters, J. (2011). Model Learning in Robotics: a Survey, Cognitive Processing, 12(4), pp.319?340, doi: 10.1007/s10339-011-0404-1 http://robot-learning.de/pmwiki/uploads/Publications/Nguyen_CP_2011.pdf Any feedback -- or constructive reader comments would be highly appreciated! Best wishes, Jan Peters From manuel.lopes at inria.fr Fri Sep 13 03:59:45 2013 From: manuel.lopes at inria.fr (Manuel Lopes) Date: Fri, 13 Sep 2013 09:59:45 +0200 (CEST) Subject: Connectionists: Robotics and machine learning positions (engineers and postdocs) @ Inria, France In-Reply-To: <396216594.3524934.1370515373161.JavaMail.root@inria.fr> Message-ID: <1031470670.8170541.1379059185328.JavaMail.root@inria.fr> The Flowers Team at Inria and Ensta ParisTech (France) is seeking for highly motivated and talented engineers and postdocs interested in the following topics: * Machine Learning for Robotics * Human-Robot Collaboration and Interfaces * Motor control and skill learning * Personal robotics * Lifelong robot learning in the context of assistive robotics The Flowers team is a highly stimulating research environment which has been developing cutting edge research in autonomous robot learning and development, artificial curiosity, imitation learning of motor skills, human-robot adaptive interaction and robot language acquisition. Web: http://flowers.inria.fr We have currently multiple engineer and postdoc positions funded by several EU-FP7-ICT "Cognitive Systems, Interaction and Robotics" projects: * 3 year post-doc The candidate must have strong skills in mathematics, machine learning and control theory, and record of publications in relevant conferences (e.g. IROS, ICRA, RSS, NIPS) and journals (e.g. TRO, RAS, TAMD, IJRR, JMLR). Experience on active learning and reinforcement learning will be appreciated. * 3 year expert engineer in robotics Must have experience in robotics and be capable to conduct complex robotic experiments in an international collaborative project. Programming proficiency in C/C++ and Python. Expertise with real robot systems and the ROS system will be appreciated. * 3 year expert engineer in human-machine interface Must have experience in developing human-machine interfaces for augmented reality and interaction with virtual worlds. Programming proficiency in C/C++ and Python. The candidates will be involved in a european research project on human-robot collaboration, co-working and adaptive interaction. This will also involve close collaborations with several international laboratories, including the Intelligent Autonomous Systems Lab (IAS) at the Technical University of Darmstadt (TU Darmstadt), the Machine Learning & Robotics Lab (Univ. Stuttgart), and the Intelligent Systems group at the University of Innsbruck (Austria). To apply send a letter including: * detailed CV * course transcripts * motivation letter * internship reports Application should be sent by email to Manuel Lopes: manuel.lopes at inria.fr https://flowers.inria.fr/mlopes/ Flowers Team: http://flowers.inria.fr About Inria: http://www.inria.fr Inria is a major research institution at the international level in applied mathematics and computer sciences. Inria?s 3,400 researchers strive to invent the digital technologies of the future. The institute is dedicated to fundamental and applied research in information and communication science and technology (ICST) but also plays a major role in technology transfer by fostering training through research, disseminating scientific and technical information, and participating in international programs. Inria develops many partnerships with industry and fosters technology transfer and company foundation in the field of ICST - some ninety companies have been founded with the support of Inria Transfer, a subsidiary of Inria, specialized in guiding, evaluating, qualifying, and financing innovative high-tech IT start-up companies. Inria is involved in standardization committees such as the IETF, ISO and the W3C of which Inria was the European host from 1995 to 2002. Throughout its eight research centres located, Inria has a workforce of 3800 (2,800 of whom are scientists from Inria or from Inria?s partner organisations such as CNRS (the French National Centre for Scientific Research), universities and leading engineering schools). The researchers at Inria published over 4,800 articles in 2010. They are behind over 270 active patents and 105 start-ups. In 2010, Inria's budget came to 252.5 million euros, 26% of which represented its own resources. They work in 173 project-teams. Many Inria researchers are also professors who supervise around 1000 doctoral students, their theses work contributing to Inria research projects. Inria maintains important international relations and exchanges. In Europe, Inria is a member of ERCIM, which brings together research institutes from 19 European countries. Inria is a partner in about 120 FP6 actions and 128 FP7 actions, with 71 proposals in the ICST field. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ghio.alessandro at gmail.com Fri Sep 13 11:45:07 2013 From: ghio.alessandro at gmail.com (Alessandro Ghio) Date: Fri, 13 Sep 2013 17:45:07 +0200 Subject: Connectionists: "Byte the bullet: learning on real-world computing architectures" - ESANN 2014 Special Session Call for Papers Message-ID: <304331BD-741E-465D-AA41-CCC398F0E9CE@gmail.com> *** Apologies for cross posting *** ESANN 2014 Special Session - "Byte the bullet: learning on real-world computing architectures" - CALL FOR PAPERS European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2014). 23-25 April 2014, Bruges, Belgium - http://www.esann.org Submissions are invited for next year ESANN Special Session "Byte the bullet: learning on real-world computing architectures". Organizers: Davide Anguita, Alessandro Ghio, Luca Oneto University of Genoa (Italy) ESANN 2014 Special Session "Byte the bullet: learning on real-world computing architectures" webpage: http://btb.smartlab.ws ABSTRACT Fast, effective, reliable models: these are the desiderata of every theorist and practitioner. Machine Learning (ML) algorithms, proposed in the last decades, proved to be effective and reliable in solving complex real-world problems. A huge amount of work has been spent to properly reformulate or revise these techniques, which are usually designed without taking into account the destination computing architecture, in order to make them run as fast as possible. This effort is often motivated by application-specific requirements, such as the need to accelerate the learning process with dedicated/distributed hardware (e.g. cloud computing) or to foster energy-sparing requirements of applications based on mobile standalone devices (e.g. smartphones, sensor networks). Contemplating the destination computing architecture influences overall performance, but can also be exploited for implementation benefits: it is the case of quantum computing, and of recent advances in ML showing how the generalization capability of learnt models can take advantage of computational constraints in learning. TOPICS In this special session, we would like to encourage submissions related to the development and the application of fast, effective, reliable techniques, which consider possibilities, potentialities and constraints of real-world computing architectures as basic cornerstones and motivations. This list includes (despite not being limited to): Bit-based models (e.g. trained with quantum computing approaches, Weightless Neural Networks) & their applications (e.g. sensor networks) Learning on dedicated architectures (e.g. GPU) Linear & sub-linear ML algorithms for High-Performance Computing Learning on large, distributed and cloud architectures. SUBMISSION & IMPORTANT DATES We kindly invite you to submit a paper to this special session. Each paper will undergo to a peer reviewing process for its acceptance. Paper submission should be done exclusively through the ESANN portal following the instructions provided in: (http://www.elen.ucl.ac.be/esann/index.php?pg=submission). Paper submission deadline : 29 November 2013 Notification of acceptance : 31 January 2014 Deadline for final papers : 21 February 2014 ESANN 2014 conference : 23-25 April 2014 NOTES You can find details about the special session at http://btb.smartlab.ws. If you have any questions concerning the special session, please do not hesitate to contact us via email to: btb at smartlab.ws More information about the Conference Program, accommodation facilities and registration fees is available on the ESANN website www.esann.org --- Dr. Alessandro Ghio, Ph.D. DITEN - University of Genoa Via Opera Pia 11a, I-16145 Genoa (Italy) T. +39-(0)10-3532192 F. +39-(0)10-3532897 @ Alessandro.Ghio at smartlab.ws W http://smartlab.ws/ --- -------------- next part -------------- An HTML attachment was scrubbed... URL: From sturaga at gatsby.ucl.ac.uk Sat Sep 14 11:16:19 2013 From: sturaga at gatsby.ucl.ac.uk (Srini Turaga) Date: Sat, 14 Sep 2013 16:16:19 +0100 Subject: Connectionists: NIPS 2013 Workshop on "Acquiring and analyzing the activity of large neural ensembles" Message-ID: <56F9844B-0DA9-43D0-83C4-D3CA7BC3D89D@gatsby.ucl.ac.uk> ******************************************************************* NIPS 2013 Workshop Announcement "Acquiring and analyzing the activity of large neural ensembles" http://www.bccn-tuebingen.de/events/nips-workshop-2013.html Lake Tahoe, Nevada, United States 10th December, 2013 with partial support from Bernstein Center for Computational Neuroscience, T?bingen, Germany ******************************************************************* For many years, measurements of neural activity have either been restricted to recordings from single neurons or a very small number of neurons, and anatomical reconstructions to very sparse and incomplete neural circuits. Major advances in optical imaging (e.g. 2-photon and light-sheet microscopic imaging of calcium signals) and new electrode array technologies are now beginning to provide measurements of neural activity at an unprecedented scale. High-profile initiatives such as BRAIN (Brain Research through Advancing Innovative Neurotechnologies) will fuel the development of ever more powerful techniques for mapping the structure and activity of neural circuits. Computational tools will be important to both the high-throughput acquisition of these large-scale datasets and in the analysis. Acquiring, analyzing and integrating these sources of data raises major challenges and opportunities for computational neuroscience and machine learning: ? What kind of data will be generated by large-scale functional measurements in the next decade? How will it be quantitatively or qualitatively different to the kind of data we have had previously? ? Algorithmic methods have played an important role in data acquisition, e.g. spike-sorting algorithms or spike-inference algorithms from calcium traces. In the future, what role will computational tools play in the process of high-throughput data acquistion? ? One of the key-challenges is to link anatomical with functional data -- what computational analysis tools will help in providing a link between these two disparate source of data? What can we learn by measuring ?functional connectivity?? ? What have we really learned from high-dimensional recordings that is new? What will we learn? What theories could we test, if only we had access to recordings from more neurons at the same time? We have invited scientists whose research addresses these questions including prominent technologists, experimental neuroscientists, theorists and computational neuroscientists. We foresee active discussions amongst this multi-disciplinary group of scientists to catalyze exciting new research and collaborations. Confirmed speakers include: ? Terry Sejnowski, Salk Institute (Keynote) ? Misha Ahrens, HHMI Janelia Farm Research Campus ? Mitya Chklovskii, HHMI Janelia Farm Research Campus ? Konrad Koerding, Northwestern University ? Jonathan Pillow, University of Texas at Austin ? Andreas Tolias, Baylor College of Medicine ? Joshua Vogelstein, Duke University Submission details: We invite abstract submissions for poster presentation at the workshop. Please submit abstracts (1 page max in pdf format) by email to neuralensembles at gmail.com by October 9th, 2013. Important dates: Abstract submission deadline (for poster presentations): October 9th, 2013 Acceptance for poster presentation will be announced by October 23th, 2013 Organizing Committee: ? Srini Turaga (Gatsby Unit & WIBR, University College London) ? Lars B?sing (Gatsby Unit, University College London) ? Maneesh Sahani (Gatsby Unit, University College London) ? Jakob Macke (Max Planck Institute for Biological Cybernetics and Bernstein Center for Computational Neuroscience, T?bingen, Germany) From ajyu at ucsd.edu Mon Sep 16 15:34:20 2013 From: ajyu at ucsd.edu (Angela Yu) Date: Mon, 16 Sep 2013 12:34:20 -0700 Subject: Connectionists: Postdoc and PhD positions at UCSD (Angela Yu) In-Reply-To: References: Message-ID: <2CA8167A-7CAE-47DD-99EF-EB5EBDF6FAC2@ucsd.edu> Post-doctoral Applicants Applications are invited for a postdoctoral position in the Computational Cognitive Neuroscience Lab, led by Angela Yu, at University of California, San Diego. Initial appointment is for one year, with flexible start date and possibility of renewal. The project is to develop a decision-theoretical framework for the inter-related problems of perceptual decision-making, active sensing, active learning, and social decision-making. Candidates must have a strong mathematical and modeling background in Bayesian statistics, reinforcement learning, machine learning, and control theory. Experience with measure-theoretic probability theory, stochastic processes, stochastic control theory (stopping problems, bandit problems, sequential decision problems), and/or dynamical systems analysis is also desirable. Applicants should be committed to applying rigorous mathematical tools to modeling cognitive and neural processes, as well as carrying out human behavioral experiments and collaborating with other human/animal neuroscience laboratories. Research experience with behavioral experiments and fMRI neuroimaging, and/or data analysis for search experiments, is a bonus. Dr. Yu's lab is situated within the Natural Computation Lab in the Cognitive Science department of UCSD. It is affiliated with the Computer Science Department, the Temporal Dynamics of Learning Center, the UCSD Neurosciences Graduate Program, and the Institute of Neural Computation. It provides ample opportunities for collaboration with related labs across the UCSD main campus, the medical school, and the Salk Institute. Interested candidates should send a research statement, along with a CV including publications, to Dr. Angela Yu (ajyu at ucsd.edu). Two or more letters of references should be sent directly to the same address. PhD Applicants Interested PhD applicants should apply through the UCSD Department of Cognitive Science PhD Program. Dr. Yu may also advise PhD students from the Neurosciences Graduate Program, Department of Computer Science and Engineering, and the Department of Electrical and Computer Engineering. PhD applicants should have strong mathematical and computational training, fluency in Matlab programming (or equivalent), as well as coureswork in psychology, cognitive science, and/or neuroscience. Research experience in behavioral experiments or fMRI brain imaging would be a bonus. Applicants should be committed to applying rigorous, quantitative tools to modeling cognitive and neural processes, as well as carrying out human behavioral experiments and/or collaborating with other human or animal resesarch laboratories. --------------------------------------------------------- Angela J. Yu Assistant Professor Department of Cognitive Science UCSD, Mail Code 0515 9500 Gilman Drive La Jolla, CA 92093-0515 Email: ajyu at ucsd.edu Phone: 858-822-3317 Fax: 858-534-1128 Website: www.cogsci.ucsd.edu/~ajyu --------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From Colin.Wise at uts.edu.au Sun Sep 15 23:46:13 2013 From: Colin.Wise at uts.edu.au (Colin Wise) Date: Mon, 16 Sep 2013 13:46:13 +1000 Subject: Connectionists: AAI Short Course - 'Data Mining - an Introduction' - Wednesday 9 October 2013 Message-ID: <8112393AA53A9B4A9BDDA6421F26C68A01410958D8B3@MAILBOXCLUSTER.adsroot.uts.edu.au> Dear Colleague, AAI Short Course - 'Data Mining - an Introduction' - Wednesday 9 October 2013 https://shortcourses-bookings.uts.edu.au/Clientview/Schedules/ScheduleDetail.aspx?ScheduleID=1357 Our AAI short course 'Data Mining - an Introduction' may be of interest to you and or others in your organisation or network. The Data Mining short course is an introduction to the foundations of data mining and knowledge discovery methods and their application to practical problems. It brings together the state-of-the-art research and practical techniques in data mining. Please register here LINK An important foundation short course in the AAI series of advanced data analytic short courses - please view this short course and others here LINK We are happy to discuss at your convenience. Thank you and regards. Colin Wise Operations Manager Advanced Analytics Institute (AAI) Blackfriars Building 2, Level 1 University of Technology, Sydney (UTS) Email: Colin.Wise at uts.edu.au Tel. +61 2 9514 9267 M. 0448 916 589 AAI: www.analytics.uts.edu.au/ Reminder - AAI Short Course - Advanced Data Analytics - an Introduction - Tuesday 19 November 2013 Future short courses on Data Analytics and Big Data may be viewed at LINK AAI Education and Training Short Courses Survey - you may be interested in completing our AAI Survey at LINK AAI June 2013 Newsletter LINK AAI Email Policy - should you wish to not receive this periodic communication on