From cpoon at mit.edu Tue Jul 1 10:08:22 2014 From: cpoon at mit.edu (Chi-Sang Poon) Date: Tue, 1 Jul 2014 10:08:22 -0400 Subject: Connectionists: A multiscale perspective of the BRAIN Initiative In-Reply-To: <5D1C6602-9738-4652-A2A8-FFFF54D6CD34@columbia.edu> References: <5D1C6602-9738-4652-A2A8-FFFF54D6CD34@columbia.edu> Message-ID: <019301cf9535$eb62a6b0$c227f410$@edu> An upcoming paper titled "Multiscale fingerprinting of neuronal functional connectivity" in the journal Brain Structure and Function (in press) is available in MIT's open access collection: https://dspace.mit.edu/handle/1721.1/88126 SUMMARY. Current cellular-based connectomics approaches aim to delineate the functional or structural organizations of mammalian brain circuits through neuronal activity mapping and/or axonal tracing. To discern possible connectivity between functionally identified neurons in widely distributed brain circuits, reliable and efficient network-based approaches of cross-registering or cross-correlating such functional-structural data are essential. Here, a novel cross-correlation approach that exploits multiple timing-specific, response-specific and cell-specific neuronal characteristics as coincident fingerprint markers at the systems, network and cellular levels is proposed. Application of this multiscale temporal-cellular coincident fingerprinting assay to the respiratory central pattern generator network in rats revealed a descending excitatory pathway with characteristic activity pattern and projecting from a distinct neuronal population in pons to its counterparts in medulla that control the post-inspiratory phase of the respiratory rhythm important for normal breathing, airway protection and respiratory-vocalization coordination. This enabling neurotracing approach may prove valuable for functional connectivity mapping of other brain circuits. -------------- next part -------------- An HTML attachment was scrubbed... URL: From silvio.sabatini at unige.it Tue Jul 1 02:40:45 2014 From: silvio.sabatini at unige.it (Silvio P. Sabatini) Date: Tue, 01 Jul 2014 08:40:45 +0200 Subject: Connectionists: =?utf-8?q?PhD_position=2C_University_of_Genoa=2C_?= =?utf-8?q?Italy_=E2=80=93_Multidimensional_peripersonal_space_sensing?= Message-ID: <53B257ED.9080401@unige.it> Applications are invited for one full-time PhD studentship (with scholarship) for a period of 3 years, starting Nov 2014, at ?The Physical Structure of Perception and Computation? (PSPC) lab of the Department of Informatics, Bioengineering, Robotics, and System Engineering (DIBRIS), University of Genoa, Italy. The proposed PhD research project will be focused on ?Representing peripersonal space through sensorimotor likelihoods?. On the ground of the research framework developed in the PSPC lab at DIBRIS (see www.eyeshots.it, [1]), the activity will focus on the design of theoretical models by converting computational approaches from engineering into cortical-like models of implicit representations of the peripersonal space. Such implicit representations, besides advancing experimental predictions about neuronal activity, are expected to drive learning of meaningful interactions with the environment thus achieving fluid multi-dimensional motor control in the presence of multiple sensory channels, and with minimal a priori knowledge. [1] Antonelli M., Gibaldi A., Beuth F., Duran A.J., Canessa A., Chessa M., Solari F., del Pobil A.P., Hamker F., Chinellato E. and Sabatini S.P. (in press) A hierarchical system for a distributed representation of the peripersonal space of a humanoid robot. IEEE Trans. on Autonomous Mental Development. The project will provide the opportunity to work on neural modeling, visual psychophysics, robotics, or a combination of them. Experimental, modeling, and theoretical approaches might be pursued with a different accent according to personal attitude. Ongoing cooperation, at international level, with research groups of different disciplines, will ensure a highly interdisciplinary and stimulating environment. Full details on the call and the application procedure are available at: http://phd.dibris.unige.it/biorob/index.php/how-to-apply Successful applicants would have a good honors degree in bioengineering, computer science, physics or related disciplines, strong interest in computational neuroscience, and an open mind for interdisciplinary research. On-line application will be soon opening (deadline: August 30th, 2014 at 12:00 noon (Italian time/CET)) Prospective students, please contact: Silvio Sabatini (silvio.sabatini at unige.it). DIBRIS is a unique inter-school department of the University of Genoa, bridging together researchers from the former Science and Engineering Faculties. It offers an excellent multidisciplinary, interactive and collaborative research environment combining expertise in computer vision, computational neuroscience, neuromorphic computing, robotics and mechatronics. PSPC-Lab (www.pspc.unige.it), has a long-standing expertise in visual coding and multidimensional signal representation, robot perception and computer vision. In the last five years, the lab?s research activity focused on the analysis of the structural mechanisms of visuo-spatial cognition, responsible for orienting and interacting in the 3D space. -- --------------------------------------------------------------------- Silvio P. SABATINI, PhD [PSPC Research Group] Professor of Bioengineering DIBRIS - University of Genova | e_mail:silvio.sabatini at unige.it Via Opera Pia, 11A | phone: +39 010 3532092/3532794 I-16145 Genova (ITALY) | fax: +39 010 3532289/3536533 URL:http://pspc.unige.it --------------------------------------------------------------------- "Imagination is more important than knowledge..." [Albert Einstein] From silvio.sabatini at unige.it Tue Jul 1 03:03:42 2014 From: silvio.sabatini at unige.it (Silvio P. Sabatini) Date: Tue, 01 Jul 2014 09:03:42 +0200 Subject: Connectionists: PhD position, University of Genoa, Italy - 3D shape visual descriptors Message-ID: <53B25D4E.1020401@unige.it> Applications are invited for one full-time PhD studentship (with scholarship) for a period of 3 years, starting Nov 2014, at ?The Physical Structure of Perception and Computation? lab of the Department of Informatics, Bioengineering, Robotics, and System Engineering (DIBRIS), University of Genoa, Italy. The proposed PhD research project will be focused on ?Learning compositional visual representation of 3D shapes in vergent geometry?. The goal is to derive a deep architecture for abstracting the statistically relevant information present in the disparity patterns obtained by binocular fixations. Starting from a neuromorphic early representation of 2D binocular disparity, the resulting 3D visual descriptors should be characterized by generalized perceptual constancy. The project will provide the opportunity to work on neural modeling, visual psychophysics, computer vision, or a combination of them. Experimental, modeling, and theoretical approaches might be pursued with a different accent according to personal attitude. Ongoing cooperation, at international level, with research groups of different disciplines, will ensure a highly interdisciplinary and stimulating environment. Successful applicants will have at their disposal state-of-the-art sw and hw, 3D VR-AR experimental set-ups, a high precision 3D laser scanner, a large-scale CPU/GPU-based neuromorphic architecture for joint stereo and motion cortical representation, and an iCub 6dof binocular robot head. Successful applicants would have a good honors degree in bioengineering, computer science, physics or related disciplines, strong interest in computational neuroscience, and an open mind for interdisciplinary research. On-line application will be soon opening (deadline: August 30th, 2014 at 12:00 noon (Italian time/CET)) Prospective students, please contact: Silvio Sabatini (silvio.sabatini at unige.it). DIBRIS is a unique inter-school department of the University of Genoa, bridging together researchers from the former Science and Engineering Faculties. It offers an excellent multidisciplinary, interactive and collaborative research environment combining expertise in computer vision, computational neuroscience, neuromorphic computing, robotics and mechatronics. PSPC-Lab (www.pspc.unige.it), has a long-standing expertise in visual coding and multidimensional signal representation, robot perception and computer vision. In the last five years, the lab?s research activity focused on the analysis of the structural mechanisms of visuo-spatial cognition, responsible for orienting and interacting in the 3D space. -- --------------------------------------------------------------------- Silvio P. SABATINI, PhD [PSPC Research Group] Professor of Bioengineering DIBRIS - University of Genova | e_mail:silvio.sabatini at unige.it Via Opera Pia, 11A | phone: +39 010 3532092/3532794 I-16145 Genova (ITALY) | fax: +39 010 3532289/3536533 URL:http://pspc.unige.it --------------------------------------------------------------------- "Imagination is more important than knowledge..." [Albert Einstein] -------------- next part -------------- An HTML attachment was scrubbed... URL: From A.Soltoggio at lboro.ac.uk Tue Jul 1 10:12:59 2014 From: A.Soltoggio at lboro.ac.uk (Andrea Soltoggio) Date: Tue, 1 Jul 2014 15:12:59 +0100 Subject: Connectionists: Neural plasticity for rich and uncertain robotic information streams. Call for participation to our upcoming Frontiers research topic. Message-ID: Dear all, I would like to inform you that the research topic ?Neural plasticity for rich and uncertain information streams?, hosted by Frontiers in Neurorobotics, has now opened for submission. Description: Models of adaptation and neural plasticity are often demonstrated in robotic scenarios with heavily pre-processed and regulated information streams to provide learning algorithms with appropriate, well timed, and meaningful data to match the assumptions of learning rules. On the contrary, natural scenarios are often rich of raw, asynchronous, overlapping and uncertain inputs and outputs whose relationships and meaning are progressively acquired, disambiguated, and used for further learning. Therefore, recent research efforts focus on neural embodied systems that rely less on well timed and pre-processed inputs, but rather extract autonomously relationships and features in time and space. In particular, realistic and more complete models of plasticity must account for delayed rewards, noisy and ambiguous data, emerging and novel input features during online learning. Such approaches model the progressive acquisition of knowledge into neural systems through experience in environments that may be affected by ambiguities, uncertain signals, delays, or novel features. This research topic promises to unveil fundamental properties and dynamics of neural learning system that are naturally immersed in a rich information flow. We invite papers describing advances in robotic neural learning systems that model adaptation or plasticity with a rich and realistic stream of information. Abstract Submission Deadline: Aug 11, 2014, Article Submission Deadline: Jan 12, 2015 Topic Editor(s): Andrea Soltoggio, Fran van der Velde Frontiers, a Swiss open-access publisher, recently partnered with Nature Publishing Group to expand its researcher-driven Open Science platform. Frontiers articles are rigorously peer-reviewed, can be disseminated freely and are widely read by your colleagues and by the broader scientific and medical research communities. The idea behind a research topic is to create an organized, comprehensive collection of several contributions, as well as a forum for discussion and debate. Contributions can be articles describing original research, methods, hypothesis & theory, opinions, etc. We have created a homepage on the Frontiers website (Frontiers in Neurorobotics) where all articles will appear after peer-review and where participants in the topic will be able to hold relevant discussions: http://www.frontiersin.org/Neurorobotics/researchtopics/Neural_plasticity_for_rich_and/3107 . Frontiers will also compile an e-book, as soon as all contributing articles are published, that can be used in classes, be sent to foundations that fund your research, to journalists and press agencies, or to any number of other organizations. As such, a manuscript accepted for publication incurs a publishing fee, which varies depending on the article type. Research Topic manuscripts receive a significant discount on publishing fees. Please take a look at this fee table: http://www.frontiersin.org/about/PublishingFees. Once published, your articles will remain free to access for all readers, and will be indexed in PubMed and other academic archives. As an author in Frontiers, you retain the copyright to your own papers and figures. Should you choose to participate, please confirm by sending me a quick email and then your abstract no later than Aug 11, 2014 using the following link: http://www.frontiersin.org/Neurorobotics/researchtopics/Neural_plasticity_for_rich_and/3107 With best regards, Andrea Soltoggio Guest Associate Editor, Frontiers in Neurorobotics www.frontiersin.org Lecturer in Computer Science and Artificial Intelligence Haslegrave Building, N.2.03 Loughborough University LE11 3TU UK -------------- next part -------------- An HTML attachment was scrubbed... URL: From cookie at ucsd.edu Tue Jul 1 12:51:42 2014 From: cookie at ucsd.edu (Santamaria, Cookie) Date: Tue, 1 Jul 2014 16:51:42 +0000 Subject: Connectionists: POSTDOCTORAL RESEARCHER IN SYSTEMS NEUROSCIENCE Message-ID: POSTDOCTORAL RESEARCHER IN SYSTEMS NEUROSCIENCE The BioCircuits Institute (BCI) and Departments of Physics, Chemistry/Biochemistry, Bioengineering, and Psychology and Neurobiology at the University of California, San Diego invite applications for a postdoctoral position in systems neuroscience, for experiments leading to the neuromorphic engineering of cognitive abilities. The ideal candidate will have experience with in vivo electrophysiology, in awake behaving animals, and desire to apply biologically inspired algorithms to VLSI circuits and systems. Close interaction with other project researchers in computational and theoretical neuroscience, nonlinear dynamical systems, and neuromorphic engineering is involved. We will accept applications immediately and will begin making selections on 1 September 2014, until the position is filled. Appointments are for two years (in one-year increments) with the possibility of a third. Send your statement of qualifications and interest with curriculum vitae, your two most significant publications and three letters of reference to Tim Gentner, Henry Abarbanel, Gert Cauwenberghs, Katja Lindenberg, Mikhail Rabinovich, and Terrence Sejnowski via email to: >. A Ph.D. or equivalent doctoral degree is required prior to the appointment. UCSD is an EO/AA employer. -------------- next part -------------- An HTML attachment was scrubbed... URL: From birgit.ahrens at bcf.uni-freiburg.de Wed Jul 2 06:35:03 2014 From: birgit.ahrens at bcf.uni-freiburg.de (Birgit Ahrens) Date: Wed, 02 Jul 2014 12:35:03 +0200 Subject: Connectionists: BCF/NWG course "Analysis and Models in Neurophysiology" - Deadline Extension to July 14 In-Reply-To: <53901842.9070501@bcf.uni-freiburg.de> References: <538EF514.1070307@bcf.uni-freiburg.de> <53901842.9070501@bcf.uni-freiburg.de> Message-ID: <53B3E057.9090706@bcf.uni-freiburg.de> The application deadline for the BCF/NWG course is extended to *Monday, July 14, 2014*. Please find more information on the course and the application process below. --------------------------------------------------------------------------------------------------------------------------------------------------------------- BCF/NWG-Course "Analysis and Models in Neurophysiology" /Sunday, October 5 - Friday, October 10, 2014 / /Bernstein Center Freiburg, Hansastra?e 9a, 79104 Freiburg, Germany/ *Aim of the course:* The course is intended to provide advanced Diploma/Masters and PhD students, as well as young researchers from the neurosciences with approaches for the analysis of electrophysiological data and the theoretical concepts behind them. *The course includes various topics such as*: * Neuron Models and Point Processes (Prof. Stefan Rotter) * Local field potentials (Prof. Ulrich Egert) * Neural Coding (Dr. Robert Schmidt) * Neural Decoding (Prof. Carsten Mehring) The course will consist of lectures in the morning and and matching exercises using Matlab, Mathematica and Python in the afternoon. Experience with these software packages will be helpful but is not required for registration. The participants should have a basic understanding of scientific programming. This course is designated especially for advanced diploma/master-students and PhD-students (preferentially in their first year). *Application:* Please apply by sending one pdf document containing your CV and a meaningful letter of motivation to nwg-course at bcf.uni-freiburg.de. The letter of motivation should refer to the following points: * Reasons for wanting to take this course * Background in mathematics * Experience in using Matlab/Python/Mathematica * Background in neuroscience The course is limited to 20 participants. *Course fees:* NWG members - 50EUR, others - 125EUR *Application deadline: *July 14, 2014 *More information: *http://www.bcf.uni-freiburg.de/events/conferences-workshops/20141005-nwgcourse *-- Dr. Birgit Ahrens --* Teaching & Training Coordinator Bernstein Center Freiburg University of Freiburg Hansastr. 9a D - 79104 Freiburg Germany Phone: +49 (0) 761 203-9575 Fax: +49 (0) 761 203-9559 -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.butz at fz-juelich.de Wed Jul 2 07:39:55 2014 From: m.butz at fz-juelich.de (Dr. Markus Butz-Ostendorf) Date: Wed, 2 Jul 2014 13:39:55 +0200 Subject: Connectionists: Open position: Graduate researcher (f/m) Message-ID: <53B3EF8B.60400@fz-juelich.de> Open position: Graduate researcher (f/m) Advertising institute: JSC - J?lich Supercomputing Centre Reference number: 2014-120 URL: http://www.fz-juelich.de/SharedDocs/Stellenangebote/_common/dna/2014-120-EN-JSC.html http://www.fz-juelich.de/ias/jsc/EN/Expertise/SimLab/slns/_node.html JARA, the J?lich Aachen Research Alliance, is an innovative model of collaboration between RWTH Aachen University and Forschungszentrum J?lich. The alliance brings together an internationally renowned technical university with a leading European research centre (www.jara.org). The scientists of the section JARA-HPC combine know-how in High Performance Computing (HPC) with domain-specific research competence. Through the J?lich Supercomputing Centre (JSC) they have access to supercomputers of the worldwide highest performance class. On the basis of own scientific research, several "Simulation Labs" at the JSC provide community-oriented support in the area of complex simulations on supercomputers and the relevant methods. We are looking to recruit a Graduate researcher (f/m) Your Job: The successful candidate will be member of the Simulation Lab Neuroscience, which is funded by JARA-HPC and by the Helmholtz Association in the framework of the Helmholtz Portfolio Theme "Supercomputing and Modeling for the Human Brain". As the "Bernstein Facility for Simulation and Database Technology" the new lab contributes its expertise in simulation and database technology to the National Bernstein Network Computational Neuroscience (www.nncn.de). Your work will be dedicated to the solution of fundamental questions in neuroscience through the use of the most advanced high performance computers, and will include one or more of the following activities: * Developing models of neural plasticity in the healthy and diseased brain * Developing self-organizing, large-scale neuronal network models of the human brain * Application of these models in high performance computing simulations of lesions in the visual and motor system * Models of multiple sclerosis and Alzheimer's disease * Interdisciplinary work at the interface of Computer Science, Biology and Medicine. Your Profile: * Diploma or Master degree in Computational Neuroscience, Theoretical Biology, Physics or Informatics with a specialization in Biology * Ideally, profound background in modelling neuronal networks as well as good programming skills in Python, Matlab or C++ * Experience in modelling with NEST would be a plus * Ability to work independently in a team of researchers with heterogeneous backgrounds * Strong communication skills in English are a necessity Our Offer: * A diverse range of activities in an interdisciplinary, international research group and a friendly work Environment * Excellent research and computing infrastructure of an internationally recognised technical university and one of the largest research centres in Europe * Possibility of working towards a doctorate * Employment initially limited to 2 years but with possible longer-term perspective * Salary and social benefits in conformity with the provisions of the Collective Agreement for the Civil Service (TV?D). Forschungszentrum J?lich aims to employ more women in this area and therefore particulary welcomes applications from women. We also welcome applications from disabled persons. We look forward to receiving your application, preferably online via our online recruitment system (https://www.hrecruiting.de/obf2/bewerbermanagement.php?kunden_nr=t5ChjatkIfdwmACO&link_id=K9k4mcLjM3qcsEQVud&obf_strukt_id=IouH41AHnbR0WmxFQg&lang=en), quoting the above-mentioned reference number. Contact P-E Henning Eggert Tel.:02461 61-9700 ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Juelich GmbH 52425 Juelich Sitz der Gesellschaft: Juelich Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender), Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt, Prof. Dr. Sebastian M. Schmidt ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Thu Jul 3 01:06:04 2014 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 02 Jul 2014 22:06:04 -0700 Subject: Connectionists: NEURAL COMPUTATION - August 1, 2014 In-Reply-To: Message-ID: Neural Computation - Contents -- Volume 26, Number 8 - August 1, 2014 Available online for download now: http://www.mitpressjournals.org/toc/neco/26/8 ----- Articles Bayesian Active Learning of Neural Firing Rate Maps With Transformed Gaussian Process Priors Mijung Park, J. Patrick Weller, Gregory D. Horwitz, and Jonathan Pillow How to Compress Sequential Memory Patterns Into Periodic Oscillations: General Reduction Rules Kechen Zhang Letters The Competing Benefits of Noise and Heterogeneity in Neural Coding Eric G Hunsberger, Matthew Scott, and Chris Eliasmith Anatomical Constraints on Lateral Competition in Columnar Cortical Architectures Dylan Richard Muir, Matthew Cook ROC-Based Estimates of Neural-Behavioral Covariations Using Matched Filters Kamal Farah, Jackson Smith, and Erik Cook Tonically Balancing Intracortical Excitation and Inhibition by GABAergic Gliotransmission Meihong Zheng, Takami Matsuo, Ai Miyamoto, and Osamu Hoshino Information-theoretic Semi-supervised Metric Learning via Entropy Regularization Gang Niu, Bo Dai, Makoto Yamada, and Masashi Sugiyama Incremental Learning by Message Passing in Hierarchical Temporal Memory Erik Mikael Rehn, Davide Maltoni ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp SUBSCRIPTIONS - 2014 - VOLUME 26 - 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 n.lepora at sheffield.ac.uk Thu Jul 3 02:03:01 2014 From: n.lepora at sheffield.ac.uk (Nathan F Lepora) Date: Thu, 3 Jul 2014 07:03:01 +0100 Subject: Connectionists: [meetings] Living Machines III: Final call for Participation in Conference, Demos and Workshops Message-ID: _____________________________________________________________ Final Call for Participation in Conference, Demos and Workshops Living Machines: The 3rd International Conference on Biomimetic Robotics and Biohybrid Systems. A Convergent Science Network Event 29th July to 1st August 2014 Museo Nazionale della Scienza e della Tecnologia, Leonardo Da Vinci Milano http://csnetwork.eu/livingmachines/conf2014 *** Deadine for early registration extended to July 15th 2014 *** ______________________________________________________________ News & Highlights * Deadline for early registration extended to July 15th, 2014. * Book on time accommodation for good value and availability. see LM2014 for suggestions http://csnetwork.eu/livingmachines/conf2014/accommodation * Main conference programme now online, 6 plenary talks, 1 invited talk, 18 single-track oral presentations, 10 poster spotlights, 40 posters. * 4 satellite workshops also available for registration as separate events, topics include autonomous locomotion systems, the robot self, emergent social behavior, and biomimetics in design. * Bring a demo, be it a robot or an installation, for an exhibition on biomimetic robots, biohybrid computer art, live robot performance or videos. * If you wish to bring a demo please contact us. info.csnetwork at upf.edu * If you need help with transporting your demo to Milano contact us at info.csnetwork at upf.edu * You can book the social dinner as a separate event. Contact info.csnetwork at upf.edu for all enquiries. ABOUT LIVING MACHINES 2014 The 3rd International Conference on Biomimetic and