Data Analytics Learning please reply to our email (to sender) with UNSUBSCRIBE in the Subject. We will delete you from our database. Thank you for your past and future support. UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any accompanying attachments may contain confidential information. If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or attachments. If you have received this message in error, please notify the sender immediately and delete this message. Any views expressed in this message are those of the individual sender, except where the sender expressly, and with authority, states them to be the views of the University of Technology Sydney. Before opening any attachments, please check them for viruses and defects. Think. Green. Do. Please consider the environment before printing this email. -------------- next part -------------- An HTML attachment was scrubbed... URL: From bernabe at imse-cnm.csic.es Mon Sep 16 06:54:16 2013 From: bernabe at imse-cnm.csic.es (bernabe) Date: Mon, 16 Sep 2013 11:54:16 +0100 Subject: Connectionists: PostDoc in Neuromorphic Engineering at Sevilla Microelectronics Institute Message-ID: <5236E358.20907@imse-cnm.csic.es> Apologies for cross-posting ------------------------------------- The Neuromorphic Group at the Sevilla Microelectronics Institute is seeking a Post-Doc for working at Event-Driven Neuromorphic Systems, with strong emphasis on hardware (chips, FPGAs, interfacing to other systems such as SpiNNaker), focusing on event-driven vision sensing as well as high-level processing (such as object recognition). Gross salary is in the order of 28,000 euros per year. Starting date would be as soon as possible (after all bureaucratic clearances) but is negotiable. Interested candidates, please contact me at bernabe at imse-cnm.csic.es. Please distribute this announcement. Best wishes, Bernabe -- -- ------------------------------------------------------------------------- Bernabe Linares-Barranco, PhD, IEEE Fellow Full Professor (Profesor de Investigacion) CSIC Instituto Microelectronica Sevilla (IMSE) Phone: 34-954-466643/66 National Microelectronics Center, CNM-CSIC Fax: 34-954-466600 Av. Americo Vespucio s/n E-mail: Bernabe.Linares(AT)imse-cnm.csic.es 41092 Sevilla, SPAIN URL: http://www.imse-cnm.csic.es/~bernabe ------------------------------------------------------------------------- From grlmc at urv.cat Sat Sep 14 13:39:03 2013 From: grlmc at urv.cat (GRLMC) Date: Sat, 14 Sep 2013 19:39:03 +0200 Subject: Connectionists: LATA 2014: 3rd call for papers Message-ID: *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* ************************************************************************* 8th INTERNATIONAL CONFERENCE ON LANGUAGE AND AUTOMATA THEORY AND APPLICATIONS LATA 2014 Madrid, Spain March 10-14, 2014 Organized by: Research Group on Implementation of Language-Driven Software and Applications (ILSA) Complutense University of Madrid Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/lata2014/ ********************************************************************* AIMS: LATA is a yearly conference on theoretical computer science and its applications. Following the tradition of the diverse PhD training events in the field developed at Rovira i Virgili University in Tarragona since 2002, LATA 2014 will reserve significant room for young scholars at the beginning of their career. It will aim at attracting contributions from both classical theory fields and application areas (bioinformatics, language technology, artificial intelligence, etc.). VENUE: LATA 2014 will take place in Madrid, the capital of Spain. The venue will be the School of Informatics of Complutense University. SCOPE: Topics of either theoretical or applied interest include, but are not limited to: algebraic language theory algorithms for semi-structured data mining algorithms on automata and words automata and logic automata for system analysis and programme verification automata, concurrency and Petri nets automatic structures cellular automata codes combinatorics on words compilers computability computational complexity data and image compression decidability issues on words and languages descriptional complexity DNA and other models of bio-inspired computing digital libraries and document engineering foundations of finite state technology foundations of XML fuzzy and rough languages grammars (Chomsky hierarchy, contextual, unification, categorial, etc.) grammatical inference and algorithmic learning graphs and graph transformation language varieties and semigroups language-based cryptography language-theoretic foundations of artificial intelligence and artificial life natural language and speech automatic processing parallel and regulated rewriting parsing patterns power series quantum, chemical and optical computing semantics string and combinatorial issues in computational biology and bioinformatics string processing algorithms symbolic dynamics symbolic neural networks term rewriting transducers trees, tree languages and tree automata weighted automata STRUCTURE: LATA 2014 will consist of: invited talks invited tutorials peer-reviewed contributions INVITED SPEAKERS: Javier Esparza (Munich Tech, DE), On Trees and Fixed Point Equations (tutorial) Leslie A. Goldberg (Oxford, UK), The Complexity of Approximate Counting Oscar H. Ibarra (Santa Barbara, US), tba Sanjeev Khanna (Philadelphia, US), tba Helmut Seidl (Munich Tech, DE), tba PROGRAMME COMMITTEE: Dana Angluin (Yale, US) Eugene Asarin (Paris Diderot, FR) Jos Baeten (Amsterdam, NL) Christel Baier (Dresden, DE) Jan Bergstra (Amsterdam, NL) Jin-Yi Cai (Madison, US) Marek Chrobak (Riverside, US) Andrea Corradini (Pisa, IT) Mariangiola Dezani (Turin, IT) Ding-Zhu Du (Dallas, US) Michael R. Fellows (Darwin, AU) J?rg Flum (Freiburg, DE) Nissim Francez (Technion, IL) J?rgen Giesl (Aachen, DE) Annegret Habel (Oldenburg, DE) Kazuo Iwama (Kyoto, JP) Sampath Kannan (Philadelphia, US) Ming-Yang Kao (Northwestern, US) Deepak Kapur (Albuquerque, US) Joost-Pieter Katoen (Aachen, DE) S. Rao Kosaraju (Johns Hopkins, US) Evangelos Kranakis (Carleton, CA) Gad M. Landau (Haifa, IL) Andrzej Lingas (Lund, SE) Jack Lutz (Iowa State, US) Ian Mackie (?cole Polytechnique, FR) Carlos Mart?n-Vide (Tarragona, ES, chair) Giancarlo Mauri (Milan, IT) Faron G. Moller (Swansea, UK) Paliath Narendran (Albany, US) Enno Ohlebusch (Ulm, DE) Helmut Prodinger (Stellenbosch, ZA) Jean-Fran?ois Raskin (Brussels, BE) Wolfgang Reisig (Humboldt Berlin, DE) Marco Roveri (Bruno Kessler, Trento, IT) Micha?l Rusinowitch (LORIA, Nancy, FR) Yasubumi Sakakibara (Keio, JP) Davide Sangiorgi (Bologna, IT) Colin Stirling (Edinburgh, UK) Jianwen Su (Santa Barbara, US) Jean-Pierre Talpin (IRISA, Rennes, FR) Andrzej Tarlecki (Warsaw, PL) Rick Thomas (Leicester, UK) Sophie Tison (Lille, FR) Rob van Glabbeek (NICTA, Sydney, AU) Helmut Veith (Vienna Tech, AT) ORGANIZING COMMITTEE: Adrian Horia Dediu (Tarragona) Ana Fern?ndez-Pampill?n (Madrid) Carlos Mart?n-Vide (Tarragona, co-chair) Antonio Sarasa (Madrid) Jos?-Luis Sierra (Madrid, co-chair) Bianca Truthe (Magdeburg) Florentina Lilica Voicu (Tarragona) SUBMISSIONS: Authors are invited to submit non-anonymized papers in English presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (including eventual appendices) and should be formatted according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0). Submissions have to be uploaded to: https://www.easychair.org/conferences/?conf=lata2014 PUBLICATIONS: A volume of proceedings published by Springer in the LNCS series will be available by the time of the conference. A special issue of a major journal will be later published containing peer-reviewed extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation. REGISTRATION: The period for registration is open from July 15, 2013 to March 10, 2014. The registration form can be found at: http://grammars.grlmc.com/lata2014/Registration.php DEADLINES: Paper submission: October 14, 2013 (23:59 CET) Notification of paper acceptance or rejection: November 25, 2013 Final version of the paper for the LNCS proceedings: December 2, 2013 Early registration: December 9, 2013 Late registration: February 24, 2014 Starting of the conference: March 10, 2014 End of the conference: March 14, 2014 Submission to the post-conference journal special issue: June 14, 2014 QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu at urv.cat POSTAL ADDRESS: LATA 2014 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34-977-559543 Fax: +34-977-558386 ACKNOWLEDGEMENTS: Departament d?Economia i Coneixement, Generalitat de Catalunya Universidad Complutense de Madrid Universitat Rovira i Virgili From tomas.hromadka at gmail.com Sun Sep 15 18:04:49 2013 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Mon, 16 Sep 2013 00:04:49 +0200 Subject: Connectionists: COSYNE 2014: Meeting Announcement and Call for Abstracts (abstract deadline Nov 18 2013) Message-ID: <52362F01.5010808@gmail.com> ================================================================== Computational and Systems Neuroscience (Cosyne) MAIN MEETING WORKSHOPS Feb 27 - Mar 2, 2014 Mar 3 - Mar 4, 2014 Salt Lake City, Utah Snowbird Ski Resort, Utah http://www.cosyne.org ================================================================== The annual Cosyne meeting provides an inclusive forum for the exchange of empirical and theoretical approaches to problems in systems neuroscience, in order to understand how neural systems function. The MAIN MEETING is single-track. A set of invited talks are selected by the Executive Committee, and additional talks and posters are selected by the Program Committee, based on submitted abstracts. The WORKSHOPS feature in-depth discussion of current topics of interest, in a small group setting. Cosyne topics include but are not limited to: neural coding, natural scene statistics, dendritic computation, neural basis of persistent activity, nonlinear receptive field mapping, representations of time and sequence, reward systems, decision-making, synaptic plasticity, map formation and plasticity, population coding, attention, and computation with spiking networks. This year we would like to foster increased participation from experimental groups as well as computational ones. Please circulate widely and encourage your students and postdocs to apply. IMPORTANT DATES: Abstract submission opens: 07 Oct 2013 Abstract submission deadline: 18 Nov 2013 INVITED SPEAKERS: Rui Costa (Champalimaud) Catherine Dulac (Harvard) Joshua Gold (U Pennsylvania) Thomas Jessell (Columbia) John Krakauer (Johns Hopkins) Jeffrey Magee (Janelia Farm) Thomas Mrsic-Flogel (Universitat Basel) Yael Niv (Princeton) Elad Schneidman (Weizmann Institute) Doris Tsao (Caltech) Nachum Ulanovsky (Weizmann Institute) Linda Wilbrecht (UC Berkeley) When preparing an abstract, authors should be aware that not all abstracts can be accepted for the meeting, due to space constraints. Abstracts will be selected based on the clarity with which they convey the substance, significance, and originality of the work to be presented. ORGANIZING COMMITTEE: General Chairs: Marlene Cohen (U Pittsburgh) and Peter Latham (UCL) Program Chairs: Michael Long (NYU) and Stephanie Palmer (U Chicago) Workshop Chairs: Robert Froemke (NYU) and Tatyana Sharpee (Salk) Publicity Chair: Eugenia Chiappe (Champalimaud) EXECUTIVE COMMITTEE: Anne Churchland (CSHL) Zachary Mainen (Champalimaud) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) From jkrichma at uci.edu Mon Sep 16 21:30:53 2013 From: jkrichma at uci.edu (Jeff Krichmar) Date: Mon, 16 Sep 2013 18:30:53 -0700 Subject: Connectionists: Invitation to Irvine workshop on modeling and neuroscience Message-ID: <60AD6ABC-ED38-4B97-8A84-C9CE70D23A29@uci.edu> Workshop on Interfacing Models with Brain Signals to Investigate Cognition The Department of Cognitive Sciences at the University of California, Irvine is pleased to announce the first workshop on Interfacing Models with Brain Signals to Investigate Cognition, to be held in Irvine, CA, on November 7, 2013. The workshop is scheduled close in time and place to the 43rd annual meeting of the Society for Neuroscience, which will take place in nearby San Diego from 9-13 November. The topic of the workshop is the intersection of neuroscience and cognitive modeling. Its goal is to explore and exploit the mutual contributions the two fields can make to one another, and how we can fruitfully integrate both. The workshop will feature presentations by a number of experts in the fields of cognitive modeling and neuroscience. It is a full-day workshop, taking place on UC Irvine?s beautiful campus, and it is open to all and free to attend, but registration is required. In addition to spoken presentations, the workshop will host a poster session to which all contributions relevant to the intersection between formal modeling and neuroscience are invited. The experts who will present at the workshop are Will Alexander (University of Ghent), Nathaniel Daw (NYU), Birte Forstmann and Eric-Jan Wagenmakers (University of Amsterdam), Mimi Liljeholm (UC Irvine), David Noelle (UC Merced), Thomas Palmeri (Vanderbilt University), Roger Ratcliff (Ohio State University), John Serences (UC San Diego), and Brandon Turner (Stanford University). You are cordially invited, Joachim Vandekerckhove (joachim at uci.edu) Jeff Krichmar (jkrichma at uci.edu) Ramesh Srinivasan (r.srinivasan at uci.edu) Announcement: http://bit.ly/1ez8qIl Workshop website: http://sites.uci.edu/ws13 Registration website: https://cnm13.eventbrite.com/ To contribute a poster: joachim at uci.edu Time and place: UCI campus, SBSG 1517, 9:00am-6:00pm -- 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 -------------- next part -------------- An HTML attachment was scrubbed... URL: From neurogirl at hotmail.com Tue Sep 17 10:39:31 2013 From: neurogirl at hotmail.com (neuro girl) Date: Tue, 17 Sep 2013 10:39:31 -0400 Subject: Connectionists: =?cp1256?q?neural_coding_and_neuroprosthetics_lab?= =?cp1256?q?=FE?= Message-ID: Hey guys - I have a couple of openings in my lab, one for a programmer and one for a postdoc.Take a look if you might be interested: Postdoctoral fellow:Are you interested in upper-limb neuroprosthetics? Do you have experience with non-human primates? Do you have experience with chronically implanted electrode arrays? Do you have mad MATLAB skills? Do you like/love math? Are you reasonably personable? If you?ve responded affirmatively to most or all of these questions, read on? One of the objectives of the lab is to develop ways to convey somatosensory feedback through intracortical microstimulation in a non-human primate model. Our approach consists of training Rhesus macaques to perform sensory tasks based on natural stimulation, and assessing whether they can perform these same tasks based on electrical stimulation of their somatosensory cortices. You can check us out at http://bensmaialab.uchicago.edu . There is also a write up on us at http://theinstitute.ieee.org/technology-focus/technology-topic/prosthetic-limbs-offer-a-sense-of-touch. We are looking for a postdoctoral scholar to keep pushing this exciting work forward. What do you think? Candidates with a completed PhD degree in neuroscience, biomedical engineering or a related field are encouraged to apply. Send a vitae and a brief and sincere statement of purpose to sliman at uchicago.edu.Programmer:Neuroscience and neuroprosthetics lab is seeking a research assistant with extensive experience with computer programming. This individual would be responsible for interfacing the various machines in the lab (sensors, motors, data acquisition systems, etc.) with computers and with each other to run neurophysiological and behavioral experiments with human and non-human primates. BS in computer science or engineering required. Would prefer an individual who could commit for several years. One of the objectives of the lab is to discover the neural basis of somatosensation: How to patterns of activation in the nerve and in the brain mediate out ability to feel objects by touch and sense the position and movements of our limbs in space? Another objective of the lab is to develop ways to convey somatosensory feedback through intracortical microstimulation. You can check us out at http://bensmaialab.uchicago.edu. There is also a write up on us at http://theinstitute.ieee.org/technology-focus/technology-topic/prosthetic-limbs-offer-a-sense-of-touch.Please contact sliman at uchicago.edu with a CV and a brief statement of purpose. -- ________________________________________________________ Sliman Bensmaia Assistant Professor Department of Organismal Biology and AnatomyUniversity of Chicago 773.834.5203 http://bensmaialab.uchicago.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From benoit.frenay at uclouvain.be Tue Sep 17 01:27:58 2013 From: benoit.frenay at uclouvain.be (=?ISO-8859-1?Q?Beno=EEt_Fr=E9nay?=) Date: Tue, 17 Sep 2013 07:27:58 +0200 Subject: Connectionists: Special session on "Label noise in classification" at ESANN 2014 Message-ID: <5237E85E.9060805@uclouvain.be> [Apologies if you receive multiple copies of this CFP] *Call for papers: special session on "***Label noise in classification*" at **ESANN 2014* European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2014). 