Biohybrid systems comprises 4 days of events including 3 days of single-track oral presentations with 6 plenary speakers; a 1-day with five satellite workshops on themes ranging from autonomous robots to robot ?selves? to biomimetics in design and social impacts of living machines. On Wednesday there will be a reception offered by the Tailor & Francis group http://www.taylorandfrancis.com/ and, on Thursday there will be the LM2014 banquet. We hope you will join us for this exciting programme! The conference registration site is open. Please register soon to take advantage of early registration?deadline July 15th ***From every accepted paper at least 1 author must be registered and present at the Conference*** CONFERENCE PROGRAMME **Program now available online** http://csnetwork.eu/livingmachines/conf2014/programme The main conference will take the form of a single-track oral presentation programme, 30th July to midday 1st August 2014 that will include 6 plenary lectures from leading international researchers in biomimetic and biohybrid systems. Agreed speakers are: Mandyam Srinivasan Queensland Brain Institute, Australia Insect-inspired cognition and vision Andrew Schwartz University of Minnesota, Pittsburgh, USA Neural control of prosthetics Sarah Bergbreiter University of Maryland, USA Microrobotics Darwin Caldwell Italian Institute of Technology, Genova, Italy Legged Locomotion Ricard Sole Universitat Pompeu Fabra, Barcelona, Spain Evolution of complex networks Minoru Asada Osaka University, Japan. Cognitive and Affective Developmental Robotics There will also be 18 regular talks of 30 min, 1 invited talk on Thursday at midday on Biomimetics in Design by Franco Lodato, 10 Poster Spotlights of 5 min and 2 poster sessions of 90 mins each (midday of July 30st and August 1st) featuring 40 posters. Particular themes include: Soft Robotics Neuromechanics Social Robotics Locomotion Biohybrid Brain-based Active Sensing WORKSHOPS In addition to the main conference there is one further day of workshops, each with their own full program that will be available soon on the Living Machines website. Monday 29th July Embodied Interaction and Internal Models: Key Features of Autonomous Locomotion Systems - Organisers: Volker D?rr, Biological Cybernetics, Bielefeld University, Germany, Paolo Arena, Electrical Engineering, University of Catania, Italy The Robot Self - Organizers: Tony Prescott, University of Sheffield, UK; Paul Verschure Universitat Pompeu Fabra Barcelona, CSNII Emergent social behaviours in bio-hybrid systems - Organizers: Jos? Halloy: Universite Paris Diderot. Thomas Schmickl: Karl-Franzens-University Graz, Stuart Wilson, University of Sheffield Rotational Geometry and the Creation of Bionic Models. - Organizers: Pino Trogu, San Francisco State University, USA, Franco Lodato, Creative Director VSN Mobil with Istituto Europeo di Design, Milano Neuro-chip interfaces and Neuroprostheses - Organizers: Stefano Vassanelli, University of Padova, Italy Attendance at workshops will attract a small fee intended to cover the costs of the meeting. We have reserved meeting rooms at the Italian Institute of Technology in Milan each with capacity for up to 40 people. Please book early. Separate registration for satellite events is possible. ABOUT THE VENUE The organisers are delighted to have secured the Museo Nazionale della Scienza e della Tecnologia, Leonardo Da Vinci Milano as the main venue for our conference. The museum is a centre dedicated to Leonardo da Vinci a symbol of the connection between artistic and scientific-technological cultures, two complementary expressions of human creativity. KEY DATES June 30th 2014 Deadline for early registration July 30th - August 1st 2014 Conference We are looking forwards to seeing you in Milano. ORGANISING COMMITTEE Tony Prescott (co-chair) Paul Verschure (co-chair) Armin Duff (programme chair) Roberto Cingolani (local organizer) Barbara Mazzolai (workshops) Nathan Lepora (communications) Anna Mura (communications and web-site) Contact and Conference Secretariat: Info.csnetwork at upf.edu living-machines at sheffield.ac.uk From zhaoping at gatsby.ucl.ac.uk Thu Jul 3 08:44:42 2014 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Thu, 3 Jul 2014 13:44:42 +0100 (BST) Subject: Connectionists: New book "Understanding Vision: theory, models, and data" Message-ID: The book's Table of Contents can be viewed at http://www0.cs.ucl.ac.uk/staff/zhaoping.li/prints/TableOfContents.pdf Teaching and learning support for the book (e.g., ppt files for the figures in the book) is also available and will be updated at http://www0.cs.ucl.ac.uk/staff/zhaoping.li/VisionBook.html . Readership: Computational neuroscientists, visual psychologists/cognitive scientists, Visual neuroscientists/physiologists/anatomists, Researchers in machine vision or computer vision or robot vision The book is written in such a way that vision scientists, unfamiliar with mathematical details, should be able to conceptually follow the theoretical principles and their relationship with physiological, anatomical, and psychological observations, without going through the more mathematical pages. For those with a physical science background, especially those from machine vision, this book serves as an analytical introduction to biological vision. It can be used as a textbook or a reference book in a vision course, or a computational neuroscience course for graduate students or advanced undergraduate students. It is also suitable for self-learning by motivated readers. In addition, for those with a focused interest in just one of the topics in the book, it is feasible to read just the chapter on this topic without having read or fully comprehended the other chapters. In particular, Chapter 2 presents a brief overview of experimental observations on biological vision; Chapter 3 is on encoding of visual inputs, Chapter 5 is on visual attentional selection driven by sensory inputs, and Chapter 6 is on visual perception or decoding. Please let me know if you need more information. best wishes, Li Zhaoping From pierre-yves.oudeyer at inria.fr Thu Jul 3 13:27:44 2014 From: pierre-yves.oudeyer at inria.fr (Pierre-Yves Oudeyer) Date: Thu, 3 Jul 2014 19:27:44 +0200 Subject: Connectionists: [publication and call for dialog] IEEE CIS Newsletter on Autonomous Mental Development 10th anniversary ! Message-ID: Dear colleagues, It is my pleasure to announce the release of the latest issue of the IEEE CIS Newsletter on Autonomous Mental Development, which is now celebrating its 10th anniversary ! This is the biannual newsletter of the computational developmental sciences and developmental robotics community, studying mechanisms of lifelong learning and development in machines and humans. It has progressively become a place of lively and inspiring scientific dialogues spanning an incredible network of topics over the years, with the contributions of many key actors of computational developmental sciences. It is available at: http://www.cse.msu.edu/amdtc/amdnl/AMDNL-V11-N1.pdf Highlights of this issue: === Dialog initiated by Katarina Pastra, with responses from Rick Dale, Katharina Rohlfing et al., Gary Lupyan, Catriona Silvey, Kerstin Fischer and Emmanuel Dupoux. === "How are Grammatical Constructions Linked to Embodied Meaning Representations?" This dialog explores various facets of the interaction between the formation of linguistic and conceptual/sensorimotor structures, and in particular the hypothesis that language as a communication system may have evolved as a byproduct of language as a tool for organising conceptual structures. === New dialog initiated by Katharina Rohlfing, Britta Wrede and Gerhard Sagerer === ?Trained on everything" In the years to come, one very important challenge in developmental sciences is education. Taking an integrated and interdisciplinary approach requires to handle with dexterity concepts and methods from diverse scientific fields ranging from psychology, neuroscience, biology, robotics, computer science or mathematics. How can we grow a community of young researchers mastering the latest advances? How can we teach them to establish cross-disciplinary collaboration and impact? These are the questions raised in the new dialogue initiation. Those of you interested in reacting to this dialog initiation are welcome to submit a response (contact pierre-yves.oudeyer at inria.fr) by Septembet 15th, 2014. The length of each response must be between 600 and 800 words (including references). Let me remind you that previous issues of the newsletter are all open-access and available at: http://www.cse.msu.edu/amdtc/amdnl/ I wish you a stimulating reading! Best regards, Pierre-Yves Oudeyer, Editor of the IEEE CIS Newsletter on Autonomous Mental Development Research director, Inria Head of Flower project-team Inria and Ensta ParisTech, France http://www.pyoudeyer.com https://flowers.inria.fr http://www.poppy-project.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From pierre-yves.oudeyer at inria.fr Fri Jul 4 11:23:41 2014 From: pierre-yves.oudeyer at inria.fr (Pierre-Yves Oudeyer) Date: Fri, 4 Jul 2014 17:23:41 +0200 Subject: Connectionists: [job offer] Open-Source 3D printed humanoid robotics: Experienced engineer in electronics Message-ID: <98340322-C69E-4A8F-A3E7-DA84A425BC12@inria.fr> Job offer at Inria Flowers, France within Poppy Project: Open-Source 3D printed humanoid robotics, http://www.poppy-project.org === Title: Experienced electronics engineer (2 years) === Apply at: pierre-yves.oudeyer at inria.fr and matthieu.lapeyre at inria.fr === Context The Flowers lab is a mixed team (Inria/Ensta ParisTech) composed of about 20 researchers and engineers. Flowers is a research team internationally renowned in developmental and humanoid robotics. It collaborates with several European, American and Asian laboratories, and coordinates several European projects. The team is also very active in the dissemination of science among the general public, and regularly participates in exhibitions and collaborations with artists as acting to make younger discover robotics. Web: https://flowers.inria.fr === Mission The research work conducted in the Flowers team led to the conception of Poppy (http://www.poppy-project.org/), one of the first humanoid robot in the world to be both open-source and 3D printed. It aims to become a community and multi-disciplinary platform for exploration and experimentation in robotics for Research, Art and Educational purposes. In its current version, Poppy is about 80cm tall for 3.5 kg. It has 25 joints motorized by Robotis smart-actuators (http://www.robotis.com/xe/dynamixel_en). These servo-motors, although effective, cost about 5.000? on the 7.500? of Poppy. Poppy is a low-cost robot in the world of research, however for its educational, training and scientific mediation missions, the cost limit its diffusion. Several improvements should be made ??in order to take down it cost and make Poppy even more accessible. In a team with a mechanical engineer and relying on existing work as Open Servo (http://openservo.com/) and Supermodified (http://letsmakerobots.com/node/18615) your role will be to work on control and automation of Poppy 2. You will also take involved in the execution of projects related to Poppy, and in a international working environment. === Description Conception of the general electronics architecture of the next versions of Poppy and working on low-cost actuator integration. Development of the library and low level control and integration with pypot (https://github.com/poppy-project/pypot). Profile ? Practical experience in the design of electronics boards (electronic design automation (Eagle or KiCad), routing design rules, protection (ESD, short-cut), noise filtering) ? Theoretical and practical experience with embedded systems (programming microcontroller, low-level communication, sensors, real time) ? Control and design of medium power electronics (control loop, H bridge, design of heat sink) ? Familiarity with the Arduino environment ? Familiarity with the Python programming language ? English proficiency ? Team work Requirements ? Minimum 2 years of experience ? Master degree Benefits ? Partial support of transportation costs. ? Food restauration available on site. ? Dynamic and pleasant working ambiance Additional Information ? Duration of contract: 24 months ? Estimated date of employment: 1 October 2014 ? Monthly gross salary: 2600 euros to 3500 euros (depending on experience). For more information about the position, contact pierre-yves.oudeyer at inria.fr and matthieu.lapeyre at inria.fr -------------- next part -------------- An HTML attachment was scrubbed... URL: From bcbt at upf.edu Fri Jul 4 11:42:25 2014 From: bcbt at upf.edu (=?UTF-8?Q?BCBT=2C_B=C3=BAstia_Compartida?=) Date: Fri, 4 Jul 2014 17:42:25 +0200 Subject: Connectionists: Reminder CfP BCBT2014 Summer School, Barcelona, Spain Message-ID: Dear all, applications and scholarships to attend the BCBT2014 summer school are now open. Do not miss it! Kind regards BCBT2014 *Barcelona Cognition, Brain and Technology Summer School (BCBT2014)* University Pompeu Fabra, Barcelona, Spain. September 1-12, 2014 http://bcbt.upf.edu/bcbt14/ We would like you to join us for the annual *"Barcelona Cognition, Brain and Technology summer school - BCBT2014 *" to be held from September 1-12, 2014 in Barcelona Spain. The summer school is at its seventh edition and is part of a series of events organized by the European coordination action Convergent Science Network of Biomimetics and Neurotechnology (http://csnetwork.eu/). BCBT is positioned at the interface between biology and future and emerging technologies with an emphasis on the principles underlying brains and their translation to avant-garde technologies. BCBT promotes a shared systems-level understanding of the functional architecture of the brain and its possible emulation in artificial systems. This is the 7th year of BCBT, which ran with great success in previous years thanks to an excellent line-up of outstanding speakers (see bcbt.upf.edu for previous editions of the school). BCBT lectures are available online (see http://csnetwork.eu/) as well as the CSN *Podcast interviews *with many of the BCBT speakers.. BCBT caters to the students and researchers involved in projects that are in the ambit of ?Bio-ict convergence?, "Brain Inspired ICT", ?Cognitive systems-robotics?. BCBT will offer up to 30 student slots for the practical workshops while as many researchers can register to attend the presentations and discussion sessions as are interested. For the lectures the limit will be placed at 60-70 given the capacity of the available lecture theatre. The atmosphere of the BCBT summer school is informal with the goal to stimulate in-depth discussion. There are presentations in the morning, usually 2, with the afternoons reserved for tutorials and projects for student participants and road-mapping workshops or further discussion for senior scientists. For the 2014 edition we plan a *1st week* of the school addressing *Evolutionary and Developmental aspects of nervous systems and behavior *(*Session 1*, 1-5 Sept*)*, while the *2nd week* will include presentations aimed at the investigation of *Core Brain Systems* with emphasis on the basal ganglia (*Session 2*, 8-9 Sept) followed by roadmapping sessions (*Session 3*, 10-11 Sept). Friday 12 is reserved for the presentation of the student projects to which everybody is invited. *Application deadline: August 2nd, 2014* For more information and to apply, please go to http://bcbt.upf.edu/bcbt14 *BCBT offers a number of scholarships.* These are CSN scholarships and may cover travel expenses, accommodation and registration fee.http://bcbt.upf.edu/bcbt14 BCBT2014 is supported by the Convergent Science Network of Biomimetics and Neurotechnology (http://csnetwork.eu/). and is co-organized by Paul Verschure (BCBT Chair) SPECS, University Pompeu Fabra Barcelona, ES Tony Prescott (BCBT Co-Chair) University of Sheffield, UK Leah Krubizer (BCBT Co-Chair) UC Davis, CA, USA Anna Mura (BCBT Co-Chair) SPECS, University Pompeu Fabra Barcelona, ES -------------- next part -------------- An HTML attachment was scrubbed... URL: From Hugo.Larochelle at USherbrooke.ca Fri Jul 4 09:17:38 2014 From: Hugo.Larochelle at USherbrooke.ca (Hugo Larochelle) Date: Fri, 4 Jul 2014 13:17:38 +0000 Subject: Connectionists: NIPS 2014 - 2nd Call for Demonstrations Message-ID: <1DB33625-2C9E-472B-BF0A-FC23B29FEE7B@usherbrooke.ca> The Neural Information Processing Systems Conference 2014 http://nips.cc/Conferences/2014/ has a Demonstration Track running in parallel with some of the evening Poster Sessions, December 8-11, 2014, in Montreal, Quebec, Canada. Demonstration Proposal Deadline: Monday September 15, 2014, 11pm Universal Time (4pm Pacific Daylight Time). http://nips.cc/Conferences/2014/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/2014/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: Hugo Larochelle > http://nips.cc/Conferences/2014/CallForDemonstrations -------------- next part -------------- An HTML attachment was scrubbed... URL: From michel.verleysen at uclouvain.be Sun Jul 6 05:34:46 2014 From: michel.verleysen at uclouvain.be (Michel Verleysen) Date: Sun, 6 Jul 2014 09:34:46 +0000 Subject: Connectionists: ESANN 2015: call for special sessions Message-ID: ESANN 2015: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges, Belgium, 22-23-24 April 2015 http://www.esann.org (still with ESANN 2014 information, will be updated soon) Call for special sessions ------------------------------- ESANN 2015 builds upon a successful series of conferences organized each year since 1993. ESANN has become a major scientific event in the machine learning, computational intelligence and artificial neural networks fields over the years. Each year, 5-6 special sessions on selected hot topics in the field are organized at ESANN. We are currently looking for proposals to organize special sessions. Candidate organizers are invited to read the call for special sessions at https://www.elen.ucl.ac.be/esann/index.php?pg=cfss. The other pages of the ESANN website will be updated in the next few weeks; currently they still contain information about ESANN 2014. Candidates for the organization of special sessions should send an e-mail to esann at uclouvain.be at the latest on August 25, 2014 (however the soonest is the best). Details on the information to be sent is available from https://www.elen.ucl.ac.be/esann/index.php?pg=cfss. The conference will be organized in Bruges, one of the most beautiful medieval towns in Europe. Designated as the "Venice of the North", the city has preserved all the charms of the medieval heritage. Its centre, which is inscribed on the Unesco World Heritage list, is in itself a real open air museum. We remain of course at your disposal for any information about ESANN 2015 and the organization of special sessions. Sincerely yours, Michel Verleysen ======================================================== ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning http://www.esann.org/ * For submissions of papers, reviews, registrations: Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at uclouvain.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at uclouvain.be ======================================================== -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Mon Jul 7 02:00:51 2014 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 07 Jul 2014 02:00:51 -0400 Subject: Connectionists: CNS 2014 workshop on using the NSG for parallel simulations Message-ID: <53BA3793.8040300@yale.edu> The Neuroscience Gateway Portal (NSG) eliminates most administrative and technical barriers to High Performance Computing (HPC) resources, so that computational neuroscientists can readily use simulators such as Brian, GENESIS 3, NEST, NEURON, and PyNN to carry out parallel simulations. To find out how the NSG can accelerate your own modeling project, come to the workshop "Running parallel simulations on HPC resources via the Neuroscience Gateway Portal" which starts at 9 AM on Wednesday, July 30, at the CNS 2014 meeting. The workshop will include a presentation on the NSG itself, plus * presentations by modelers who are using NSG in their research projects --Timothy Rumbell, Mount Sinai School of Medicine, New York, USA: "Modeling of cortical neurons in aging monkeys", --Marianne Bezaire, University of California Irvine, Irvine, USA: "Using the NSG for a large-scale parallel computer model of the CA1 network," * a presentation by a member of the development team of one of the simulators that is available through the NSG --Marcel Stimberg, ?cole Normale Sup?rieure and Institut de la Vision, Paris, France: "The Brian 2 spiking neuronal network simulation tool" Relevant webpages: http://www.cnsorg.org/cns-2014-workshops-program http://www.nsgportal.org/workshop.html From juergen at idsia.ch Tue Jul 8 07:40:06 2014 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Tue, 8 Jul 2014 13:40:06 +0200 Subject: Connectionists: First Deep Learning Networks in 1965 Message-ID: <7B480C11-9974-45DA-B1BA-90943E264DA1@idsia.ch> Who created the first Deep Learning networks? To my knowledge, this was done by Olexiy Hryhorovych (Alexey Grigoryevich) Ivakhnenko and colleagues in 1965. Here a brief summary: Networks trained by the Group Method of Data Handling (GMDH) (Ivakhnenko and Lapa, 1965; Ivakhnenko et al., 1967; Ivakhnenko, 1968, 1971) were perhaps the first Deep Learning systems of the Feedforward Multilayer Perceptron type. The units of GMDH nets may have polynomial activation functions implementing Kolmogorov-Gabor polynomials (more general than other widely used neural network activation functions). Given a training set, layers are incrementally grown and trained by regression analysis (e.g., Legendre, 1805; Gauss, 1809, 1821), then pruned with the help of a separate validation set (using today?s terminology), where Decision Regularisation is used to weed out superfluous units. The numbers of layers and units per layer can be learned in problem-dependent fashion. To my knowledge, this was the first example of hierarchical representation learning in NNs. A paper of 1971 already described a deep GMDH network with 8 layers (Ivakhnenko, 1971). There have been numerous applications of GMDH-style nets, e.g. (Ikeda et al., 1976; Farlow, 1984; Madala and Ivakhnenko, 1994; Ivakhnenko, 1995; Kondo, 1998; Kordik et al., 2003; Witczak et al., 2006; Kondo and Ueno, 2008) ? Precise references and more history in: Deep Learning in Neural Networks: An Overview PDF & LATEX source & complete public BIBTEX file under http://www.idsia.ch/~juergen/deep-learning-overview.html Juergen Schmidhuber From juergen at idsia.ch Tue Jul 8 09:28:41 2014 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Tue, 8 Jul 2014 15:28:41 +0200 Subject: Connectionists: First Deep Learning Networks in 1965 In-Reply-To: <2DBAE45A-6FA4-4A02-9C08-F490BBD59075@cs.umass.edu> References: <7B480C11-9974-45DA-B1BA-90943E264DA1@idsia.ch> <2DBAE45A-6FA4-4A02-9C08-F490BBD59075@cs.umass.edu> Message-ID: <7213D884-8CDB-439C-B09C-D5B3AB9EEF95@idsia.ch> Andy, thanks a lot - in fact, the survey mentions the work of Utgoff & Stracuzzi in Sec. 5.6.3 - related important work includes: ... constructive and pruning algorithms, e.g., layer-by-layer sequential network construction (e.g., Ivakhnenko, 1968, 1971; Ash, 1989; Moody, 1989; Gallant, 1988; Honavar and Uhr, 1988; Ring, 1991; Fahlman, 1991;Weng et al., 1992; Honavar and Uhr, 1993; Burgess, 1994; Fritzke, 1994; Parekh et al., 2000; Utgoff and Stracuzzi, 2002) (see also Sec. 5.3, 5.11), input pruning (Moody, 1992; Refenes et al., 1994), unit pruning (e.g., Ivakhnenko, 1968, 1971; White, 1989; Mozer and Smolensky, 1989; Levin et al., 1994) ? Cheers, Juergen On Jul 8, 2014, at 3:13 PM, Barto Andy wrote: > Juergen, > > It is great that you bring attention to GMDH. It is not so widely known, although in his 1990 book Neurocomputing, Robert Hecht-Nielson provides a nice discussion of it. It is related to the general idea of a beam search. People might also want to know about the work of my late colleague Paul Utgoff and his student Dave Stracuzzi, who were very interested in what they called ?many-layered learning?. Clearly not the first, but interesting too I think: > > Utgoff, P.E., & Stracuzzi, D.J. (2002a). Many-layered learning. Neural Computation, 14, 2497-2539. > > Best, > Andy > > > > On Jul 8, 2014, at 7:40 AM, Schmidhuber Juergen wrote: > >> Who created the first Deep Learning networks? >> >> To my knowledge, this was done by Olexiy Hryhorovych (Alexey Grigoryevich) Ivakhnenko and colleagues in 1965. Here a brief summary: >> >> Networks trained by the Group Method of Data Handling (GMDH) (Ivakhnenko and Lapa, 1965; Ivakhnenko et al., 1967; Ivakhnenko, 1968, 1971) were perhaps the first Deep Learning systems of the Feedforward Multilayer Perceptron type. The units of GMDH nets may have polynomial activation functions implementing Kolmogorov-Gabor polynomials (more general than other widely used neural network activation functions). Given a training set, layers are incrementally grown and trained by regression analysis (e.g., Legendre, 1805; Gauss, 1809, 1821), then pruned with the help of a separate validation set (using today?s terminology), where Decision Regularisation is used to weed out superfluous units. The numbers of layers and units per layer can be learned in problem-dependent fashion. To my knowledge, this was the first example of hierarchical representation learning in NNs. A paper of 1971 already described a deep GMDH network with 8 layers (Ivakhnenko, 1971). There have been numerous ap! >> >> plications of GMDH-style nets, e.g. (Ikeda et al., 1976; Farlow, 1984; Madala and Ivakhnenko, 1994; Ivakhnenko, 1995; Kondo, 1998; Kordik et al., 2003; Witczak et al., 2006; Kondo and Ueno, 2008) ? >> >> Precise references and more history in: >> >> Deep Learning in Neural Networks: An Overview >> PDF & LATEX source & complete public BIBTEX file under >> http://www.idsia.ch/~juergen/deep-learning-overview.html >> >> Juergen Schmidhuber >> >> >> > From quel.caroline at gmail.com Mon Jul 7 16:43:54 2014 From: quel.caroline at gmail.com (Quel) Date: Mon, 7 Jul 2014 17:43:54 -0300 Subject: Connectionists: Job announcement Message-ID: [sorry for cross-posting] On the behalf of Hospital Israelita Albert Einstein, *Open** position for Professor of Neurosciences **in **S**a**o Paulo, Brazil.