23-25 April 2014, Bruges, Belgium - http://www.esann.org *DESCRIPTION*: In classification, it is difficult to obtain completely reliable labels. Indeed, labels are often polluted by label noise, due to e.g. insufficient information or expert mistakes. Many works have tackled the problem of learning in the presence of label noise. Filtering methods have been developed to detect and remove mislabelled instances. Also, recent approaches attempt to take label noise into account while learning, using e.g. probabilistic models of label noise or prior knowledge about the influence of label noise on specific methods. Other settings like e.g. semi-supervised learning have also been studied. This special session aims to provide a forum where researchers could discuss the most recent developments in the field of label noise. Contributions should propose new methods to deal with label noise, new applications where label noise must be taken into account, theoretical results about learning in the presence of label noise or experimental results which provide insight about existing methods. Examples of topics of interest include (but are not limited to) the following: * when are noisy labels better than no labels at all? * what makes a classifier robust to label noise? * dealing with different types of label noise (random, non-random, malicious, or adversarial) * conditions for the consistency of classification in the presence of label noise * label noise in high dimensional small sample settings * the issue of model order selection in the presence of label noise * feature selection and dimensionality reduction in the presence of label noise * label-noise aware classification algorithms in static and dynamic scenarios * learning with side information to counter label noise * SUBMISSION: * Prospective authors must submit their paper through the ESANN portal following the instructions provided in http://www.elen.ucl.ac.be/esann/index.php?pg=submission. Each paper will undergo a peer reviewing process for its acceptance. Authors should send as soon as possible an e-mail with the tentative title of their contribution to the special session organisers.* IMPORTANT DATES**:* Paper submission deadline : 29 November 2013 Notification of acceptance : 31 January 2014 The ESANN 2014 conference : 23-25 April 2014 * SPECIAL SESSION ORGANISERS**:* Dr. Beno?t Fr?nay Universit? catholique de Louvain, Belgium E-mail: benoit.frenay at uclouvain.be Phone: +32 10 478133 Dr. Ata Kaban University of Birmingham, United Kingdom E-mail: A.Kaban at cs.bham.ac.uk Phone: +44 121 41 42792 -------------- next part -------------- An HTML attachment was scrubbed... URL: From S.M.Bohte at cwi.nl Tue Sep 17 09:17:31 2013 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Tue, 17 Sep 2013 15:17:31 +0200 Subject: Connectionists: CFP "Advances in Spiking Neural Information Processing Systems" - ESANN 2014 Special Session Call for Papers Message-ID: *** Apologies for cross posting *** *ESANN** 2014 Special Session - "**Advances in Spiking Neural Information Processing Systems (SNIPS)**" - CALL FOR PAPERS** * European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2014). 23-25 April 2014, Bruges, Belgium - *http://www.esann.org* ------------------------------ Submissions are invited for next year ESANN Special Session "Advances in Spiking Neural Information Processing Systems (SNIPS)". *Organizers*: Sander Bohte (CWI, The Netherlands) Andr? Gr?ning (University of Surrey, United Kingdom) *ABSTRACT* Spiking neural networks have been heralded as "the third generation" of neural networks quite a while ago already. Over the last decade, various spiking neural network models have been proposed, alongside a similar increasing interest in spiking models of computation in computational neuroscience. Still, state-of-the-art neural networks, like deep learning models, are based on traditional neural networks. In this special session, we want to bring together advances in spiking neural networks that challenge, or go beyond, the current state-of-the-art in neural networks. *TOPICS* In this special session, we are looking to bring together researchers interested in developing and applying learning algorithms for spiking neural networks that ? make use of learning, ? are supervised or unsupervised, ? aim to be biologically plausible, ? aim to be cognitively plausible or ? aim to be technically efficient. Examples of such work could include probabilistic, efficient, logical and/or dynamical spiking computation. *SUBMISSION & IMPORTANT DATES* We kindly invite you to submit a paper to this special session. Each paper will undergo to a peer reviewing process for its acceptance. Paper submission should be done exclusively through the ESANN portal following the instructions provided in: (http://www.elen.ucl.ac.be/esann/*)*. Kind regards, Sander Bohte and Andr? Gr?ning -- ============================= Dr Sander M. Bohte CWI Amsterdam, Dept Life Sciences PI Dynamical Neural Processing http://www.cwi.nl/~sbohte tel +31-205924074 -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Tue Sep 17 14:52:59 2013 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 17 Sep 2013 14:52:59 -0400 Subject: Connectionists: NEURON course at SFN 2013 Meeting Message-ID: <5238A50B.4080208@yale.edu> Space is still available in the NEURON course that will be presented on Friday, November 8, as a satellite session to this year's SFN meeting in San Diego. This course is designed to provide --an executive summary for PIs who need to decide whether NEURON would be useful for their research --a time-saving introduction for new NEURON users who need an introduction to NEURON's powerful tools for constructing and using models, and would benefit by seeing the typical workflow involved in implementing models --a quick refresher and update for established NEURON users who might have missed something in a prior course, or want to find out what's new (for example, reaction-diffusion via Python) If this sounds good to you, sign up now because space is limited, and the registration deadline is October 25, just a bit more than a month away, and on-site registration will not be accepted. For more information and the online registration form, see http://www.neuron.yale.edu/neuron/static/courses/sd2013/sd2013.html --Ted From ranzato at cs.toronto.edu Tue Sep 17 12:48:02 2013 From: ranzato at cs.toronto.edu (Marc'Aurelio Ranzato) Date: Tue, 17 Sep 2013 12:48:02 -0400 (EDT) Subject: Connectionists: IJCV: special issue on Deep Learning Message-ID: Dear Colleague, We are pleased to announce that the International Journal of Computer Vision will have a special issue on Deep Learning. We welcome submissions on any topic related to deep learning and feature learning applied to vision. The submission deadline is February 9th, 2014. For more information, please see the attached call for papers. Best regards, Marc'Aurelio Ranzato Geoffrey Hinton Yann LeCUn -------------- next part -------------- A non-text attachment was scrubbed... Name: cfp_ijcv_si_deeplearning.pdf Type: application/pdf Size: 97857 bytes Desc: URL: From j.m.mooij at uva.nl Wed Sep 18 09:31:20 2013 From: j.m.mooij at uva.nl (Joris Mooij) Date: Wed, 18 Sep 2013 15:31:20 +0200 Subject: Connectionists: Fully funded PhD position at the University of Amsterdam in causal discovery with applications in biology Message-ID: <20130918133119.GB8687@zaphod.jorismooij.nl> The Informatics Institute at the University of Amsterdam invites applications for a fully funded position for a PhD student in the area causal discovery with applications in biology. The position is within the Intelligent Autonomous Systems (IAS) Group, led by Prof. Dr. Max Welling, and will be supervised by Dr. Joris Mooij. Application closing date: October 16, 2013 Starting date: January 1, 2014 (later starting date is possible) Duration: 4 years The research will focus on the development of new theory and efficient algorithms for robust discovery of causal relationships and estimation of causal effects from data, with a strong focus on applications in molecular biology (for example, using gene or protein expression data). Applicants must have a master's degree in computer science, mathematics, physics, artificial intelligence or a closely related area. In addition, a successful candidate should have: * excellent math skills. * good programming skills in at least one of the following languages: C++, MatLab, R or Python. * good knowledge of modern machine learning methods (specific knowledge of Bayesian methods, probabilistic graphical modeling or causal discovery methods is a plus). * excellent oral and written communication skills. * commitment and a cooperative attitude. The successful candidate will be based in the Intelligent Systems Lab Amsterdam (ISLA) within the Informatics Institute at the University of Amsterdam. The institute was recently ranked among the top 50 computer science departments in the world by the 2011 QS World University IT Rankings. ISLA consists of 20 members of faculty, 20 post-doctoral researchers, and more than 50 PhD students. Members of the lab are actively pursuing a variety of research initiatives, including machine learning, decision-theoretic planning and learning, causal discovery, multi-agent systems, human-computer-interaction, natural language processing, information retrieval, and computer vision. Conditions of employment ------------------------ Based on a full-time appointment (38 hours per week) the gross monthly salary will range from ?2,083.-- in the first year to ?2,664.-- in the last year. There are also secondary benefits, such as 8% holiday allowance per year and the end of year allowance of 8.3%. The Collective Employment Agreement (CAO) of the Dutch Universities is applicable. Some of the things we have to offer: * competitive pay and excellent benefits * extremely friendly working environment * high-level of interaction * location near the city center (10 minutes by bicycle) of one of Europe's most beautiful and lively cities * international environment (10+ nationalities in the group) * access to high-end computing facilities (cluster with 4,000+ cores) * brand-new building. Since Amsterdam is a very international city where almost everybody speaks and understands English, candidates need not be afraid of the language barrier. Additional information ---------------------- For further information, including instructions on submitting an application, see the official job ad at: http://www.uva.nl/en/about-the-uva/working-at-the-uva/vacancies/item/13-296.html Informal inquiries can be made by email to Joris Mooij (j.m.mooij at uva.nl). From benoit.frenay at uclouvain.be Wed Sep 18 07:59:20 2013 From: benoit.frenay at uclouvain.be (=?ISO-8859-1?Q?Beno=EEt_Fr=E9nay?=) Date: Wed, 18 Sep 2013 13:59:20 +0200 Subject: Connectionists: Neurocomputing Special Issue: Advances in Learning with Label Noise Message-ID: <52399598.4080303@uclouvain.be> [Apologies if you receive multiple copies of this CFP] *Call for Papers: Neurocomputing Special Issue on "Advances in Learning with Label Noise**" * *_AIMS AND SCOPE_* Label noise is an important issue in classification. It is both expensive and difficult to obtain completely reliable labels, yet traditional classifiers expect a perfectly labelled training set. In real-world data sets, however, the labels available often contain mistakes. Mislabelling may occur for several reasons, including lack of information, speedy labelling by non-experts, the subjective nature of class memberships, expert errors, and communication problems. Furthermore, label noise may take several different forms -- for instance, labelling errors may occur at random, or may depend on particular values of the data features, or they may be adversarial. Errors may affect all data classes equally or asymmetrically. A large body of literature exists on the effects of label noise, which shows that mislabelling may detrimentally affect the classification performance, the complexity of the learned models, and it may impair pre-processing tasks such as feature selection. Many methods have been proposed to deal with label noise. Filter approaches aim at identifying and removing any mislabelled instances. Label noise sensitive algorithms aim at dealing with label noise during learning, by modelling the process of label corruption as part of modelling the data. Some methods have been modified to take label noise into account in an embedded fashion. The current literature on learning with label noise is a lively mixture of theoretical and experimental studies which clearly demonstrate both the complexity and the importance of the problem. Dealing with mislabelled instances needs to be flexible enough to accommodate label uncertainty, yet constrained enough to guide the learning process in its decisions regarding when to trust the label and when to trust the classifier. This special issue aims to stimulate new research in the area of learning with label noise by providing a forum for authors to report on new advances and findings in this problem area. Topics of interest include, but are not limited to: * new methods to deal with label noise; * new applications where label noise must be taken into account; * theoretical results about learning in the presence of label noise; * experimental results which provide insight about existing methods; * dealing with different types of label noise (random, non-random, malicious, or adversarial); * conditions for the consistency of classification in the presence of label noise; * label noise in high dimensional small sample settings; * the issue of model meta-parameters/order selection in the presence of label noise; * feature selection and dimensionality reduction in the presence of label noise; * label-noise aware classification algorithms in static and dynamic scenarios; * on-line learning with label noise * learning with side information to counter label noise; * model assessment in the presence of label noise in test data. _*SUBMISSION OF MANUSCRIPTS*__* *_ If you intend to contribute to this special issue, please send a title and abstract of your contribution to the guest editors. Authors should prepare their manuscript according to the Guide for Authors available at http://www.journals.elsevier.com/neurocomputing. All the papers will be peer-reviewed following the Neurocomputing reviewing procedures. Authors must submit their papers electronically by using online manuscript submission at http://ees.elsevier.com/neucom. To ensure that all manuscripts are correctly included into the special issue, it is important that authors select "SI: Learning with label noise" when they reach the "Article Type" step in the submission process. For technical questions regarding the submission website, please contact the support office at Elsevier or the guest editors. _*IMPORTANT DATES*_ Deadline of paper submission: 15 February 2014 Notification of acceptance: 15 July 2014 _*GUEST EDITORS*_ Beno?t Fr?nay (Managing Guest Editor) Universit? catholique de Louvain, Belgium E-mail: benoit.frenay at uclouvain.be Website:http://bfrenay.wordpress.com Phone: +32 10 478133 Ata Kaban (Special Issue Guest Editor) University of Birmingham, United Kingdom E-mail: A.Kaban at cs.bham.ac.uk Website:http://www.cs.bham.ac.uk/~axk Phone: +44 121 41 42792 -------------- next part -------------- An HTML attachment was scrubbed... URL: From A.K.Seth at sussex.ac.uk Wed Sep 18 17:47:09 2013 From: A.K.Seth at sussex.ac.uk (Anil Seth) Date: Wed, 18 Sep 2013 21:47:09 +0000 Subject: Connectionists: Funded PHD position available at Sackler Centre in VR and consciousness Message-ID: Apologies for cross-posting. Please do pass on to any potentially interested people. Application deadline October 14. Funded PhD available on VR, psychophysiology, and consciousness Applications are invited for a 3.5 year PhD studentship funded by the European Research Council to join a team within the Psychiatry group, BSMS and the Sackler Centre for Consciousness Science, University of Sussex. The aims of the research project are to examine the effects of heart-timing on the processing of fear and threat stimuli and the implications for human-machine interaction. We have shown that signals from the heart affect the processing of fearful and threatening stimuli and influences behavioural, neural and bodily responses to these stimuli. Even the timing of an individual heartbeat can determine if a brief stimulus is perceived as a threat. Further research into these mechanisms, and their application, is supported by an ERC Advanced Grant ?Cardiac control of fear in the brain? to Prof Hugo Critchley. The studentship will be based at BSMS Psychiatry and the Sackler Centre for Consciousness Science, University of Sussex. Prof Hugo Critchley and Prof Anil Seth will supervise. Experimental work will include a) implementation of heart-timing manipulations of stimuli in virtual and augmented reality (VR/AR) settings to explore effects on fear processing, fear-learning (conditioning) and safety-learning (extinction). b) testing the effect of heart rhythms and heartbeat timing on behavioural responses to potentially threatening ?ballistic? stimuli presented in VR/AR to quantify the impact on stimulus detection and avoidance behaviour. c) testing if coupling of operator interfaces to physiological signals can enhance functional and experiential aspects of human-machine interaction. d) Methodological development including a refinement of remote heartbeat sensing, noting recently published methods to derive heart timing information from video information, as well as novel ?electric potential? sensors developed within the Engineering group at Sussex. The studentship will suit candidates with a computer science or similar strong technical background with a keen interest in cognitive neuroscience and related disciplines. The student will work within a team of basic and clinical neuroscientists focusing on mind-brain-body interactions using integrative approaches including behavioural psychophysiology and brain imaging. The project offers a range of training opportunities through which the student will be able to acquire skills in cognitive and behavioural neuroscience, autonomic psychophysiology and related areas of computational science, psychology and neurobiology. This will provide the student with critical