* We seek an outstanding senior researcher as a professor of the Brain Institute at the Albert Einstein Institute for Research and Education. For more information and how to apply for the position, please refer to the attached document. Best regards, Anna *Anna Ringheim Cadete* Coordinator - Brain Institute - IIEP SBIB Hospital Albert Einstein -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Open position for Professor of Neurosciences_Hospital Israelita Albert Einstein (1).pdf Type: application/pdf Size: 204844 bytes Desc: not available URL: From christopher.honey at gmail.com Mon Jul 7 16:54:42 2014 From: christopher.honey at gmail.com (Christopher Honey) Date: Mon, 7 Jul 2014 16:54:42 -0400 Subject: Connectionists: Call for Nominations: Tang Prize for Achievements in Psychology Message-ID: APPLICATIONS INVITED FOR INAUGURAL TANG PRIZE FOR ACHIEVEMENTS IN PSYCHOLOGY ? CALL FOR NOMINATIONS The Department of Psychology at the University of Toronto is pleased to announce the call for nominations for the 2014 inaugural TANG Prize for Achievements in Psychology. As a Department at a public university, we believe in furthering the science of Psychology in service of enhancing human wellbeing. Applications are encouraged from internationally-recognized scholars in Psychology or a closely-related field who have shown creativity, and rigour in their approach and whose record of achievement has left an indelible mark on the field. This award has been made possible through generous support from the TANG Foundation. The TANG Foundation is a charitable institution with the mandate to raise awareness of the importance of psychological wellbeing in the world. The recipient of the TANG Prize for Achievements in Psychology will be awarded a cash prize of $100,000 CAD at a ceremony held on the University of Toronto campus on November 12, 2014. During the campus visit, the recipient will be asked to meet with University of Toronto students and to hold a public lecture. Applicants should outline in no more than two pages the ways in which they have a major impact on the progress of psychology, anywhere in the world, particularly in its application to the psychological wellbeing of humanity. This application letter should highlight how the applicant has contributed to the science, practice, or application of Psychology as it pertains to the understanding, promotion, restoration, or application of psychological methods, research, and techniques in addressing challenges related to wellbeing at the individual or community level. In addition to this application letter, applications should also include a current CV. Nomination packages (application letter and CV) should be submitted electronically in one email by August 15, 2014 to tangprize at psych.utoronto.ca. Applicants should also ask three referees, who must be internationally acknowledged experts in the field, to send reference letters directly to the Department via email to tangprize at psych.utoronto.ca by August 30, 2014. Up to three additional supporting letters of endorsement from individuals who have been directly impacted by the applicant?s scholarly work and/or who have knowledge of the direct impact of the applicant?s scholarly work can be sent to the same email address by August 30, 2014. For more information on this award, about the Department of Psychology at the University of Toronto, and the TANG Foundation, please visit www.psych.utoronto.ca/tangprize. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Call_Tang foundation.PDF Type: application/pdf Size: 436762 bytes Desc: not available URL: From barto at cs.umass.edu Tue Jul 8 09:13:23 2014 From: barto at cs.umass.edu (Barto Andy) Date: Tue, 8 Jul 2014 09:13:23 -0400 Subject: Connectionists: First Deep Learning Networks in 1965 In-Reply-To: <7B480C11-9974-45DA-B1BA-90943E264DA1@idsia.ch> References: <7B480C11-9974-45DA-B1BA-90943E264DA1@idsia.ch> Message-ID: <2DBAE45A-6FA4-4A02-9C08-F490BBD59075@cs.umass.edu> Juergen, It is great that you bring attention to GMDH. It is not so widely known, although in his 1990 book Neurocomputing, Robert Hecht-Nielson provides a nice discussion of it. It is related to the general idea of a beam search. People might also want to know about the work of my late colleague Paul Utgoff and his student Dave Stracuzzi, who were very interested in what they called ?many-layered learning?. Clearly not the first, but interesting too I think: Utgoff, P.E., & Stracuzzi, D.J. (2002a). Many-layered learning. Neural Computation, 14, 2497-2539. Best, Andy On Jul 8, 2014, at 7:40 AM, Schmidhuber Juergen wrote: > Who created the first Deep Learning networks? > > To my knowledge, this was done by Olexiy Hryhorovych (Alexey Grigoryevich) Ivakhnenko and colleagues in 1965. Here a brief summary: > > Networks trained by the Group Method of Data Handling (GMDH) (Ivakhnenko and Lapa, 1965; Ivakhnenko et al., 1967; Ivakhnenko, 1968, 1971) were perhaps the first Deep Learning systems of the Feedforward Multilayer Perceptron type. The units of GMDH nets may have polynomial activation functions implementing Kolmogorov-Gabor polynomials (more general than other widely used neural network activation functions). Given a training set, layers are incrementally grown and trained by regression analysis (e.g., Legendre, 1805; Gauss, 1809, 1821), then pruned with the help of a separate validation set (using today?s terminology), where Decision Regularisation is used to weed out superfluous units. The numbers of layers and units per layer can be learned in problem-dependent fashion. To my knowledge, this was the first example of hierarchical representation learning in NNs. A paper of 1971 already described a deep GMDH network with 8 layers (Ivakhnenko, 1971). There have been numerous ap! > > plications of GMDH-style nets, e.g. (Ikeda et al., 1976; Farlow, 1984; Madala and Ivakhnenko, 1994; Ivakhnenko, 1995; Kondo, 1998; Kordik et al., 2003; Witczak et al., 2006; Kondo and Ueno, 2008) ? > > Precise references and more history in: > > Deep Learning in Neural Networks: An Overview > PDF & LATEX source & complete public BIBTEX file under > http://www.idsia.ch/~juergen/deep-learning-overview.html > > Juergen Schmidhuber > > > From christos.dimitrakakis at gmail.com Thu Jul 10 15:40:14 2014 From: christos.dimitrakakis at gmail.com (Christos Dimitrakakis) Date: Thu, 10 Jul 2014 21:40:14 +0200 Subject: Connectionists: CFP: AISec 2014 Message-ID: <53BEEC1E.1080008@gmail.com> Call For Papers AISec 2014 7th ACM Workshop on Artificial Intelligence and Security Held in Conjunction with ACM CCS 2014 http://www.cse.chalmers.se/~aikmitr/AISec2014.html November 7, 2014 The Scottsdale Plaza Resort, Scottsdale, Arizona, USA The relation of artificial intelligence (AI), machine learning, and data mining to security and privacy problems is ever-more critical, with AI algorithms controlling important infrastructure, such as electrical grids, road networks and healthcare applications. More generally, AI and ML are increasingly important for autonomous real-time analysis and decision-making in domains with a wealth of data or that require quick reactions to ever-changing situations. Particularly, these intelligent technologies offer new solutions to security problems involving Big Data analysis, which can be scaled through cloud-computing. Further, the use of learning methods in security sensitive domains creates new frontiers for security research, in which adversaries may attempt to mislead or evade intelligent machines. The 2014 ACM Workshop on Artificial Intelligence and Security (AISec) provides a venue for presenting and discussing new developments in this fusion of security/privacy with AI and machine learning. We invite original research papers relating to the theory and applications of AI or machine learning for security, privacy and related problems. We also invite position and open problem papers discussing the role of AI or machine learning in security and privacy. Submitted papers of these types may not substantially overlap papers that have been published previously or that are simultaneously submitted to a journal or conference/workshop proceedings. This year, we also invite presentation-only papers, describing research published or submitted in 2014. * Paper format * This year we invite both original submissions and presentation-only papers. Please indicate the type of submission when submitting. Original submissions: This include original research, and open problem/position papers. They must be at most 10 pages in double-column ACM format (note: pages must be numbered) excluding the bibliography and well-marked appendices, and at most 12 pages overall. Committee members are not required to read the appendices, so the paper should be intelligible without them. Submissions need not be anonymized. We recommend the use of the ACM SIG Proceedings templates for submissions. The ACM format is the required template for the camera-ready version. Accepted papers will be published by the ACM Digital Library and/or ACM Press. Both research and open problem papers will undergo a thorough review process. Presentation-only papers: As an experiment, this year we also invite presentation-only papers, for research currently under review elsewhere or published in 2014. These need not adhere to the ACM format and will not be published in the proceedings. They will undergo a light review for correctness, relevance and importance. Priority will be given to original submissions. --------------------------------------------- Important Dates Paper submissions due: 25 July 2014 Acceptance notification: 25 August 2014 Camera ready (FIRM DEADLINE): 9 September 2014 Workshop: 7 November 2014 --------------------------------------------- Submissions Submissions can be made through EasyChair at: https://www.easychair.org/conferences/?conf=aisec2014 -------------------------------------------- Topics Topics of interest include, but are not limited to: Theoretical topics related to security - Adversarial Learning - Robust Statistics - Learning in stochastic games - Online learning - Differential-privacy Security Applications - Computer Forensics - Spam detection - Phishing detection & prevention - Botnet detection - Intrusion detection and response - Malware identification - Authorship Identification - Big data analytics for security Security-related AI problems - Distributed inference and decision making for security - Secure multiparty computation and cryptographic approaches - Privacy-preserving data mining - Adaptive side-channel attacks - Design and analysis of CAPTCHAs - AI approaches to trust and reputation - Vulnerability testing through intelligent probing (e.g. fuzzing) - Content-driven security policy management & access control - Techniques and methods for generating training and test sets - Anomalous behavior detection (e.g. for the purpose of fraud detection, authentication) From m.reske at fz-juelich.de Wed Jul 9 09:32:41 2014 From: m.reske at fz-juelich.de (Martina Reske) Date: Wed, 9 Jul 2014 15:32:41 +0200 Subject: Connectionists: 2 PhD positions in Computational Neuroscience in Juelich, Germany Message-ID: <53BD4479.4090807@fz-juelich.de> Dear community, we are seeking two PhD candidates to support our team! Project 1: In the framework of the Klinische Forschergruppe (KFO) 219 "Basal ganglia-cortex loops: Mechanisms of pathologic interactions and their therapeutic modulation" we have an open PhD student position in work package 9: "Mathematical modeling of development and suppression of pathological activation in basal ganglia ? cortex loops?. This project focuses on the generation of pathological beta band oscillations in basal ganglia and their susceptibility to suppression by means of pharmacological challenges or deep brain stimulation. Specifically, this projects aims to model dynamics in basal ganglia ? thalamus ? cortex loops drawing on computational neuroscience approaches and data deriving from other work packages within the research consortium. We are seeking for a candidate with a master?s degree in physics, mathematics or computer science. The candidate will develop microscopic network models and will be supervised by the projects leaders, particularly by a postdoctoral fellow supervising the entire work package as well as Prof. Morrison. Programming expertise is appreciated. The candidate will be primarily based at the J?lich Research Center to foster interactions with theoretical neuroscientists. In addition, the candidate is expected to work jointly with project partners at the University Clinic of Cologne. We offer a position in a creative and international team, themes ranging from computational neuroscience to simulation technology. The J?lich Research Center is one of the largest research centers in Germany, with excellent scientific equipment, located on a green campus, and near the cultural centers K?ln, D?sseldorf, and Aachen. The PhD position is available for 3 years, starting as soon as possible. Applications, including a motivation letter, CV, publication list, copies of university certificates, and one reference letter should be sent as a single PDF email attachment (max. 10MB) mentioning the internal reference code KFO219-TP9 to should be sent to: Dr. Martina Reske (m.reske at fz-juelich.de) ? Scientific Coordinator The call is open until the position has been filled. Project 2: Project title: Neural circuit mechanisms of reinforcement learning Project description: Reinforcement learning is considered to play a major role in decision-making, and impairments in RL have been associated with various neuropsychiatric disorders including addiction and depression. Since it was found that the activity of midbrain dopamine (DA) neurons appears to represent the reward prediction error, various brain regions in the cerebral cortex and the basal ganglia have been shown to represent several variables appeared in mathematical formulations of RL algorithms. However, underlying mechanisms at the cellular and circuit levels within and between each of those regions remain largely unknown. In this project, we address this issue by developing and study neuronal network models of learning from reward and punishment in the brain's basal ganglia network. The project will be carried out by the group Functional Neural Circuits at the Institute for Neuroscience and Medicine (INM-6) and Institute for Advanced Simulation (IAS-6) led by Prof. Abigail Morrison, together with our Japanese collegues (Kenji Morita, University of Tokyo). The project is supported by German Ministry of Science (BMBF) in the framework of the German-Japan cooperation in Computational Neuroscience. The project incorporates tools and methods from different fields, ranging from neuroscience to physics and mathematical modeling to build large scale simulations of neural networks. Supervision is provided by Prof. Abigail Morrison and Dr. Jenia Jitsev, both having considerable experience in neural network modeling, with focus on plasticity and learning. We seek a highly motivated candidate with curiosity and persistence. A preferable candidate will have background and strong Master degree in either in neuroscience, physics, mathematics, biology, computer science or a related field of natural science. The candidate should have experience in basic software engineering techniques (minimal requirement is ability to write clear well-structured code in either C++ or Python). Furthermore, a solid basis in mathematical modelling (handling differential equations, basics of stability analysis) is essential. The most important requirement is the ability to learn new things and to find ways to solve novel problems. The PhD position is available for 3 years, starting as soon as possible. During the PhD, you will also have opportunity to visit conferences, workshops, summer schools and labs of our partners in Tokyo and benefit from their experience, too. You will be a part of a creative and young team, rich with inspiration for the different state-of-the art topics in experimental and theoretical neuroscience, and have the opportunity to take part at the forefront of current neuroscientific research. Research Center J?lich, Germany, is located on a green campus and hosts excellent facilities, including the J?lich Supercomputing Center, and is part of newly starting EU Human Brain Project, the largest neuroscientific initiative to study the brain funded in Europe. J?lich is close to large urban centers like Cologne, Aachen and D?sseldorf and offers thus a rich cultural environment to spend time in. Applications, including a motivation letter, a CV, copies of university certificates, and one letter of reference should be sent as a single PDF email attachment (max. 10MB) mentioning the internal reference code BRDJ-PhD to: Dr. Martina Reske (m.reske at fz-juelich.de) ? Scientific Coordinator The call is open until the position has been filled. -- Dr. Martina Reske Scientific Coordinator Institute of Neuroscience and Medicine (INM-6) Computational and Systems Neuroscience & Institute for Advanced Simulation (IAS-6) Theoretical Neuroscience J?lich Research Centre and JARA J?lich, Germany Work +49.2461.611916 Work Cell +49.151.26156918 Fax +49.2461.619460 www.csn.fz-juelich.de ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Juelich GmbH 52425 Juelich Sitz der Gesellschaft: Juelich Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender), Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt, Prof. Dr. Sebastian M. Schmidt ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ From stephan.chalup at newcastle.edu.au Sat Jul 5 10:32:20 2014 From: stephan.chalup at newcastle.edu.au (Stephan Chalup) Date: Sat, 5 Jul 2014 14:32:20 +0000 Subject: Connectionists: CfP: Australasian Conference on Artificial Life and Computational Intelligence (ACALCI 2015) Message-ID: CfP: Australasian Conference on Artificial Life and Computational Intelligence (ACALCI 2015), 5-7 February 2015, The University of Newcastle, Australia http://robots.newcastle.edu.au/ACALCI2015 PAPER SUBMISSION DEADLINE: 1 September 2014 DESCRIPTION: While Artificial Life (AL) attempts to understand nature through modelling and simulation, Computational Intelligence (CI) attempts to translate this understanding into algorithms for learning and optimisation. The Australasian Conference on Artificial Life and Computational Intelligence (ACALCI 2015) features international research in AL and CI and provides a forum for innovative, interdisciplinary research associated with the computational concepts underlying living and intelligent systems. SCOPE: ACALCI 2015 will be organised in broad technical sessions that bring together experts from different fields in AL, CI and associated areas. The forum also hopes to encourage ALCI applied research in domains as diverse as health, the creative arts and finance (to name a few). ACALCI encourages presentations, demonstrations, performances and discussions on new innovative research and interdisciplinary projects. Invited are high-quality papers relevant to AL or CI where the topics of interest include but are not limited to: Adaptive Ecologies, Affective Computing, ALCI in Design and Music, Ant Colony Optimisation, Applications of ALCI, Autonomous Agents, Architecture and ALCI, Artificial Neural Networks, Artificial Societies and Markets, Augmented and Virtual Realities, Big Data, Bioinformatics, BCIs, Braintheory, Chatbots, Cognitive Neuroscience, Complex Systems, Computational Neuroscience, Connectionism, Consciousness and Mind, Creative Arts and CI, Data Mining, Deep Learning, Developmental Learning, Digital Societies, Dimensionality Reduction, Embodiment and Robotics, Emergence of Collaborative Behaviour, Emotional AI, Engineering of Consciousness and Mind, Epidemiology Simulations, Ethics and Security in CI, Evolutionary Computation, Evolutionary Design, Facial Expression Analysis, Game Playing Agents, Human-Machine Interaction, Humanities and ALCI, Humanoid Robots, Implementation Techniques, Information Theoretic Learning, Intelligent Home Automation, Language Processing, Machine Learning, Mathematical Models, Medical Image Analysis, Memetic Algorithms, Metalearning, Models of Emotions, Multi-Agent Systems, Non-player Game Characters, Pattern Recognition, Philosophy of Artificial Life, Reservoir Computing, Self-Organisation, Simulation and Modelling, Smart Grid Techniques, Social Networks and ALCI, Spiking Neural Networks, Statistical Learning Theory, Swarm Algorithms, Synthetic Life Computations, Visual Information Processing. SUBMISSION and PRESENTATION: Authors are invited to submit papers that have between 6 and 14 pages in Springer LNAI style including results, figures and references. Longer papers up to 20 pages can be considered in exceptional cases. All relevant papers will be fully peer-reviewed by at least three reviewers from the ACALCI 2015 International Program Committee before acceptance for publication in the proceedings. It is expected that submitted manuscripts are original and have neither been published nor submitted for publication elsewhere. The submitted papers and all their underlying research must comply with the professional standards of the discipline. All accepted papers that are presented at the conference would be published in the ACALCI 2015 proceedings as a LNAI volume by Springer-Verlag. The LNAI volumes are indexed by the following services: Scopus, Zentralblatt MATH, IO-Port, MathSciNet, ACM Digital Library, dblp, EI Engineering Index (Compendex and Inspec databases), and the ISI Conference Proceedings Citation Index - Science (CPCI-S), included in ISI Web of Science. It is planned to run the conference for three days as a single stream of high quality presentations with attached poster sessions, demonstrations and performances. In exceptional cases where an author cannot travel, a presentation (poster or oral) via skype or video conferencing can be organised. LOCATION and VENUE: The University of Newcastle Conservatorium of Music Concert Hall, Newcastle, Australia. This is a stylish venue about 2.5 hours north of Sydney. Williamtown Airport is a 25 minute taxi/car drive away. It is close to several hotels, YHA, intercity train station and the beautiful Newcastle beaches. WORKSHOPS, TUTORIALS and PERFORMANCES: If you would like to organise a workshop, tutorial or performance in connection with ACALCI2015 please contact the organisers as soon as possible. CONFERENCE ORGANISERS (Australia): General Chair: Stephan Chalup (UoN, Australia) Program Chairs: Alan Blair (UNSW, Australia), Marcus Randall (Bond Univ., Australia) Tutorial Chair: Oliver Obst (CSIRO, Sydney, Australia) Workshop Chair: Philip Hingston (Edith Cowan University, Australia) Performance Chairs: Frank Millward (UoN, Australia), Richard Vella (UoN, Newcastle) Local Organising Committee: Alexandre Mendes (UoN, Australia), David Cornforth (UoN, Australia), Nasimul Noman (UoN, Australia), Shamus Smith (UoN, Australia) CONFERENCE WEBPAGE with further details: http://www.newcastle.edu.au/ACALCI2015 CONTACT email of the conference chair: ACALCI2015 at gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From feeds at sentic.net Mon Jul 7 05:45:00 2014 From: feeds at sentic.net (SenticNet) Date: Mon, 7 Jul 2014 04:45:00 -0500 (EST) Subject: Connectionists: [SenticNet] CFP: IES'14 special session on Intelligent and Evolutionary Systems for Natural Language Processing Message-ID: <1819635547.3535384.1404726300973.open-xchange@bosoxweb03.eigbox.net> Apologies for cross-posting, Submissions are invited for a special session on "Intelligent and Evolutionary Systems for Natural Language Processing" of the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES'14), to be held from 10th to 12th November 2014 in Singapore. RATIONALE As the Web rapidly evolves, Web users and Web contents are evolving with it. In an era of social connectedness, people are becoming increasingly enthusiastic about interacting, sharing, and collaborating through social networks, online communities, blogs, Wikis, and other online collaborative media. In recent years, this collective intelligence has spread to many different areas, with particular focus on fields related to everyday life such as commerce, tourism, education, and health, causing the size of the Web to expand exponentially. The distillation of knowledge from such a large amount of unstructured information, however, is an extremely difficult task, as the contents of today's Web are perfectly suitable for human consumption, but remain hardly accessible to machines. To this end, biologically and linguistically motivated computational paradigms that go beyond syntax are needed. Intelligent and evolutionary systems potentially have a large future possibility to play an important role in natural language processing (NLP) research for tasks such as grammatical evolution, knowledge discovery, and rule learning. In this light, this Special Session focuses on the introduction, presentation, and discussion of novel NLP systems that are not merely based on domain-dependent corpora or word co-occurrence counts, but rather systems that can be considered intelligent and evolutionary. The main motivation for the Special Session, in particular, is to go beyond a mere word-level analysis of text and provide novel concept-level approaches to natural language processing that allow a more efficient passage from (unstructured) textual information to (structured) machine-processable data, in potentially any domain. Articles are thus invited in areas such as AI, Semantic Web, knowledge-based systems, machine learning, and computational intelligence for NLP research. Topics include, but are not limited to: - Intelligent and evolutionary systems for information extraction and retrieval - Intelligent and evolutionary systems for text summarization and visualization - Intelligent and evolutionary systems for topic modeling - Intelligent and evolutionary systems for sentiment analysis - Intelligent and evolutionary systems for knowledge acquisition - Intelligent and evolutionary systems for social network analysis - Intelligent and evolutionary systems for adaptive and transfer learning - Intelligent and evolutionary systems for agents and complex systems - Intelligent and evolutionary systems for evolutionary game theory - Intelligent and evolutionary systems for bioinformatics The Special Session also welcomes papers on specific application domains of natural language procesing, e.g., social data mining, influence networks, customer experience management, computer mediated human-human communication, social media marketing, multimedia management, personalization and persuasion, enterprise feedback management, human-agent, -computer and -robot interaction, intelligent user interfaces, patient opinion mining, surveillance, art. The authors will be required to follow the Author's Guide for manuscript submission to the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems (http://ies-2014.org/submission.html). TIMEFRAME Submission Deadline: August 1st, 2014 Notification of Acceptance: September 1st, 2014 Final Manuscripts Due: October 1st, 2014 Session dates: November 10-12th, 2014 ORGANIZATION Erik Cambria, Nanyang Technological University, Singapore Amir Hussain, University of Stirling, UK Yunqing Xia, Tsinghua University, China From c.lorenz at fcdonders.ru.nl Thu Jul 10 03:33:44 2014 From: c.lorenz at fcdonders.ru.nl (Lorenz, C.M.) Date: Thu, 10 Jul 2014 09:33:44 +0200 (CEST) Subject: Connectionists: Job opening: 7 PhD positions in Dutch research consortium "Language in Interaction In-Reply-To: <131672860.3785419.1404977556508.JavaMail.root@draco.zimbra.ru.nl> Message-ID: <577229301.3785558.1404977624321.JavaMail.root@draco.zimbra.ru.nl> Seven PhD Positions in the Dutch Research Consortium 'Language in Interaction' Closing date: 30 September 2014 For more information: http://www.languageininteraction.nl/jobs/id-2nd-phd-call-general.html We are looking for highly motivated PhD candidates to enrich a unique consortium of researchers that aims to unravel the neurocognitive mechanisms of language at multiple levels. The goal is to understand both the universality and the variability of the human language faculty from genes to behaviour. The Netherlands has an outstanding track record in the language sciences. This research consortium sponsored by a large grant from the Netherlands Organization for Scientific research (NWO) brings together many of the excellent research groups in the Netherlands with a research programme on the foundations of language. The research team consists of 43 Principal Investigators. In addition to the excellence in the domain of language and related relevant fields of cognition, our consortium provides state-of-the-art research facilities and a research team with ample experience in the complex research methods that will be invoked to address the scientific questions at the highest level of methodological sophistication. These include methods from genetics, neuroimaging, computational modelling, and patient-related research. This consortium realizes both quality and critical mass for studying human language at a scale not easily found anywhere else. Currently, the consortium advertises seven PhD positions for a period of 4 years. Depending on the PhD position applied for, candidates will be appointed at one of the home institutions of the consortium. These positions provide the opportunity for conducting world-class research as a member of an interdisciplinary team. Click for more information on the PhD positions and how to apply: http://www.languageininteraction.nl/jobs/id-2nd-phd-call-general.html -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.reske at fz-juelich.de Fri Jul 11 03:47:15 2014 From: m.reske at fz-juelich.de (Martina Reske) Date: Fri, 11 Jul 2014 09:47:15 +0200 Subject: Connectionists: Job offer in Juelich, Germany - IT-Solutions Architect (f/m) Message-ID: <53BF9683.60901@fz-juelich.de> The Institute of Neuroscience and Medicine (INM) investigates the structure and function of the brain. The department INM-6 is conducting research in the field of Computational and Systems Neuroscience with currently four work groups and one Helmholtz Young Investigator Group (www.csn.fz-juelich.de). The Ju?lich Supercomputing Centre (JSC) as part of the Institute for Advanced Simulation (IAS) offers high performance computing resources for scientific and technical applications which are among the most powerful in Europe and worldwide. The Simulation Lab Neuroscience at JSC is dedicated to enabling and supporting the Computational Neuroscience community in leveraging these resources for their research. These institutes are jointly looking for an IT-Solutions Architect (f/m) Your Job: * Design and development of web solutions * Implementation of web sites on the basis of open source solutions (e.g., WordPress/MediaWiki) * Integration of own and third-party components into the web sites * Writing of scripts/programs (e.g. in Python) in a neuroscience environment * Interaction with scientists to find the optimal solution for different situations * Proactive updates and creation of content for web sites in the field of neuroscientific simulation software * Creation of documentation of simulation of software in collaboration with scientists * The successful candidate will work half-time for INM-6 and the Simulation Lab Neuroscience at JSC, respectively. Your Profile: * Completed training in mathematical-technical software development or Bachelor in the area of Computer Science or comparable qualification * Very good knowledge of the relevant web technologies: PHP, MySQL, (X)HTML, JavaScript, CSS * Experience with the administration of web servers under Linux (LAMP) Experience with a common content management system (e.g., WordPress, MediaWiki, Typo3) * Good knowledge of shell and scripting languages like bash and Python * Fluently spoken and written English * Background in neuroscience or another natural science would be a plus * Interest in working with an interdisciplinary team of researchers with highest scientific standards Our Offer: * A diverse range of activities in a creative, interdisciplinary, international team * Forschungszentrum J?lich offers an excellent scientific research infrastructure on a green campus close to Cologne, D?sseldorf and Aachen * Salary and social benefits in conformity with the provisions of the Collective Agreement for the Civil Service (TV?D). Forschungszentrum J?lich aims to employ more women in this area and therefore particulary welcomes applications from women. We also welcome applications from disabled persons. We look forward to receiving your application, preferably online via our online recruitment system (see here: http://www.fz-juelich.de/SharedDocs/Stellenangebote/_common/dna/2014-115-EN-JSC.html), quoting the reference number 2014-115. Martina Reske -- Dr. Martina Reske Scientific Coordinator Institute of Neuroscience and Medicine (INM-6) Computational and Systems Neuroscience & Institute for Advanced Simulation (IAS-6) Theoretical Neuroscience J?lich Research Centre and JARA J?lich, Germany Work +49.2461.611916 Work Cell +49.151.26156918 Fax +49.2461.619460 www.csn.fz-juelich.de ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Juelich GmbH 52425 Juelich Sitz der Gesellschaft: Juelich Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender), Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt, Prof. Dr. Sebastian M. Schmidt ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From alessandra.sciutti at gmail.com Fri Jul 11 11:31:33 2014 From: alessandra.sciutti at gmail.com (Alessandra Sciutti) Date: Fri, 11 Jul 2014 17:31:33 +0200 Subject: Connectionists: [jobs] PHD Opening in "Learning visual cues of interactions for humanoid robots" at University of Genoa and Italian Institute of Technology Message-ID: <53c00354.c9dbc20a.2def.ffffe559@mx.google.com> **************************************************************************** ************************** APOLOGIZE FOR MULTIPLE POSTINGS Applications to the PhD in Bioengineering and Robotics - Universit? degli Studi di Genova are open! The Phd program in Biogengineering and Robotics is rooted in the multiple ongoing collaborations between Universit? degli Studi di Genova/University of Genoa ( www.unige.it), Fondazione Istituto Italiano di Tecnologia/Italian Institute of Technology Foundation ( www.iit.it) and the University of Cagliari ( www.unica.it) Deadline for application (strict): 22/08/2014 - 12:00 (noon). More information on the PhD program, its curricula, research themes, and application modalities can be found at http://phd.dibris.unige.it/biorob/ and http://www.iit.it/en/openings/phd-calls/2015.html. Within the program, I would like to draw your attention on the following research theme, highly interdisciplinary, with elements of computer science, cognitive science and robotics, and very ambitious in its scope: Learning visual cues of interactions for humanoid robots Theme n. 10 - curriculum on ?Cognitive Sciences, Interactive and Rehabilitation Technologies?. Tutors: Prof. Francesca Odone (DIBRIS Universit? dei Genova) Prof. Giulio Sandini (RBCS Dept., IIT), Dr. Alessandra Sciutti (RBCS Dept., IIT) Description: Since the earliest stage of their development, humans learn how to interact with other people. More specifically, babies begin to decode their own movements by acquiring visual evidence of the result of their motor commands. Then, as soon as they learn to perform a given action they also start to anticipate its outcome even when they see it executed by others. Hence, the knowledge accumulated by acting is exploited to understand and predict someone else?s intention. The general goal of this project will be to provide iCub with a similar ability that will guarantee a more natural and proficient interaction with human users. The pipeline of the computational system includes an attentional module able to localize the portion of the scene containing biological motion. Then, iCub exploits this information to focus on the selected area and to describe it more precisely using its stereo system. The visual properties of the observed movements will be used by the robot to decode the intentionality of the interacting partner by using machine learning techniques. View-invariance will be one of the crucial aspects of the system, together with the capability of inferring information about the 3D orientation of an agent. Reference: * Sciutti A., Noceti N., Rea F., Odone F., Verri A. & Sandini G. 2014,'The informative content of optical flow features of biological motion', 37th European Conference on Visual Perception (ECVP 2014), Belgrade, Serbia, August, 24-28, 2014 See also: ? Sciutti A., Patan? L., Nori F. & Sandini G., 2014, ?Understanding object weight from human and humanoid lifting actions?, IEEE Transactions on Autonomous Mental Development, vol. 6, no. 2, pp. 80-92, doi: 10.1109/TAMD.2014.2312399 Requirements: degree in robotics, bioengineering, computer science, computer engineering, or related disciplines, attitude for problem solving, basic skills on c++ programming. A background on computer vision and machine learning is an asset. Highly motivated students are welcome to apply! Contacts Applicants are strongly encouraged to contact the perspective tutors before they submit their application: francesca.odone at unige.it, giulio.sandini at iit.it, alessandra.sciutti at iit.it ----------------------------------------- Alessandra Sciutti (PhD) Robotics Brain and Cognitive Sciences Dept. - Italian Institute of Technology Via Morego 30, 16163 Genova, Italy email: alessandra.sciutti at iit.it -------------- next part -------------- An HTML attachment was scrubbed... URL: From grlmc at urv.cat Sat Jul 12 10:06:57 2014 From: grlmc at urv.cat (GRLMC) Date: Sat, 12 Jul 2014 16:06:57 +0200 Subject: Connectionists: TPNC 2014: extended submission deadline 24 July Message-ID: <8A44F1818A694CA6879F5BF81AA06588@Carlos1> *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* ---------------------------------------------------------------------------- ***** SUBMISSION DEADLINE EXTENDED: July 24 ***** ---------------------------------------------------------------------------- **************************************************************************** ************ 3rd INTERNATIONAL CONFERENCE ON THE THEORY AND PRACTICE OF NATURAL COMPUTING TPNC 2014 Granada, Spain December 9-11, 2014 Organized by: Soft Computing and Intelligent Information Systems (SCI2S) University of Granada Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/tpnc2014/ **************************************************************************** ************ AIMS: TPNC is a conference series intending to cover the wide spectrum of computational principles, models and techniques inspired by information processing in nature. TPNC 2014 will reserve significant room for young scholars at the beginning of their career. It aims at attracting contributions to nature-inspired models of computation, synthesizing nature by means of computation, nature-inspired materials, and information processing in nature. VENUE: TPNC 2014 will take place in Granada, in the region of Andaluc?a, to the south of Spain. The city is the seat of a rich Islamic historical legacy, including the Moorish citadel and palace called Alhambra. SCOPE: Topics of either theoretical, experimental, or applied interest include, but are not limited to: * Nature-inspired models of computation: - amorphous computing - cellular automata - chaos and dynamical systems based computing - evolutionary computing - membrane computing - neural computing - optical computing - swarm intelligence * Synthesizing nature by means of computation: - artificial chemistry - artificial immune systems - artificial life * Nature-inspired materials: - computing with DNA - nanocomputing - physarum computing - quantum computing and quantum information - reaction-diffusion computing * Information processing in nature: - developmental systems - fractal geometry - gene assembly in unicellular organisms - rough/fuzzy computing in nature - synthetic biology - systems biology * Applications of natural computing to: algorithms, bioinformatics, control, cryptography, design, economics, graphics, hardware, learning, logistics, optimization, pattern recognition, programming, robotics, telecommunications etc. A flexible "theory to/from practice" approach would be the perfect focus for the expected contributions. STRUCTURE: TPNC 2014 will consist of: - invited talks - peer-reviewed contributions INVITED SPEAKERS: Kalyanmoy Deb (East Lansing, US), Multi-Criterion Problem Solving: A Niche for Natural Computing Methods Marco Dorigo (Brussels, BE), Swarm Intelligence Francisco Herrera (Granada, ES), Bioinspired Real Parameter Optimization: Where We Are and What?s Next PROGRAMME COMMITTEE: Hussein A. Abbass (Canberra, AU) Uwe Aickelin (Nottingham, UK) Thomas B?ck (Leiden, NL) Christian Blum (San Sebasti?n, ES) Jinde Cao (Nanjing, CN) Vladimir Cherkassky (Minneapolis, US) Sung-Bae Cho (Seoul, KR) Andries P. Engelbrecht (Pretoria, ZA) Terence C. Fogarty (London, UK) Fernando Gomide (Campinas, BR) Inman Harvey (Brighton, UK) Francisco Herrera (Granada, ES) Tzung-Pei Hong (Kaohsiung, TW) Thomas Jansen (Aberystwyth, UK) Yaochu Jin (Guildford, UK) Okyay Kaynak (Istanbul, TR) Satoshi Kobayashi (Tokyo, JP) Soo-Young Lee (Daejeon, KR) Derong Liu (Chicago, US) Manuel Lozano (Granada, ES) Carlos Mart?n-Vide (Tarragona, ES, chair) Ujjwal Maulik (Kolkata, IN) Risto Miikkulainen (Austin, US) Frank Neumann (Adelaide, AU) Leandro Nunes de Castro (S?o Paulo, BR) Erkki Oja (Aalto, FI) Lech Polkowski (Warsaw, PL) Brian J. Ross (St. Catharines, CA) Marc Schoenauer (Orsay, FR) Biplab Kumar Sikdar (Shibpur, IN) Dipti Srinivasan (Singapore, SG) Darko Stefanovic (Albuquerque, US) Umberto Straccia (Pisa, IT) Thomas St?tzle (Brussels, BE) Ponnuthurai N. Suganthan (Singapore, SG) Johan Suykens (Leuven, BE) El-Ghazali Talbi (Lille, FR) Jon Timmis (York, UK) Fernando J. Von Zuben (Campinas, BR) Michael N. Vrahatis (Patras, GR) Xin Yao (Birmingham, UK) ORGANIZING COMMITTEE: Adrian Horia Dediu (Tarragona) Carlos Garc?a-Mart?nez (C?rdoba) Carlos Mart?n-Vide (Tarragona, co-chair) Manuel Lozano (Granada, co-chair) Francisco Javier Rodr?guez (Granada) 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, references, etc.) and should be prepared according to the standard format for the 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=tpnc2014 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 the journal Soft Computing (Springer, 2012 JCR impact factor: 1.124) will be later published containing peer-reviewed substantially 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 April 5 to December 9, 2014. The registration form can be found at: http://grammars.grlmc.com/tpnc2014/Registration.php DEADLINES: Paper submission: July 24, 2014 (23:59h, CET) ? EXTENDED ? Notification of paper acceptance or rejection: August 24, 2014 Final version of the paper for the LNCS proceedings: September 7, 2014 Early registration: September 7, 2014 Late registration: November 25, 2014 Submission to the post-conference journal special issue: March 11, 2015 QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu at urv.cat POSTAL ADDRESS: TPNC 2014 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34 977 559 543 Fax: +34 977 558 386 ACKNOWLEDGEMENTS: Universidad de Granada Universitat Rovira i Virgili --- Este mensaje no contiene virus ni malware porque la protecci?n de avast! Antivirus est? activa. http://www.avast.com From ted.carnevale at yale.edu Mon Jul 14 16:48:29 2014 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 14 Jul 2014 16:48:29 -0400 Subject: Connectionists: NEURON course at 2014 SFN Meeting Message-ID: <53C4421D.4000102@yale.edu> Using NEURON to Model Cells and Networks Satellite Symposium, Society for Neuroscience Meeting 9 AM - 5 PM on Friday, November 14, 2014 Speakers include Ted Carnevale, Bill Lytton, and Gordon Shepherd This course emphasizes practical issues that are key to the most productive use of NEURON, an advanced simulation environment for realistic modeling of biological neurons and neural circuits. Through lectures and live computer demonstrations, we will address topics that include the following: Partial list of topics that will be covered: * Efficient design and implementation of models of neurons and networks. * Constructing and managing models with NEURON's GUI, hoc, and Python. * Using the built-in variable-order variable-timestep integrator for improved speed and accuracy. * Parallelizing models of cells and networks to take advantage of multicore PCs and Macs, workstation clusters, and parallel supercomputers. * Expanding NEURON's repertoire of biophysical mechanisms, including an introduction to using the new RxD feature to implement models that involve reactive diffusion. * Databases for empirically-based modeling. Each registrant will receive a comprehensive set of notes. Registration is limited to 25 individuals on a first-come, first-serve basis. The registration deadline is Friday, October 31, 2014. NO on-site registration will be accepted. For more information and the online registration form, see http://www.neuron.yale.edu/neuron/static/courses/dc2014/dc2014.html --Ted From ted.carnevale at yale.edu Mon Jul 14 17:07:16 2014 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 14 Jul 2014 17:07:16 -0400 Subject: Connectionists: 2014 SFN Meeting Workshop: NSG Portal for parallel simulations Message-ID: <53C44684.3080502@yale.edu> What: Using the Neuroscience Gateway Portal for Parallel Simulations A Satellite Symposium at the 2014 Society for Neuroscience Meeting Where: Lodation to be announced in downtown Washington, DC When: 9 AM - Noon on Saturday, November 15, 2014 Speakers to include: A. Majumdar, S. Sivagnanam, and T. Carnevale Registration deadline: Friday, October 31, 2014 This workshop is intended for neuroscientists who are already using, or would like to use, the Neuroscience Gateway Portal (NSG http://www.nsgportal.org/) for parallel simulations. The NSG portal eliminates most administrative and technical barriers that face neuroscientists who need to use high performance computing resources for large modeling projects. Its web-based interface simplifies the tasks of uploading models, specifying job parameters, monitoring job status, and storing and retrieving output data. Simulators currently installed include Brian, MOOSE, GENESIS3, NEST, NEURON, and PyNN. The workshop will combine didactic presentations by NSG's developers, discussions with experienced users, and hands on instruction in how to use the portal. For more information and the online registration form see http://www.neuron.yale.edu/neuron/static/courses/nsg2014/nsg2014.html --Ted From Vittorio.Murino at iit.it Tue Jul 15 09:19:53 2014 From: Vittorio.Murino at iit.it (Vittorio Murino) Date: Tue, 15 Jul 2014 15:19:53 +0200 Subject: Connectionists: 2014/2015 PhD Course on Sciences & Technologies For Electronics & Telecommunication - Curriculum in Computer Vision, Pattern Recognition and Machine Learning Message-ID: <53C52A79.8000607@iit.it> Fondazione Istituto Italiano di Tecnologia (IIT - www.iit.it ) together with the University of Genova opened the call for the *2014/2015* *Doctoral Course on Sciences & Technologies For Electronics & Telecommunication - Curriculum in Computer Vision, Pattern Recognition and Machine Learning.* In this context, Ph.D. positions are available at the Pattern Analysis and Computer Vision (PAVIS) dept. to work in Computer Vision, Pattern Recognition and Machine Learning, and more specifically on the following themes: Theme A: Computer vision for behavioral analysis and activity recognition Theme B: Part-based human body modeling for Socially-Aware Computer Vision Theme C: Crowd behavioral analysis and event recognition Theme D: Re-identification using soft biometric cues Theme E: Long term visual learning for 3D scene understanding Theme F: Biomedical imaging and connectomics analysis Theme G: Animal behavior analysis More info on the above research topics can be found at: http://www.iit.it/images/phd-xxx/ResearchTopics2014_IIT-PAVIS.pdf or directly asked to Prof. V. Murino (vittorio.murino at iit.it ) or any other tutor indicated for each theme. The PhD program on the listed themes will take place at the PAVIS department of the Istituto Italiano di Tecnologia (IIT) located in Genova (www.iit.it ) The department focuses on activities related to the analysis and understanding of images and patterns in general, thus representing a reference for the other IIT Departments and labs which have to deal with such kind of data. The PAVIS staff has a wide expertise on image processing, computer vision and pattern recognition, machine learning, and related applications. Actually, the research in PAVIS is devoted to study and to build intelligent systems for real applications, especially related, but not limited, to surveillance & security, biomedical imaging, and bioinformatics. One of the primary goals is to design and develop innovative video surveillance systems, characterized by the use of highly-functional smart sensors and advanced video analytics features. To this end, PAVIS performs cutting edge research in computer vision and pattern recognition, but also in biometrics, multimodal data and sensor fusion, sensors networks, and embedded computer vision. Further, another target of the lab is to explore novel strategies in biomedical image analysis and bioinformatics, due to the versatility of the techniques it can manage. You can also browse the PAVIS webpages to see our activities and research at: http://www.iit.it/pavis.html *To apply, follow the instructions indicated in the links, in short: a detailed CV, a research proposal under one or more themes chosen among those above indicated, reference letters, and any other formal document concerning the degrees earned.