skills and a depth and breadth of experience to make them a highly competitive candidate for a postdoctoral research position. For more information see http://www.findaphd.com/search/ProjectDetails.aspx?PJID=45836&LID=207 For more about the ?Cardiac Control of Fear in the Brain? project seehttp://www.bsms.ac.uk/about/news/fear-controlling-research-win-european-grant/. More about the Sackler Centre for Consciousness Science is herehttp://www.sussex.ac.uk/sackler/. ------------------------------------------- Anil K. Seth, D.Phil. Professor of Cognitive and Computational Neuroscience Co-Director, Sackler Centre for Consciousness Science University of Sussex www.anilseth.com a.k.seth at sussex.ac.uk -------------- next part -------------- An HTML attachment was scrubbed... URL: From pam.bailey at novartis.com Tue Sep 17 20:42:32 2013 From: pam.bailey at novartis.com (Bailey, Pam) Date: Wed, 18 Sep 2013 00:42:32 +0000 Subject: Connectionists: Neuroscience Computational Biologist, Novartis, Cambridge, MA Message-ID: <57BB1464F128764083ADC112501C07751705099E@023-CH1MPN1-082.023d.mgd.msft.net> We are currently seeking an innovative scientist who will work in a dynamic, agile 'dry-lab' research environment committed to the discovery of novel medicines for neurological diseases. Drawing on a background investigating the nervous system in either model systems or clinical studies, this person will be provide critical support to colleagues by working closely with other investigators to develop mechanistic hypotheses underlying cognitive and degenerative disorders and to provide high quality, timely analyses of large scale experimental data. Qualifications include a PhD in computational biology, bioinformatics, neuroscience, cell and developmental biology, or a related field, along with experience in morphometric and electrophysiology data analysis, a demonstrated understanding of statistics and quantitative data analysis, experience with 'omic data analysis, especially NGS, microarrays and proteomic technologies, and experience with Spotfire and R/Bioconductor. For more information and to apply, please visit: http://novartis.avature.net/jobs#ViewJob/295 -------------- next part -------------- An HTML attachment was scrubbed... URL: From gluck at pavlov.rutgers.edu Sun Sep 22 09:52:35 2013 From: gluck at pavlov.rutgers.edu (Mark Gluck) Date: Sun, 22 Sep 2013 09:52:35 -0400 Subject: Connectionists: Apply to the Behavioral & Neural Sciences Ph.D. Program at Rutgers University-Newark (Deadline: December 15th, 2013) In-Reply-To: <341B022F-2805-4752-9E5D-83DCF4804B9D@pavlov.rutgers.edu> References: <341B022F-2805-4752-9E5D-83DCF4804B9D@pavlov.rutgers.edu> Message-ID: [Please Share With Potential Applicants]: Dear Colleagues: If you know of bright and highly motivated graduating seniors or research assistants at your institution who are interested in pursuing a Ph.D. in neuroscience, we would be obliged if you would pass this email on to them. The goal of the Graduate Program in Behavioral and Neural Sciences (BNS) at Rutgers University-Newark is to provide training across all areas of neuroscience as well as to provide intensive instruction within one area of focus so that graduates will be prepared for careers as academicians, educators and research scientists. Students are fully funded by the graduate program (not by individual faculty) for five years with a stipend, tuition and comprehensive health insurance. The BNS curriculum offers a wide range of courses that provide both breadth and depth. The program has only a few required courses but many electives so that students may tailor coursework to their individual backgrounds and needs. Students are primarily trained to conduct independent research and to present and discuss their results orally and in written form. Students also gain experience in undergraduate and graduate teaching and mentoring. The recent integration into Rutgers of the former UMDNJ Medical School provides our students with additional clinically-relevant training opportunities. The campus of the BNS program is located in Newark, New Jersey, 13 miles from Manhattan, New York City, with extensive public transportation links between the two. For more information, and links to faculty profiles and related resources, see: http://www.neuroscience.newark.rutgers.edu Additional information on our brain imaging center can be found at http://rubic.rutgers.edu The admissions link can be reached directly at: http://www.bns.rutgers.edu The deadline for applications is December 15, 2013 and interviews of the top candidates will take place mid/late February, 2014. Late applications may be considered on a case by case basis. Regards, Mark Gluck & James Tepper, BNS Admissions Committee Ian Creese, Director, Behavioral and Neural Sciences Ph.D Program Denis Pare, Director, Center for Molecular and Behavioral Neuroscience -------------- next part -------------- An HTML attachment was scrubbed... URL: From bhammer at techfak.uni-bielefeld.de Thu Sep 19 04:08:34 2013 From: bhammer at techfak.uni-bielefeld.de (Barbara Hammer) Date: Thu, 19 Sep 2013 10:08:34 +0200 Subject: Connectionists: special session on Learning and Modelling Big Data Message-ID: <523AB102.1070204@techfak.uni-bielefeld.de> *** Apologies for cross posting *** Special Session on Learning and Modeling Big Data at ESANN 2014, 23-25 April 2014, Bruges, Belgium, http://www.esann.org Organizers: Barbara Hammer (Bielefeld University, DE), Haibo He (Rhode Island, USA), Thomas Martinetz (University of Luebeck, DE) Abstract: Big data in the sense of large or streaming data sets, very high dimensionality, or complex data formats constitute one of the major challenges faced by machine learning today, caused by powerful sensors and digitalization techniques as well as dramatically increased storage capabilities. In this realm, a couple of typical assumptions of machine learning can no longer be met, causing the need for novel algorithmic developments and paradigm shifts, such as * online learning and techniques for streaming data * learning from non i.i.d. data and skewed distributions * life-long adaptation of model complexity and hyper-parameters * linear or sublinear algorithms with limited online memory capacity * parallel implementations * sparse representation of data, efficient information compression * interpretable models * learning from the crowd * good priors in the context of extremely high dimensionality We solicit contributions focussing on novel algorithmic developments, theoretical investigations or applications connected to this non-exhaustive list of topics. Schedule: Paper submission deadline : 29 November 2013 Notification of acceptance : 31 January 2014 Deadline for final papers : 21 February 2014 ESANN 2014 conference : 23-25 April 2014 Infos on submissions can be found at http://www.esann.org -- Prof. Dr. Barbara Hammer CITEC centre of excellence Bielefeld University D-33594 Bielefeld Phone: +49 521 / 106 12115 Fax: +49 521 / 106 12181 From jeffclune at uwyo.edu Wed Sep 18 20:09:39 2013 From: jeffclune at uwyo.edu (Jeff Clune) Date: Wed, 18 Sep 2013 18:09:39 -0600 Subject: Connectionists: Fully funded Ph.D. position in evolving artificial intelligence (neural networks, robotics, and/or deep learning) Message-ID: <5978056D-6245-449D-AC9A-5932FBF9052A@uwyo.edu> Hello all, Please forward this email to anyone who might be interested. A fully funded computer science Ph.D. position is available in any of the following areas, especially in combinations of them: evolving artificial intelligence, neural networks, robotics, and deep learning. Postdoctoral positions are also available, but under different funding arrangements (please email jeffclune at uwyo.edu for details). Positions ideally start this coming Spring (January 2014), but alternate start dates, including next fall, are possible. I (Jeff Clune) direct the Evolving Artificial Intelligence Lab at the University of Wyoming. The lab focus is on evolving artificial intelligence by producing artificially intelligent robots, including physical robots and agents in simulated worlds. The lab will also study other bio-inspired AI techniques, such as deep learning. Part of these efforts will involve investigating how evolution produced the complex, intelligent, diverse life on this planet by trying to computationally recreate it. A major focus will be on evolving large-scale, structurally organized neural networks (i.e. networks with millions of connections that are modular, regular, and hierarchical). I am also interested in combining neuroevolution with learning algorithms (Hebbian, neuromodulation, etc.). Please see my website (http://JeffClune.com) for example publications, press articles about the work, videos, etc. Here are some keywords that describe related fields: evolutionary algorithms (also known as genetic algorithms or evolutionary computation), neural networks (including evolving neural networks, having them learn, deep learning, and computational neuroscience), robotics, artificial intelligence, and research into the evolution of intelligence, complexity, evolvability, and diversity. If you are interested in joining the lab or would like more information about the positions, please follow the instructions at http://jeffclune.com/positionsAvailable.html Here is a video that summarizes my research: http://goo.gl/wA6Fe Other videos about my research are here: http://jeffclune.com/videos.html The University of Wyoming is located in Laramie, a college town in the heart of the Rocky Mountain West. Nestled between two mountain ranges, Laramie has more than 300 days of sunshine a year and is home to year-round outdoor activities including hiking, camping, rock climbing, downhill skiing, cross-country skiing, fishing and mountain biking. Laramie is also near many of Colorado's major cities and university communities (e.g. Fort Collins, Boulder, and Denver). The University of Wyoming is an Affirmative Action/Equal Opportunity employer. All qualified applicants receive consideration for employment without regard to race, color, religion, gender, pregnancy, sexual orientation, age, national origin, disability, marital, veteran or any other legally protected status. Best regards, Jeff Clune Assistant Professor Computer Science University of Wyoming jeffclune at uwyo.edu jeffclune.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From grlmc at urv.cat Sun Sep 22 06:40:08 2013 From: grlmc at urv.cat (GRLMC) Date: Sun, 22 Sep 2013 12:40:08 +0200 Subject: Connectionists: AlCoB 2014: 1st call for papers Message-ID: <5B8F9CC8CA0E4F679A696BFD55498C39@Carlos1> *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* ********************************************************************* 1st INTERNATIONAL CONFERENCE ON ALGORITHMS FOR COMPUTATIONAL BIOLOGY AlCoB 2014 Tarragona, Spain July 1-3, 2014 Organized by: Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/alcob2014/ ********************************************************************* AIMS: AlCoB aims at promoting and displaying excellent research using string and graph algorithms and combinatorial optimization to deal with problems in biological sequence analysis, genome rearrangement, evolutionary trees, and structure prediction. The conference will address several of the current challenges in computational biology by investigating algorithms aimed at: 1) assembling sequence reads into a complete genome, 2) identifying gene structures in the genome, 3) recognizing regulatory motifs, 4) aligning nucleotides and comparing genomes, 5) reconstructing regulatory networks of genes, and 6) inferring the evolutionary phylogeny of species. Particular focus will be put on methodology and significant room will be reserved to young scholars at the beginning of their career. VENUE: AlCoB 2014 will take place in Tarragona, located 90 kms. to the south of Barcelona. The venue will be the Catalunya Campus. SCOPE: Topics of either theoretical or applied interest include, but are not limited to: Exact sequence analysis Approximate sequence analysis Pairwise sequence alignment Multiple sequence alignment Sequence assembly Genome rearrangement Regulatory motif finding Phylogeny reconstruction Phylogeny comparison Structure prediction Compressive genomics Proteomics: molecular pathways, interaction networks ... Transcriptomics: splicing variants, isoform inference and quantification, differential analysis Next-generation sequencing: population genomics, metagenomics, metatranscriptomics ... Microbiome analysis Systems biology STRUCTURE: AlCoB 2014 will consist of: invited talks invited tutorials peer-reviewed contributions INVITED SPEAKERS: to be announced PROGRAMME COMMITTEE: Tatsuya Akutsu (Kyoto, JP) Amihood Amir (Ramat-Gan, IL) Alberto Apostolico (Atlanta, US) Joel Bader (Baltimore, US) Pierre Baldi (Irvine, US) Serafim Batzoglou (Stanford, US) Bonnie Berger (Cambridge, US) Francis Y.L. Chin (Hong Kong, HK) Benny Chor (Tel Aviv, IL) Keith A. Crandall (Washington, US) Bhaskar DasGupta (Chicago, US) Joaqu?n Dopazo (Valencia, ES) Liliana Florea (Baltimore, US) Olivier Gascuel (Montpellier, FR) David Gilbert (Uxbridge, UK) Gaston H. Gonnet (Zurich, CH) Roderic Guig? (Barcelona, ES) Dan Gusfield (Davis, US) Vasant Honavar (University College, US) Sorin Istrail (Providence, US) Tao Jiang (Riverside, US) Inge Jonassen (Bergen, NO) Anders Krogh (Copenhagen, DK) Giovanni Manzini (Alessandria, IT) Carlos Mart?n-Vide (Tarragona, ES, chair) Satoru Miyano (Tokyo, JP) Burkhard Morgenstern (G?ttingen, DE) Shinichi Morishita (Tokyo, JP) C?dric Notredame (Barcelona, ES) Graziano Pesole (Bari, IT) Mark Ragan (Brisbane, AU) Timothy Ravasi (Thuwal, SA) Allen G. Rodrigo (Durham, US) Steven Salzberg (Baltimore, US) David Sankoff (Ottawa, CA) Thomas Schiex (Toulouse, FR) Jo?o C. Setubal (S?o Paulo, BR) Steven Skiena (Stony Brook, US) Peter F. Stadler (Leipzig, DE) Wing-Kin Sung (Singapore, SG) Alfonso Valencia (Madrid, ES) Jacques van Helden (Marseille, FR) Arndt von Haeseler (Vienna, AT) Lusheng Wang (Hong Kong, HK) Limsoon Wong (Singapore, SG) Xiaohui Xie (Irvine, US) Dong Xu (Columbia, US) Zohar Yakhini (Santa Clara, US) Alex Zelikovsky (Atlanta, US) Michael Q. Zhang (Dallas, US) ORGANIZING COMMITTEE: Adrian Horia Dediu (Tarragona) Carlos Mart?n-Vide (Tarragona, chair) Bianca Truthe (Magdeburg) Florentina Lilica Voicu (Tarragona) SUBMISSIONS: Authors are invited to submit non-anonymized papers in English presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (including eventual appendices) and should be formatted according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0). Submissions have to be uploaded to: https://www.easychair.org/conferences/?conf=alcob2014 PUBLICATIONS: A volume of proceedings expectedly published by Springer in the LNBI series will be available by the time of the conference. A special issue of a major journal will be later published containing peer-reviewed extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation. REGISTRATION: The period for registration is open from September 21, 2013 to July 1, 2014. The registration form can be found at: http://grammars.grlmc.com/alcob2014/Registration.php DEADLINES: Paper submission: February 4, 2014 (23:59 CET) Notification of paper acceptance or rejection: March 15, 2014 Final version of the paper for the proceedings: March 22, 2014 Early registration: March 29, 2014 Late registration: June 17, 2014 Starting of the conference: July 1, 2014 End of the conference: July 3, 2014 Submission to the post-conference journal special issue: October 3, 2014 QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu at urv.cat POSTAL ADDRESS: AlCoB 2014 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34 977 559543 Fax: +34 977 558386 ACKNOWLEDGEMENTS: Departament d?Economia i Coneixement, Generalitat de Catalunya Universitat Rovira i Virgili From standage at queensu.ca Mon Sep 23 11:22:31 2013 From: standage at queensu.ca (Dominic Standage) Date: Mon, 23 Sep 2013 15:22:31 +0000 Subject: Connectionists: Research topic on the speed-accuracy trade-off Message-ID: <25A86FE23942874DA05B4C6980672A970D8E76B2@MP-DUP-MBX-02.AD.QUEENSU.CA> Dear colleagues - apologies for cross-posting. Please see below the details of the Frontiers Research Topic "Toward a unified view of the speed-accuracy trade-off: behaviour, neurophysiology and modelling", hosted by Frontiers in Decision Neuroscience. The manuscript submission deadline is December 1. Please let me know if you're interested in submitting a manuscript or if you have questions about the suitability of material for the topic. -- Toward a unified view of the speed-accuracy trade-off: behaviour, neurophysiology and modelling http://www.frontiersin.org/Decision_Neuroscience/researchtopics/Toward_a_unified_view_of_the_s/1647 Topic Editors: Dominic Standage, Queen's University, Canada Da-Hui Wang, Beijing Normal University, China Richard P. Heitz, Vanderbilt University, USA Patrick Simen, Oberlin College, USA Deadline for full article submission: 01 Dec 2013 When we make faster decisions, we make more mistakes. When we make slower decisions, we miss more deadlines and we limit the number of decisions we can make. These principles are intuitively obvious and are applicable to decisions in any domain, on any timescale, by any species or automated system. Their resolution defines the speed-accuracy trade-off (SAT). The SAT has long been the subject of experimental and theoretical enquiry. In experiments, subjects make slower, more accurate decisions when motivated to favour accuracy and make faster, less accurate decisions when motivated to favour speed. Computationally, the SAT is well characterized within the framework of bounded integration, where noisy evidence for the alternatives is integrated over time. When the evidence for one of the alternatives reaches a