* ** *Notice that these documents are mandatory in order to consider valid the application.* ** *IMPORTANT:*You need to specify the theme (one or more) you want to apply and include a research statement (research proposal/project/plan/rationale) on such theme. *ONLINE APPLICATION DEADLINE is August 22, 2014 at 12:00 p.m. (noon -- Italian time/CET) Strict deadline, no extension.* ** *ONLINE APPLICATIONS only, look at: *http://www.studenti.unige.it/postlaurea/dottorati/XXX/ENG/ For more information on administrative issues, please e-mail: pavis at iit.it ---------------------------------------------------------------------------------------------- -- Vittorio Murino ******************************************* Prof. Vittorio Murino, Ph.D. PAVIS - Pattern Analysis & Computer Vision IIT Istituto Italiano di Tecnologia Via Morego 30 16163 Genova, Italy Phone: +39 010 71781 504 Mobile: +39 329 6508554 Fax: +39 010 71781 236 E-mail:vittorio.murino at iit.it Secretary: Sara Curreli email: sara.curreli at iit.it Phone: +39 010 71781 917 http://www.iit.it/pavis ******************************************** -------------- next part -------------- An HTML attachment was scrubbed... URL: From dwang at cse.ohio-state.edu Tue Jul 15 13:59:17 2014 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Tue, 15 Jul 2014 13:59:17 -0400 Subject: Connectionists: NEURAL NETWORKS, July 2014 Message-ID: <53C56BF5.4090402@cse.ohio-state.edu> Neural Networks - Volume 55, July 2014 http://www.journals.elsevier.com/neural-networks Detecting cells using non-negative matrix factorization on calcium imaging data Ryuichi Maruyama, Kazuma Maeda, Hajime Moroda, Ichiro Kato, Masashi Inoue, Hiroyoshi Miyakawa, Toru Aonishi Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning Xiong Yang, Derong Liu, Ding Wang, Qinglai Wei Stochastic nonlinear time series forecasting using time-delay reservoir computers: Performance and universality Lyudmila Grigoryeva, Julie Henriques, Laurent Larger, Juan-Pablo Ortega A general soft label based Linear Discriminant Analysis for semi-supervised dimensionality reduction Mingbo Zhao, Zhao Zhang, Tommy W.S. Chow, Bing Li Exponential synchronization of delayed memristor-based chaotic neural networks via periodically intermittent control Guodong Zhang, Yi Shen A collective neurodynamic optimization approach to bound-constrained nonconvex optimization Zheng Yan, Jun Wang, Guocheng Li Stability analysis of fractional-order Hopfield neural networks with time delays Hu Wang, Yongguang Yu, Guoguang Wen Towards limb position invariant myoelectric pattern recognition using time-dependent spectral features Rami N. Khushaba, Maen Takruri, Jaime Valls Miro, Sarath Kodagoda Model, analysis, and evaluation of the effects of analog VLSI arithmetic on linear subspace-based image recognition Gonzalo Carvajal, Miguel Figuero From fmschleif at googlemail.com Wed Jul 16 04:58:43 2014 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Wed, 16 Jul 2014 09:58:43 +0100 Subject: Connectionists: Two Weeks left ! - Call for papers 2nd International Workshop on High Dimensional Data Mining (HDM'14) at ICDM 2014 Message-ID: +++ PLEASE, APOLOGIZE MULTIPLE COPIES +++ +++ Submission deadline: August 1, 2014 +++ =================================================================== Call for Papers The 2nd International Workshop on High Dimensional Data Mining (HDM?14) http://www.cs.bham.ac.uk/~axk/HDM14.htm http://hdataskforce.wordpress.com/ In conjunction with the IEEE International Conference on Data Mining (IEEE ICDM 2014) http://icdm2014.sfu.ca/home.html =================================================================== Description of Workshop Stanford statistician David Donoho predicted that the 21st century will be the century of data. "We can say with complete confidence that in the coming century, high-dimensional data analysis will be a very significant activity, and completely new methods of high-dimensional data analysis will be developed; we just don't know what they are yet." -- D. Donoho, 2000. Beyond any doubt, unprecedented technological advances lead to increasingly high dimensional data sets in all areas of science, engineering and businesses. These include genomics and proteomics, biomedical imaging, signal processing, astrophysics, finance, web and market basket analysis, among many others. The number of features in such data is often of the order of thousands or millions - that is much larger than the available sample size. A number of issues make classical data analysis methods inadequate, questionable, or inefficient at best when faced with high dimensional data spaces: 1. High dimensional geometry defeats our intuition rooted in low dimensional experiences, and this makes data presentation and visualisation particularly challenging. 2. Phenomena that occur in high dimensional probability spaces, such as the concentration of measure, are counter-intuitive for the data mining practitioner. For instance, distance concentration is the phenomenon that the contrast between pair-wise distances may vanish as the dimensionality increases. This makes the notion of nearest neighbour meaningless, together with a number of methods that rely on a notion of distance. 3. Bogus correlations and misleading estimates may result when trying to fit complex models for which the effective dimensionality is too large compared to the number of data points available. 4. The accumulation of noise may confound our ability to find low dimensional intrinsic structure hidden in the high dimensional data. 5. The computation cost of processing high dimensional data or carrying out optimisation over a high dimensional parameter spaces is often prohibiting. Topics This workshop aims to promote new advances and research directions to address the curses and uncover and exploit the blessings of high dimensionality in data mining. Topics of interest include (but are not limited to): - Systematic studies of how the curse of dimensionality affects data mining methods - New data mining techniques that exploit some properties of high dimensional data spaces - Theoretical underpinning of mining data whose dimensionality is larger than the sample size - Stability and reliability analyses for data mining in high dimensions - Adaptive and non-adaptive dimensionality reduction for noisy high dimensional data sets - Methods of random projections, compressed sensing, and random matrix theory applied to high dimensional data mining and high dimensional optimisation - Models of low intrinsic dimension, such as sparse representation, manifold models, latent structure models, and studies of their noise tolerance - Classification of high dimensional complex data sets - Functional data mining - Data presentation and visualisation methods for very high dimensional data sets - Data mining applications to real problems in science, engineering or businesses where the data is high dimensional Paper submission High quality original submissions are solicited for oral and poster presentation at the workshop. Papers should not exceed a maximum of 8 pages, and must follow the IEEE ICDM format requirements of the main conference. All submissions will be peer-reviewed, and all accepted workshop papers will be published in the proceedings by the IEEE Computer Society Press. Submit your paper here. Important dates Submission deadline: August 1, 2014 Notifications to authors: September 26, 2014 Workshop date: December 14, 2014 We are looking forward to welcome you in Shenzhen with best regards Ata Kaban Frank-Michael Schleif Thomas Villmann (Workshop Organizers) -- ------------------------------------------------------- PD Dr. rer. nat. habil. Frank-Michael Schleif School of Computer Science The University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom - email: fschleif at techfak.uni-bielefeld.de http://promos-science.blogspot.de/ ------------------------------------------------------- From jboedeck at informatik.uni-freiburg.de Wed Jul 16 09:27:06 2014 From: jboedeck at informatik.uni-freiburg.de (Joschka Boedecker) Date: Wed, 16 Jul 2014 15:27:06 +0200 Subject: Connectionists: 1st Call for Abstracts for the 7th Int'l Workshop on Guided Self-Organisation (Freiburg, Dec 16-18, 2014) Message-ID: <53C67DAA.1070409@informatik.uni-freiburg.de> Dear colleagues, This is an announcement and Call for Abstracts for the Seventh International Workshop on Guided Self-Organisation (GSO-2014) to be held from December 16-18, 2014 in Freiburg, Germany. http://ml.informatik.uni-freiburg.de/events/gso14/index The workshop will bring together researchers from a richly diverse background who share interest in understanding and designing self-organising systems. Of particular interest are well-founded, but general methods for characterizing such systems in a principled way with the view of ultimately allowing them to be guided toward prespecified goals. Information theory, nonlinear dynamics and graph theory are core to many of these methods, and quantifying complexity and its sources is a common theme. This year, the workshop is organised in collaboration with the BrainLinks-BrainTools cluster of excellence at University of Freiburg ( https://www.brainlinks-braintools.uni-freiburg.de/ ), and one focus theme will be guided self-organisation in neural systems. Submissions to the workshop are extended abstracts (one-two pages). If interested in participating, send an extended abstract (by September 7th, 2014) by email to: jboedeck at informatik dot uni-freiburg dot de The notifications are expected by September 21st, 2014. Authors of accepted submissions will present the content to the workshop (scheduled 30 minutes presentation). It is expected that post-workshop publication of selected papers will follow in a special journal issue (as has been the case for previous GSO workshops). Please consult the website above and also http://guided-self.org/ for more information. Best wishes, Joschka Boedecker Mikhail Prokopenko Martin Riedmiller From j.bonaiuto at ucl.ac.uk Tue Jul 15 05:27:31 2014 From: j.bonaiuto at ucl.ac.uk (James Bonaiuto) Date: Tue, 15 Jul 2014 10:27:31 +0100 Subject: Connectionists: Linking Brain Models and Data: An Invitation from James Bonaiuto and Michael A. Arbib Message-ID: The USC Brain Project has just released a new version of their neuroinformatics tool, the Brain Operation DataBase (BODB) v4.0. BODB is a tool for modelers and experimentalists to document computational models of the brain and their linkages to summaries of experimental data. Models can be compared in terms of these relations, and experimental data summaries can be visualized in a variety of ways. Groups of users can build collaboratory workspaces which allow them to share groups of models and data and work together to develop new models. This latest version of BODB includes many new features: - Improved search functionality: users can now search federated databases such as CoCoMac (macaque neural connectivity) and Brede (human brain imaging) directly as well as use boolean combinations of search terms - Users can now maintain a list of their favorite entries outside any workspace - Model and BOP diagrams: users can generate clickable and zoomable graphs showing the relationships between brain operating principles (BOPs) and between models and summaries of empirical data (SEDs) - ERP SED visualization: users can view the locations of ERP components on a standard electrode placement system - Improved workspaces: workspaces now include an activity stream, discussion board, and bookmarks. Workspaces administrators can send invitations to other users to join the workspace. - ModelDB import: users can search ModelDB for models and import them to BODB for documentation of their linkage to SEDs - New Documentation System: the new system is far more extensive, is linked from pages on BODB, and users can now search the documentation - Web API: it is now possible to return BODB entries in JSON aand XML format through a simple URL protocol An overview of our general methodology for the neuroinformatics of brain modeling can be found at http://www.ncbi.nlm.nih.gov/pubmed/24234915. It is just one paper from a special issue of Neuroinformatics (Volume 12, Number 1, January 2014) on ?Action, Language and Neuroinformatics? (Michael Arbib, Guest Editor). The Manual for BODB can be found at http://bodb.usc.edu/media/BODB_Manual.pdf. We invite you to register for a free account on BODB and add your own models and experimental data: http://bodb.usc.edu ------------------------------------------------------ James Bonaiuto, PhD Research Associate Sobell Department of Motor Neuroscience and Movement Disorders UCL Institute of Neurology 33 Queen Square, London WC1N3BG, United Kingdom -------------- next part -------------- An HTML attachment was scrubbed... URL: From chiestand at salk.edu Wed Jul 16 20:59:48 2014 From: chiestand at salk.edu (Chris Hiestand) Date: Wed, 16 Jul 2014 17:59:48 -0700 Subject: Connectionists: NIPS Reminder: Deadline for Workshop Applications In ~2 Weeks Message-ID: <49BAD39E-02C7-4535-B5CD-566A5B734B34@salk.edu> NIPS*2014 Post-Conference Workshops Friday December 12 and Saturday December 13, 2014 Palais des Congr?s de Montr?al/Convention and Exhibition Center, Montreal, Quebec, Canada Following the NIPS*2014 main conference, workshops on a variety of current topics will be held on Friday December 12 and Saturday December 13, 2014, in Montreal, Canada. We invite researchers interested in chairing one of these workshops to submit workshop proposals. The goal of the workshops is to provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are encouraged as workshop topics. There will be seven hours of workshop meetings per day, split into morning and afternoon sessions, with free time between the sessions for individual exchange or outdoor activities. Note that this year, there is no skiing at NIPS; the workshop schedule will thus differ from past NIPS workshops (the morning session will be 8:30am-12pm, and the afternoon session will be 3pm-6:30pm). Potential workshop topics range from Neuroscience to Bayesian Methods to Representation Learning to Kernels to Clustering, and include Application Areas such as Computational Biology, Speech, Vision or Social Networks. Detailed descriptions of previous workshops may be found at: http://nips.cc/Conferences/2013/Program/schedule.php?Session=Workshops Workshop organizers have several responsibilities, including: Coordinating workshop participation and content as well as providing the program for the workshop in a timely manner. Submission Instructions A nips.cc account is required to submit the Workshops application. Please follow the URL below and check the required format for the application well before the proposal deadline. You can edit your application online right up until this deadline. We have funding to video record a limited number of workshops for later online viewing. Workshop proposals should state if they wish their workshop to be recorded. Interested parties must submit a proposal by **23:59 UTC on Friday August 2nd, 2014** Proposals should be submitted electronically at the following URL: https://nips.cc/Workshops/ Preference will be given to one-day workshops that reserve a significant portion of time for open discussion or panel discussion and to workshops with a greater fraction of confirmed speakers. We suggest that organizers allocate sufficient time for questions, discussion, and breaks. Past experience suggests that workshops otherwise degrade into mini-conferences as talks begin to run over. Organizers should explicitly state the expected fraction of time for discussion & questions and the expected number of talks per day at the end of the proposal. We strongly recommend that each workshop include no more than 12 talks per day. We would like to attempt to partially unify the NIPS workshop important dates across all of the workshops. Therefore, please consider using the following date guidelines for your workshop in order to provide program information in time for publication: We suggest workshop organizers to adopt the following schedule: * Workshop acceptance notification will be on August 14th, 2014 * Your workshop should be publicized on or before August 21st, 2014. * Internal submission deadline should be on or before October 9th, 2014. * Internal acceptance decisions should be mailed out on or before October 23rd, 2014. * Submit finalized workshop organizers, abstract, and URL on or before October 30th, 2014. NIPS does not provide travel funding for workshop speakers. In the past, some workshops have sought and received funding from external sources to bring in outside speakers. The organizers of each accepted workshop can name four individuals per day of workshop to receive free workshop registration. Please feel free to contact us if you have any questions: Francis Bach and Amir Globerson NIPS*2014 Workshops Chairs Web URL: http://nips.cc/Conferences/2014/CallForWorkshops From ecai2014 at guarant.cz Fri Jul 18 09:00:03 2014 From: ecai2014 at guarant.cz (=?utf-8?q?ECAI_2014?=) Date: Fri, 18 Jul 2014 15:00:03 +0200 Subject: Connectionists: =?utf-8?q?ECAI_2014_conference_starts_in_a_month?= Message-ID: <20140718130003.535E717446E@gds25d.active24.cz> =============================================================== ECAI 2014 Prague, Czech Republic 18-22 August 2014 http://www.ecai2014.org/ =============================================================== ECAI 2014 CONFERENCE STARTS IN A MONTH (August 18) REGISTRATION On-line form available on the website PRELIMINARY PROGRAMME Programmes of all sessions have been finalized and published on the website Monday, August 18 - Czech Technical University Tutorials, Workshops, STAIRS, RuleML, Angry Birds Tuesday, August 19 - Czech Technical University Tutorials, Workshops, STAIRS, RuleML, Angry Birds Welcome Drink and Opening Ceremony in the Bethlehem Chapel Wednesday, August 20 - Clarion Congress Hotel Keynote Lecture, Parallel Sessions, PAIS, RuleML, Angry Birds Thursday, August 21 - Clarion Congress Hotel Keynote Lecture, Parallel Sessions, PAIS, Angry Birds Conference Dinner in the Monastery Restaurant Friday, August 22 - Clarion Congress Hotel Keynote Lecture, Parallel Sessions, Angry Birds =============================================================== This email is not intended to be spam or to go to anyone who wishes not to receive it. If you do not wish to receive this letter and wish to re?move your email address from our database please reply to this message with ?Unsubscribe? in the subject line From grlmc at urv.cat Fri Jul 18 10:05:47 2014 From: grlmc at urv.cat (URV - RESEARCH GROUP ON MATHEMATICAL LINGUISTICS) Date: Fri, 18 Jul 2014 16:05:47 +0200 Subject: Connectionists: BigDat 2015: 23 July registration deadline Message-ID: *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* ***************************************************** INTERNATIONAL WINTER SCHOOL ON BIG DATA BigDat 2015 Tarragona, Spain January 26-30, 2015 Organized by Rovira i Virgili University http://grammars.grlmc.com/bigdat2015/ ***************************************************** --- 2nd registration deadline: July 23, 2014 --- ***************************************************** AIM: BigDat 2015 is a research training event for graduates and postgraduates in the first steps of their academic career. It aims at updating them about the most recent developments in the fast developing area of big data, which covers a large spectrum of current exciting research, development and innovation with an extraordinary potential for a huge impact on scientific discoveries, medicine, engineering, business models, and society itself. Renowned academics and industry pioneers will lecture and share their views with the audience. All big data subareas will be displayed, namely: foundations, infrastructure, management, search and mining, security and privacy, and applications. Main challenges of analytics, management and storage of big data will be identified through 4 keynote lectures and 24 six-hour courses, which will tackle the most lively and promising topics. The organizers believe outstanding speakers will attract the brightest and most motivated students. Interaction will be a main component of the event. ADDRESSED TO: Graduate and postgraduates from around the world. There are no formal pre-requisites in terms of academic degrees. However, since there will be differences in the course levels, specific knowledge background may be required for some of them. BigDat 2015 is also appropriate for more senior people who want to keep themselves updated on recent developments and future trends. They will surely find it fruitful to listen and discuss with major researchers, industry leaders and innovators. REGIME: In addition to keynotes, 3 courses will run in parallel during the whole event. Participants will be able to freely choose the courses they will be willing to attend as well as to move from one to another. VENUE: BigDat 2015 will take place in Tarragona, located 90 kms. to the south of Barcelona. The venue will be: Campus Catalunya Universitat Rovira i Virgili Av. Catalunya, 35 43002 Tarragona KEYNOTE SPEAKERS: Ian Foster (Argonne National Laboratory), tba Geoffrey C. Fox (Indiana University, Bloomington), Mapping Big Data Applications to Clouds and HPC C. Lee Giles (Pennsylvania State University, University Park), Scholarly Big Data: Information Extraction and Data Mining William D. Gropp (University of Illinois, Urbana-Champaign), tba COURSES AND PROFESSORS: Hendrik Blockeel (Katholieke Universiteit Leuven), [intermediate] Decision Trees for Big Data Analytics Diego Calvanese (Free University of Bozen-Bolzano), [introductory/intermediate] End-User Access to Big Data Using Ontologies Jiannong Cao (Hong Kong Polytechnic University), [introductory/intermediate] Programming with Big Data Edward Y. Chang (HTC Corporation, New Taipei City), [introductory/advanced] From Design of Distributed and Online Algorithms to Hands-on Code Lab Practice on Real Datasets Ernesto Damiani (University of Milan), [introductory/intermediate] Process Discovery and Predictive Decision Making from Big Data Sets and Streams Gautam Das (University of Texas, Arlington), [intermediate/advanced] Mining Deep Web Repositories Maarten de Rijke (University of Amsterdam), tba Geoffrey C. Fox (Indiana University, Bloomington), [intermediate] Using Software Defined Systems to Address Big Data Problems Minos Garofalakis (Technical University of Crete, Chania) [intermediate/advanced], Querying Continuous Data Streams Vasant G. Honavar (Pennsylvania State University, University Park) [introductory/intermediate], Learning Predictive Models from Big Data Mounia Lalmas (Yahoo! Research Labs, London), [introductory] Measuring User Engagement Tao Li (Florida International University, Miami), [introductory/intermediate] Data Mining Techniques to Understand Textual Data Kwan-Liu Ma (University of California, Davis), [intermediate] Big Data Visualization Christoph Meinel (Hasso Plattner Institute, Potsdam), [introductory/intermediate] New Computing Power by In-Memory and Multicore to Tackle Big Data David Padua (University of Illinois, Urbana-Champaign), [intermediate] Data Parallel Programming Manish Parashar (Rutgers University, Piscataway), [intermediate] Big Data in Simulation-based Science Srinivasan Parthasarathy (Ohio State University, Columbus), [intermediate] Scalable Data Analysis Evaggelia Pitoura (University of Ioannina), [intermediate] Online Social Networks Vijay V. Raghavan (University of Louisiana, Lafayette), [introductory/intermediate] Visual Analytics of Time-evolving Large-scale Graphs Pierangela Samarati (University of Milan), [intermediate], Data Security and Privacy in the Cloud Peter Sanders (Karlsruhe Institute of Technology), [introductory/intermediate] Algorithm Engineering for Large Data Sets Johan Suykens (Katholieke Universiteit Leuven), [introductory/intermediate] Fixed-size Kernel Models for Big Data Domenico Talia (University of Calabria, Rende), [intermediate] Scalable Data Mining on Parallel, Distributed and Cloud Computing Systems Jieping Ye (Arizona State University, Tempe), [introductory/advanced] Large-Scale Sparse Learning and Low Rank Modeling ORGANIZING COMMITTEE: Adrian Horia Dediu (Tarragona) Carlos Mart?n-Vide (Tarragona, chair) Florentina Lilica Voicu (Tarragona) REGISTRATION: It has to be done at http://grammars.grlmc.com/bigdat2015/registration.php The selection of up to 8 courses requested in the registration template is only tentative and non-binding. For the sake of organization, it will be helpful to have an approximation of the respective demand for each course. Since the capacity of the venue is limited, registration requests will be processed on a first come first served basis. The registration period will be closed and the on-line registration facility disabled when the capacity of the venue will be complete. It is much recommended to register prior to the event. FEES: As far as possible, participants are expected to stay full-time. Fees are a flat rate covering the attendance to all courses during the week. There are several early registration deadlines. Fees depend on the registration deadline. ACCOMMODATION: Suggestions of accommodation will be provided in due time. CERTIFICATE: Participants will be delivered a certificate of attendance. QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu at urv.cat POSTAL ADDRESS: BigDat 2015 Lilica Voicu Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34 977 559 543 Fax: +34 977 558 386 ACKNOWLEDGEMENTS: Universitat Rovira i Virgili From psadowsk at uci.edu Fri Jul 18 16:41:56 2014 From: psadowsk at uci.edu (Peter Sadowski) Date: Fri, 18 Jul 2014 13:41:56 -0700 Subject: Connectionists: Deep Learning in High-Energy Physics and Dropout: Recent Publications Message-ID: Readers of this mailing list may be interested in the following two recently published papers: The Dropout Learning Algorithm *Artificial Intelligence* www.sciencedirect.com/science/article/pii/S0004370214000216 Searching for Exotic Particles in High-Energy Physics with Deep Learning *Nature Communications* www.nature.com/ncomms/2014/140702/ncomms5308/full/ncomms5308.html Cheers, Peter Sadowski Department of Computer Science University of California, Irvine -------------- next part -------------- An HTML attachment was scrubbed... URL: From francisco.pereira at gmail.com Wed Jul 16 11:15:40 2014 From: francisco.pereira at gmail.com (Francisco Pereira) Date: Wed, 16 Jul 2014 11:15:40 -0400 Subject: Connectionists: Research Specialist position at Princeton University Message-ID: A Research Specialist position is available in Matthew Botvinick's lab in the Princeton Neuroscience Institute, in collaboration with Francisco Pereira at Siemens Corporate Technology. This is a position within a team participating in the IARPA Knowledge Representation in Neural Systems program. The goal of the program is to develop models of how the brain represents conceptual knowledge, and how that knowledge is used when carrying out tasks like reading a sentence. These models will be tested using brain imaging data. The main role in this position is as a programmer writing the code needed to build such models, while also being involved in experiment design and data analysis. Examples of tasks you might be asked to do: - prepare text corpora for use in developing models - implement evaluation tasks that the models developed will be benchmarked with - collect material from online resources and behavioral experiments - prepare stimuli for brain imaging experiments or model building - help in designing and carrying out brain imaging and behavioral experiments - analyze behavioral and brain imaging experimental data It is an unusual position in that you will be gaining experience in both machine learning and cognitive neuroscience. In addition to the core research goals, we will also be delivering a concrete system to the funding agency, and hence this will be a fast-paced project. You will be working directly with the PIs and also graduate students and research scientists in the team. Essential qualifications are experience developing software in MATLAB or Python (Perl is also useful), as well as an undergraduate degree in computer science, biomedical engineering, cognitive neuroscience or a related field. Preferred qualifications are knowledge in natural language processing, machine learning, and collection, preprocessing and analysis of brain imaging data (e.g. SPM, FSL or AFNI). The final candidate will be required to pass a background check successfully. This is a 1 year position, starting as soon as possible, with an additional year possible contingent on funding availability and performance. To apply, please go to https://jobs.princeton.edu/applicants/jsp/shared/Welcome_css.jsp and use ?Search Open Positions? with requisition number 1400452. Please email francisco.pereira at gmail.com with any pre-application inquiries. -------------- next part -------------- An HTML attachment was scrubbed... URL: From jbaimon at sandia.gov Wed Jul 16 23:55:43 2014 From: jbaimon at sandia.gov (Aimone, James Bradley) Date: Thu, 17 Jul 2014 03:55:43 +0000 Subject: Connectionists: Postdoc position in neural inspired computation Message-ID: <387158083FC22D43AF38637EBFD90C28289E97D7@EXMB02.srn.sandia.gov> A postdoctoral research position is available for research on neural algorithm development for a neural-inspired computing hardware project within the cognitive modeling group at Sandia National Laboratories. The successful applicant will join a broad interdisciplinary team that includes computational neuroscientists, computer scientists, and electrical engineers focused on developing methods for hardware acceleration of neural algorithms. He or she will be expected to leverage research from the broader neuroscience research community to develop computational approaches for addressing real-world problems. Previous experience both in neuroscience research and in data analytics / machine learning domains is ideal. For more information, please contact Dr. Brad Aimone (technical contact, jbaimon at sandia.gov ) or Dr. John Wagner (department manager, jswagne at sandia.gov). For the full posting and necessary qualifications, go to careers.sandia.gov and search for posting ID 646640 -------------- next part -------------- An HTML attachment was scrubbed... URL: From A.Cangelosi at plymouth.ac.uk Sat Jul 19 07:11:45 2014 From: A.Cangelosi at plymouth.ac.uk (Angelo Cangelosi) Date: Sat, 19 Jul 2014 11:11:45 +0000 Subject: Connectionists: 2 PhD positions: Cognitive robotics modelling + human-robot interaction psychology experiments Message-ID: Can you please post this PhD advert in the connectionist mailing list? THRIVE project: Trust in Human Robot Interaction Via Embodiment Plymouth University, Centre for Cognitive and Neural Systems https://www1.plymouth.ac.uk/research/crns Two PhD Studentships: one on Cognitive Robotics Modelling and one in Human-Robot Interaction Psychology Experiments Project Description This research is part of the new project ?THRIVE: Trust in Human-Robot Interaction Via Embodiment.? This project aims at the investigation of embodiment and socio-cognitive mechanisms in the development of trust between humans and robots engaged in joint tasks. The work will be based on the strategic coupling of developmental robotics modelling and of empirical human-robot interaction experiments. These will investigate the robot?s embodiment properties (e.g. voice, gaze, emotional, humanoid appearance) and socio-cognitive mechanisms (e.g. joint attention, joint action, group assimilation) in establishing trust. This is a 4-year project, funded by the European Office of Aerospace Research and Development. The robotics PhD student will be responsible for the design and implementation of motor and social strategies in robot platforms (e.g. iCub, Nao, Scitos G5), using a cognitive and developmental robotics approach. The psychology PhD student will be responsible for the design, execution and data analysis of psychology experiments on trust in human-robot interaction experiments. The two post holder will collaborate closely for joint robotics and hri experiments. Eligibility for Cognitive Robotics PhD Applicants should have, or expect to obtain, a high grade Bachelors or Masters Degree in Computer Science, Robotics, Electronics or related disciplines. The candidate must have excellent programming skills and a strong motivation for research. Previous experience on robotics or human-robot interaction is desirable. Eligibility for Psychology PhD Applicants should have, or expect to obtain, a high grade Bachelors or Masters Degree in Psychology or related disciplines. The candidate must have good knowledge of experimental psychology research methods and a strong motivation for research. Previous experience on human-robot interaction is desirable. The post holder will collaborate closely with a second PhD student responsible for the design of psychology experiments on human-robot interaction. This second position, for a Psychology/HRI student, is also open. Funding The studentship will have a 4-year duration and consists of an annual bursary of approximately ?13,863 per annum. The tuition fees will be paid directly by the project. There will be a 6-month probation period. The start date is 1 January 2015. For further information on the project or for an informal discussion, please contact Professor Angelo Cangelosi at a.cangelosi at plymouth.ac.uk. Details about Plymouth University can be found at www.plymouth.ac.uk. For an application form and full details on how to apply, please visit www.plymouth.ac.uk/postgraduate. Applicants should send a completed application form with copies of their qualifications and transcripts, two academic references, English Language qualification (if appropriate), a covering letter and a CV to Mrs Carole Watson, Graduate School, 3rd Floor Link Building, Plymouth University, Drake Circus, Plymouth, PL4 8AA or via email to c.watson at plymouth.ac.uk. Closing date for applications: 12 noon, 29 August 2014 Interviews will be held on 26 September 2014 ________________________________ [http://www.plymouth.ac.uk/images/email_footer.gif] This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form. From saketn at andrew.cmu.edu Sat Jul 19 12:49:02 2014 From: saketn at andrew.cmu.edu (Saket) Date: Sat, 19 Jul 2014 12:49:02 -0400 Subject: Connectionists: BDA 2014 -- last call for submissions! Message-ID: ======================================================== The 2nd Workshop on Biological Distributed Algorithms (BDA 2014) October 11-12, 2014, Austin, Texas USA - in conjunction with DISC 2014 http://www.cs.cmu.edu/~saketn/BDA2014/ ======================================================== We are excited to announce the second workshop on Biological Distributed Algorithms (BDA). BDA is focused on the relationships between distributed computing and distributed biological systems and in particular, on analysis and case studies that combine the two. Such research can lead to better understanding of the behavior of the biological systems while at the same time developing novel computational algorithms that can be used to solve basic distributed computing problems. The first BDA workshop, BDA 2013, was collocated with DISC 2013 (the 27th International Symposium on Distributed Computing) in Jerusalem. BDA 2014 will be collocated with DISC 2014 in Austin, Texas. It will take place just before DISC, on Saturday and Sunday, October 11-12, 2014. BDA 2014 will include talks on distributed algorithms related to a variety of biological systems. However, this time we will devote special attention to communication and coordination in insect colonies (e.g. foraging, navigation, task allocation, construction) and networks in the brain (e.g. learning, decision-making, attention). =========== SUBMISSIONS =========== We solicit submissions of extended abstracts describing recent results relevant to biological distributed computing. We especially welcome extended abstracts describing new insights and / or case studies regarding the relationship between distributed computing and biological systems even if these are not fully formed. Since a major goal of the workshop is to explore new directions and approaches, we especially encourage the submission of ongoing work. Selected contributors would be asked to present, discuss and defend their work at the workshop. By default, the submissions will be evaluated for either oral or poster presentation, though authors may indicate in their submission if it should be only considered for one of the presentation types. Submissions should be in PDF and include title, author information, and a 4-page extended abstract. Shorter submissions are also welcome, particularly for poster presentation. Please use the following EasyChair submission link: http://www.easychair.org/conferences/?conf=bda2014 Note: The workshop will not include published proceedings. In particular, we welcome submissions of extended abstracts describing work that has appeared or is expected to appear in other venues. ================================================== Financial support for student/postdoc participants ================================================== We will cover the registration fee and up to $500 of travel costs for selected participants at the student/postdoc level. Please refer to the workshop's website for further details. =============== IMPORTANT DATES =============== July 23, 2014 - Extended abstract submission deadline August 18, 2014 - Decision notifications October 11-12, 2014 - Workshop ================ INVITED SPEAKERS ================ Dmitri Chklovskii - HHMI Janelia Farm Alex Cornejo - Harvard Anna Dornhaus - University of Arizona Ofer Feinerman - Weizmann Institute Ila Fiete - UT Austin Deborah Gordon - Stanford Laurent Keller - University of Lausanne Amos Korman - CNRS and University of Paris Diderot Nancy Lynch - MIT James Marshall - University of Sheffield Radhika Nagpal - Harvard Saket Navlakha - CMU Stephen Pratt - Arizona State University Andrea Richa - Arizona State University Nir Shavit - MIT ================= PROGRAM COMMITTEE ================= Ziv Bar-Joseph - CMU (co-chair) Anna Dornhaus - University of Arizona Yuval Emek - Technion (co-chair) Amos Korman - CNRS and University of Paris Diderot (co-chair) Nancy Lynch - MIT Radhika Nagpal - Harvard Saket Navlakha - CMU Nir Shavit - MIT -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen at idsia.ch Tue Jul 22 08:22:28 2014 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Tue, 22 Jul 2014 14:22:28 +0200 Subject: Connectionists: Who invented backpropagation? In-Reply-To: <7B480C11-9974-45DA-B1BA-90943E264DA1@idsia.ch> References: <7B480C11-9974-45DA-B1BA-90943E264DA1@idsia.ch> Message-ID: Efficient backpropagation (BP) is central to the ongoing Neural Network (NN) ReNNaissance and "Deep Learning." Who invented it? It is easy to find misleading accounts of BP's history. I had a look at the original papers from the 1960s and 70s, and talked to BP pioneers. Here is a summary derived from my recent survey, which has additional references: The minimisation of errors through gradient descent (Hadamard, 1908) in the parameter space of complex, nonlinear, differentiable, multi-stage, NN-related systems has been discussed at least since the early 1960s (e.g., Kelley, 1960; Bryson, 1961; Bryson and Denham, 1961; Pontryagin et al., 1961; Dreyfus, 1962; Wilkinson, 1965; Amari, 1967; Bryson and Ho, 1969; Director and Rohrer, 1969), initially within the framework of Euler-LaGrange equations in the Calculus of Variations (e.g., Euler, 1744). Steepest descent in the weight space of such systems can be performed (Bryson, 1961; Kelley, 1960; Bryson and Ho, 1969) by iterating the chain rule (Leibniz, 1676; L?Hopital, 1696) ? la Dynamic Programming (DP, Bellman, 1957). A simplified derivation of this backpropagation method uses the chain rule only (Dreyfus, 1962). The systems of the 1960s were already efficient in the DP sense. However, they backpropagated derivative information through standard Jacobian matrix calculations from one ?layer? to the previous one, without explicitly addressing either direct links across several layers or potential additional efficiency gains due to network sparsity (but perhaps such enhancements seemed obvious to the authors). Explicit, efficient error backpropagation (BP) in arbitrary, discrete, possibly sparsely connected, NN-like networks apparently was first described in a 1970 master?s thesis (Linnainmaa, 1970, 1976), albeit without reference to NNs. BP is also known as the reverse mode of automatic differentiation (e.g., Griewank, 2012), where the costs of forward activation spreading essentially equal the costs of backward derivative calculation. See early BP FORTRAN code (Linnainmaa, 1970) and closely related work (Ostrovskii et al., 1971). BP was soon explicitly used to minimize cost functions by adapting control parameters (weights) (Dreyfus, 1973). This was followed by some preliminary, NN-specific discussion (Werbos, 1974, section 5.5.1), and a computer program for automatically deriving and implementing BP for any given differentiable system (Speelpenning, 1980). To my knowledge, the first NN-specific application of efficient BP as above was described in 1981 (Werbos, 1981). Related work was published several years later (Parker, 1985; LeCun, 1985). A paper of 1986 significantly contributed to the popularisation of BP (Rumelhart et al., 1986). Compare also the first adaptive, deep, multilayer perceptrons (Ivakhnenko et al., since 1965), whose layers are incrementally grown and trained by regression analysis, as well as a more recent method for multilayer threshold NNs (Bobrowski, 1978). Precise references and more history in: Deep Learning in Neural Networks: An Overview PDF & LATEX source & complete public BIBTEX file under http://www.idsia.ch/~juergen/deep-learning-overview.html Juergen Schmidhuber http://www.idsia.ch/~juergen/whatsnew.html P.S.: I'll give talks on Deep Learning and other things in the NYC area around 1-5 and 18-19 August, and in the Bay area around 7-15 August; videos of previous talks can be found under http://www.idsia.ch/~juergen/videos.html From p.geurts at ulg.ac.be Tue Jul 22 18:24:10 2014 From: p.geurts at ulg.ac.be (Pierre Geurts) Date: Wed, 23 Jul 2014 00:24:10 +0200 Subject: Connectionists: Call for participation and posters - MLSB14, Machine Learning in Systems Biology Message-ID: <5EA6A518-E738-40AE-BCC8-F44B0CF423B5@ulg.ac.be> [Apologies for cross-postings] Call for Participation and Poster Presentations MLSB14, the eighth International Workshop on Machine Learning in Systems Biology http://www.mlsb.cc Organized in conjunction with ECCB 2014 Strasbourg, France, September 6-7, 2014. --- We invite you to join us for the eighth installment of Machine Learning in Systems Biology (MLSB) 2014, which will be held as a 2-day ECCB workshop on September 6 and 7 in Strasbourg, France The full program of MLSB 2014 can be found online at http://mlsb.cc The highlights of MLSB 2014 include five invited talks by * Pierre Baldi, UCI University, California, USA Carbon-Based Computing Vs Silicon-Based Computing: A New Theory of Circadian Rhythms Abstract * Anne-Laure Boulesteix, Department of Computational Molecular Medecine, IBE, Ludwig-Maximilians Universit?t M?nchen, Germany Title to be announced * Karsten Borgwardt, Department of Biosystems Science and Engineering (D-BSSE), ETH Z?rich Machine Learning for Personalized Medicine Abstract * Jean-Loup Faulon, IBSS, CNRS, Genopole, University of Evry, France Using Machine Learning in Synthetic Biology: The Design-Build-Test and Learn cycle Abstract * Nicola Segata, Centre for Integrative Biology, University of Trento, Italy Machine learning challenges in computational meta'omics One page abstract can still be submitted through the easychair submission system until August, 15 for poster presentation at the workshop: http://www.easychair.org/conferences/?conf=mlsb2014 Please note that the early registration deadline for MLSB/ECCB is August 1, 2014 (for registration visit http://www.eccb14.org/registration). We are looking forward to meeting you in Strasbourg! Best regards, Florence d'Alch?-Buc and Pierre Geurts From jkrichma at uci.edu Tue Jul 22 19:23:26 2014 From: jkrichma at uci.edu (Jeff Krichmar) Date: Tue, 22 Jul 2014 16:23:26 -0700 Subject: Connectionists: Faculty Position in Computational Neuroscience at the University of California, Irvine Message-ID: Dear Connectionists, The following job position may be of interest to many of you. ************************** University of California, Irvine Faculty Position in Computational Neuroscience The Department of Cognitive Sciences (www.cogsci.uci.edu) at the University of California, Irvine (UCI) invites applications for a faculty position at the Associate or Full Professor level. We are especially interested in candidates who use mathematical, computational, or robotics approaches to study the neural basis of cognition in any of these areas: (1) vision, hearing, and attention; (2) memory and decision-making; (3) learning and development; (4) language. Applicants whose research relates to human behavior are preferred. A strong record of publications and extramural funding is essential. Exceptional candidates at the Assistant Professor level will also be considered. The online application includes: A cover letter, CV, research and teaching statements, 3 recent publications, and contact information for 3-5 referees. Interested candidates can apply for the position at: https://recruit.ap.uci.edu/apply/JPF02452. To ensure full consideration, please complete the application by November 15, 2014. The University of California, Irvine is an Equal Opportunity/Affirmative Action Employer committed to excellence through diversity. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability, age, protected veteran status, or other protected categories covered by the UC nondiscrimination policy. ************************** Best regards, Jeff Krichmar Department of Cognitive Sciences 2328 Social & Behavioral Sciences Gateway University of California, Irvine Irvine, CA 92697-5100 jkrichma at uci.edu http://www.socsci.uci.edu/~jkrichma From huajin.tang at gmail.com Sun Jul 20 21:43:43 2014 From: huajin.tang at gmail.com (Huajin Tang) Date: Mon, 21 Jul 2014 09:43:43 +0800 Subject: Connectionists: CFP: IEEE TNNLS Special Issue on "Learning in Neuromorphic Systems and Cyborg Intelligence" Message-ID: Call For Papers *IEEE Transactions on Neural Networks and Learning Systems* Special Issue on *Learning in Neuromorphic Systems and Cyborg Intelligence* Emulating brain-like learning performance has been a key challenge for research in neural networks and learning systems, including recognition, memory and perception. In the last few decades, a variety of approaches for brain-like learning and information processing have been proposed, including approaches based on sparse representations or hierarchical/deep architectures. While capable of achieving impressive performance, these methods still perform poorly compared to biological systems under a wide variety of conditions. With the availability of neuromorphic hardware providing a fundamentally different technique for data representation, neuromorphic systems, using neural spikes to represent the outputs of sensors and for communication between computing blocks, and using spike timing based learning algorithms, have shown appealing computing characteristics. However, current neuromorphic learning systems cannot yet achieve the performance figures comparable to what machine learning approaches can offer. Neuromorphic systems are also compatible with another framework called cyborg intelligence. Cyborg intelligence aims to deeply integrate machine intelligence with biological intelligence by connecting machines and living beings via brain-machine interfaces, enhancing strengths and compensating for weaknesses by combining the biological cognition capability with the machine computational capability. In cyborg intelligence, the real-time interaction and exchange of information between biological and artificial neural systems is still an important open challenge, and existing learning approaches would not be able to meet such a challenge. The goal of the special issue is to consolidate the efforts for developing a suitable learning framework for neuromorphic systems and cyborg intelligence and promote research activities in this area. *SCOPE OF THE SPECIAL ISSUE* We invite original contributions related to learning in neuromorphic systems and cyborg intelligence, from theories, algorithms, modelling and experiment studies to applications. Topics include but are not limited to: - Cognitive computing and cyborg intelligence - Neuromorphic information/signal processing - Brain-inspired data representation models - Neuromorphic learning and cognitive systems - Co-learning in bio-machine systems - Spike-based sensing and learning - Neuromorphic sensors and hardware systems - Intelligence for embedded systems - Cognition mechanisms for big data - Embodied cognition and neuro-robotics. *Important Dates * 15 Nov 2014 ? Deadline for manuscript submission 15 Feb 2015 ? Notification of authors 15 Apr 2015? Deadline for submission of revised manuscripts 15 May 2015 ? Final decision *Guest Editors * Zhaohui Wu Zhejiang University, China (wzh at zju.edu.cn) Ryad Benosman University of Pierre and Marie Curie, France ( ryad.benosman at upmc.fr) Huajin Tang Institute for Infocomm Research, Singapore and Sichuan University (huajin.tang at ieee.org) Shih-Chii Liu Institute of Neuroinformatics, University of Zurich and ETH Zurich (shih at ini.phys.ethz.ch) *Submission Instructions* 1. Read the information for Authors at http://cis.ieee.org/tnnls 2. Submit the manuscript by 15th Nov 2014 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 Neuromorphic Systems and Cyborg Intelligence. *Send also an email to the guest editors with subject ?TNNLS special issue submission? to notify about your submission. -------------- next part -------------- An HTML attachment was scrubbed... URL: From feeds at sentic.net Wed Jul 23 02:50:27 2014 From: feeds at sentic.net (SenticNet) Date: Wed, 23 Jul 2014 01:50:27 -0500 (EST) Subject: Connectionists: [SenticNet] CFP: ICDM workshop series on opinion mining Message-ID: <222240518.1350768.1406098227974.open-xchange@bosoxweb05.eigbox.net> Apologies for cross-posting, Submissions are invited for the 4th edition of Sentiment Elicitation from Natural Text for Information Retrieval and Extraction (SENTIRE), the IEEE ICDM workshop series on opinion mining. The term SENTIRE comes from the Latin feel and it is root of words such as sentiment and sensation. SENTIRE aims to provide an international forum for researchers in the field of opinion mining and sentiment analysis to share information on their latest investigations in social information retrieval and their applications both in academic research areas and industrial sectors. The broader context of the workshop comprehends Web mining, AI, Semantic Web, information retrieval and natural language processing. The workshop is going to be held in Shenzhen on 14th December 2014. For more information, please visit: http://sentic.net/sentire RATIONALE Memory and data capacities double approximately every two years and, apparently, the Web is following the same rule. User-generated contents, in particular, are an ever-growing source of opinion and sentiments which are continuously spread worldwide through blogs, wikis, fora, chats and social networks. The distillation of knowledge from such sources is a key factor for applications in fields such as commerce, tourism, education and health, but the quantity and the nature of the contents they generate make it a very difficult task. Due to such challenging research problems and wide variety of practical applications, opinion mining and sentiment analysis have become very active research areas in the last decade. Our understanding and knowledge of the problem and its solution are still limited as natural language understanding techniques are still pretty weak. Most of current research in sentiment analysis, in fact, merely relies on machine learning algorithms. Such algorithms, despite most of them being very effective, produce no human understandable results such that we know little about how and why output values are obtained. All such approaches, moreover, rely on syntactical structure of text, which is far from the way human mind processes natural language. Next-generation opinion mining systems should employ techniques capable to better grasp the conceptual rules that govern sentiment and the clues that can convey these concepts from realization to verbalization in the human mind. TOPICS SENTIRE aims to provide an international forum for researchers in the field of opinion mining and sentiment analysis to share information on their latest investigations in social information retrieval and their applications both in academic research areas and industrial sectors. The broader context of the workshop comprehends Web mining, AI, Semantic Web, information retrieval and natural language processing. Topics of interest include but are not limited to: ? Sentiment identification & classification ? Opinion and sentiment summarization & visualization ? Explicit & latent semantic analysis for sentiment mining ? Concept-level opinion and sentiment analysis ? Sentic computing ? Opinion and sentiment search & retrieval ? Time evolving opinion & sentiment analysis ? Semantic multidimensional scaling for sentiment analysis ? Multidomain & cross-domain evaluation ? Domain adaptation for sentiment classification ? Multimodal sentiment analysis ? Multimodal fusion for continuous interpretation of semantics ? Multilingual sentiment analysis & re-use of knowledge bases ? Knowledge base construction & integration with opinion analysis ? Transfer learning of opinion & sentiment with knowledge bases ? Sentiment corpora & annotation ? Affective knowledge acquisition for sentiment analysis ? Biologically inspired opinion mining ? Sentiment topic detection & trend discovery ? Big social data analysis ? Social ranking ? Social network analysis ? Social media marketing ? Comparative opinion analysis ? Opinion spam detection TIMEFRAME ? August 1st, 2014: Submission deadline ? September 26th, 2014: Notification of acceptance ? October 20th, 2014: Final manuscripts due ? December 14th, 2014: Workshop date SUBMISSIONS AND PROCEEDINGS Authors are required to follow IEEE Computer Society Press Proceedings Author Guidelines. The paper length is limited to 10 pages, including references, diagrams, and appendices, if any. Manuscripts are to be submitted through EasyChair. Each submitted paper will be evaluated by three PC members with respect to its novelty, significance, technical soundness, presentation, and experiments. Accepted papers will be published in IEEE ICDM proceedings. Selected, expanded versions of papers presented at the workshop will be invited to a forthcoming Special Issue of Cognitive Computation on opinion mining and sentiment analysis. ORGANIZERS ? Erik Cambria, Nanyang Technological University (Singapore) ? Bing Liu, University of Illinois at Chicago (USA) ? Yunqing Xia, Tsinghua University (China) ? Yongzheng Zhang, LinkedIn Inc. (USA) From hugo.cornelis at gmail.com Wed Jul 23 13:46:09 2014 From: hugo.cornelis at gmail.com (Hugo Cornelis) Date: Wed, 23 Jul 2014 19:46:09 +0200 Subject: Connectionists: Announcement: GENESIS 2.4 beta tutorial at CNS Message-ID: This is a public announcement of the GENESIS-2.4 tutorial at the Computational Neuroscience meeting (CNS) in Quebec City and the official public beta release of GENESIS 2.4. This new release includes support for spike-timing dependent plasticity in large networks of multicompartmental cells, bug fixes, comes with new python utilities and tutorial materials. The "Ultimate GENESIS Tutorial Distribution", included in this release, contains updated course materials for the tutorial Constructing biologically realistic neuron and network models with GENESIS. The tutorial brings together material that is available as separate downloads from the GENESIS web site and through the GENESIS Users Group. It includes several simulator-independent tutorials on biologically realistic neural modeling, as well as both tutorial and research simulations that have been implemented with GENESIS. The latest version of this GENESIS tutorial distribution will be available at http://genesis-sim.org/GENESIS/UGTD.html. The GENESIS tutorial at the CNS meeting is introductory and aimed at people who are new to or have only elementary knowledge about the GENESIS-2 simulator, as well as those who have used GENESIS in the past and would like to learn of new developments in cortical network modeling with GENESIS. * introduction and overview ** Why are we doing this? ** resources ** installation and configuration overview * single neuron modeling and visualization * debugging model and script * fast simulations with hsolve * network modeling * spike-timing dependent plasticity During the last hour of the tutorial, I will show in detail how to technically debug models, scripts and source code, at various levels of implementation. The latest news can always be found at http://genesis-sim.org/GENESIS/ -- Hugo -- Hugo Cornelis Ph.D. GENESIS-3 -- lead architect http://www.genesis-sim.org/ Neurospaces Project Architect http://www.neurospaces.org/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From cgunay at emory.edu Thu Jul 24 12:12:16 2014 From: cgunay at emory.edu (=?UTF-8?Q?Cengiz_G=C3=BCnay?=) Date: Thu, 24 Jul 2014 12:12:16 -0400 Subject: Connectionists: CNS*14 Tutorial on Neuronal Model Parameter Search Techniques Message-ID: Dear colleagues, You are invited to attend our shortly upcoming full-day tutorial session at CNS*2014 in Quebec City. *Where:* Organization for Computational Neurosciences (OCNS) Conference, Quebec City Conference Center, Room 2105 *When:* Saturday July 26, 2014 between 9am - 4:30pm *T9: Neuronal Model Parameter Search Techniques* Parameter tuning of model neurons to mimic biologically realistic activity is a non?trivial task. Multiple models may exhibit similar dynamics that match experimental data ? i.e., there is no single ?correct? model. To address this issue, the ensemble modeling technique proposes to represent properties of living neurons with a set of neuronal models. Several approaches to ensemble modeling have been proposed over the years, but the two most prevalent parameter tuning methods are systematic ?brute?force? searches [1, 2] and various evolutionary algorithms?based techniques [3, 4, 5, 6]. Both approaches relay on traversing a very large parameter space (with thousands to millions of model instances), but utilize diametrically different ways to accomplish that. In both cases, however, entire collections of biologically realistic models are generated, whose neural activity characteristics can then be cataloged and studied using a database [1, 2]. The tutorial covers ?tips and tricks,? as well as various pitfalls in all stages of model construction, large?scale simulations on high performance computing clusters [S2], database construction and analysis of neural data, along with a discussion about the strengths and weaknesses of the two parameter search techniques. We will review software implementations for each technique: PANDORA Matlab Toolbox [7][S1] for the brute force method and NeRvolver (i.e., evolver of nerve cells) for evolutionary algorithms. PANDORA was used in recent projects for tuning models of rat globus pallidus neurons [2][M1], lobster pyloric network calcium sensors [8][M2], leech heart interneurons [9][M3,S3] and hippocampal O?LM interneurons (Skinner Lab, TWRI/UHN and Univ. Toronto). NeRvolver is a prototype of a computational intelligence?based system for automated construction, tuning, and analysis of neuronal models, which is currently under development in the Computational Intelligence and Bio (logical) informatics Laboratory at Delaware State University [10]. Through the utilization of computational intelligence methods (i.e., Multi?Objective Evolutionary Algorithms and Fuzzy Logic), the NeRvolver system generates classification rules describing biological phenomena discovered during the process of model creation or tuning. Thus in addition to producing neuronal models, NeRvolver provides?via such rules?insights into the functioning of the biological neurons being modeled. In the tutorial, we will present basic functionalities of the system and demonstrate how to analyze the results returned by the software. We will allocate enough time for Q&A and if participants bring a laptop pre?loaded with Matlab, they can follow some of our examples. *Lecturers/Organizers:* Cengiz G?nay, Anca Doloc?-Mihu (Emory University, USA) Vladislav Sekuli? (University of Toronto, Canada), Tomasz G. Smolinski (Delaware State University, USA) *References * [1] Astrid A. Prinz, Cyrus P. Billimoria, and Eve Marder. Alternative to hand?tuning conductance?based models: Construction and analysis of databases of model neurons. J Neurophysiol, 90:3998?4015, 2003. [2] Cengiz G?nay, Jeremy R. Edgerton, and Dieter Jaeger. Channel density distributions explain spiking variability in the globus pallidus: A combined physiology and computer simulation database approach. J. Neurosci., 28(30):7476?91, July 2008. [3] Pablo Achard and Erik De Schutter. Complex parameter landscape for a complex neuron model. PLoS Comput Biol, 2(7):794?804, Jul 2006. [4] Tomasz G. Smolinski and Astrid A. Prinz. Computational intelligence in modeling of biological neurons: A case study of an invertebrate pacemaker neuron. In Proceedings of the International Joint Conference on Neural Networks, pages 2964?2970, Atlanta, GA, 2009. [5] Tomasz G. Smolinski and Astrid A. Prinz. Multi?objective evolutionary algorithms for model neuron parameter value selection matching biological behavior under different simulation scenarios. BMC Neuroscience, 10(Suppl 1):P260, 2009. [6] Damon G. Lamb and Ronald L. Calabrese. Correlated conductance parameters in leech heart motor neurons contribute to motor pattern formation. PLoS One, 8(11):e79267, 2013. [7] Cengiz G?nay, Jeremy R. Edgerton, Su Li, Thomas Sangrey, Astrid A. Prinz, and Dieter Jaeger. Database analysis of simulated and recorded electrophysiological datasets with PANDORA?s Toolbox. Neuroinformatics, 7(2):93?111, 2009. [8] Cengiz G?nay and Astrid A. Prinz. Model calcium sensors for network homeostasis: Sensor and readout parameter analysis from a database of model neuronal networks. J Neurosci, 30:1686?1698, Feb 2010. NIHMS176368,PMC2851246. [9] Anca Doloc?Mihu and Ronald L. Calabrese. A database of computational models of a half?center oscillator for analyzing how neuronal parameters influence network activity. J Biol Phys, 37(3):263?283, Jun 2011. [10] Emlyne Forren, Myles Johnson?Gray, Parth Patel, and Tomasz G. Smolinski. Nervolver: a computational intelligence?based system for automated construction, tuning, and analysis of neuronal models. BMC Neuroscience, 13(Suppl 1):P36, 2012. -Cengiz -- Cengiz Gunay Postdoctoral Fellow, Dept. of Biology Visiting Faculty, Dept. of Math & CS Emory University cgunay at emory.edu http://www.biology.emory.edu/research/Prinz/Cengiz/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From ciaramella at uniparthenope.it Thu Jul 24 12:14:26 2014 From: ciaramella at uniparthenope.it (ciaramella at uniparthenope.it) Date: Thu, 24 Jul 2014 18:14:26 +0200 Subject: Connectionists: Call for Papers - Special Issue on "Advances in Mathematical and Computational Modelling for Biological Data" Message-ID: <20140724181426.22423zivachz6mzm@webmail.uniparthenope.it> Dear all it is my pleasure to invite you and members of your research group to submit an article for a special issue of the Journal of Applied Mathematics (Hindawi), on the subject of Mathematical and Computational Modelling for Biological Data for which I will serve as Lead Guest Editor. Journal of Applied Mathematics (http://www.hindawi.com/journals/jam/) is a refereed journal devoted to the publication of original research papers and review articles in all areas of applied, computational, and industrial mathematics (I.F. 0.834, it is included in several databases/resources, among others Scopus). The aim of the special issue is to review the recent research advances in the fields of mathematical and computational methods concerning biological data. Potential topics include, but are not limited to: ? Mathematical and computational methods ? Statistical models ? Iterative methods ? Machine learning and data mining techniques ? Soft computing, fuzzy, and neurofuzzy methodologies ? Nonlinear data analysis approaches. Particularly when applied to: ? OMICs and high, throughput data in the broad context of genomics, epigenomics, transcriptomics, and proteomics ? Models capable of explaining the pathogenesis or predicting the predisposition and/or the clinical outcome of human diseases ? The evaluation of protein folding and/or protein ligand interactions (where ligands are proteins, DNA, RNA, and small molecules), also in the context of genetic variation ? The identification of potential gene regulatory elements (i.e., binding of transcription factors, and miRNAs) Furthermore, software tools designed for addressing any of the above topics might be also considered relevant for the issue. You can find full details about the Special Issues at: http://www.hindawi.com/journals/jam/si/670760/cfp/ Sincerely, Angelo Ciaramella -------------------------------------- | Dr. Angelo Ciaramella, Ph.D | | Department of Science and Technology | | University of Naples "Parthenope" | | Room 431, Isola C4, | | Centro Direzionale | | I-80143 Napoli, ITALY | | Tel.: 0815476674 | -------------------------------------- ****************************************************************************** IL MERITO DEGLI STUDENTI VIENE RICONOSCIUTO Il 5 per mille all'Universita' degli Studi di Napoli "Parthenope" incrementa le borse di studio agli studenti - codice fiscale 80018240632 http://www.uniparthenope.it/index.php/5xmille Questa informativa e' inserita in automatico dal sistema al fine esclusivo della realizzazione dei fini istituzionali dell'ente. From christos.dimitrakakis at gmail.com Thu Jul 24 16:36:51 2014 From: christos.dimitrakakis at gmail.com (Christos Dimitrakakis) Date: Thu, 24 Jul 2014 22:36:51 +0200 Subject: Connectionists: CFP: AISec-2014 Deadline Extension Message-ID: <53D16E63.1020407@gmail.com> Call For Papers AISec 2014 7th ACM Workshop on Artificial Intelligence and Security Held in Conjunction with ACM CCS 2014 http://www.cse.chalmers.se/~aikmitr/AISec2014.html November 7, 2014 The Scottsdale Plaza Resort, Scottsdale, Arizona, USA The relation of artificial intelligence (AI), machine learning, and data mining to security and privacy problems is ever-more critical, with AI algorithms controlling important infrastructure, such as electrical grids, road networks and healthcare applications. More generally, AI and ML are increasingly important for autonomous real-time analysis and decision-making in domains with a wealth of data or that require quick reactions to ever-changing situations. Particularly, these intelligent technologies offer new solutions to security problems involving Big Data analysis, which can be scaled through cloud-computing. Further, the use of learning methods in security sensitive domains creates new frontiers for security research, in which adversaries may attempt to mislead or evade intelligent machines. The 2014 ACM Workshop on Artificial Intelligence and Security (AISec) provides a venue for presenting and discussing new developments in this fusion of security/privacy with AI and machine learning. We invite original research papers relating to the theory and applications of AI or machine learning for security, privacy and related problems. We also invite position and open problem papers discussing the role of AI or machine learning in security and privacy. Submitted papers of these types may not substantially overlap papers that have been published previously or that are simultaneously submitted to a journal or conference/workshop proceedings. This year, we also invite presentation-only papers, describing research published or submitted in 2014. * Paper format * This year we invite both original submissions and presentation-only papers. Please indicate the type of submission when submitting. Original submissions: This include original research, and open problem/position papers. They must be at most 10 pages in double-column ACM format (note: pages must be numbered) excluding the bibliography and well-marked appendices, and at most 12 pages overall. Committee members are not required to read the appendices, so the paper should be intelligible without them. Submissions need not be anonymized. We recommend the use of the ACM SIG Proceedings templates for submissions. The ACM format is the required template for the camera-ready version. Accepted papers will be published by the ACM Digital Library and/or ACM Press. Both research and open problem papers will undergo a thorough review process. Presentation-only papers: As an experiment, this year we also invite presentation-only papers, for research currently under review elsewhere or published in 2014. These need not adhere to the ACM format and will not be published in the proceedings. They will undergo a light review for correctness, relevance and importance. Priority will be given to original submissions. --------------------------------------------- Important Dates Paper submissions due: 30 July 2014 Acceptance notification: 25 August 2014 Camera ready (FIRM DEADLINE): 9 September 2014 Workshop: 7 November 2014 --------------------------------------------- Submissions Submissions can be made through EasyChair at: https://www.easychair.org/conferences/?conf=aisec2014 -------------------------------------------- Topics Topics of interest include, but are not limited to: Theoretical topics related to security - Adversarial Learning - Robust Statistics - Learning in stochastic games - Online learning - Differential-privacy Security Applications - Computer Forensics - Spam detection - Phishing detection & prevention - Botnet detection - Intrusion detection and response - Malware identification - Authorship Identification - Big data analytics for security Security-related AI problems - Distributed inference and decision making for security - Secure multiparty computation and cryptographic approaches - Privacy-preserving data mining - Adaptive side-channel attacks - Design and analysis of CAPTCHAs - AI approaches to trust and reputation - Vulnerability testing through intelligent probing (e.g. fuzzing) - Content-driven security policy management & access control - Techniques and methods for generating training and test sets - Anomalous behavior detection (e.g. for the purpose of fraud detection, authentication) --------------------------------------------- Program Chairs - Christos Dimitrakakis, Chalmers University of Technology, Sweden - Katerina Mitrokotsa, Chalmers University of Technology, Sweden - Benjamin I. P. Rubinstein, The University of Melbourne, Australia Program Committee: - Battista Biggio, University of Cagliari, Italy - Michael Br?ckner, Amazon.com Inc, Germany - Alvaro A. C?rdenas, University of Texas at Dallas, TX, USA - Kamalika Chaudhuri, University of California at San Diego, CA, USA - Rachel Greenstadt, Drexel University, PA, USA - Guofei Gu, Texas A&M University, TX, USA - Anthony Joseph, UC Berkeley, CA, USA - Alex Kantchelian, UC Berkeley, CA, USA - Pavel Laskov, University of T?bingen, Germany - Daniel Lowd, University of Oregon, OR, USA - Pratyusa Manadhata, HP Labs, USA - Roberto Perdisci, University of Georgia, GA, USA - Vasyl Pihur, Google Inc., CA, USA - Konrad Rieck, University of G?ttingen, Germany - Fabio Roli, University of Cagliari, Italy - Robin Sommer, ICSI and LBNL, CA, USA - Jessica Staddon, Google Inc., CA, USA - Doug Tygar, UC Berkeley, CA, USA - Shobha Venkataraman, AT&T Research, USA -- Christos Dimitrakakis http://www.cse.chalmers.se/~chrdimi/ From grlmc at urv.cat Sat Jul 26 10:07:18 2014 From: grlmc at urv.cat (GRLMC) Date: Sat, 26 Jul 2014 16:07:18 +0200 Subject: Connectionists: LATA 2015: 1st call for papers Message-ID: <2E8168DB9316434CAE2F3696951F20EC@Carlos1> *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* **************************************************************************************** 9th INTERNATIONAL CONFERENCE ON LANGUAGE AND AUTOMATA THEORY AND APPLICATIONS LATA 2015 Nice, France March 2-6, 2015 Organized by: CNRS, I3S, UMR 7271 Nice Sophia Antipolis University Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/lata2015/ **************************************************************************************** AIMS: LATA is a conference series 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 2015 will reserve significant room for young scholars at the beginning of their career. It will aim at attracting contributions from classical theory fields as well as application areas. VENUE: LATA 2015 will take place in Nice, the second largest French city on the Mediterranean coast. The venue will be the University Castle at Parc Valrose. 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 networks automata, concurrency and Petri nets automatic structures cellular automata codes combinatorics on words computational complexity data and image compression descriptional complexity 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 parallel and regulated rewriting parsing patterns power series string and combinatorial issues in bioinformatics string processing algorithms symbolic dynamics term rewriting transducers trees, tree languages and tree automata unconventional models of computation weighted automata STRUCTURE: LATA 2015 will consist of: invited talks invited tutorials peer-reviewed contributions INVITED SPEAKERS: to be announced PROGRAMME COMMITTEE: Andrew Adamatzky (West of England, Bristol, UK) Andris Ambainis (Latvia, Riga, LV) Franz Baader (Dresden Tech, DE) Rajesh Bhatt (Massachusetts, Amherst, US) Jos?-Manuel Colom (Zaragoza, ES) Bruno Courcelle (Bordeaux, FR) Erzs?bet Csuhaj-Varj? (E?tv?s Lor?nd, Budapest, HU) Aldo de Luca (Naples Federico II, IT) Susanna Donatelli (Turin, IT) Paola Flocchini (Ottawa, CA) Enrico Formenti (Nice, FR) Tero Harju (Turku, FI) Monika Heiner (Brandenburg Tech, Cottbus, DE) Yiguang Hong (Chinese Academy, Beijing, CN) Kazuo Iwama (Kyoto, JP) Sanjay Jain (National Singapore, SG) Maciej Koutny (Newcastle, UK) Anton?n Ku?era (Masaryk, Brno, CZ) Thierry Lecroq (Rouen, FR) Salvador Lucas (Valencia Tech, ES) Veli M?kinen (Helsinki, FI) Carlos Mart?n-Vide (Rovira i Virgili, Tarragona, ES, chair) Filippo Mignosi (L?Aquila, IT) Victor Mitrana (Madrid Tech, ES) Ilan Newman (Haifa, IL) Joachim Niehren (INRIA, Lille, FR) Enno Ohlebusch (Ulm, DE) Arlindo Oliveira (Lisbon, PT) Jo?l Ouaknine (Oxford, UK) Wojciech Penczek (Polish Academy, Warsaw, PL) Dominique Perrin (ESIEE, Paris, FR) Alberto Policriti (Udine, IT) Sanguthevar Rajasekaran (Connecticut, Storrs, US) J?rg Rothe (D?sseldorf, DE) Frank Ruskey (Victoria, CA) Helmut Seidl (Munich Tech, DE) Ayumi Shinohara (Tohoku, Sendai, JP) Bernhard Steffen (Dortmund, DE) Frank Stephan (National Singapore, SG) Paul Tarau (North Texas, Denton, US) Andrzej Tarlecki (Warsaw, PL) Jacobo Tor?n (Ulm, DE) Frits Vaandrager (Nijmegen, NL) Jaco van de Pol (Twente, Enschede, NL) Pierre Wolper (Li?ge, BE) Zhilin Wu (Chinese Academy, Beijing, CN) Slawomir Zadrozny (Polish Academy, Warsaw, PL) Hans Zantema (Eindhoven Tech, NL) ORGANIZING COMMITTEE: S?bastien Autran (Nice) Adrian Horia Dediu (Tarragona) Enrico Formenti (Nice, co-chair) Sandrine Julia (Nice) Carlos Mart?n-Vide (Tarragona, co-chair) Christophe Papazian (Nice) Julien Provillard (Nice) Pierre-Alain Scribot (Nice) Bianca Truthe (Giessen) 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, references, etc.) and should be prepared 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=lata2015 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 substantially 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 21, 2014 to March 2, 2015. The registration form can be found at: http://grammars.grlmc.com/lata2015/Registration.php DEADLINES: Paper submission: October 10, 2014 (23:59 CET) Notification of paper acceptance or rejection: November 18, 2014 Early registration: November 25, 2014 Final version of the paper for the LNCS proceedings: November 26, 2014 Late registration: February 16, 2015 Submission to the journal special issue: June 6, 2015 QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu at urv.cat POSTAL ADDRESS: LATA 2015 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34 977 559 543 Fax: +34 977 558 386 ACKNOWLEDGEMENTS: Nice Sophia Antipolis University Rovira i Virgili University --- Este mensaje no contiene virus ni malware porque la protecci?n de avast! Antivirus est? activa. http://www.avast.com From marco.signoretto at gmail.com Fri Jul 25 04:10:45 2014 From: marco.signoretto at gmail.com (Marco Signoretto) Date: Fri, 25 Jul 2014 10:10:45 +0200 Subject: Connectionists: Last Call for Contributions - TCMM 2014 International Workshop on Technical Computing for Machine Learning and Mathematical Engineering Message-ID: TCMM 2014 International Workshop on Technical Computing for Machine Learning and Mathematical Engineering 8 - 12 September, 2014 - Leuven, Belgium Workshop homepage: http://www.esat.kuleuven.be/stadius/tcmm2014/ The workshop will provide a venue for researchers and practitioners to interact on the latest developments in technical computing in relation to machine learning and mathematical engineering problems and methods (including also optimization, system identification, computational statistics, signal processing, data visualization, deep learning, compressed sensing and big-data). The emphasis is especially on open-source implementations in high-level programming languages, including but not limited to Julia, Python, Scala and R. For further information see the workshop homepage. The 3 days main event (8-10 September) will consist of invited and contributed talks as well as poster presentations. It will be followed by a 2 days additional event (11-12 September) including software demos and hands-on tutorials on selected topics. Submission of extended abstracts are solicited for the main event. Submission of demo presentations are solicited for the two days additional event. Important dates: Deadline extended abstract/demo submission: 31 July 2014 Deadline for registration: 1 September 2014 Confirmed invited speakers (talks and tutorials): James Bergstra, Center for Theoretical Neuroscience, University of Waterloo: Theano and Hyperopt: Modelling, Training, and Hyperparameter Optimization in Python Jeff Bezanson, MIT: TBA Luis Pedro Coelho, European Molecular Biology Laboratory (EMBL): Large Scale Analysis of Bioimages Using Python Steven Diamond, Stanford University TBA Stefan Karpinski, MIT TBA Graham Taylor, School of Engineering, University of Guelph: An Overview of Deep Learning and Its Challenges for Technical Computing Ewout van den Berg, IBM T.J. Watson Research Center: Tools and Techniques for Sparse Optimization and Beyond Organizing committee: Marco Signoretto, Department of Electrical Engineering, KU Leuven Johan Suykens, Department of Electrical Engineering, KU Leuven Vilen Jumutc , Department of Electrical Engineering, KU Leuven For further information (including Registration, Location and Venue) see http://www.esat.kuleuven.be/stadius/tcmm2014/ -- -- dr. Marco Signoretto FWO research fellow, ESAT - STADIUS, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, B-3001 LEUVEN - HEVERLEE (BELGIUM) Tel: +32 (0)16 328651 Fax: +32 (0)16 321970 Homepage: http://homes.esat.kuleuven.be/~msignore/ Email : marco.signoretto at esat.kuleuven.be From xu218 at purdue.edu Thu Jul 24 22:19:36 2014 From: xu218 at purdue.edu (Zenglin Xu) Date: Thu, 24 Jul 2014 22:19:36 -0400 Subject: Connectionists: IEEE BigData 2014 Workshop on Scalable Machine Learning: Theory and Applications Message-ID: ------- Apology for multiple postings -------- IEEE BigData 2014 Workshop on Scalable Machine Learning: Theory and Applications *In conjunction with the **IEEE International Conference on Big Data** (IEEE BigData 2014 ) on **October 27, 2014, **Washington DC, USA* Big data are encountered in various areas, including Internet search, social networks, finance, business sectors, meteorology, genomics, complex physics simulations, biological and environmental research. Machine learning as an important tool of big data analytics is playing more and more important roles in the big data era. However, the characteristics of large volume, high velocity, variety and veracity bring challenges to current machine learning techniques. It is therefore desirable to discuss (1) how to scale up existing machine learning techniques for modeling and analyzing big data from various domains; (2) how to design new machine learning algorithms for various parallel/distributed machine learning platforms (such as Hadoop, GraphLab, Spark, etc.); and (3) how to design universal machine learning interfaces for GPUs or cloud computing architectures, and so on. *Topics of Interest* - *Distributed data analytics architectures* - Data separation and integration techniques - Machine learning algorithms for GPUs - Machine learning algorithms for clouds - Machine learning algorithms for clusters - *Theory and algorithms of data reduction techniques for big data* - Online/incremental/stochastic learning algorithms - Random projection - Hashing techniques - Data sampling algorithms - *Theory and algorithms of large-scale matrix approximation* - Bound analysis of matrix approximation algorithms - Distributed matrix factorization - Distributed multiway array analysis - Online dictionary learning - Distributed topic modeling algorithms - *Heterogeneous learning on big multimodal data* - Multiview learning - Multitask learning - Transfer learning - Semi-supervised learning - Active learning - *Temporal analysis and spatial analysis in big data* - Real-time analysis for data stream - Trend prediction in financial data - Topic detection in instant message systems - Real time modeling of events in dynamic networks - Spatial modeling on maps - *Scalable machine learning in large graphs* - Communities discovery and analysis in social networks - Link prediction in networks - Anomaly detection in social networks - Fusion of information from multiple blogs, rating systems, and social networks - Integration of text, videos, images, sounds in social networks - Recommender systems - *Novel applications of scalable machine learning in big data* - Decision making with big data - Counterfactual reasoning with big data - Medical/health informatics big data analysis - Security big data analysis - Astronomy big data analysis - Biological big data analysis - Urban/smart city big data analysis - Education big data analysis *Important Dates* - August 30, 2014: Due date for workshop paper submission - September 20, 2014: Notification of paper decision to authors - October 5, 2014: Camera-ready of accepted papers - October 27-30, 2014: Workshop *Paper Sub**mission* We call for original and unpublished research contributions of (up to 8 pages and IEEE double-column format) manuscripts to the workshop. Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (see the link to "Paper Format ") and submitted to the Submission Website . *Keynote Talks* - Mikhail Bilenko , Microsoft Research - Eric Xing , Carnegie Mellow University - Ping Li, Rutgers University *Organizing Committee* - Zenglin Xu , University of Electronic Science and Technology of China & Purdue University - Haiqin Yang , The Chinese University of Hong Kong - Irwin King , The Chinese University of Hong Kong - Michael R. Lyu , The Chinese University of Hong Kong - Lihong Li , Microsoft Research -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Tue Jul 29 11:28:01 2014 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 29 Jul 2014 08:28:01 -0700 Subject: Connectionists: Seizure Detection Challenge In-Reply-To: Message-ID: Seizure Detection Challenge 21 days to go in this open competition to predict seizures from ECoG recordings in humans and dogs. Kaggle site: https://www.kaggle.com/c/seizure-detection Press release: http://www.uphs.upenn.edu/news/News_Releases/2014/07/kaggle/ Ends: 11:59 pm, Tuesday 19 August 2014 UTC Terry ----- From margulies at cbs.mpg.de Wed Jul 30 09:21:18 2014 From: margulies at cbs.mpg.de (Daniel Margulies) Date: Wed, 30 Jul 2014 15:21:18 +0200 Subject: Connectionists: Post-doctoral research position investigating brain connectivity Message-ID: We are currently inviting applications for a postdoctoral research position in the Max Planck Research Group for Neuroanatomy & Connectivity. Our research investigates the organization of connectivity in the human cerebral cortex using MRI. The research projects will address the topological structure of cortical connectivity patterns and their relationship to underlying cortical morphology. Specific topics may range from graph theoretical approaches and describing network structure to cortical developmental modeling and addressing data visualization challenges. The duration of the position is flexible, beginning with an initial period of two years. Candidates should have a PhD (or equivalent) in neuroscience, computer science, or a related discipline, with a strong background in data analysis and programming. Previous experience in neuroscience and working with brain imaging data is an advantage, but not a requirement. Applicants should nonetheless have an outstanding scientific track record with clear evidence of leadership and scholarly output in the form of publications and other achievements. The position is primarily devoted to research, with no formal teaching requirements, but ample opportunity to mentor graduate students. The Max Planck Institute for Human Cognitive and Brain Sciences offers a collaborative, international research environment with English being the language spoken in the lab. The Institute has a state-of-the-art research infrastructure, including several 3T scanners and one 7T MRI scanner, TMS/tDCS, EEG, MEG, etc, and substantial computing resources. Applicants are requested to provide a cover letter describing their qualifications and research interests, a curriculum vitae, and the contact information of at least two personal references. This should be sent as a single PDF file to personal at cbs.mpg.de with the subject heading ?PD NC 14?. Please submit applications by September 15th, 2014. Starting date for the position is flexible, but ideally in the autumn of 2014. Salary is dependent on experience and based on standard post-doctoral MPI stipends. The Max Planck Society is an equal opportunity employer, and international applicants are encouraged to apply. Contact for questions: Dr. Daniel Margulies e-mail: margulies at cbs.mpg.de Lab website: http://www.cbs.mpg.de/groups/misc/nac Max Planck Research Group for Neuroanatomy & Connectivity Max Planck Institute for Human Cognitive and Brain Sciences Stephanstra?e 1A, 04103 Leipzig, Germany -------------- next part -------------- An HTML attachment was scrubbed... URL: From LeeChonho at ntu.edu.sg Tue Jul 29 02:33:34 2014 From: LeeChonho at ntu.edu.sg (Lee Chonho (Dr)) Date: Tue, 29 Jul 2014 06:33:34 +0000 Subject: Connectionists: CFP: BICT 2014 (formerly BIONETICS) Submission due: August 4 Message-ID: <6CD750AC10BC594581D900DBB37ED5F00250C0@EXCHMBOX32.staff.main.ntu.edu.sg> CFP: 8th International Conference on Bio-inspired Information and Communications Technologies (BICT 2014, formerly BIONETICS) http://www.bionetics.org/ December 1 (Mon) - December 3, 2014 (Wed) Boston, MA, USA In-corporation with ACM SIGSIM BICT 2014 aims to provide a world-leading and multidisciplinary venue for researchers and practitioners in diverse disciplines that seek the understanding of key principles, processes and mechanisms in biological systems and leverage those understandings to develop novel information and communications technologies (ICT). BICT 2014 targets two thrusts: THRUST 1: Indirect/Weak Bioinspiration (ICT designed after biological principles, processes and mechanisms). Examples include evolutionary computation, artificial gene regulatory networks, neural computation, swarm intelligence, cellular automata, artificial immune systems, artificial life, artificial chemistry, reaction-diffusion computing, simulated annealing, self-organization and network science. THRUST 2: Direct/Strong Bioinspiration (ICT utilizing biological materials and systems). Examples include cellular computing, molecular computing/communication, membrane computing, DNA computing and memory, bacterial computing, Physarum computing and quantum computing. Expected, but not exclusive, topics are: * Signal/information processing and communication for bio-inspired ICT * Algorithms and their applications for bio-inspired ICT * Formal models and methods for bio-inspired ICT * Bio-inspired software and hardware systems * Modeling, simulations and empirical experiments of bio-inspired ICT * Self-* and stability properties in bio-inspired ICT * Security, robustness and resilience in bio-inspired ICT * Design, configuration and management issues in bio-inspired ICT * Software engineering and performance engineering in bio-inspired ICT * Tools, testbeds and deployment aspects in bio-inspired ICT * Applications, experiences and standardization of bio-inspired ICT * Socially-aware, game theoretic and other metaphor-assisted interdisciplinary research Application domains include, but not limited to, autonomic computing, bioinformatics, biomedical engineering, computer networks, computer vision, data mining, e-health, green computing and networking, grid/cloud computing, intelligent agents, mechanical engineering, molecular communication, nano-scale computing and networking, optimization, pervasive computing, robotics, security, social networks, software engineering and systems engineering. IMPORTANT DATES: Regular paper submission due: August 4 Short and poster/demo paper submission due: September 22 Notification for regular papers: September 15 Notification for short and poster/demo papers: October 6 Camera ready due: October 13 SPECIAL TRACKS: In addition to the regular track that covers general/mainstream topics, BICT 2014 features the following special tracks that focus on specific, emerging or underrepresented topics. * Artificial, Biological and Bio-Inspired Intelligence (ABBII) * Artificial Intelligence and Software Engineering (AISE) * Body Area Soft Computing (BASC) * Biologically-Inspired Process Calculi (BIPC) * Bio-Inspired Machine Vision (BIMV) * Bio-inspired/Biomimetic Microsystems & Microdevices (BMM) * Bio-inspired Wireless Network Security (BWNS) * Complex Adaptive Systems (CAS) * Engineering Applications from Molecular and Gene Regulatory Networks (EMNET) * Molecular Communication and Networking (MCN) * Morphogenetic Collective Systems (MCS) * Modularization for Practical Software Engineering (MPSE) * Resilient Networks (RN) * Swarm and Modular Robotics (SAMR) * Smart Body Area Networks (SBAN) * Security and Privacy in Bio-inspired Networks (SPBN) PAPER SUBMISSION: Authors are invited to submit regular papers (up to 8 pages each), short papers (up to 4 pages each) or poster/demo papers (up to 2 pages each) in ACM's paper template. Up to two extra pages are allowed for each paper with extra page charges. See http://bionetics.org/2014/show/initial-submission for more details. PUBLICATION: All accepted paper will be published through ACM Digital Library and submitted for indexing by SI, EI Compendex, Scopus, ACM Library, Google Scholar and many more. Selected papers will be considered for publication in leading journals including: * ACM/Springer Mobile Networks and Applications * Elsevier Information Sciences * Elsevier Nano Communication Networks Journal * Int'l Journal of Software Engineering and Knowledge Engineering * Cloud-integrated Cyber-Physical Systems (Springer book) KEYNOTE SPEAKERS: * Gabriel Ciobanu Romanian Academy, Institute of Computer Science, Romania * Andrew Eckford, York University, Canada * Valeriy Perminov, BioTeckFarm, Ltd., Russia * Hiroki Sayama, SUNY Binghamton, USA * Jon Timmis, University of York, UK * Honggang Wang, University of Massachusetts, Dartmouth, USA * Justin Werfel, Harvard University, USA GENERAL CHAIR: Jun Suzuki, University of Massachusetts, Boston, USA PC CHAIR: Tadashi Nakano, Osaka University, Japan PC VICE CHAIRS: Andrew Adamatzky, University of the West of England, UK Gabriel Ciobanu, Romanian Academy, Institute of Computer Science, Romania Douglas Dow, Wentworth Institute of Technology, USA Hiroaki Fukuda, Shibaura Institute of Technology, Japan Tyler Garaas, Mitsubishi Electric Research Laboratories, USA Preetam Ghosh, Virginia Commonwealth University, USA Isao Hayashi, Kansai University, Japan Yu-Hsiang Hsu, National Taiwan University, Taiwan Saori Iwanaga, Japan Coast Guard Academy, Japan Masao Kubo, National Defense Academy, Japan Paul Leger, Universidad Cat?lica del Norte, Chile Shih-Hsi "Alex" Liu, California State University, Fresno, USA Michael L. Mayo, US Army Engineer Research and Development Center, USA Parisa Memarmoshrefi, University of Goettingen, Germany Marjan Mernik, University of Maribor, Slovenia Alan Millard, University of York, UK Michael Moore, Marc Pomplun, University of Massachusetts Boston, USA Florian Raudies, Boston University, USA Hiroshi Sato, National Defense Academy, Japan Hiroki Sayama, SUNY Binghamton, USA Tomohiro Shirakawa, National Defense Academy of Japan, Japan Jon Timmis, University of York, UK Athanasios Vasilakos, University of Western Macedonia, Greece Honggang Wang, University of Massachusetts Dartmouth, USA Jun Zhou, Shanghai Jiao Tong University, China ________________________________ CONFIDENTIALITY:This email is intended solely for the person(s) named and may be confidential and/or privileged.If you are not the intended recipient,please delete it,notify us and do not copy,use,or disclose its contents. Towards a sustainable earth:Print only when necessary.Thank you. -------------- next part -------------- An HTML attachment was scrubbed... URL: From martin.butz at uni-tuebingen.de Wed Jul 30 09:43:43 2014 From: martin.butz at uni-tuebingen.de (Martin Butz) Date: Wed, 30 Jul 2014 15:43:43 +0200 Subject: Connectionists: =?utf-8?q?KogWis_2014_=E2=80=93_Call_for_Particip?= =?utf-8?q?ation_=E2=80=93_Early_Bird_Registration_ends_on_31st_of_July?= Message-ID: <53D8F68F.3090206@uni-tuebingen.de> Dear colleagues, dear cognitive science students, the Cognitive Science Conference KogWis 2014 (http://www.ccs.uni-tuebingen.de/kogwis-2014.html ) takes place in T?bingen from September 29 until October 2nd. Early Bird Registration with reduced feeds ends on July 31st. Please register if you intend to participate! The conference features 6 renowned plenary speakers: Harold Bekkering Henrik Ehrsson Karl Friston Wayne Gray Gregor Sch?ner Natalie Sebanz Moreover, 10 symposia on selected topics in cognitive science, 6 tutorials, talks from peer-reviewed submissions and poster sessions are offered ? all included with registration. A preliminary program is available online: http://www.ccs.uni-tuebingen.de/kogwis-2014/program.html You are cordially invited to join this exciting event! Direct link to registration: https://www.regonline.com/builder/site/?eventid=1536126 Sincerely, Martin Butz & the organizing team -- Prof. Dr. Martin V. Butz Computer Science, Cognitive Modeling Raum C415 - Sand 14 -- Eberhard Karls Universit?t T?bingen Sand 14 ? 72076 T?bingen ? Germany Phone +49 7071 29-70429 ? Fax +49 7071 29-5719 martin.butz at uni-tuebingen.de http://cm.inf.uni-tuebingen.de/ Attend KogWis 2014! http://www.ccs.uni-tuebingen.de/kogwis-2014.html -------------- next part -------------- An HTML attachment was scrubbed... URL: From wermter at informatik.uni-hamburg.de Thu Jul 31 07:52:08 2014 From: wermter at informatik.uni-hamburg.de (Stefan Wermter) Date: Thu, 31 Jul 2014 13:52:08 +0200 Subject: Connectionists: [meetings] ICANN 2014 - Final Program and Call for Participation Message-ID: <53DA2DE8.5040204@informatik.uni-hamburg.de> ------------------------------------------------------------------- Call for Participation and Conference Program ICANN 2014: 24th Annual Conference on Artificial Neural Networks 15 - 19 September 2014, University of Hamburg, Germany http://icann2014.org/ =================================================================== We invite you to attend the 2014 International Conference on Artificial Neural Networks (ICANN), which is the annual flagship conference of the European Neural Network Society (ENNS). In 2014 the University of Hamburg will organize the 24th ICANN Conference from 15th to 19th September 2014 in Hamburg, Germany. CONFERENCE PROGRAM: The main conference program is now available. The program includes 72 oral presentations, 33 posters and 2 live Demonstrations. http://icann2014.org/program/ REGISTRATION: The ICANN 2014 registration is open. The full registration costs 490 ? and 390 ? for students. ENNS members pay a reduced rate of 440 ?, and 340 ? for students. The registration includes access to scientific sessions and plenary talks, coffee breaks during the main conference, welcome event, conference dinner, one copy of the proceedings (USB), one conference bag. Additional tickets for the conference dinner can be purchased for 70 ?. http://icann2014.org/registration/ VENUE AND TRANSPORTATION: Hamburg is the second-largest city in Germany, home to over 1.8 million people. Situated at the river Elbe, the port of Hamburg is the second-largest port in Europe. The University of Hamburg is the largest institution for research and education in the north of Germany. The venue of the conference is the ESA building of the University of Hamburg, situated at Edmund-Siemers-Allee near the city centre and easily reachable from Dammtor Railway Station. Hamburg Airport can be reached easily via public transport. ACCOMMODATION: For the accomodation we arranged guaranteed rates for a couple of hotels in Hamburg for ICANN 2014. http://icann2014.org/accommodation/ CHAIRS and ORGANISATION: General Chair: Stefan Wermter (Hamburg, Germany) Program co-Chairs Alessandro E.P. Villa (Lausanne, Switzerland, ENNS President) Wlodzislaw Duch (Torun, Poland, ENNS Past-President) Timo Honkela (Helsinki, Finland) Petia Koprinkova-Hristova (Sofia, Bulgaria) G?nther Palm (Ulm, Germany) Cornelius Weber (Hamburg, Germany) Local Organizing Committee Chairs: Sven Magg, Johannes Bauer, Jorge Chacon, Stefan Heinrich, Doreen Jirak, Katja Koesters, Erik Strahl KEYNOTE SPEAKERS: Christopher M. Bishop (Microsoft Research, Cambridge, UK) Jun Tani (KAIST, Daejeon, Republic of Korea) Paul Verschure (Universitat Pompeu Fabra, Barcelona, Spain) Yann LeCun (New York University, NY, USA) Barbara Hammer (Bielefeld University, Bielefeld, Germany) Kevin Gurney (University of Sheffield, Sheffield, UK) CONFERENCE TOPICS: ICANN 2014 will feature the main tracks Brain Inspired Computing and Machine Learning research, with strong cross-disciplinary interactions and applications. All research fields dealing with Neural Networks will be present at the conference. A non-exhaustive list of topics includes: Brain Inspired Computing: Cognitive models, Computational Neuroscience, Self-organization, Reinforcement Learning, Neural Control and Planning, Hybrid Neural-Symbolic Architectures, Neural Dynamics, Recurrent Networks, Deep Learning. Machine Learning: Neural Network Theory, Neural Network Models, Graphical Models, Bayesian Networks, Kernel Methods, Generative Models, Information Theoretic Learning, Reinforcement Learning, Relational Learning, Dynamical Models. Neural Applications for: Intelligent Robotics, Neurorobotics, Language Processing, Image Processing, Sensor Fusion, Pattern Recognition, Data Mining, Neural Agents, Brain-Computer Interaction, Neural Hardware, Evolutionary Neural Networks. CONFERENCE WEBSITE: http://www.icann2014.org *********************************************** Professor Dr. Stefan Wermter Chair of Knowledge Technology Department of Computer Science University of Hamburg Vogt Koelln Str. 30 22527 Hamburg, Germany http://www.informatik.uni-hamburg.de/~wermter/ http://www.informatik.uni-hamburg.de/WTM/ ***********************************************