threshold or bound, a choice is made for that alternative. Higher thresholds therefore favour accuracy at the expense of speed. This framework captures a remarkable volume of experimental data, but there is a prominent discrepancy between model fits to behavioural and electrophysiological data. The latter have been taken to suggest that decision thresholds are fixed. If so, then how do we trade speed and accuracy? This question is the focus of intense research interest. A growing number of studies have investigated the neural mechanisms underlying the SAT within the framework of bounded integration, where a convergence of neuroimaging and electrophysiological methods with mathematical and biophysical modelling has provided new perspectives on the mechanisms by which decision times are determined. For example, with a fixed decision threshold, the time spent integrating evidence may be adjusted by modulating the baseline activity of neural integrators, the rate and onset of integration, or the functional connectivity between integrators and other sources of input to thresholding circuitry. Furthermore, there is increasing evidence that the encoding of elapsed time plays a crucial role in the SAT, sometimes referred to as urgency. These and other hypotheses suggest that the conflicting demands of speed and accuracy may be resolved by the differential encoding, readout and integration of evidence. Striking the optimal balance between speed and accuracy in a given context further requires a means to control these mechanisms. In this Research Topic, we welcome articles that characterize or explain the SAT and its optimization according to any experimental factor or neural mechanism, using any experimental or theoretical methodology. While we take temporal integration as a starting point, we encourage articles expressing disagreement with the premises of the bounded integration framework and reporting evidence in favour of alternative explanations of the SAT. All Frontiers article types are welcome, including original research articles, methods articles, hypothesis and theory articles, opinions, perspectives and reviews. -- Best Dominic Standage Research Scientist Department of Biomedical and Molecular Sciences / Centre for Neuroscience Studies Queen's University, Botterell Hall, Room 230 Kingston, Ontario, Canada K7L 3N6 Tel: (613) 533-6000 (ext 77446) Email: standage at queensu.ca -------------- next part -------------- An HTML attachment was scrubbed... URL: From ian.stevenson at uconn.edu Mon Sep 23 10:33:55 2013 From: ian.stevenson at uconn.edu (Stevenson, Ian) Date: Mon, 23 Sep 2013 14:33:55 +0000 Subject: Connectionists: NIPS 2013 Workshop Call For Papers: High-dimensional Statistical Inference in the Brain Message-ID: <0F90EEF092192947853D183C3EE11788E23CFD@MailH.grove.ad.uconn.edu> NIPS WORKSHOP 2013 CALL FOR PAPERS High-dimensional Statistical Inference in the Brain Monday, December 9th, 2013 Lake Tahoe, Nevada USA -------- Organizers: Mitya Chklovskii Alyson Fletcher Fritz Sommer Ian Stevenson -------- Overview: Understanding high-dimensional phenomena is at the heart of many fundamental questions in neuroscience. How does the brain process sensory data? How can we model the encoding of the richness of the inputs, and how do these representations lead to perceptual capabilities and higher level cognitive function? Similarly, the brain itself is a vastly complex nonlinear, highly-interconnected network and neuroscience requires tractable, generalizable models for these inherently high-dimensional neural systems. Recent years have seen tremendous progress in high-dimensional statistics and methods for ``big data" that may shed light on these fundamental questions. This workshop seeks to leverage these advances and bring together researchers in mathematics, machine learning, computer science, statistics and neuroscience to explore the roles of dimensionality reduction and machine learning in neuroscience. Call for Papers We invite high quality submissions of extended abstracts on topics including, but not limited to not limited to, the following fundamental questions: -- How is high-dimensional sensory data encoded in neural systems? What insights can be gained from statistical methods in dimensionality reduction including sparse and overcomplete representations? How do we understand the apparent dimension expansion in higher level cognitive functions from a machine learning and statistical perspective? -- What is the relation between perception and high-dimensional statistical inference? What are suitable statistical models for natural stimuli in vision and auditory systems? -- How does the brain learn such statistical models? What are the connections between unsupervised learning, latent variable methods, online learning and distributed algorithms? How do such statistical learning methods relate to and explain experience-driven plasticity and perceptual learning in neural systems? -- How can we best build meaningful, generalizable models of the brain with predictive value? How can machine learning be leveraged toward better design of functional brain models when data is limited or missing? What role can graphical models coupled with newer techniques for structured sparsity play in this dimensionality reduction? -- What are the roles of statistical inference in the formation and retrieval of memories in the brain? We wish to invite discussion on the very open questions of multi-disciplinary interest: for memory storage, how does the brain decode the strength and pattern of synaptic connections? Is it reasonable to conjecture the use of message passing algorithms as a model? -- Which estimation algorithms can be used for inferring nonlinear and inter-connected structure of these systems? Can new compressed sensing techniques be exploited? How can we model and identify dynamical aspects and temporal responses? We have invited researchers from a wide range of disciplines in electrical engineering, psychology, statistics, applied physics, machine learning and neuroscience with the goals of fostering interdisciplinary insights. We hope that active discussions between these groups can set in motion new collaborations and facilitate future breakthroughs on fundamental research problems. Submissions should be in the NIPS_2013 format (include link http://nips.cc/Conferences/2013/PaperInformation/StyleFiles) with a maximum of four pages, not including references. Dates: Submission deadline: 23 October, 2013 11:59 PM PDT (UTC -7 hours) Acceptance notification: 30 October , 2013 Web: http://users.soe.ucsc.edu/~afletcher/hdnips2013.html email: hdnips2013 at rctn.org Organizers: Mitya Chklovskii, HHMI Janelia Farm Allie Fletcher, UCSC Fritz Sommer, UC Berkeley Ian Stevenson, University of Connecticut Confirmed Speakers Liam Paninski, Columbia University Maneesh Sahani, University College London Jonathon Pillow, University of Texas Surya Ganguli, Stanford University Matthias Bethge, University of Tuebingen From jebara at cs.columbia.edu Sun Sep 22 22:30:13 2013 From: jebara at cs.columbia.edu (Tony Jebara) Date: Sun, 22 Sep 2013 22:30:13 -0400 Subject: Connectionists: International Conference on Machine Learning 2014 Message-ID: <642C6910-BAC4-4266-9BE4-195FBCEF78B1@cs.columbia.edu> We are happy to announce that the submission site for the 31st International Conference on Machine Learning (ICML 2014) is open with a deadline for Cycle I papers on October 4th. Please follow the link below to proceed with account creation and manuscript submission: https://cmt.research.microsoft.com/ICML2014 When preparing your manuscript, please follow the formatting instructions available at http://icml.cc/2014/14.html where you will find a downloadable template folder you to use. Submissions not complying with page limit and format requirements will not be reviewed and will be automatically rejected. This year, ICML has reached an agreement with the Journal of Machine Learning Research (JMLR) to facilite a "JMLR fast-track" for selected ICML accepted papers. For papers accepted during the first cycle, the ICML program committee will recommend a small subset of excellent papers to be considered for publication at JMLR through a fast-track reviewing process. Therein, authors of selected papers are invited to submit an expanded full version at the same time that the conference camera-ready version is submitted. The expanded version will be reviewed again by the same Area Chair, two reviewers who originally reviewed the conference version of the recommended paper, plus one additional reviewer who will be determined by the AC. We expect that this fast-track approach will significantly reduce the journal review time. It also provides a more consistent evaluation as the processing of the full journal paper and the conference paper will be better aligned. The journal version may still be rejected if it does not meet the standards of JMLR. Authors will be asked during their ICML paper submission to indicate whether or not they want their submission to be considered for the JMLR fast-track. With this consent, authors commit to submitting a full journal version before or on the camera-ready deadline. For your information, an updated CFP is attached. We look forward to receiving your submissions! Eric Xing and Tony Jebara Program Co-Chairs, ICML 2014 http://icml.cc/2014/ Call for Papers International Conference on Machine Learning http://icml.cc/2014/ Beijing, June 21-26, 2014 The 31st International Conference on Machine Learning (ICML 2014) will be held in Beijing, China, from June 21 to 26, 2014. The conference will, tentatively, consist of one day of tutorials, followed by three days of main conference sessions, followed by two days of workshops. We invite submissions of papers on all topics related to machine learning for the conference proceedings, and proposals for tutorials and workshops. After reviewing author and reviewer feedback from the previous conference, ICML 2014 will adopt a two-cycle submission/review format, of which the first submission/review cycle will facilitate both regular one-time review/rebuttal of submissions, as well as invitation-only resubmission into the second cycle, whereas the second cycle will only allow regular first-time submission plus resubmission of papers invited from the first cycle. We are also exploring the possibility of a JMLR track at ICML that allows direct submission of papers intended for JMLR to be reviewed under the same time frame of ICML, more detail will be available soon once agreement with JMLR has been reached. Accepted papers will be announced and posted online shortly after acceptance and will be considered published and available for citation at that time. Paper Format and Electronic Submission The submission of papers and the management of the paper reviewing process for the main conference will be entirely electronic. Submissions for a given reviewing cycle will be accepted until 23:59 Universal Time (3:59pm Pacific Daylight Time) on the date of the deadline. Detailed formatting and submission instructions for authors will be available soon on the conference web site. Submitted papers can be up to eight pages long, not including references, and up to nine pages when references are included. Any paper exceeding this length will automatically be rejected. Authors have the option of submitting a supplementary file containing further details of their work; it is entirely up to the reviewers to decide whether they wish to consult this additional material. All submissions must be anonymized and must closely follow the formatting guidelines in the templates; otherwise they will automatically be rejected. Dual Submission Policy Submitted papers must not be substantially similar to another paper currently under review, or accepted for publication, in a journal, conference or workshop with peer-reviewed proceedings. Similarly, authors must withdraw their papers if they submit an overlapping paper to a different peer-reviewed venue during the ICML review period. If a paper submitted to ICML 2014 is found to significantly overlap with a published or submitted paper at another peer-reviewed venue, then the submission may be rejected and the incident will be recorded with further consequence at the conference organizers? discretion. JMLR fast-track We are happy to announce that an agreement with JMLR has been reached to facilite a "JMLR fast-track" for selected ICML accepted papers. For papers accepted during the first cycle, the ICML program committee will recommend a small subset of excellent papers to be considered for publication at JMLR through a fast-track reviewing process. Therein, authors of selected papers are invited to submit an expanded full version at the same time that the conference camera-ready version is submitted. The expanded version will be reviewed again by the same Area Chair, two reviewers who originally reviewed the conference version of the recommended paper, plus one additional reviewer who will be determined by the AC. We expect that this fast-track approach will significantly reduce the journal review time. It also provides a more consistent evaluation as the processing of the full journal paper and the conference paper will be better aligned. The journal version may still be rejected if it does not meet the standards of JMLR. Authors are asked during their ICML paper submission to indicate whether or not they want their submission to be considered for the JMLR fast-track. With this consent, authors commit to submitting a full journal version before or on the camera-ready deadline. Reviewing Criteria Accepted papers must contain significant novel results. Results can be either theoretical or empirical. Results will be judged on the degree to which they have been objectively established and/or their potential for scientific and technological impact. Main Conference Paper Dates Cycle I: Cycle I paper submissions due October 4, 2013 Cycle I author response period November 13 ? 17, 2013 Cycle I author notification December 9, 2013 Cycle I final version due January 17, 2014 Cycle II: Cycle II paper submissions due January 31, 2014 Cycle II author response period March 12-16, 2014 Cycle II author notification April 9, 2014 Cycle II final version submission due TBA Some fraction of papers rejected in cycle I will be invited to resubmit with modifications in cycle II. Papers rejected in cycle II will not be eligible for resubmission to ICML 2014. ORGANIZATION GENERAL CHAIR David McAllester (Toyota Technological Institute at Chicago) PROGRAM CHAIRS Eric Xing (Carnegie Mellon University) Tony Jebara (Columbia University) WORKSHOP CHAIR Alex Ihler (University of California Irvine) TUTORIAL CHAIR Ruslan Salakhutdinov (University of Toronto) PUBLICITY CHAIR Jingrui He (Stevens Institute of Technology) VOLUNTEER CHAIR John Paisley (Columbia University) FINANCIAL CHAIR Artur Dubrawski (Carnegie Mellon University) Charles Isbell (Georgia Institute of Technology) WORKFLOW CHAIR Kui Tang (Columbia University) Junming Yin (Carnegie Mellon University) LOCAL CHAIRS Changshui Zhang (Tsinghua University) Jun Zhu (Tsinghua University) Tie-Yan Liu (Microsoft Research Asia) -------------- next part -------------- An HTML attachment was scrubbed... URL: From commons at tiac.net Tue Sep 24 14:07:17 2013 From: commons at tiac.net (Michael Lamport Commons) Date: Tue, 24 Sep 2013 14:07:17 -0400 (GMT-04:00) Subject: Connectionists: Possibilities of Building "Stacked Neural Networks" Message-ID: <5524902.1380046037954.JavaMail.root@wamui-haziran.atl.sa.earthlink.net> Dear Members of this list-serve: Would it be possible to build ?stacked neural networks? like the one shown in the attached document? You may have a few questions about the stacked neural network. First, what is a stacked neural network? What is the difference between stacked neural networks and the existing neural network? A brief description is provided in the attached document. Based on this brief description, I would like to know how would one go about building such stacked neural networks cheaply and easily? Is there any software available that can do this? How much would it cost? Please feel free to contact me if you think that it would be possible or easier to apply stacked neuron network into a more practical field? Suggestions are welcome as well. My best, Michael Lamport Commons, Ph.D. Assistant Clinical Professor Department of Psychiatry Harvard Medical School Beth Israel Deaconess Medical Center commons at tiac.net 617-497-5270 Telephone 617-491-5270 Fax http://www.dareassociation.org/ From robomotic at gmail.com Wed Sep 25 04:59:39 2013 From: robomotic at gmail.com (Paolo Di Prodi) Date: Wed, 25 Sep 2013 09:59:39 +0100 Subject: Connectionists: Possibilities of Building "Stacked Neural Networks" In-Reply-To: <5524902.1380046037954.JavaMail.root@wamui-haziran.atl.sa.earthlink.net> References: <5524902.1380046037954.JavaMail.root@wamui-haziran.atl.sa.earthlink.net> Message-ID: Hello Prof., I can't see the attached document, it was probably removed by the mailing list filter. Could you upload it online somewhere? Cheers. On 24 September 2013 19:07, Michael Lamport Commons wrote: > Dear Members of this list-serve: > > Would it be possible to build ?stacked neural networks? like the > one shown in the attached document? > > You may have a few questions about the stacked neural network. > First, what is a stacked neural network? What is the difference between > stacked neural networks and the existing neural network? A brief > description is provided in the attached document. > > Based on this brief description, I would like to know how would one > go about building such stacked neural networks cheaply and easily? Is > there any software available that can do this? How much would it cost? > > Please feel free to contact me if you think that it would be > possible or easier to apply stacked neuron network into a more practical > field? Suggestions are welcome as well. > > > My best, > > Michael Lamport Commons, Ph.D. > > Assistant Clinical Professor > Department of Psychiatry > Harvard Medical School > > Beth Israel Deaconess Medical Center > commons at tiac.net > > 617-497-5270 Telephone > 617-491-5270 Fax > http://www.dareassociation.org/ > > --- > Wiki: http://grey.colorado.edu/Connectionists -- Dr. Paolo Di Prodi -------------- next part -------------- An HTML attachment was scrubbed... URL: From bazhenov at salk.edu Wed Sep 25 14:42:03 2013 From: bazhenov at salk.edu (Maxim Bazhenov) Date: Wed, 25 Sep 2013 11:42:03 -0700 Subject: Connectionists: postdoctoral position to study information coding in the olfactory system Message-ID: <52432E7B.3010309@salk.edu> Applications are invited for NIH-funded post-doctoral position in the laboratory of Dr. Maxim Bazhenov at the University of California, Riverside to study information coding in the olfactory system. This project involves close collaboration with laboratory of Dr. Mark Stopfer at NIH. For relevant references see, Assisi et al., Neuron 2011, 69(2):373-86; Ito et al., Neuron 2009, 64(5):692-706; Assisi at al., Nature Neurosci, 2007, 10(9):1176-84. The ultimate goal of this work is to understand mechanisms and functions of biological rhythms and the role of neuronal dynamics in information processing. The successful candidate will be responsible for design and analysis of the network models of olfactory system based on existing experimental data. These models will be used to understand underlying neural mechanisms, as well as guide data analysis and produce novel experimental predictions. Qualified applicants are expected to have experience in computational/theoretical neuroscience and conductance-based neural modeling. Programming experience with C/C++ is required. Knowledge of PYTHON or MATLAB is a plus. The University of California offers excellent benefits. Salary is based on research experience. The initial appointment is for 1 year with a possibility of extension. Applicants should send a brief statement of research interests, a CV and the names of three references to Maxim Bazhenov at maksim.bazhenov at ucr.edu -- Maxim Bazhenov, Ph.D. Professor, Cell Biology and Neuroscience University of California Riverside, CA 92521 Ph: 951-827-4370 http://biocluster.ucr.edu/~mbazhenov/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From dnoelle at ucmerced.edu Wed Sep 25 16:16:44 2013 From: dnoelle at ucmerced.edu (David Noelle) Date: Wed, 25 Sep 2013 20:16:44 +0000 Subject: Connectionists: Open Faculty Position in Computational Linguistics at the University of California, Merced Message-ID: <62C18050-4D98-4BB9-98AF-B308184D4504@ucmerced.edu> The University of California, Merced has one Computational Linguistics position open at the Assistant Professor (tenure-track) level in the area of Cognitive and Information Sciences. Preference will be given to applicants whose doctorate is in Linguistics or a closely related field and whose research program makes use of quantitative linguistics methods. Especially desirable are individuals with expertise in one or more of the following areas: computational phonetics/phonology, quantitative cognitive linguistics, corpus-based approaches to linguistic analysis, statistical natural language processing, and comparative or typological methods. The successful candidate will develop and teach new undergraduate and graduate courses in the Cognitive and Information Sciences program and round out its emphasis in language. The successful candidate is expected to actively pursue extramural funding, participate in program building, and mentor students from diverse groups. For this position, three letters of reference are requested. Applications must be received no later than December 2, 2013 to be considered. The University of California, Merced is an affirmative action/equal opportunity employer with a strong institutional commitment to the achievement of diversity among its faculty, staff, and students. The University is supportive of dual career couples. For more information, please see "https://jobs.ucmerced.edu/n/academic/position.jsf?positionId=4919". -------------- next part -------------- An HTML attachment was scrubbed... URL: From urundogan at gmail.com Thu Sep 26 06:08:04 2013 From: urundogan at gmail.com (urun dogan) Date: Thu, 26 Sep 2013 13:08:04 +0300 Subject: Connectionists: NIPS 2013 New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks (Reminder of Submission Deadline) Message-ID: Apologies for cross-posting. Please forward this to those who may be interested. Thank you. ========================================================================= CALL FOR PAPERS (Reminder of Submission Deadline) NIPS 2013 New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks December 10, 2013 Lake Tahoe, Nevada, USA https://sites.google.com/site/learningacross/ Submission Deadline: October 9, 2013 ========================================================================= The main objective of the workshop is to document and discuss the recent rise of new research questions on the general problem of learning across domains and tasks. This includes the main topics of transfer and multi-task learning, together with several related variants as domain adaptation and dataset bias. In the last years there has been an increasing boost of activity in these areas, many of them driven by practical applications, such as object categorization. Different solutions were studied for the considered topics, mainly separately and without a joint theoretical framework. On the other hand, most of the existing theoretical formulations model regimes that are rarely used in practice (e.g. adaptive methods that store all the source samples). This NIPS 2013 workshop will focus on closing this gap by providing an opportunity for theoreticians and practitioners to get together in one place, to share and debate over current theories and empirical results. The goal is to promote a fruitful exchange of ideas and methods between the different communities, leading to a global advancement of the field. Transfer Learning - Transfer Learning (TL) refers to the problem of retaining and applying the knowledge available for one or more source tasks, to efficiently develop an hypothesis for a new target task. Each task may contain the same (domain adaptation) or different label sets (across category transfer). A lot of the effort has been devoted to binary classification, while most interesting practical transfer problems are intrinsically multi-class and the number of classes can often increase in time. Hence, it is natural to ask: - How to formalize knowledge transfer across multi-class tasks and provide theoretical guarantees on this setting? - Can interclass transfer and incremental class learning be properly integrated? - Can learning guarantees be provided when the adaptation relies only on pre-trained source hypotheses without explicit access to the source samples, as it is often the case in real world scenarios? Multi-task Learning - Learning over multiple related tasks can outperform learning each task in isolation. This is the principal assertion of Multi-task learning (MTL) and implies that the learning process may benefit from common information shared across the tasks. In the simplest case, transfer process is symmetric and all the tasks are considered as equally related and appropriate for joint training. - What happens when this condition does not hold, e.g. how to avoid negative transfer? - Can RHKS embeddings be adequately integrated into the learning process to estimate and compare the distributions underlying the multiple tasks? - How may embedding probability distributions help learning from data clouds? - Can deep learning or multiple kernel learning help to get a step closer towards the complete automatization of multi-task learning? - How can notions from reinforcement learning such as source task selection be connected to notions from convex multi-task learning such as the task similarity matrix? Confirmed Invited Speakers - Shai Ben-David (University of Waterloo) - Massimiliano Pontil (University College London) - Fei Sha (University of Southern California) - Arthur Gretton (Gatsby Computational Neuroscience Unit) - Sinno Jialin Pan (Institute for Infocomm Research and National University of Singapore) ========================================================================= Submission: We invite submission of extended abstracts to the workshop on all topics related to transfer and multi-task learning with special interest in - New views and unifying theories on TL and MTL - Learning the task similarities/dissimilarities from the data - Sparse vs non sparse regularization in similarity learning - Domain adaptation - Dataset bias - Use of deep and reinforcement learning for TL and MTL - Large scale and online TL and MTL - Connections of multiple kernel learning to TL and MTL - Innovative applications, e.g. in computer vision or computational biology. Preference will be given to submissions which propose new principled TL and MTL methods or which are likely to generate new debate by rising general issues or suggesting directions for future work. Submissions should be no longer than 4 pages in the NIPS latex style. The extended abstract may be accompanied by an unlimited appendix and other supplementary material, with the understanding that anything beyond 4 pages may be ignored by the program committee. Topics that were recently published or presented elsewhere are allowed, provided that the extended abstract mentions this explicitly. Please send your submission by email to ml-newdirectionsinmtl at lists.tu-berlin.de Important Dates Submission deadline: October 9th, 2013 Acceptance decision: October 23th, 2013 Workshop: December 10th, 2013 Organizers Urun Dogan (Skype Labs / Microsoft) Marius Kloft (Courant Institute of Mathematical Sciences & Memorial Sloan-Kettering Cancer Center) Francesco Orabona (Toyota Technological Institute, Chicago) Tatiana Tommasi (KU Leuven) -------------- next part -------------- An HTML attachment was scrubbed... URL: From peter.ljunglof at heatherleaf.se Wed Sep 25 17:08:24 2013 From: peter.ljunglof at heatherleaf.se (=?iso-8859-1?Q?peter_ljungl=F6f?=) Date: Wed, 25 Sep 2013 23:08:24 +0200 Subject: Connectionists: EACL 2014: 2nd Call for tutorial proposals Message-ID: <8AFAE4ED-5C8E-41DA-84F8-F70BD13B7F62@heatherleaf.se> EACL 2014 SECOND CALL FOR TUTORIAL PROPOSALS Proposals are invited for the Tutorial Program of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), to be held in Gothenburg, Sweden, from 26 to 30 April 2014. The selected tutorials will be given on the Saturday and Sunday preceding the main conference (26 and 27 April). EACL 2014 seeks proposals for tutorials in all areas of computational linguistics, broadly conceived to include disciplines such as Linguistics, Speech, Information Retrieval, Psycholinguistics, and Multimodal Processing. We particularly welcome (1) tutorials which cover advances in newly emerging areas not previously covered in an *ACL related tutorial, and (2) tutorials which provide introductions into related fields which are potentially relevant for the CL community (e.g. bioinformatics, neuroscience, human language processing, video and image analysis, machine learning techniques). In order to gather a widespread audience, the experience and qualifications of the instructors will also be taken into account. REMUNERATION Remuneration for tutorials is regulated by ACL policies: http://aclweb.org/adminwiki/index.php?title=Policy_on_tutorial_teacher_payment Please note that remuneration for tutorial presenters is fixed according to the above policy and does not cover registration fees for the main conference. SUBMISSION DETAILS Proposals for tutorials should contain: 1. A title and brief description of the tutorial content and its relevance to the ACL community (not more than 2 pages). 2. A brief outline of the tutorial structure showing that the tutorial's core content can be covered in a three-hour slot (excluding a coffee break). In exceptional cases six-hour tutorial slots are available as well. 3. The names, postal addresses, phone numbers, and email addresses of the tutorial instructors, including a one-paragraph statement of their research interests and areas of expertise. 4. A list of previous venues and approximate audience sizes, if the same or a similar tutorial has been given elsewhere; otherwise an estimate of the audience size. 5. A description of special requirements for technical equipment (e.g. internet access). Proposals should be submitted by electronic mail, in plain ASCII text, to "tutorials at eacl2014 dot org", no later than 1 November 2013. The subject line should be: "EACL 2014 Tutorial Proposal". Please note that only proposals submitted by e-mail will be taken into account. TUTORIAL SPEAKER RESPONSIBILITIES Accepted tutorial speakers will be notified by 15 November 2013, and must then provide abstracts of their tutorials for inclusion in the conference registration material by 15 December 2013. The description should be in two formats: an ASCII version that can be included in email announcements and published on the conference web site, and a PDF version for inclusion in the electronic proceedings (detailed instructions to follow). Tutorial speakers must provide tutorial materials, at least containing copies of the course slides as well as a bibliography for the material covered in the tutorial, by 1 February 2014. IMPORTANT DATES Submission deadline for tutorial proposals: 1 November 2013 Notification of acceptance: 15 November 2013 Tutorial descriptions due: 15 December 2013 Tutorial course material due: 1 February 2014 Tutorial dates: 26-27 April 2014 TUTORIAL CHAIRS Marco Baroni, University of Trento, Italy Afra Alishahi, Tilburg University, Netherlands Please send inquiries concerning EACL 2014 tutorials to "tutorials at eacl2014 dot org". From rsalakhu at cs.toronto.edu Thu Sep 26 20:20:49 2013 From: rsalakhu at cs.toronto.edu (Ruslan Salakhutdinov) Date: Thu, 26 Sep 2013 20:20:49 -0400 (EDT) Subject: Connectionists: NIPS 2013 Deep Learning Workshop Message-ID: ============================================================ CALL FOR PAPERS NIPS 2013 Deep Learning Workshop December 9th or 10th, 2013 Lake Tahoe, USA. https://sites.google.com/site/deeplearningworkshopnips2013/ Important dates: Submission deadline: October 9th, 2013 Acceptance notification: October 23rd, 2013 ============================================================ Overview: Deep Learning algorithms attempt to discover good representations, at multiple levels of abstraction. There has been rapid progress in this area in recent years, both in terms of algorithms and in terms of applications, but many challenges remain. In this workshop, we will bring together researchers interested in deep learning to review the recent technical progress, discuss the challenges, and identify promising future research directions. The workshop invites paper submissions that will be either presented as oral or in poster format. We encourage submissions on the following (non-exhaustive) list of topics: * deep learning algorithms and models (dropout, deep Boltzmann machines, recurrent neural network, etc.) * unsupervised feature learning models (restricted Boltzmann machines, autoencoders, sparse coding, etc.) * inference and optimization algorithms * semi-supervised and transfer learning algorithms * theoretical foundations of unsupervised / deep learning * applications of deep learning (convolutional networks, word and sentence representation models, etc.) Through invited talks, a panel discussion and presentations by the participants, this workshop will showcase the latest advances in deep learning and address questions that are at the center of current deep learning research (what roles do stochasticity/unsupervised learning/optimization play in deep learning, what are the desiderata for models of images/text/speech, etc.). Panel discussions will be led by the members of the organizing committee as well as by prominent representatives of the machine learning, computer vision and natural language processing communities. Submissions: We solicit submissions of unpublished research papers. Authors are encouraged to restrict themselves to 8 pages (plus 1 additional page containing references only) and must satisfy the formatting instructions of the NIPS 2013 call for papers. Style files are available at http://nips.cc/PaperInformation/StyleFiles. More details on the submission process will be posted shortly. The best papers will be awarded by an oral presentation, all other accepted papers will have a poster presentation. Workshop Organizers: Yoshua Bengio (Universite de Montreal) Hugo Larochele (Universite de Sherbrooke) Ruslan Salakhutdinov (University of Toronto) https://sites.google.com/site/deeplearningworkshopnips2013/ From pascal.fua at epfl.ch Fri Sep 27 07:44:17 2013 From: pascal.fua at epfl.ch (Pascal Fua) Date: Fri, 27 Sep 2013 13:44:17 +0200 Subject: Connectionists: Post-doctoral Positions in Computer Vision at EPFL Message-ID: <52456F91.6040905@epfl.ch> EPFL's Computer Vision Laboratory (http://cvlab.epfl.ch/) has openings for several post-doctoral fellows in the field of Computer Vision. The positions is initially offered for 12 months and can be extended. In particular, we are looking for people interested in: - Augmented Reality. We are about to start an EU project that focuses on developing Augmented Reality techniques for games on mobile devices. It will build on our earlier work on binary descriptors. - Video-based people tracking. We are about to start a project involving tracking multiple players in team sports, with a view to deployment in major sports venues in 2012. See http://cvlab.epfl.ch/research/body/surv/ for more details. - Modeling neurons from microscopy images. Since microscopes now routinely produce high-resolution imagery in such large quantities that the need for automated processing and interpretation is becoming critical, we are working on approaches to providing it. See http://cvlab.epfl.ch/research/medical/neurons/ for more details. 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. EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers away from the city of Geneva. Salaries are in the order of CHF 80000 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 Science, and to have a track record of publications in top conferences and journals. Strong programming skills (C or C++) are a plus. 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. From jaakko.peltonen at aalto.fi Sun Sep 29 15:32:35 2013 From: jaakko.peltonen at aalto.fi (Peltonen Jaakko) Date: Sun, 29 Sep 2013 19:32:35 +0000 Subject: Connectionists: Second Call for Papers: AISTATS 2014, Seventeenth International Conference on Artificial Intelligence and Statistics Message-ID: <34678FBC663BDC47BAD0B96BB3FF28580120D8166B@EXMDB01.org.aalto.fi> ============================================================================== AISTATS 2014 Call for Papers Seventeenth International Conference on Artificial Intelligence and Statistics April 22 - 25, 2014, Reykjavik, Iceland http://www.aistats.org Colocated with a MLSS Machine Learning Summer School ============================================================================== AISTATS is an interdisciplinary gathering of researchers at the intersection of computer science, artificial intelligence, machine learning, statistics, and related areas. Since its inception in 1985, the primary goal of AISTATS has been to broaden research in these fields by promoting the exchange of ideas among them. We encourage the submission of all papers which are in keeping with this objective at http://www.aistats.org. Keynote Speakers: ----------------- Peter Buhlmann, ETH Zurich http://stat.ethz.ch/~buhlmann/ Talk title TBA Andrew Gelman, Columbia University http://www.stat.columbia.edu/~gelman/ Talk title: Weakly Informative Priors: When a little information can do a lot of regularizing Michael I. Jordan, University of California, Berkeley http://www.cs.berkeley.edu/~jordan/ Talk title: On the Computational and Statistical Interface and "Big Data" Tutorial Speakers: ------------------ Roderick Murray-Smith, University of Glasgow http://www.dcs.gla.ac.uk/~rod/ Talk title TBA Christian P. Robert, Ceremade - Universite Paris-Dauphine https://www.ceremade.dauphine.fr/~xian/ Talk title: Approximate Bayesian computation (ABC), methodology and applications Havard Rue, Norwegian University of Science and Technology http://www.ntnu.edu/employees/havard.rue Talk title: Bayesian computing with INLA Paper Submission: ----------------- Proceedings track: This is the standard AISTATS paper submission track. Papers will be selected via a rigorous double-blind peer-review process. All accepted papers will be presented at the Conference as contributed talks or as posters and will be published in the Proceedings. A selected set of papers will be designated as "notable papers" which will be clearly distinguished in the Proceedings. Highlight talks track: We will include talks on recent high-impact work on AISTATS themes. This is an opportunity to raise discussion and get additional exposure to already published work, in particular in journals. The talks will be selected based on one-page abstracts and the existing papers, and they do not lead to a paper in the Proceedings. Late-breaking posters track: Some time at the conference will be set aside for "breaking news" posters having a one-page abstract. These are reports on ongoing or unpublished projects, projects already published elsewhere, partially developed ideas, negative results etc, and are meant as informal forums to encourage discussion. The review process of the late-breaking posters will be very light-touch and presentation at the Conference will not lead to publication in the Proceedings. 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 * Software for and applications of AI and statistics For a more detailed list of keywords, see http://www.aistats.org/keywords.php. Submission Requirements for Proceedings Track: ---------------------------------------------- Electronic submission of papers is required. Papers may be up to 8 double-column pages in length, excluding references. Authors may optionally submit also supplementary material. Formatting and submission information is available at http://www.aistats.org/submit.php. All accepted papers will be published in the Proceedings in the Journal of Machine Learning Research Workshop and Conference Proceedings series. Papers for talks and posters will be treated equally in publication. Submission Deadlines: --------------------- Submissions will be considered if they are received by the following strict deadlines. Proceedings track paper submissions: 1 November, 2013, 23:59 UTC Highlight talk abstract submissions: 24 January, 2014, 23:59 UTC Late-breaking poster abstract submissions: 24 January, 2014, 23:59 UTC See the conference website for additional important dates: http://www.aistats.org/dates.php. Colocated Events: ----------------- A Machine Learning Summer School (MLSS) will be held after the conference (April 25th-May 4th). April 25 will be an AISTATS/MLSS joint tutorial + MLSS poster session day. The summer school features an exciting program with talks from leading experts in the field, see http://mlss2014.hiit.fi for details. Venue: ------ AISTATS 2014 will be held in Reykjavik, the capital of Iceland, in Grand Hotel Reykjavik. Reykjavik and its environs offer a unique mix of culture and varied nature, from glaciers to waterfalls to geysers and thermal pools. This is a unique opportunity to spend an AISTATS afternoon break at a geothermal warm beach, the famous Blue Lagoon. Reykjavik is easily reachable by several airlines; travel information will be available on http://www.aistats.org. Program Chairs: --------------- Samuel Kaski, Aalto University and University of Helsinki Jukka Corander, University of Helsinki Local Chair: Deon Garrett, School of Computer Science, Reykjavik University and Icelandic Institute for Intelligent Machines Senior Program Committee: ------------------------- Edoardo Airoldi, Harvard University Cedric Archambeau, Amazon Peter Auer, University of Leoben Yoshua Bengio, Universite de Montreal Carlo Berzuini, University of Manchester Jeff A. Bilmes, University of Washington Wray Buntine, NICTA Lawrence Carin, Duke University Guido Consonni, Universita Cattolica del Sacro Cuore Koby Crammer, The Technion Emily B. Fox, University of Washington Aapo Hyvarinen, University of Helsinki Timo Koski, KTH Jan Peters, Technische Universitat Darmstadt Volker Roth, Universitat Basel Scott Sisson, University of New South Wales Suvrit Sra, Max-Planck Institute for Intelligent Systems Masashi Sugiyama, Tokyo Institute of Technology Joe Suzuki, Osaka University Bill Triggs, Centre National de Recherche Scientifique Jean-Philippe Vert, Mines ParisTech and Curie Institute Stephen Walker, University of Texas at Austin Kun Zhang, Max Planck Institute for Intelligent Systems To be completed. The European meetings of AISTATS are organized by the European Society for Artificial Intelligence and Statistics. ============== for more information see http://www.aistats.org =============== From fred.hamker at informatik.tu-chemnitz.de Mon Sep 30 14:46:47 2013 From: fred.hamker at informatik.tu-chemnitz.de (Fred Hamker) Date: Mon, 30 Sep 2013 20:46:47 +0200 Subject: Connectionists: Lecturer and research Position (Akademische/r Assistent/in) in Neuro-Robotics Message-ID: <83279E93-B6CF-4253-A7CD-3140DF80FFB2@informatik.tu-chemnitz.de> Lecturer and research Position (Akademische/r Assistent/in) in Neuro-Robotics The position is available at Chemnitz University of Technology in the Department of Computer Science within the Professorship of Artificial Intelligence. It requires teaching and research. Teaching is required about 4 hours per week within the semester and involves lectures and exercises in robotics and neuro-robotics as well as exercises in artificial intelligence or image processing. The candidate is expected to contribute to research in neuro-robotics, e.g. to develop brain inspired models of motor or cognitive processes run on robotic platforms. He or she should have a PhD in computer science or related fields, e.g. electrical engineering. Prior experience in robotics or neuro-computational modeling is advantageous. Good English language skills are necessary. Good German is initially not required, but the candidate should have an interest to learn the German language. We offer a stimulating international and interdisciplinary environment. Available and recently ordered robotic platforms include an iCub head, two Nao, a Koala with stereo pan-tilt vision and several K-Junior V2 robots. The salary is according to German standards (E 13 TV-L or A 13). The position is initially for 4 years, but can be extended. The starting date is April 2014 or earlier. Chemnitz is the third-largest city of the state of Saxony and close to scenic mountains. Major cities nearby are Leipzig and Dresden with a rich tradition of music and culture. Further details (in german) can be found here: http://www.tu-chemnitz.de/verwaltung/personal/stellen/257030_AA_Rab.php Applications should be sent by email (preferably in PDF format) to (fred.hamker at informatik.tu-chemnitz.de). The deadline was on 30.09.2013, but applications will be considered until the position is filled. In addition to a CV the candidate should provide an overview of his planned research for the next 4 years. -------------------- Prof. Dr. Fred H Hamker Artificial Intelligence & Neuro Cognitive Systems Department of Computer Science Chemnitz University of Technology Strasse der Nationen 62 D - 09107 Chemnitz Germany Tel: +49 (0)371 531-37875 Fax: +49 (0)371 531-25739 email: fred.hamker at informatik.tu-chemnitz.de www: http://www.tu-chemnitz.de/informatik/KI/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From z.kourtzi at bham.ac.uk Mon Sep 30 09:56:55 2013 From: z.kourtzi at bham.ac.uk (Zoe Kourtzi) Date: Mon, 30 Sep 2013 14:56:55 +0100 Subject: Connectionists: [PhD/early stage post-doc] Marie Curie ESR University of Cambridge Message-ID: <5FF74E0E-7CE7-48A3-B50F-1E08638D482F@bham.ac.uk> Marie Curie Early Stage Researcher (ESR) University of Cambridge We have an ESR [PhD/early stage post-doc] position to work on the visual perception of shape and material. The project is part of the PRISM network (www.prism-network.eu) that aims to uncover how the brain represents the richly detailed visual 'look and feel' of surfaces and objects in our everyday surroundings. We aim to shed light on how we perceive the 3D shapes, material properties and illumination in the scenes we encounter as we move through the world. The training network provides multi-disciplinary research training at the interface between psychology, neuroscience, computer science, engineering and industrial design. The successful applicant will combine behavioural paradigms to assess 3D shape and material perception, with state-of-the-art fMRI analysis and computational modelling. The applicant may be in the later stages of a PhD programme or just embarking on their academic career. If desired, they will be able to apply for the Ph.D. programme in Cambridge. Applicants should have a strong academic track record in a relevant area (e.g., Experimental Psychology, Biology, Neuroscience, Mathematics, Physics). They must satisfy the eligibility requirements that apply to all Marie Curie Early Stage Researchers: they cannot be in possession of a PhD qualification, and should not have resided in the UK for more than 12 months before appointment. Informal enquiries should be directed to Dr Andrew Welchman: andrew at welchman.org Full details can be found here: http://www.jobs.cam.ac.uk/job/2122/ Closing date for applications is 26th October 2013 ------ Andrew E Welchman, PhD Wellcome Trust Senior Research Fellow in Basic Biomedical Science Department of Psychology University of Cambridge Downing Street Cambridge CB2 3EB From z.kourtzi at bham.ac.uk Mon Sep 30 09:58:08 2013 From: z.kourtzi at bham.ac.uk (Zoe Kourtzi) Date: Mon, 30 Sep 2013 14:58:08 +0100 Subject: Connectionists: [post-doc] Neural basis of 3D perception Message-ID: <96DACC6E-028B-460B-A6F9-F9B30C534FCA@bham.ac.uk> Post-doc positions on 3D vision University of Cambridge Two post-doc positions are available to work on the neural basis of 3D vision. The project examines the representation of depth information within visually responsive cortex using fMRI, TMS and EEG. We study the representation of binocular disparity signals, the integration of different depth cues and association between neuronal responses and perception. The successful candidates will join a dynamic international and interdisciplinary team within the Department of Psychology, University of Cambridge. The lab is well equipped and the intellectual environment of the Department and wider University outstanding. Candidates should hold or expect to hold a Ph.D. in Experimental Psychology, Neuroscience, Computer Science, Physics, Mathematics or a related field. Programming skills (e.g. Matlab, C) are essential and experience with brain imaging methods (fMRI, EEG, TMS) is desirable. Informal enquiries should be directed to Dr Andrew Welchman: andrew at welchman.org Full details can be found here: http://www.jobs.cam.ac.uk/job/2119/ Closing date for applications is 26th October 2013 ------ Andrew E Welchman, PhD Wellcome Trust Senior Research Fellow in Basic Biomedical Science Department of Psychology University of Cambridge Downing Street Cambridge CB2 3EB From twaldron at Princeton.EDU Mon Sep 30 13:50:35 2013 From: twaldron at Princeton.EDU (Timothy P. Waldron) Date: Mon, 30 Sep 2013 17:50:35 +0000 Subject: Connectionists: Faculty Positions at the Princeton Neuroscience Institute Message-ID: <565CB0B8EFE92946A689DC622A64ABE60DD5B72D@CSGMBX201W.pu.win.princeton.edu> Princeton University is committed to the continued expansion and development of neuroscience on its campus. In addition to other outstanding resources, a newly constructed 248,000 square foot building will open in late fall 2013 housing state-of-the-art facilities for the full range of neuroscientific methods, including human brain imaging, cellular and circuit level imaging in model organisms, structural neurobiology, studies of non-human primates, and computation and theory. These new facilities will support the continued growth of neuroscience at Princeton, including the three new positions described below. We are seeking qualified individuals working at all levels of neuroscience, to study development, learning, memory, perception, attention and higher level cognitive functions in humans and non-human species. Tenured Full Professor Position The Princeton Neuroscience Institute invites applications for a tenured appointment at the associate or full professor level to begin on or after September 2014. Key selection criteria will be research excellence, originality of science, future impact on the field of neuroscience and related disciplines, and leadership capabilities. Applicants must have an excellent record of research productivity and demonstrate the ability to develop a rigorous research program. We seek applicants pursuing research directions with significant conceptual and/or empirical integration across traditional disciplinary boundaries. The appointee could be either an experimentalist or theorist. The successful candidate will join the Neuroscience Institute and may also join a department appropriate to the individual's background and interests, with possibilities including (but not limited to) Psychology, Molecular Biology, Mathematics, Physics, Electrical Engineering and Computer Science. Applicants should be prepared to teach courses both at the undergraduate and graduate levels in neuroscience. Please submit a curriculum vitae, a brief research description, and contact information for three references at http://jobs.princeton.edu, requisition # 1300694. Applications will be considered on a rolling basis, and the search will remain open until the position is filled. Tenure Track Assistant Professor Position The Princeton Neuroscience Institute invites applications for a tenure track appointment at the assistant professor level to begin on or after September 2014. Key selection criteria will be research excellence, originality of science, and future impact on the field of neuroscience and related disciplines. We seek applicants pursuing research directions with significant conceptual and/or empirical integration across traditional disciplinary boundaries. The successful candidate will join the Neuroscience Institute and may also join a department appropriate to the individual's background and interests, with possibilities including (but not limited to) Psychology, Molecular Biology, Mathematics, Physics, Electrical Engineering and Computer Science. Applicants should be prepared to teach courses both at the undergraduate and graduate levels in neuroscience. Please submit a curriculum vitae, a brief research description, and contact information for three references at http://jobs.princeton.edu, requisition #1300702. Applications will be considered on a rolling basis, and the search will remain open until the position is filled. Position in Theoretical Neuroscience The Princeton Neuroscience Institute invites applications for a tenure track appointment at the assistant professor level to begin on or after September 2014. Key selection criteria will be research excellence, originality of science, and future impact on the field of neuroscience and related disciplines. The appointee would be expected to make contributions to theoretical and/or computational neuroscience and to engage with theoretically, computationally, and empirically inclined neuroscience researchers and trainees across a wide range of departments. The successful candidate will join the Neuroscience Institute and may also join a department appropriate to the individual's background and interests, with possibilities including (but not limited to) Psychology, Molecular Biology, Mathematics, Physics, Electrical Engineering and Computer Science. The applicant would be expected to participate in the graduate and undergraduate training programs in neuroscience and should be prepared to teach courses as part of each. Please submit a curriculum vitae, a brief research description, and contact information for three references at http://jobs.princeton.edu, requisition #1300701. Applications will be considered on a rolling basis, and the search will remain open until the position is filled. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Mon Sep 30 14:40:19 2013 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 30 Sep 2013 14:40:19 -0400 Subject: Connectionists: Neuroscience Gateway Portal workshop at SFN 2013 meeting Message-ID: <5249C593.9020105@yale.edu> The Neuroscience Gateway Portal workshop at the SFN 2013 meeting is for neuroscientists who are interested in running simulations on high performance computing resourses. The NSG http://www.nsgportal.org/ is designed to make this task much easier. It already has Brian, MOOSE, NEST, NEURON, PGENESIS, and PyNN installed, and free CPU time is available. Come to the NSG workshop to see how your own research might benefit from this tool. The workshop will run from 9 AM to noon on Saturday, November 9, just a couple of blocks from the convention center. Attendance is limited to 20 participants, and the registration deadline is Friday, October 25, so be sure to sign up now at http://www.neuron.yale.edu/neuron/static/courses/nsg2013/nsg2013.html --Ted From sumitb at microsoft.com Mon Sep 30 16:21:02 2013 From: sumitb at microsoft.com (Sumit Basu) Date: Mon, 30 Sep 2013 20:21:02 +0000 Subject: Connectionists: Final Call for Papers (and deadline extension): NIPS 2013 Workshop on Data-Driven Education Message-ID: <6abc870fc2184f0bb8867c96bd347559@BN1PR03MB201.namprd03.prod.outlook.com> It is our pleasure to invite contributions to: The NIPS 2013 Workshop on Data-Driven Education December 10, 2013 Lake Tahoe, Nevada, USA http://lytics.stanford.edu/datadriveneducation IMPORTANT DATES + Paper Submission --- October 16th, 2013 (a one-week extension of the original deadline) + Author notification --- October 23rd, 2013 + Camera-ready deadline for accepted submissions --- October 28th, 2013 + Finalized workshop schedule out --- October 30th, 2013 + Data-Driven Education Workshop --- Tuesday, December 10th, 2013 WORKSHOP DESCRIPTION Given the incredible technological leaps that have changed so many aspects of our lives in the last hundred years, it's surprising that our approach to education today is much the same as it was a century ago. While successful educational technologies have been developed and deployed in some areas, we have yet to see a widespread disruption in teaching methods at the primary, secondary, or post-secondary levels. However, as more and more people gain access to broadband internet, and new technology-based learning opportunities are introduced, we may be witnessing the beginnings of a revolution in educational methods. In the realm of higher education, rising college tuition accompanied with cuts in funding to schools and an ever increasing world population that desires high-quality education at low cost has spurred the need to use technology to transform how we deliver education. With these technology-based learning opportunities, the rate at which educational data is being collected has also exploded in recent years as an increasing number of students have turned to online resources, both at traditional universities as well as massively open-access online courses (MOOCs) for formal or informal learning. This change raises exciting challenges and possibilities particularly for the machine learning and data sciences communities. These trends and changes are the inspiration for this workshop, and our first goal is to highlight some of the exciting and impactful ways that our community can bring tools from machine learning to bear on educational technology. Some examples include (but are not limited to) the following: + Adaptive and personalized education + Gamification and crowdsourcing in learning + Large scale analytics of MOOC data + Multimodal sensing + Optimization of pedagogical strategies and curriculum design + Content recommendation for learners + Interactive Tutoring Systems + Intervention evaluations and causality modeling + Supporting collaborative and social learning + Data-driven models of human learning + Analysis of social networks of students and teachers + Automated, semi-automated, and crowdsourced methods for formative and summative assessment. The second goal of the workshop is to accelerate the progress of research in these areas by addressing the challenges of data availability. At the moment, there are several barriers to entry including the lack of open and accessible datasets as well as unstandardized formats for such datasets. We hope that by (1) surveying a number of the publicly available datasets, and (2) proposing ways to distribute other datasets such as MOOC data in a spirited panel discussion we can make real progress on this issue as a community, thus lowering the barrier for researchers aspiring to make a big impact in this important area. TARGET AUDIENCE + Researchers interested in analyzing and modeling educational data, + Researchers interested in improving or developing new data-driven educational technologies, + Others from the NIPS community curious about the trends in online education and the opportunities for machine learning research in this rapidly-developing area. CONFIRMED SPEAKERS + Ken Koedinger, CMU + Andrew Ng, Coursera/Stanford (tentative) + Peter Norvig, Google + Zoran Popovic, UW + Jascha Sohl-Dickstein, Stanford/Khan Academy + Daniel Seaton, MIT/EdX CONFIRMED PANELISTS + Eliana Feasley, Khan Academy, + Una-May O'Reilly, MIT, + Jim Bower UT Austin/Numedeon + as well as the invited speakers. ORGANIZERS + Jonathan Huang, Stanford (jhuang11 at stanford.edu) + Sumit Basu, Microsoft Research (sumitb at microsoft.com) + Kalyan Veeramachaneni, CSAIL, MIT (kalyan at csail.mit.edu) SUBMISSION DETAILS Submissions should follow the NIPS format and are encouraged to be up to six pages. Papers submitted for review do not need to be anonymized. There will be no official proceedings, but the accepted papers will be made available on the workshop website. Accepted papers will be either presented (both) as a poster and a short spotlight presentation. We welcome submissions on novel research work as well as extended abstracts on work recently published or under review in another conference or journal (please state the venue of publication in the latter case); we encourage submission of visionary position papers on the emerging trends in data driven education. Please submit papers in PDF format tonipsdde2013 at gmail.com. For more information, please visit: http://lytics.stanford.edu/datadriveneducation From y.hayashi at reading.ac.uk Mon Sep 30 17:28:35 2013 From: y.hayashi at reading.ac.uk (Yoshikatsu Hayashi) Date: Mon, 30 Sep 2013 21:28:35 +0000 Subject: Connectionists: Second Call for Papers: AISTATS 2014, Seventeenth International Conference on Artificial Intelligence and Statistics In-Reply-To: <34678FBC663BDC47BAD0B96BB3FF28580120D8166B@EXMDB01.org.aalto.fi> Message-ID: -- --------------------------------------------------------------------------- Yoshikatsu Hayashi (PhD) Lecturer in Cybernetical Physics Affiliation: Brain Embodiment Lab, School of Systems Engineering, University of Reading Address: PO Box 225, Whiteknights, Reading RG6 6AY, UK Tel: +44-118-378-5024 E-mail: y.hayashi at reading.ac.uk Website: http://bel.reading.ac.uk/ --------------------------------------------------------------------------- On 2013/09/29 20:32, "Peltonen Jaakko" wrote: >========================================================================== >==== >AISTATS 2014 Call for Papers >Seventeenth International Conference on Artificial Intelligence and >Statistics >April 22 - 25, 2014, Reykjavik, Iceland >http://www.aistats.org > >Colocated with a MLSS Machine Learning Summer School >========================================================================== >==== > >AISTATS is an interdisciplinary gathering of researchers at the >intersection >of computer science, artificial intelligence, machine learning, >statistics, >and related areas. Since its inception in 1985, the primary goal of >AISTATS >has been to broaden research in these fields by promoting the exchange of >ideas among them. We encourage the submission of all papers which are in >keeping with this objective at http://www.aistats.org. > > >Keynote Speakers: >----------------- >Peter Buhlmann, ETH Zurich >http://stat.ethz.ch/~buhlmann/ >Talk title TBA > >Andrew Gelman, Columbia University >http://www.stat.columbia.edu/~gelman/ >Talk title: Weakly Informative Priors: When a little information can do a >lot >of regularizing > >Michael I. Jordan, University of California, Berkeley >http://www.cs.berkeley.edu/~jordan/ >Talk title: On the Computational and Statistical Interface and "Big Data" > > >Tutorial Speakers: >------------------ >Roderick Murray-Smith, University of Glasgow >http://www.dcs.gla.ac.uk/~rod/ >Talk title TBA > >Christian P. Robert, Ceremade - Universite Paris-Dauphine >https://www.ceremade.dauphine.fr/~xian/ >Talk title: Approximate Bayesian computation (ABC), methodology and >applications > >Havard Rue, Norwegian University of Science and Technology >http://www.ntnu.edu/employees/havard.rue >Talk title: Bayesian computing with INLA > > >Paper Submission: >----------------- >Proceedings track: This is the standard AISTATS paper submission track. >Papers >will be selected via a rigorous double-blind peer-review process. All >accepted >papers will be presented at the Conference as contributed talks or as >posters >and will be published in the Proceedings. A selected set of papers will be >designated as "notable papers" which will be clearly distinguished in the >Proceedings. > >Highlight talks track: We will include talks on recent high-impact work on >AISTATS themes. This is an opportunity to raise discussion and get >additional >exposure to already published work, in particular in journals. The talks >will >be selected based on one-page abstracts and the existing papers, and they >do >not lead to a paper in the Proceedings. > >Late-breaking posters track: Some time at the conference will be set >aside for >"breaking news" posters having a one-page abstract. These are reports on >ongoing or unpublished projects, projects already published elsewhere, >partially developed ideas, negative results etc, and are meant as informal >forums to encourage discussion. The review process of the late-breaking >posters will be very light-touch and presentation at the Conference will >not >lead to publication in the Proceedings. > > >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 >* Software for and applications of AI and statistics > >For a more detailed list of keywords, see >http://www.aistats.org/keywords.php. > > >Submission Requirements for Proceedings Track: >---------------------------------------------- >Electronic submission of papers is required. Papers may be up to 8 >double-column pages in length, excluding references. Authors may >optionally >submit also supplementary material. Formatting and submission information >is >available at http://www.aistats.org/submit.php. > >All accepted papers will be published in the Proceedings in the Journal of >Machine Learning Research Workshop and Conference Proceedings series. >Papers >for talks and posters will be treated equally in publication. > > >Submission Deadlines: >--------------------- >Submissions will be considered if they are received by the following >strict >deadlines. > >Proceedings track paper submissions: 1 November, 2013, 23:59 UTC >Highlight talk abstract submissions: 24 January, 2014, 23:59 UTC >Late-breaking poster abstract submissions: 24 January, 2014, 23:59 UTC > >See the conference website for additional important dates: >http://www.aistats.org/dates.php. > > >Colocated Events: >----------------- >A Machine Learning Summer School (MLSS) will be held after the conference >(April 25th-May 4th). April 25 will be an AISTATS/MLSS joint tutorial + >MLSS >poster session day. The summer school features an exciting program with >talks >from leading experts in the field, see http://mlss2014.hiit.fi for >details. > > >Venue: >------ >AISTATS 2014 will be held in Reykjavik, the capital of Iceland, in Grand >Hotel >Reykjavik. Reykjavik and its environs offer a unique mix of culture and >varied >nature, from glaciers to waterfalls to geysers and thermal pools. This is >a >unique opportunity to spend an AISTATS afternoon break at a geothermal >warm >beach, the famous Blue Lagoon. > >Reykjavik is easily reachable by several airlines; travel information >will be >available on http://www.aistats.org. > > >Program Chairs: >--------------- >Samuel Kaski, Aalto University and University of Helsinki >Jukka Corander, University of Helsinki > >Local Chair: Deon Garrett, School of Computer Science, Reykjavik >University >and Icelandic Institute for Intelligent Machines > > >Senior Program Committee: >------------------------- >Edoardo Airoldi, Harvard University >Cedric Archambeau, Amazon >Peter Auer, University of Leoben >Yoshua Bengio, Universite de Montreal >Carlo Berzuini, University of Manchester >Jeff A. Bilmes, University of Washington >Wray Buntine, NICTA >Lawrence Carin, Duke University >Guido Consonni, Universita Cattolica del Sacro Cuore >Koby Crammer, The Technion >Emily B. Fox, University of Washington >Aapo Hyvarinen, University of Helsinki >Timo Koski, KTH >Jan Peters, Technische Universitat Darmstadt >Volker Roth, Universitat Basel >Scott Sisson, University of New South Wales >Suvrit Sra, Max-Planck Institute for Intelligent Systems >Masashi Sugiyama, Tokyo Institute of Technology >Joe Suzuki, Osaka University >Bill Triggs, Centre National de Recherche Scientifique >Jean-Philippe Vert, Mines ParisTech and Curie Institute >Stephen Walker, University of Texas at Austin >Kun Zhang, Max Planck Institute for Intelligent Systems >To be completed. > > >The European meetings of AISTATS are organized by the European Society for >Artificial Intelligence and Statistics. > >============== for more information see http://www.aistats.org >=============== > >--- >Wiki: http://grey.colorado.edu/Connectionists From Colin.Wise at uts.edu.au Mon Sep 30 20:13:35 2013 From: Colin.Wise at uts.edu.au (Colin Wise) Date: Tue, 1 Oct 2013 10:13:35 +1000 Subject: Connectionists: REMINDER - AAI Short Course - 'Data Mining - an Introduction' - Wednesday 9 October 2013 Message-ID: <8112393AA53A9B4A9BDDA6421F26C68A01410958DB9F@MAILBOXCLUSTER.adsroot.uts.edu.au> Dear Colleague, REMINDER : AAI Short Course - 'Data Mining - an Introduction' - Wednesday 9 October 2013 https://shortcourses-bookings.uts.edu.au/Clientview/Schedules/ScheduleDetail.aspx?ScheduleID=1357 Our AAI short course 'Data Mining - an Introduction' may be of interest to you and or others in your organisation or network. The Data Mining short course is an introduction to the foundations of data mining and knowledge discovery methods and their application to practical problems. It brings together the state-of-the-art research and practical techniques in data mining. Please register here LINK An important foundation short course in the AAI series of advanced data analytic short courses - please view this short course and others here LINK We are happy to discuss at your convenience. Thank you and regards. Colin Wise Operations Manager Advanced Analytics Institute (AAI) Blackfriars Building 2, Level 1 University of Technology, Sydney (UTS) Email: Colin.Wise at uts.edu.au Tel. +61 2 9514 9267 M. 0448 916 589 AAI: www.analytics.uts.edu.au/ Reminder - AAI Short Course - Advanced Data Analytics - an Introduction - Tuesday 19 November 2013 Future short courses on Data Analytics and Big Data may be viewed at LINK AAI Education and Training Short Courses Survey - you may be interested in completing our AAI Survey at LINK AAI June 2013 Newsletter LINK AAI Email Policy - should you wish to not receive this periodic communication on Data Analytics Learning please reply to our email (to sender) with UNSUBSCRIBE in the Subject. We will delete you from our database. Thank you for your past and future support. UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any accompanying attachments may contain confidential information. If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or attachments. If you have received this message in error, please notify the sender immediately and delete this message. Any views expressed in this message are those of the individual sender, except where the sender expressly, and with authority, states them to be the views of the University of Technology Sydney. Before opening any attachments, please check them for viruses and defects. Think. Green. Do. Please consider the environment before printing this email. -------------- next part -------------- An HTML attachment was scrubbed... URL: