- Comp-neuro - lists.cnsorg.org

CNS 2015: Abstract Submission and Registration opens

by Tam, Nicoladie

Organization for Computational Neurosciences (OCNS) 24th Annual Meeting Prague, Czech Republic July 18-23, 2015 The main meeting (July 19-21) will be preceded by a day of tutorials (July 18) and followed by two days of workshops (July 22-23). Invited Keynote Speakers: Jack Cowan, University of Chicago, USA Gustavo Deco, Universitat Pompeu Fabra, Spain Adrienne Fairhall, University of Washington, USA Wulfram Gerstner, EPFL, Switzerland Registration will open on January 14, 2015. Abstract submission will open on January 15, 2015 and close on February 22. Workshop proposals are now being accepted. Note that one of the authors has to register as sponsoring author for the main meeting before abstract submission is possible. In case the abstract is not accepted for presentation, the registration fee will be refunded. For up-to-date conference information, please visit http://www.cnsorg.org/cns-2015-prague ---------------------------------------- OCNS is the international member-based society for computational neuroscientists. Become a member to be eligible for travel awards and more. Visit our website for more information: http://www.cnsorg.org

Jan. 17, 2015

CoSMo 2015 summer school announcement

by Gunnar Blohm

*Fifth Annual Computational Sensory-Motor Neuroscience Summer School (CoSMo 2015)* Radboud University Nijmegen, The Netherlands June 28 - July 11, 2015 We would like to invite you to join us for the fifth annual Computational Sensory-Motor Neuroscience Summer School. The course is about experimental, computational and medical aspects of sensory-motor neuroscience with a focus on active learning. Covered topics include multi-sensory integration, motor learning & control, computational methods, sensory-motor transformations and neural coding / decoding. An important focus is on doing research as opposed to just hearing about it. Each teaching module will take up two days with morning lecture sessions. Afternoon sessions involve hands-on Matlab programming, simulation and data-analysis. Newly acquired computational tools can also be applied in 2-week evening group research projects. The course is aimed at students and post-doctoral fellows from diverse backgrounds including Life Sciences, Psychology, Computer Science, Physics, Mathematics and Engineering. Basic knowledge in calculus, linear algebra and Matlab is expected. Enrollment will be limited to 40 trainees. *Application deadline: Mar 15, 2015* For more information and to apply, please go to http://www.compneurosci.com/CoSMo/ The school is co-organized by Drs Gunnar Blohm, Paul Schrater, John van Opstal, Pieter Medendorp and Konrad Körding. This year, it receives funding from the EU FP7 Marie-Curie IDP Training Network /HealthPAC/, and the Perception, Action and Control research network of the Donders Institute at Radboud University Nijmegen. -- ------------------------------------------------------- Dr. Gunnar BLOHM Associate Professor in Computational Neuroscience Association for Canadian Neuroinformatics and Computational Neuroscience (CNCN) Centre for Neuroscience Studies, Departments of Biomedical and Molecular Sciences, Mathematics & Statistics, and Psychology, School of Computing, and Canadian Action and Perception Network (CAPnet) Queen’s University 18, Stuart Street Kingston, Ontario, Canada, K7L 3N6 Tel: (613) 533-3385 Fax: (613) 533-6840 Email: Gunnar.Blohm(a)QueensU.ca Web: http://www.compneurosci.com/

Jan. 16, 2015

New funding opportunity: Machine Intelligence from Cortical Networks (MICrONS) Program

by R. Jacob Vogelstein

I am pleased to announce the release of the Machine Intelligence from Cortical Networks (MICrONS) program Broad Agency Announcement (BAA). MICrONS seeks to revolutionize machine learning by reverse-engineering the algorithms of the brain. The program is expressly designed as a dialogue between data science and neuroscience, in which participants will have the unique opportunity to pose biological questions with the greatest potential to advance theories of neural computation and obtain answers through carefully planned experimentation and data analysis. Over the course of the program, participants will use their improving understanding of the representations, transformations, and learning rules employed by the brain to create ever more capable neurally-derived machine learning algorithms. Ultimate computational goals for MICrONS include the ability to perform complex information processing tasks such as one-shot learning, unsupervised clustering, and scene parsing, aiming towards human-like proficiency. The program overview is copied below; the full text of the announcement (and any future versions) is available from the BAA link at http://www.iarpa.gov/index.php/research-programs/microns/microns-baa. All questions about the program and/or BAA must be submitted to dni-iarpa-baa-14-06(a)iarpa.gov by February 9, 2015. Full proposals must be submitted through the IARPA IDEAS <https://iarpa-ideas.gov> system by March 13, 2015. *Do not *send any questions or proposal submissions to me directly. Please disseminate this information widely. Offerors need not be U.S. citizens or residents to apply or receive funding. Thank you, Jacob R. Jacob Vogelstein, Ph.D. Program Manager ODNI/IARPA http://go.usa.gov/FPPJ -------------------------------------------------------- Introduction Despite significant progress in machine learning over the past few years, today’s state of the art algorithms are brittle and do not generalize well. In contrast, the brain is able to robustly separate and categorize signals in the presence of significant noise and non-linear transformations, and can extrapolate from single examples to entire classes of stimuli. This performance gap between software and wetware persists despite some correspondence between the architecture of the leading machine learning algorithms and their biological counterparts in the brain, presumably because the two still differ significantly in the details of operation. The MICrONS program is predicated on the notion that it will be possible to achieve major breakthroughs in machine learning if we can construct synthetic systems that not only resemble the high-level blueprints of the brain, but also employ lower-level computing modules derived from the specific computations performed by cortical circuits. Background Many contemporary theories of cortical computing suggest that the brain performs common sensory information processing tasks—such as detection and recognition of visual objects, sounds, and odors—with algorithms that progressively transform data through a series of operations, or “stages.” Each stage of processing is further theorized to occur within a discrete region of cortex. Although different theories suggest different mathematical bases for computation, it is commonly believed that neural algorithms employ data representations, transformations, and learning rules that are conserved across stages. <#14ae94b7b82a2eef_14ae94551cb4b667_14ae942f2d046d85_14acb3be21100ccb__ftn1> It should therefore be possible to apprehend the neural computations underlying information processing (at least within a given sensory modality <#14ae94b7b82a2eef_14ae94551cb4b667_14ae942f2d046d85_14acb3be21100ccb__ftn2>) by interrogating a small fraction of the entire cortex, so long as that fraction is judiciously selected to contain sufficient evidence of the representations, transformations, and learning rules of the algorithm(s) to which it contributes. Neuroscience has a long history of inspiring innovation in machine learning, starting with the seminal work of McCulloch and Pitts in 1943. This influence is evident even in today’s state of the art “deep learning” systems, which are loosely modeled on hierarchical visual processing systems in the primate brain. However, the rate of effective knowledge transfer between neuroscience and machine learning has been slow because of divergent scientific priorities, funding sources, knowledge repositories, and lexicons. As a result, very few of the ideas about neural computing that have emerged over the past few decades have been incorporated into modern machine learning algorithms. Previous attempts to foster collaboration between neuroscience and machine learning have been stymied in part by gaps in our knowledge about the brain. The majority of what is known about the brain today regards its operation at the “micro” scale (one or a few neurons) and the “macro” scale (hundreds of thousands or millions of neurons), and some of this information is indeed reflected in the design of leading artificial neural networks. In contrast, much less is known about the “mesoscale” cortical circuits (hundreds to tens of thousands of neurons) that implement the specific data representations, transformations, and learning rules of cortical information processing algorithms, and these are therefore absent from (or speculative in) existing machine learning solutions. It is likely that explicit knowledge and use of these computations is required to move beyond the current generation of “neurally-inspired” machine learning algorithms. Program Synopsis The MICrONS program aims to create novel machine learning algorithms that use neurally-inspired architectures *and* mathematical abstractions of the representations, transformations, and learning rules employed by the brain to achieve brain-like performance. To guide the construction of these algorithms, performers will conduct targeted neuroscience experiments that interrogate the operation of mesoscale cortical computing circuits, taking advantage of emerging tools for high-resolution structural and functional brain mapping. The program is designed to facilitate iterative refinement of algorithms based on a combination of practical, theoretical, and experimental outcomes: performers will use their experiences with the algorithms’ design and performance to reveal gaps in their understanding of cortical computation, and will collect specific neuroscience data to inform new algorithmic implementations that address these limitations. Ultimately, as performers incorporate these insights into successive versions of the machine learning algorithms, they will devise solutions that can perform complex information processing tasks aiming towards human-like proficiency. Program Structure MICrONS is organized in three phases, totaling five years in duration. During each phase, performers conduct targeted neuroanatomical and neurophysiological studies to inform their understanding of the cortical computations underlying sensory information processing and, concurrently, create neurally-derived machine learning algorithms that perform similar functions. Performers motivate their experimental and algorithmic designs by formulating and updating a conceptual model or “theoretical framework” for neural information processing in a given sensory modality. They use computational neural models (i.e., executable mathematic or algorithmic simulations of neurons and neural circuits) to establish a correspondence between the computations performed by biological wetware and the computations employed by their machine learning software. Each phase ends with an information processing challenge that assesses how well the new algorithms perform on increasingly challenging machine learning tasks: similarity discrimination in Phase 1, generalization and classification in Phase 2, and invariant recognition in Phase 3. Performers use the results of their experiments in each phase to guide their development of improved algorithms in the subsequent phase (in Phase 1, performers base their algorithms on the existing neuroscience literature). Technical Areas The MICrONS program comprises three Technical Areas (TAs). Although IARPA anticipates receiving a number of holistic proposals responding to all three TAs, it recognizes that some prospective offerors may have capabilities in only a subset of the overall program scope, and wishes to maximize its opportunity to leverage these capabilities. Therefore, offerors may choose to propose to one, two, or all three TAs. Because achieving MICrONS program goals will require significant collaboration across all three TAs, offerors who propose to only one or two TAs should be prepared to work closely with performers in the remaining TAs. The TAs in MICrONS are defined as follows: · TA1 – experimental design, theoretical neuroscience, computational neural modeling, machine learning, neurophysiological data collection, and data analysis; · TA2 – neuroanatomical data collection; and · TA3 – reconstruction of cortical circuits from neuroanatomical data and development of information technology systems to store, align, and access neural circuit reconstructions with the associated neurophysiological and neuroanatomical data. Success in the MICrONS program will require extensive communication and cooperation between performers in all three TAs within or across teams. For example, in TA2, performers must collect neuroanatomical data about the same brain regions *in the same brain specimens* that are used in TA1 for neurophysiological studies; in TA3, performers must reconstruct neural circuits from the data collected in TA2; and in TA1, performers must analyze the neural circuits generated in TA3 and use the resulting insights in formulating their machine learning algorithms and theoretical frameworks. All offerors are therefore required to include in their proposal a detailed management plan and a detailed description of how their proposed technical approach in one or more TAs is likely to impact the other TAs.

Jan. 16, 2015

Bernstein Conference 2015: Call for Workshops

by Seeger, Simone

The National Bernstein Network Computational Neuroscience invites proposals for Satellite Workshops directly preceding the Bernstein Conference 2015 in Heidelberg ********************************************************************************** Call for Workshop proposals: Workshops: September 14, 2015 (Main Bernstein Conference: September 15-17, 2015) Deadline of proposal submission: March 15, 2015 Notification of acceptance: April 20, 2015 Conference Registration starts: April 27, 2015 Early Registration Deadline: July 21, 2015 ********************************************************************************** The Bernstein Conference started out as the annual meeting of the National Bernstein Network Computational Neuroscience and has become the largest single-track Computational Neuroscience conference in Europe in recent years. Since 2013, the Bernstein Conference hosts pre-conference workshops, which have developed swiftly into a well-attended event. They supply a stage to debate topical research questions and challenges in Computational Neuroscience and related fields, different points of view and scientific approaches in an informal setting. Workshops addressing controversial issues, open problems, and comparisons of competing approaches are encouraged. SCHEDULE: September 14, 2015, 9:00 - 18:30. You may apply for either half-day or full-day workshops. Workshop costs: The Bernstein Conference does not provide financial support, but workshop organizers and speakers are offered free workshop registration and reduced fees for the main conference. For further information about the conference, please visit the conference website<http://www.bernstein-conference.de>. DETAILS FOR WORKSHOP PROPOSALS: The Workshop Proposal form can be downloaded here<http://www.nncn.de/de/bernstein-conference/2015/satellite-workshops/worksho…>. Deadline for submission of Workshop Proposals: March 15, 2015 We are looking forward to meeting you in Heidelberg! THE WORKSHOP PROGRAM COMMITTEE *** Simone Seeger, M.A. Administration Bernstein Center for Computational Neuroscience Zentralinstitut für Seelische Gesundheit Postfach 12 21 20, 68072 Mannheim J5, 68159 Mannheim Telefon: 0621/1703-1326 oder 06221/54-8310 Fax: 0621/1703-2915 E-Mail: Simone.Seeger(a)zi-mannheim.de<mailto:Simone.Seeger@zi-mannheim.de> Internet: http://www.bccn-heidelberg-mannheim.de<http://www.bccn-heidelberg-mannheim.de/>

Jan. 16, 2015

Call for Papers - IJCAI15 Workshop on Sensitivity Analysis and Robustness in Probabilistic Graphical Models

by Alessandro Antonucci

IJCAI15 Workshop on Sensitivity Analysis and Robustness in Probabilistic Graphical Models Buenos Aires, July 25-27, 2015 - http://ipg.idsia.ch/wijcai15/ FIRST CALL FOR PAPERS Probabilistic graphical models are important tools in machine learning and artificial intelligence for reasoning with uncertainty. They provide means to represent large multivariate domains compactly and to perform sophisticated learning and reasoning efficiently. Examples of probabilistic graphical models are Bayesian networks, Markov Random fields, chain and factor graphs, Gaussian graphical models, to name but a few. The quantification of these models usually requires sharp (i.e., precise) assessments of the model local potentials and might be subject to robustness issues. For instance, perturbations of some parameter values may lead to different decisions from those which would be achieved by the unperturbed model, suggesting that decisions are not reliable. Reliability might also be in question because of missing data and assumptions behind the process. The workshop invites submissions of papers on all aspects of sensitivity analysis and robustness in probabilistic graphical models. Contributions may have a theoretical focus and/or an applied focus. A non-exhaustive list of topics follows. - Local and/or global sensitivity analysis. - Parameter-based and/or decision-based sensitivity analysis. - Design of robust learning, inference and/or decision making approaches. - Robust analysis and design of robustness measurements. - Extensions of probabilistic graphical models. - Reliable qualitative learning and reasoning. - Robust treatment of missing data. - Imprecise probability and other theories related to sensitivity analysis. - Computational complexity, exact and approximate algorithms. Each submission will be reviewed by peers using a double-blind process (please use the third person in self citations and take all necessary care not to identify yourselves). Accepted papers will be published electronically in a volume of the JMLR Workshop and Conference Proceedings series. There will be no rebuttal phase, but contributions considered worth publishing and needing substantial revision might be subject to a second round of reviewing/evaluation. All accepted papers will be presented at the workshop. At least one of the paper's authors should register and attend the workshop to present the work. Submissions must be formatted according to style and template files available for the Journal of Machine Learning Research (JMLR) Workshop and Conference Proceedings - two-column version. The style files are available at http:/ipg.idsia.ch/wijcai15/sarpgm15.tar.gz Papers (including figures, tables, references, etc) are expected to have between 6 and 10 pages. IMPORTANT DATES Apr 27, 2015 - Deadline for submissions of contributions May 20, 2015 - Workshop paper acceptance notification May 30, 2015 - Deadline for workshop camera-ready copy (in case of minor revision; contributions needing major revision might need additional time - this will be arranged case by case) PC MEMBERS Alessandro Antonucci*, IDSIA, Switzerland. Alessio Benavoli, IDSIA, Switzerland. Cassio P. de Campos*, Queen's University Belfast, UK. Arthur Choi, University of California, Los Angeles, USA. Giorgio Corani*, IDSIA, Switzerland. Fabio Cozman, University of Sao Paulo, Brazil. Adnan Darwiche, University of California, Los Angeles, USA. Sebastien Destercke, Univ. de Technologie de Compiegne, France. Marek Druzdzel, University of Pittsburgh, USA. Johan Kwisthout, Radboud University Nijmegen, The Netherlands. Agnieszka Onisko, Bialystok University of Technology, Poland. Denis Maua, University of Sao Paulo, Brazil. Serafin Moral, Universidad de Granada, Spain. Silja Renooij, Universiteit Utrecht, The Netherlands. Matthias Troffaes, University of Durham, UK. (*: Workshop organizers.) More details about the submission procedure are available online. http://ipg.idsia.ch/wijcai15/ ++++++++++++++++++++++++++++++++++++++++ (We apologize in case you receive multiple copies of this announcement, but yet we hope to reach the greatest possible number of people. Finding a trade-off is not an easy task.) -- _________________________________ Alessandro Antonucci IDSIA Dalle Molle Institute for Artificial Intelligence Via Cantonale (Galleria 2) CH-6928, Manno-Lugano, CH mail: alessandro(a)idsia.ch skype: alessandro.antonucci tel: +41 916108515 web: www.idsia.ch/~alessandro _________________________________

Jan. 16, 2015

Connectionists: Call for Papers (Extended Deadline to 5 Feb 2015): IEEE IJCNN'2015 Special Session on: "Emerging Methodologies for Big Data Integration"

by Dr Amir Hussain

CALL FOR PAPERS IEEE IJCNN 2015 Special Session on *"*Emerging Methodologies for Big Data Integration*"* July 12 - 17, 2015, Killarney, Ireland ( http://www.ijcnn.org/ ) ************************************************************************************** Important Announcement *************************************************************************************** Due to numerous requests, the IJCNN has kindly agreed to extend all paper submission deadlines to February 5th, 2015. ************************************************************************************* NEW: IMPORTANT DATES (REVISED) EXTENDED DEADLINE for Paper submission: February 5th, 2015 Paper Decision notification: March 25th, 2015 Camera-ready submission: April 25th, 2015 Conference Dates: July 12 - 17th, 2015 *********************************************************** Over the years, huge quantities of data have been generated by large-scale scientific experiments (biomedical, “omic”, imaging, astronomical, etc.), big industrial companies and on the web. One of the main characteristics of such Big Data is that they are multi-view, i.e. there are multiple sources (in the “omics” sciences, experiments related to mRNA, miRNA etc.), relate the same patterns (in this case patients) or multi-domain (in biomedical applications for examples, “omics, imaging and clinical data). As a consequence, new methodologies based on neural networks, machine and statistical learning, computation Intelligence and others, have been proposed to integrate these kinds of big data and to elicit relevant information to infer novel models and correlations. The aim of the special session is to solicit new approaches to real world scientific and industrial big data integration, as well as applications of above mentioned Big Data methodologies. *Topics** Papers must present original work or review the state-of-the-art in the following non-exhaustive list of topics: Multi-view learning Multi-view clustering data fusion data integration multi-view data applications multi domain data applications THE DEADLINE FOR THE PAPER SUBMISSION TO THE SPECIAL SESSION IS THE SAME OF IJCNN 2015, January 15th 2015. All the submissions will be peer-reviewed with the same criteria used for other contributed papers. Perspective authors will submit their papers through the IJCNN2015 conference submission system at http://www.ijcnn.org/ Please make sure to select the Special Session "Emerging Methodologies for Big Data Integration " from the "S. SPECIAL SESSION TOPICS" name in the "Main Research topic" dropdown list; Templates and instructions for authors will be provided on the IJCNN webpage http://www.ijcnn.org/ All papers submitted to the special sessions will be subject to the same peer-review procedure as regular papers, accepted papers will be published in the conference proceedings. Further information about IJCNN 2015 can be fond at http://www.ijcnn.org/ and about the special session at http://neuronelab.unisa.it/emerging-methodologies-for-big-data-integration/ We look forward to seeing you soon in Kilarney! *********************************************************** **Organizers** - Amir Hussain Professor of Computing Science and founding Director of the Cognitive Signal-Image Processing and Control Systems Research (COSIPRA) Laboratory, University of Stirling, UK (E-mail: ahu(a)cs.stir.ac.uk http://cs.stir.ac.uk/~ahu) - Giovanni Montana Professor and Chair in Biostatistics and Bioinformatics, Biomedical Engineering Department, King’s College, London, UK (E-mail: giovanni.montana(a)kcl.ac.uk) - Francesco Carlo Morabito Professor and Chair of the Neurolab, Dipartimento DICEAM, Università Mediterranea di Reggio Calabria, Italy (E-mail: morabito(a)unirc.it) - Roberto TAGLIAFERRI Professor and Chair of the Neuronelab, Dipartimento di Informatica, Università di Salerno, Italy (E-mail: robtag(a)unisa.it) **Technical Program Committee (being continuously updated)** Elia Mario Biganzoli, Università di Milano, Italy Erik Cambria, NTU, Singapore Ciro Donalek, Caltech, CA, USA Anna Esposito, Seconda Università di Napoli, Italy Marcos Faundez-Zanuy, Escola Universitaria Politecnica de Mataro (Tecnocampus), Spain Alexander Gelbukh, National Polytechnic Institute, Mexico Dario Greco, FIOH, Finland Newton Howard, MIT Media Lab, USA Pietro Liò, University of Cambridge, UK Bin Luo, Anhui University, China Mufti Mahmud, Antwerp University, Belgium Riccardo Rizzo, CNR, Italy Jingpeng Li, University of Stirling, UK Domenico Ursino, Università Mediterranea di Reggio Calabria, Italy Alfredo Vellido, Universidad Politécnica de Cataluña, Spain Pierangelo Veltri, Università "Magna Graecia" di Catanzaro, Italy Jonathan Wu, University of Windsor, Canada Yunqing Xia, Tsinghua University, China Kang Li, Queen's University, Belfast, UK Dongbing Gu, Essex University, UK Vincent C. Müller, Anatolia College/ACT, Greece & Oxford University, UK Dongbin Zhao, Chinese Academy of Sciences, Beijing, China Paulo Lisboa, Liverpool John Moores University, UK ************************************************************************************** -- The University of Stirling has been ranked in the top 12 of UK universities for graduate employment*. 94% of our 2012 graduates were in work and/or further study within six months of graduation. *The Telegraph The University of Stirling is a charity registered in Scotland, number SC 011159.

Jan. 15, 2015

Postdoctoral and PhD positions in computational neuroscience at Harvard

by Haim Sompolinsky

Dear colleagues, I have several openings for research in computational neuroscience at the doctoral and postdoctoral levels. See the following announcement. Best, Haim Opportunities in Theoretical Neuroscience Doctoral and Postdoctoral Opportunities in Theoretical Neuroscience I am seeking doctoral and postdoctoral associates for research on theoretical neuroscience projects. Creativity, analytical and numerical skills, drive, and a background in physics, computational neuroscience, applied mathematics, or computer science are expected. Research topics span a broad range of topics dealing with the principles underlying the links between neuronal circuits' structure, dynamics, behavior and cognition. Positions are available for work in the Swartz theoretical neuroscience group at Harvard http://cbs.fas.harvard.edu/ <http://cbs.fas.harvard.edu/> . Please submit your application including CV, list of publications and names of three possible referees to Prof. Haim Sompolinsky: haim(a)fiz.huji.ac.il <mailto:haim@fiz.huji.ac.il>. -- Haim Sompolinsky The Hebrew University For research positions, see: http://neurophysics.huji.ac.il/Opportunities

Jan. 15, 2015

CFP: HRI 2015 Workshop on “Cognition: A Bridge between Robotics and Interaction”

by Yukie Nagai

============================================================ Workshop “Cognition: A Bridge between Robotics and Interaction”, at HRI 2015, Portland (OR) USA ============================================================ March 2, 2015 Submission deadline: January 20, 2015 Notification of acceptance: January 30, 2015 website: http://www.macs.hw.ac.uk/~kl360/HRI2015W/ ============================================================ INVITED SPEAKERS: - Prof. David Vernon, Sk?vde University - Prof. Andrew Meltzoff, University of Washington INVITED PANELISTS: - Prof. Giulio Sandini, Italian Institute of Technology - Prof. Minoru Asada, Osaka University A key feature of humans is the ability to anticipate what other agents are going to do and to plan accordingly a collaborative action. This skill, derived from being able to entertain models of other agents, allows for the compensation for intrinsic delays of human motor control and is a primary support to allow for efficient and fluid interaction. Moreover, the awareness that other humans are cognitive agents who combine sensory perception with internal models of the environment and others, enables easier mutual understanding and coordination. Cognition represents therefore an ideal link between different disciplines, as the field of Robotics and that of Interaction studies, performed by neuroscientists and psychologists. From a robotics perspective, the study of cognition is aimed at implementi ng cognitive architectures leading to efficient interaction with the environment and other agents. From the perspective of the human disciplines, robots could represent an ideal stimulus to study which are the fundamental robot properties necessary to make it perceived as a cognitive agent, enabling natural human-robot interaction. Ideally, the implementation of cognitive architectures may raise new interesting questions for psychologists, and the behavioral and neuroscientific results of the human-robot in teraction studies could validate or give new inputs for robotics engineers. The aim of this workshop will be to provide a venue for researchers of different disciplines to discuss the possible points of contact and to highlight the issues and the advantages of bridging different fields for the study of cognition for interaction. T his workshop will represent an ideal continuation of the discussion began at HRI 2014, in the workshop “HRI: a bridge between Robotics and Neuroscience” (http://www.macs.hw.ac.uk/~kl360/HRI2014W/index.html) LIST OF TOPICS ------------- - Cognitive Architecture - Development of Social Cognition - Interaction - Prediction - Embodiment - Self and Other FORMAT AND SUBMISSIONS ----------------------- The workshop will consist of invited keynotes, time for discussions and will also feature a poster session. Prospective participants are invited to submit full papers (up to 8 pages) or short papers (2 pages). Submissions will be accepted in PDF format only, using the HRI formatting guidelines (http://www.macs.hw.ac.uk/~kl360/HRI2015W/papers.html) and including author names. Authors should send their papers to hri2015workshop(a)gmail.com . All submissions will be peer-reviewed. Upon available time, selected contributions may have the opportunity to be presented in the oral session. The other selected contributions will be presented as posters during a dedicated session. The submission must include 1 answer to one of the following questions: - How should cognitive research be structured to yield results useful for robotics and HRI? - How can robotics have a direct influence on neuroscience and cognitive psychology aimed at interaction studies? - Which is the minimal level of cognition needed in a robot to be able to interact with a human? - Does a robot really need cognition to be perceived as a cognitive agent by a human? - Does inserting a cognitive agent into an interaction pose a risk to the human partners? - How important is the embodiment of a robot for the development of its cognitive architecture and its social cognition? Upon available time, those questions/answers will be used to "drive" a final discussion. IMPORTANT DATES ---------------- Submission deadline: January 20, 2015 Notification of acceptance: January 30, 2015 Workshop at HRI 2015: March 2, 2015 ORGANIZERS ----------- - Alessandra Sciutti Istituto Italiano di Tecnologia - Katrin Solveig Lohan Heriot-Watt University - Yukie Nagai Osaka University — Yukie Nagai, Ph.D. Specially Appointed Associate Professor, Osaka University Visiting Researcher, Bielefeld University yukie(a)ams.eng.osaka-u.ac.jp http://cnr.ams.eng.osaka-u.ac.jp/~yukie/

Jan. 14, 2015

INNS BigData 2015 San Francisco - New Conference! Calls for Papers, Special Sessions, Tutorials and Workshops!

by Asim Roy

Apologies for cross-posting. Note the plenary talk by Juergen Schmidhuber (Prof. Jürgen Schmidhuber<http://people.idsia.ch/~juergen/>) on Deep Learning. There will also be a tutorial and a workshop on Deep Learning by Juergen Schmidhuber and Dong Yu of Microsoft Research (Dong Yu<http://research.microsoft.com/en-us/people/dongyu/>, Microsoft Research<http://research.microsoft.com/en-us/>). Note the deadlines for submission of proposals for special sessions, tutorials and workshops. See you in San Francisco. <http://www.innsbigdata.org/> [http://innsbigdata.org/wp-content/uploads/2014/09/banner.jpg]<http://www.innsbigdata.org/> INNS Conference on Big Data 2015 New approaches to solving hard Big Data problems! 8 - 10 August 2015, San Francisco www.innsbigdata.org<http://www.innsbigdata.org/> The aim of the INNS BigData conference is to promote new advances and research directions in efficient and innovative algorithmic approaches to analyzing big data (e.g. deep networks, nature-inspired and brain-inspired algorithms), implementations on different computing platforms (e.g. neuromorphic, GPUs, clouds, clusters) and applications of Big Data Analytics to solve real-world problems (e.g. weather prediction, transportation, energy management). Please refer to our website for a more detailed list of topics. Being INNS' inaugural conference on the theme of big data, we are especially motivated to synthesize ideas, promote activities and generate broad interest in areas where neural networks have many unique advantages. We also have Twitter<https://twitter.com/inns_bigdata>, Facebook<https://www.facebook.com/innsbigdata15/> and Google+<https://plus.google.com/112891798437473029046> pages! ________________________________ [http://innsbigdata.org/wp-content/uploads/2014/09/new.gif]PLENARY TALK<http://innsbigdata.org/> [http://innsbigdata.org/wp-content/uploads/2014/11/juergen.jpg] DEEP LEARNING Prof. Jürgen Schmidhuber<http://people.idsia.ch/~juergen/>, Professor of Artificial Intelligence at the University of Lugano<http://www.inf.usi.ch/index.htm>, and the Swiss AI Lab IDSIA.<http://www.idsia.ch/> Since age 15 or so, Prof. Jürgen Schmidhuber’s main scientific ambition has been to build an optimal scientist through self-improving Artificial Intelligence (AI), then retire. He has pioneered self-improving general problem solvers since 1987, and Deep Learning Neural Networks (NNs) since 1991. The Long Short-Term Memory (LSTM) recurrent NNs (RNNs), developed by his research groups at the Swiss AI Lab IDSIA & USI & SUPSI & TU Munich, were the first RNNs to win official international contests. LSTM recently helped to improve connected handwriting recognition, speech recognition, machine translation, optical character recognition, image caption generation, and are now in use at Google, Microsoft, IBM, and many other companies. IDSIA’s Deep Learners were also the first to win object detection and image segmentation contests, and achieved the world’s first superhuman visual classification results, winning nine international competitions in machine learning & pattern recognition (more than any other team). Since 2009 he has been member of the European Academy of Sciences and Arts. He has published over 300 peer-reviewed papers, earned seven best paper/best video awards, and is recipient of the 2013 Helmholtz Award of the International Neural Networks Society. ________________________________ Important Dates:<http://innsbigdata.org/important-dates/> * Paper submission:<http://innsbigdata.org/paper-submission/> March 22, 2015. * Paper Decision Notification: May 22, 2015. * Camera Ready Submission of papers: June 8, 2015. Call for Special Sessions:<http://innsbigdata.org/special-sessions/> * Deadline: January 22, 2015 * Any proposal can be sent by e-mail to: INNSBigData2015SpecialSessions(a)gmail.com<mailto:INNSBigData2015SpecialSessions@gmail.com> Call for Tutorials<http://innsbigdata.org/tutorials/> and Workshops:<http://innsbigdata.org/workshops/> * Deadline: January 22, 2015 * Any questions can be sent to the Tutorials & Workshops Chairs: Marley Vellasco (PUC-Rio. Rio de Janeiro. Brazil)<mailto:Marley%20Vellasco%20(PUC-Rio.%20Rio%20de%20Janeiro.%20Brazil)%20%3cmarley@ele.puc-rio.br%3e> and Trevor Martin (Univ. of Bristol, UK)<mailto:Trevor%09Martin%20(Univ.%20of%20Bristol.%20UK)%20%3ctrevor.martin@bristol.ac.uk%3e>. ________________________________ [http://innsbigdata.org/wp-content/uploads/2014/09/new.gif]The Elsevier USD 2000 Big Data Best Paper Award:<http://innsbigdata.org/best-paper-award/> This award recognizes the best paper presented at the INNS Big Data conference. Both application and theoretical papers will be considered. It will be awarded by the Big Data Analytics Section of the International Neural Network Society and is sponsored by Elsevier. The Award consists of a plaque and a $2000 honorarium. ________________________________ Dr. Fen Zhao Talk<http://innsbigdata.org> Dr. Fen Zhao, a Staff Associate at the Office of the Assistant Director (OAD) for Computer & Information Science & Engineering (CISE) at the National Science Foundation, will give a talk on national big data R&D initiative and on building public-private partnerships around CISE's Big Data, next generation internet, and cybersecurity R&D portfolios. ________________________________ PLENARY SPEAKERS:<http://innsbigdata.org/> [http://innsbigdata.org/wp-content/uploads/2014/11/Bin-Yu.jpg] Prof. Bin Yu<https://www.stat.berkeley.edu/~binyu/Site/Welcome.html>, Chancellor´s Professor, University of California<http://www.universityofcalifornia.edu/>, Berkeley. Bin Yu is Chancellor’s Professor in the Departments of Statistics and of Electrical Engineering & Computer Science at the University of California at Berkeley. She held faculty positions at UW-Madison and Yale University and was a Member of Technical Staff at Lucent Bell Labs. She was Chair of Department of Statistics at Berkeley from 2009 to 2012, and is a founding co-director of the Microsoft Joint Lab on Statistics and Information Technology at Peking University where she is also Chair of the scientific advisory committee of the Center for Statistical Sciences. She has published over 80 scientific papers in premier journals in statistics, machine learning, information theory, signal processing, remote sensing, neuroscience, network analysis, and bioinformatics. She is a Member of the U.S. National Academy of Sciences, and a Fellow of the American Academy of Arts and Sciences. [http://innsbigdata.org/wp-content/uploads/2014/11/Raghu.jpg] Prof. Raghu Ramakrishnan<http://pages.cs.wisc.edu/~raghu/>, Head of Cloud and Information Services Lab (CISL) and big data team, Microsoft<http://research.microsoft.com/en-us/events/fs2013/raghu-ramakrishnan_bigdat…> Raghu Ramakrishnan heads the Cloud and Information Services Lab (CISL) in the Data Platforms Group at Microsoft, and leads development for the Big Data team. From 1987 to 2006, he was a professor at University of Wisconsin-Madison, where he wrote the widely-used text “Database Management Systems” and led a wide range of research projects in database systems (e.g., the CORAL deductive database, the DEVise data visualization tool, SQL extensions to handle sequence data) and data mining (scalable clustering, mining over data streams). In 1999, he founded QUIQ, a company that introduced a cloud-based question-answering service. He joined Yahoo! in 2006 as a Yahoo! Fellow, and over the next six years served as Chief Scientist for the Audience (portal), Cloud and Search divisions, driving content recommendation algorithms (CORE), cloud data stores (PNUTS), and semantic search (“Web of Things”). Ramakrishnan has received several awards, including the ACM SIGKDD Innovations Award, the SIGMOD 10-year Test-of-Time Award, the IIT Madras Distinguished Alumnus Award, and the Packard Fellowship in Science and Engineering. [http://innsbigdata.org/wp-content/uploads/2014/11/brenda.jpg] Prof. Brenda Dietrich,<https://www-03.ibm.com/ibm/history/witexhibit/wit_fellows_dietrich.html> IBM Fellow and VP, Leads the Emerging Technologies Team for IBM Watson, IBM<http://www.ibm.com/ibm/ideasfromibm/us/ibm_fellows/> Brenda Dietrich is an IBM Fellow and Vice President. She joined IBM in 1984 and has worked in the area now called analytics for her entire career, applying data and computation to business decision processes throughout IBM. For over a decade she led the Mathematical Sciences function in the IBM Research division where she was responsible for both basic research on computational mathematics and for the development of novel applications of mathematics for both IBM and its clients. She has been the president of INFORMS, has served on the Board of Trustees of SIAM, and is a member of several university advisory boards. She holds more than a dozen patents, has co-authored numerous publications, and frequently speaks on analytics at conferences. She was elected to the National Academy of Engineering in 2014. She holds a BS in Mathematics from UNC and an MS and Ph.D. in OR/IE from Cornell. Her personal research includes manufacturing scheduling, services resource management, transportation logistics, integer programming, and combinatorial duality. She currently leads the emerging technologies team for IBM Watson, extending and applying IBM’s cognitive computing technology. ________________________________ [http://innsbigdata.org/wp-content/uploads/2014/09/new.gif]TUTORIALS & WORKSHOPS: TUTORIALS * Deep Learning - Profs. Juergen Schmidhuber<http://people.idsia.ch/~juergen/> (University of Lugano<http://www.inf.usi.ch/index.htm>, and the Swiss AI Lab IDSIA<http://www.idsia.ch/>) and Dong Yu<http://research.microsoft.com/en-us/people/dongyu/> (Microsoft Research<http://research.microsoft.com/en-us/>) * Introduction to How Brain Deals with Big Data - Juyang Weng<http://www.cse.msu.edu/~weng/> (Michigan State University<http://www.msu.edu/>) * Platforms and Algorithms for Big Data Analytics - Prof. Chandan K. Reddy<http://www.cs.wayne.edu/~reddy/> (Wayne State University<http://wayne.edu/>) * Big Data Analytics, Machine Learning Cognitive Algorithms and the Mind - Prof. Leonid I. Perlovsky<http://www.northeastern.edu/cos/psychology/people/faculty/> (Northeastern University<http://www.northeastern.edu/>) * Spiking Neural Networks and Neuromorphic Spatio-Temporal Data Machines - Prof. Nikola Kasabov <http://www.aut.ac.nz/profiles/nikola-kasabov> (Auckland University of Technology<http://www.aut.ac.nz/>) * Online Learning for Big Data Analytics - Prof. Irwin King<https://www.cse.cuhk.edu.hk/irwin.king.new/> (Chinese University of Hong Kong<http://www.cuhk.edu.hk/english/index.html>) WORKSHOPS * Deep Learning - Profs. Juergen Schmidhuber<http://people.idsia.ch/~juergen/> and Dong Yu<http://research.microsoft.com/en-us/people/dongyu/> * Neuromorphic Spatio-Temporal Big Data Machines - Prof. Nikola Kasabov <http://www.aut.ac.nz/profiles/nikola-kasabov> * Neural networks and wearable devices - Prof. Danilo Mandic<http://www.commsp.ee.ic.ac.uk/~mandic/> * Big Data and Power Systems - Profs. Dejan Sobajic and Kumar Venayagamoorthy * Crowd Behaviour and Big Data - Profs. Chrisina Jayne and Mehmed Kantardzic ________________________________ Neural Networks Special Issue: Neural Network Learning in Big Data<http://www.journals.elsevier.com/neural-networks/call-for-papers/special-is…> For this special issue of Neural Networks, we invite papers that address many of the challenges of learning from big data. In particular, we are interested in papers on efficient and innovative algorithmic approaches to analyzing big data (e.g. deep networks, nature-inspired and brain-inspired algorithms), implementations on different computing platforms (e.g. neuromorphic, GPUs, clouds, clusters) and applications of online learning to solve real-world big data problems (e.g. health care, transportation, and electric power and energy management). Manuscript submission due: January 15, 2015 Big Data Analytics Section @ INNS<http://www.inns.org/big-data-section> Considering the growing interest to process and analyse big data, the International Neural Network Society (INNS) has a new Section on Big Data Analytics (BDA) to help the neural network field position itself as a leading technology contributor to big data analytics. Anyone who is interested to know more is encouraged to visit the homepage of the INNS-BDA Section<http://www.inns.org/big-data-section>. ________________________________ We have an enthusiastic team working hard on the conference program and events. Start thinking about your paper submissions. Our Chairs for the [Special Sessions, Tutorials, and Workshops] are expecting your proposals soon - email them to discuss your ideas. Come to San Francisco next summer to take part in the future of BigData, and to have fun!! ________________________________ GENERAL CHAIRS:<http://innsbigdata.org/committees/> Asim Roy<https://webapp4.asu.edu/directory/person/9973> (email<mailto:Asim%20Roy.%20General%20Co-Chair.%20INNS%20BigData2015.%20Arizona%20StateU.%20USA%20%3cASIM.ROY@asu.edu%3e>) INNS BigData General Co-Chair Arizona State University, USA INNS Board of Governors Plamen Angelov<http://www.lancaster.ac.uk/staff/angelov/> (email<mailto:Plamen%20Angelov.%20General%20Co-Chair.%20INNS%20BigData2015.%20Lancaster%20U.%20UK%20%3cp.angelov@lancaster.ac.uk%3e>) INNS BigData General Co-Chair Lancaster University, UK Chair in Intelligent Systems ________________________________ Many thanks to our Sponsors: [http://www.inns.org/assets/site/neural.png]<http://www.inns.org/> [http://innsbigdata.org/wp-content/uploads/2014/10/elsevier-logo-300x300-150…]<http://www.elsevier.com/> To unsubscribe from this list, send an email to Jose Antonio Iglesias, INNS BigData 2015 Publicity Co-Chair, Carlos III Univ, Madrid, Spain<mailto:Jose%20Antonio%20Iglesias.%20INNS%20BigData%202015%20Publicity%20Co-Chair.%20Carlos%20III%20Univ.%20Madrid.%20Spain%20%3cBigData2015-INNS-SanFrancisco@BillHowell.ca%3e?subject=Remove%20my%20email&body=Click%20to%20send.%20This%20will%20remove%20your%20email%20address%20from%20the%20INNS%20mass%20email%20list.> with the phrase "Remove my email" in the Subject line.

Jan. 14, 2015

RLDM2015: Abstract submissions deadline in one month!

by Yael Niv

The 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2015) www.rldm.org<http://www.rldm.org/> June 7-10, The University of Alberta, Edmonton, Alberta, Canada ====================================================== Submissions to RLDM2015 are now being accepted at https://cmt.research.microsoft.com/RLDM2015 Deadline: 13 February 2015, midnight EST We invite extended abstracts for contributed poster presentations and oral presentations. We welcome submissions of original research related to “learning and decision making over time to achieve a goal”, coming from any discipline or disciplines, describing empirical results from human, animal or animat experiments, and/or theoretical work, simulations and modeling. Contributions should be aimed at an interdisciplinary audience, but not at the expense of technical excellence. This is an abstract-based meeting, with no published conference proceedings. As such, work that is intended for, or has been submitted to, other conferences or journals is also welcome, provided that the intent of communication to other disciplines is clear. Submissions should consist of a summary (max 2000 characters; text only), and an extended abstract of between one and four pages (including figures and references). LaTeX and RTF templates, and sample submissions, are available from http://rldm.org/rldm2015/submission-procedure/ Note: Only the summary will be made available in the (electronic) abstract booklets. The extended abstract will be used for reviewing, and will be available online only pending on authors’ separate explicit permission. Online availability will have no bearing on the review process and authors are encouraged to include new, unpublished, findings which they do not want to make publicly available. To submit your abstract please go to https://cmt.research.microsoft.com/RLDM2015 Submissions will be reviewed for relevance to the topic and for quality. Exceptional abstracts will be selected for oral presentations and for poster spotlight presentations. IMPORTANT DATES: Submissions open: 13 Dec 2015 Submissions close: 13 Feb 2015, 11:59pm EST Notification of acceptance: by March 28, 2015 (expedited reviewing for those needing an international visa can be requested) Early registration: 21 April 2015 Meeting: 7-10 June 2015, Edmonton, Alberta (*NEW* this year: Tutorials on the 7th) RLDM2015 Invited speakers: http://rldm.org/rldm2015/invited-speakers2015/ RLDM2015 Tutorials: http://rldm.org/rldm2015/tutorials/ RLDM2015 Programme Committee: http://rldm.org/rldm2015/committees/rldm2015-program-committee/ To ensure that you receive future announcements about RLDM2015 please join our mailing list at http://tinyurl.com/RLDMlist (you must log in to google to see the “join list” button, and choose “all email” from the options at the bottom).

Jan. 14, 2015

CFP: ICC'15 Workshop - 4th IEEE SCPA 2015 - June 8-12, 2015. London, UK

by Sandra Sendra

Apologies for crossposting -------------------- CALL FOR PAPERS (DEADLINE EXTENDED) ----------------- 4th IEEE International Workshop on Smart Communication Protocols and Algorithms (SCPA 2015) June 8-12, 2015. London, UK In conjunction with IEEE ICC 2015 http://scpa.it.ubi.pt/2015/ Selected papers will be invited to the Special Issue on Smart Protocols and Algorithms of the International Journal Network Protocols and Algorithms (ISSN 1943-3581) or to the Special Issue on Recent Patents on Telecommunications Journal ((Online)ISSN 2211-7415, (Print) ISSN 2211-7407) Communication protocols and algorithms are needed to communicate network devices and exchange data between them. The appearance of new technologies usually comes with a protocol procedure and communication rules that allows data communication while taking profit of this new technology. Recent advances in hardware and communication mediums allow proposing new rules, conventions and data structures which could be used by network devices to communicate across the network. Moreover, devices with higher processing capacity let us include more complex algorithms that can be used by the network device to enhance the communication procedure. Smart communication protocols and algorithms make use of several methods and techniques (such as machine learning techniques, decision making techniques, knowledge representation, network management, network optimization, problem solution techniques, and so on), to communicate the network devices to transfer data between them. They can be used to perceive the network conditions, or the user behavior, in order to dynamically plan, adapt, decide, take the appropriate actions, and learn from the consequences of its actions. The algorithms can make use of the information gathered from the protocol in order to sense the environment, plan actions according to the input, take consciousness of what is happening in the environment, and take the appropriate decisions using a reasoning engine. Goals such as decide which scenario fits best its end-to-end purpose, or environment prediction, can be achieved with smart protocols and algorithms. Moreover, they could learn from the past and ! use this knowledge to improve futur e decisions. In this workshop, researchers are encouraged to submit papers focused on the design, development, analysis or optimization of smart communication protocols or algorithms at any communication layer. Algorithms and protocols based on artificial intelligence techniques for network management, network monitoring, quality of service enhancement, performance optimization and network secure are included in the workshop. We welcome technical papers presenting analytical research, simulations, practical results, position papers addressing the pros and cons of specific proposals, and papers addressing the key problems and solutions. The topics suggested by the conference can be discussed in term of concepts, state of the art, standards, deployments, implementations, running experiments and applications. Topics of interest: Authors are invited to submit complete unpublished papers, which are not under review in any other conference or journal, including, but are not limited to, the following topic areas: - Smart network protocols and algorithms for multimedia delivery - Application layer, transport layer and network layer cognitive protocols - Cognitive radio network protocols and algorithms - Automatic protocols and algorithms for environment prediction. - Algorithms and protocols to predict data network states. - Intelligent synchronization techniques for network protocols and algorithms - Smart protocols and algorithms for e-health - Software applications for smart algorithms design and development. - Dynamic protocols based on the perception of their performance - Smart protocols and algorithms for Smartgrids - Protocols and algorithms focused on building conclusions for taking the appropriate actions. - Smart Automatic and self-autonomous ad-hoc and sensor networks. - Artificial intelligence applied in protocols and algorithms for wireless, mobile and dynamic networks. - Smart security protocols and algorithms - Smart cryptographic algorithms for communication - Artificial intelligence applied to power efficiency and energy saving protocols and algorithms - Smart routing and switching protocols and algorithms - Cognitive protocol and algorithm models for saving communication costs. - Any kind of intelligent technique applied to QoS, content delivery, network Monitoring and network management. - Smart collaborative protocols and algorithms - Problem recognition and problem solving protocols Genetic algorithms, fuzzy logic and neural networks applied to communication protocols and algorithms Important Dates Submission Deadline: 31st January, 2015 (FINAL DEADLINE - no further extensions) Acceptance Notification: 1st March, 2015 Camera Ready Deadline: 15th March, 2015 Submission guidelines: All submissions must be full papers in PDF format and uploaded on EDAS (http://edas.info/newPaper.php?c=18713) All submissions should be written in English with a maximum paper length of five (5) printed pages (10-point font) including figures without incurring additional page charges. General Chairs Jaime Lloret Mauri, Universitat Polit�cnica Val�ncia, Spain Joel Rodrigues, Instituto de Telecomunica��es, Univ. of Beira Interior, Portugal TPC Chairs Ivan Stojmenovic, University of Ottawa, Canada Guangjie Han, Hohai University, China Panel Chairs Honggang Wang, University of Massachusetts, USA Daqiang Zhang, Tongji University, China Industry Chairs Antonio S�nchez-Esguevillas, Telefonica R&D, Spain Neeraj Kumar, Thapar University, Patiala (Punjab), India Publicity Chair Sandra Sendra, Universitat Polit�cnica Val�ncia, Spain Web Chair Alejandro C�novas Solbes, Universitat Polit�cnica Val�ncia, Spain

Jan. 13, 2015

ECMLPKDD 2015: Call for Papers, Tutorials and Workshops

by ECMLPKDD 2015

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) will take place in Porto, Portugal, from September 7th to 11th, 2015 (http://www.ecmlpkdd2015.org) This event is the leading European scientific event on machine learning and data mining and builds upon a very successful series of 25 ECML and 18 PKDD conferences, which have been jointly organized for the past 14 years. ECMLPKDD 2015 will host three tracks, tutorials and a set of workshops. Therefore, we invite all researchers and practitioners from different communities to submit papers and/or present tutorial and workshop proposals. ************************* CALL FOR PAPERS ************************* JOURNAL TRACK ********************* Articles for this track are submitted all year long directly to either Machine Learning or Data Mining and Knowledge Discovery, and are reviewed like regular journal articles. Accepted articles appear in full in the journal and the authors are given a presentation slot at the conference. Articles deemed insufficiently mature for journal publication may be accepted for inclusion in the proceedings. Submissions to the journal track will be managed by the Guest Editorial Board. Paper Submission: Cut-off dates for the bi-weekly batches are 18 Jan, 1 Feb, 15 Fev, 1 Mar, 15 Mar, 29 Mar, 12 Apr, 26 Apr of 2015 Web Page: http://www.ecmlpkdd2015.org/submission/journal-track RESEARCH PROCEEDINGS TRACK ******************************************* The research proceedings track, which is organized in the traditional way. Accepted papers will be published in the Lecture Notes in Artificial Intelligence (LNCS/LNAI) of Springer, after reviewing by the programme committee. Abstract Submission Deadline: March 26, 2015 Paper Submission Deadline: April 2, 2015 Paper Acceptance Notification: June 1, 2015 Paper Camera Ready Submission: June 15, 2015 Web Page: http://www.ecmlpkdd2015.org/submission/research-proceedings-track INDUSTRIAL, GOVERNMENTAL & NON-GOVERNMENTAL PROCEEDINGS TRACK **************************************************************************** ************************** The NEW industrial, governmental & non-governmental (NGO) proceedings track is independent and distinct from the Research Track. Submissions to this track should solve real-world problems and focus on engineering systems, applications, and challenges. Accepted papers will be published in the Lecture Notes in Artificial Intelligence (LNCS/LNAI) of Springer, after reviewing by the programme committee. Abstract Submission Deadline: March 26, 2015 Paper Submission Deadline: April 2, 2015 Paper Acceptance Notification: June 1, 2015 Paper Camera Ready Submission: June 15, 2015 Web Page: http://www.ecmlpkdd2015.org/submission/industrial-proceedings-track ***************************************************************** CALL FOR TUTORIAL AND WORKSHOP PROPOSALS ***************************************************************** TUTORIALS ************** The tutorials are intended to provide a comprehensive introduction to established or emerging research topics of interest for the machine learning and the data mining community. These topics include related research fields or applications. The ideal tutorial should attract a wide audience. It should be broad enough to provide a basic introduction to the chosen research area, but it should also cover the most important topics in depth. We welcome half day workshop proposals. Proposal Deadline: March 2, 2015 Proposal Acceptance Notification: March 23, 2015 Web Page: http://www.ecmlpkdd2015.org/submission/call-for-tutorials WORKSHOPS **************** The workshops will be on relevant and current topics in Machine Learning and Data Mining. The scope of the proposal should be consistent with the conference themes as described in the ECMLPKDD 2015 Call for Papers (http://www.ecmlpkdd2015.org/submission) Interdisciplinary workshops that bring together researchers and practitioners from different communities are especially welcome. We encourage workshops that bridge the gap between theoretical advances and important and/or innovative applications of machine learning and data mining. We welcome both full and half day workshop proposals. Proposal Deadline: March 2, 2015 Proposal Acceptance Notification: March 23, 2015 Workshop Websites and Call for Papers Online: March 27, 2015 Workshop Proceedings (Camera-ready): August 3, 2015 Web Page: http://www.ecmlpkdd2015.org/submission/call-for-workshop-proposals Hope to see you all soon in Porto, Portugal!!! The publicity chairs of the ECMLPKDD 2015, Carlos Abreu Ferreira Ricardo Campos --- Este e-mail foi verificado em termos de vírus pelo software antivírus Avast. http://www.avast.com

Jan. 12, 2015

Fwd: Summer CAMP@Bangalore: Short course in Computational Approaches to Memory and Plasticity

by U.S.Bhalla

We would like to announce CAMP@Bangalore 2015 from 27 June 2015 to 12 July 2015. Please see the course website at http://camp.ncbs.res.in/ CAMP @ Bangalore (Computational Approaches to Memory and Plasticity at NCBS, Bangalore) is a 16-day summer school on the theory and simulation of learning, memory and plasticity in the brain. The course will start with remedial tutorials on neuroscience / math / programming and then work upwards from sub-cellular electrical and chemical signaling in neurons, onward to micro-circuits and networks, all with an emphasis on learning, memory and plasticity. Students worldwide are encouraged to apply. Accommodation and food will be free for the selected students. There is no registration fee. Students are advised to obtain independent travel grants. Instructors include: Ad Aertsen (Bernstein Center, Freiburg) Dan Johnston (UT-Austin) Sumantra Chattarji (NCBS, Bangalore) Suhita Nadkarni (Indian Institute of Science Education and Research, Pune) Michael Hausser (University College, London) Stefano Fusi (Columbia University, New York) Raghav Rajan (Indian Institute of Science Education and Research, Pune) Eric DeWitt (Champalimaud, Lisbon) Mohan Raghavan (Indian Institute of Technology, Hyderabad) Course Organizers: Upinder Bhalla (NCBS, Bangalore) Arvind Kumar (KTH Stockholm) Rishikesh Narayanan (Indian Institute of Science, Bangalore) Thank you, Upi Bhalla

Jan. 12, 2015

Postdoctoral positions in computational neuroscience at Wright State University

by Sherif Elbasiouny

*_Postdoctoral positions in computational neuroscience_* Two postdoctoral Fellow positions in Computational Neuroscience are available immediately in the laboratory of Dr. Sherif Elbasiouny (/T//he Neuro Engineering, Rehabilitation, and Degeneration Lab/) at the Department of Neuroscience, Cell Biology, and Physiology, Wright State University, Dayton, Ohio. The research work involves the development of anatomically detailed computational models of neurons in the spinal cord to investigate the basis of their neuronal excitability. Dr. Elbasiouny’s lab is currently investigating the ionic mechanisms underlying motoneuron function for neurorehabilitation applications and in neurodegenerative diseases, such as amyotrophic lateral sclerosis. *Required*: The successful applicant should have: 1) a PhD in computational neuroscience, engineering, computer science, mathematics, or related areas, 2) previous research experience in computational neuroscience. *Desired*: Although not mandatory, it is it highly desirable if the applicant has: 1) experience in the development of anatomically detailed computational models of single cells, and 2) experience in using the NEURON simulation environment. The positions are available immediately. The salary package is competitive and will be based upon the applicant’s experience. Funding for these positions is available for couple of years with possible extension upon research progress. Qualified applicants should email Dr. Elbasiouny at sherif.elbasiouny(a)wright.edu <mailto:sherif.elbasiouny@wright.edu>with the following: 1) CV including a list of publications, 2) a brief statement of research interests, and 3) three recommendation letters emailed directly by the references to Dr. Elbasiouny.For full consideration, please apply before March 1, 2015. Wright State University is an Equal Opportunity/Affirmative Action Employer. It is the university's policy to prohibit discrimination and provide equal opportunity to all employees and applicants for employment, without regard to their race, sex (including gender identity/expression), color, religion, ancestry, national origin, age, disability, veteran status, military or sexual orientation. Regards, Sherif Elbasiouny -- Sherif M. Elbasiouny, PhD, PE Assistant Professor Departments of Neuroscience, Cell Biology, & Physiology (NCBP) and Biomedical, Industrial & Human Factors Engineering (BIE) Wright State University 143 Biological Sciences II (mail) 243 Biological Sciences II (lab) 251B Biological Sciences II (office) 3640 Col Glenn Hwy Dayton OH 45435 Office Phone: 937-775-2492 https://www.med.wright.edu/ncbp/elbasiouny

Jan. 12, 2015

MOOSE 3.0.1 "Gulab Jamun"

by U.S.Bhalla

We announce the release of MOOSE 3.0.1 "Gulab Jamun" The Gulab Jamun release is the second in series 3 of MOOSE releases. Websites: http://moose.ncbs.res.in, http://sourceforge.net/projects/moose MOOSE is the Multiscale Object-Oriented Simulation Environment. It is designed to simulate neural systems ranging from subcellular components and biochemical reactions to complex models of single neurons, circuits, and large networks. MOOSE can operate at many levels of detail, from stochastic chemical computations, to multicompartment single-neuron models, to spiking neuron network models. MOOSE 3.0.1 is an evolutionary increment over 3.0.0:: - The GUI moves into beta with substantially more kinetic modeling features, as well as an early release of the neuronal modeling interface in the GUI. - Multiscale modeling updates including better cross-compartment reaction support, including stochastic reactions in subsets of the compartments. - General robustness and error reporting improvements for solvers. - HSolver updates to handle NMDA and derived classes of channels with Ca currents. - Better release packaging About the name: Gulab Jamun is a classic North Indian sweet consisting of deep brown spheres involving milk solids, cardamom and other spices, floating in a rich syrup. Best wishes and Happy New Year, The MOOSE team: Harsha Rani, Aviral Goel, Dilawar Singh, Aditya Gilra, Subhasis Ray, Upi Bhalla

Jan. 11, 2015

tenure-track faculty position - Assistant Professor - Systems biology and Alzheimer's disease

by Christopher Gaiteri

tenure-track faculty position - Assistant Professor - Systems biology and Alzheimer's disease Make creative analytic contributions to understanding Alzheimer's disease at Rush University, a major center for aging and age-related disease research, located in Chicago, IL. Our Alzheimer's center offers an integrated clinical and research environment that has a constantly growing collection of multi-omic data on hundreds of individuals, at various ages and levels of cognitive function. These omics data can be studied against a backdrop of hundreds of cognitive and behavioral phenotypes that are tracked longitudinally in these subjects and thousands of others. We are searching for a tenure-track assistant professor to construct and contribute to systems biology models that enhance our understanding of age-related dysfunction and Alzheimer's disease. These models should lead to actionable, molecular or tissue-level predictions, which can be tested in experimental systems. Requirements: MD/PhD or PhD in Neuroscience, Mathematics, Systems Biology or related fields Experience with omics and big data, including any or ideally all of: structural and functional neuroimaging, proteomics, RNAseq, genetics and methylation Expertise in R, matlab and python Interests in network-based analysis of disease-related data Preference for: Publication history in graph theory, systems biology and neuroscience Familiarity with complex disease neurobiology Experience in design and implementation of large-scale cellular simulations Java, perl, parallel programming and batch execution systems Experience designing or performing high-throughput experiments Post-doctoral training The ideal candidate is free to develop an independent research program around aging, age-related disease and/or systems biology analysis. He/she will also collaborate with current faculty and develop and maintain external funding. Salary commensurate with relevant experience and skills. Instructions for applying: Send your CV to gaiteri(a)gmail.com AND ALSO include a paragraph on one of the following topics: 1. How will you identify key pathological mechanisms in a multi-omic disease setting, potentially in collaboration with experimental labs? 2. How will you develop multi-modal or multi-scale models of complex brain diseases? 3. What is the most under-appreciated statistical or mathematical technique that you expect could lead to insights in brain diseases?

Jan. 11, 2015

summer undergrad program in computational neuroscience

by Dave Touretzky

Carnegie Mellon - University of Pittsburgh Joint Summer Undergraduate Program in Computational Neuroscience Undergraduates interested in receiving research training in computational neuroscience are encouraged to apply to an NIH-sponsored summer program at the Center for the Neural Basis of Cognition in Pittsburgh. The Center for the Neural Basis of Cognition is a joint interdisciplinary program of Carnegie Mellon University and the University of Pittsburgh. The 2015 program will most likely run from May 26 through July 31, 2015 (pending confirmation on dormitory availability). The final deadline for application is Feb 16, 2015. All participants must be United States citizens or permanent residents, must be enrolled at a 4-year accredited institution, and must be in their sophomore or junior year at the time of application. Any undergraduate may apply, but we are especially interested in attracting students with strong quantitative backgrounds with some experience in calculus, statistics and/or computer programming. Experience in neuroscience is not required. Students from groups underrepresented in the sciences are encouraged to apply. The core of the program is the opportunity to carry out an individual mentored research project working closely with a faculty mentor. Other aspects of the scientific program include: 12 faculty lectures on computational neuroscience at the beginning, followed by student presentations and discussion of articles from the scientific literature, presentations on career options and scientific ethics, and a concluding symposium in which students present their research. Application form is available at: http://www.cnbc.cmu.edu/summercompneuro Application can be returned via email or regular mail (see addresses below). In addition to the application, the following items are required for evaluation: * A brief (one page) essay about your interest and experience in neural computation. * Official transcript from the institution you are attending * Two letters from professional references. You should contact your recommenders and ask them to mail or email a letter directly to us. * SAT/ACT scores (do NOT have to be official; photocopies are acceptable) Documents should be mailed to: Computational Neuroscience Summer Program Center for the Neural Basis of Cognition Carnegie Mellon University 4400 Fifth Avenue Suite 115 Pittsburgh, PA 15213-2617 CNBC-summer-UG(a)andrew.cmu.edu Brief list of CMU-Pitt CNBC faculty working in computational neuroscience: John Anderson (Carnegie Mellon, Psychology) Aaron Batista (University of Pittsburgh, Bioengineering) Marlene Behrmann (Carnegie Mellon, Psychology) Marlene Cohen (University of Pittsburgh, Neuroscience) Carol Colby (University of Pittsburgh, Neuroscience) Steve Chase (Carnegie Mellon, ECE/Biomedical Engineering) Brent Doiron (University of Pittsburgh, Mathematics) William Eddy (Carnegie Mellon, Statistics) Bard Ermentrout (University of Pittsburgh, Mathematics) Julie Fiez (University of Pittsburgh, Psychology) Raj Gandhi (University of Pittsburgh, Department of Bioengineering) John Horn (University of Pittsburgh, Neurobiology) Robert Kass (Carnegie Mellon, Statistics) Charles Kemp (Carnegie Mellon, Psychology) Sandra Kuhlman (Carnegie Mellon, Biology) Tai Sing Lee (Carnegie Mellon, Computer Science) Tom Mitchell (Carnegie Mellon, Machine Learning) Carl Olson (Carnegie Mellon, Neural Basis of Cognition) Anne-Marie Oswald (University of Pittsburgh, Neuroscience) Monica Perez (University of Pittsburgh, Neurobiology & Rehabilitation) David Plaut (Carnegie Mellon, Psychology) Lynne Reder (Carnegie Mellon, Psychology) Erik Reichle (University of Pittsburgh, Psychology) Johnathan Rubin (University of Pittsburgh, Mathematics) Walt Schneider (University of Pittsburgh, Psychology) Andrew Schwartz (University of Pittsburgh, Bioengineering) Daniel Simons (University of Pittsburgh, Neurobiology) Matthew Smith (University of Pittsburgh, Ophthalmology) Peter Strick (University of Pittsburgh, Psychiatry) Michael Tarr (Carnegie Mellon, Psychology) Dave Touretzky (Carnegie Mellon, Computer Science) Robert Turner (University of Pittsburgh, Neurobiology) Nathan Urban (Carnegie Mellon, Biology) Valerie Ventura (Carnegie Mellon, Statistics) Timothy Verstynen (Carnegie Mellon, Psychology) Douglas Weber (University of Pittsburgh, Physical medicine and Rehabilitation) Byron Yu (Carnegie Mellon, ECE/Biomedical Engineering) A full list can be found at: http://www.cnbc.cmu.edu/

Jan. 10, 2015

Post doc/engineer position in direct brain control of muscle stimulators

by Dawn Taylor

We currently have an opening for a postdoc or engineer for the vA-funded neuroprosthetics study described below. If interested, please send a CV to Dr. Dawn Taylor at dxt42(a)case.edu. The long-term goal of this project is to enable paralyzed individuals to use their brain signals to control their upper limb via implanted muscle stimulators. Most labs working on brain-controlled neuroprosthetics decode intended limb kinematics (e.g. velocity, joint angles, etc.) from the recorded brain signals. However, that approach still requires converting those kinematic commands into the appropriate stimulation patterns required to generate the desired limb motion. That conversion process has not been resolved for the upper limb due to the limb's complex dynamical nature and the fact that the limb is subject to unknown external forces during use. We bypass this obstacle by retraining the brain to control muscle stimulators directly. We have come up with some novel, but clinically feasible ways of mapping neural signals directly to muscle stimulators. Our methods can enable the user to have good control over both limb motion and stiffness. To demonstrate and refine our methods, we are training monkeys to control the movements of a realistic musculoskeletal model of a paralyzed limb activated via implanted muscle stimulators. The paralyzed limb simulator (developed by the lab of Robert Krisch) provides real-time visual feedback to the animal of the limb motion that would result from stimulating the paralyzed muscles based on the animal's neural signals decoded in real time. The use of this real-time paralyzed arm simulator allows us to test and refine our process of brain-controlled muscle stimulation in monkeys without actually having to paralyze any animals. -- Dawn M. Taylor, Ph.D. Assistant Professor of Neuroscience, Cleveland Clinic Researcher Scientist, Cleveland VA Medical Center, Functional Electrical Stimulation Center Assistant Professor of Biomedical Engineering & of Molecular Medicine, Case Western Reserve University The Cleveland Clinic Lerner Research Institute 9500 Euclid Ave. / NC30 Cleveland, OH 44195 email: dxt42(a)case.edu or taylord8(a)ccf.org Phone: (216) 636-0140 Fax: (216) 778-4259

Jan. 9, 2015

[jobs] Post Doc position in Humanoid Robotics Research

by Patricia Hazel Shaw [phs]

We Apologise for multiple cross postings ========================================================================= Post-Doctoral Research Associate vacancy Three-year fixed-term Robotics Research Group, Department of Computer Science, Aberystwyth University, Wales, UK £32,277 – £37,384 Applicants are invited to join the Robotics Laboratory for a new project (entitled Developmental Algorithms for Robotics”). The project is focusing on developmental robotic learning based on an iCub humanoid robot. This is a three year EPSRC funded project running at Aberystwyth University, with the support of an International Scientific Advisory Board containing leading developmental psychologists. We wish to appoint two Post-Doctoral Research Associates who will develop and implement models based on the psychological literature, and conduct experiments on our iCub humanoid robot. One successful applicant will be responsible for understanding psychological literature and generating models based on the literature, whilst the other successful applicant will be responsible for software implementation and experimentation. This invitation is for the Scientific Modelling post, details below. For informal enquiries contact Patricia Shaw: phs(a)aber.ac.uk +44 (0)1970-622432 Ref: IMPACS.14.22  Closing Date: 5 February 2015  Interview Date: Week commencing 16 February 2015 For information and application forms please go to www.aber.ac.uk/en/hr/jobs/vacancies-external/ ========================================================================= The Project: “Developmental Algorithms for Robotics” The project aims to investigate a mechanism for robots, building on top of basic spatial sensorimotor competencies, that drives the autonomous development of new behaviours and self learning about novel events for which they have no prior experience. This will involve (1) expanding existing motor-babbling activity into object play behaviour, (2) formulating play behaviour as a viable mechanism for autonomous learning about unknown environments, (3) establishing an extended schema concept as a mechanism for integrating memory, experience generalization and action generation, (4) exploring action perception from the agent's experience, and (5) close monitoring of the work with psychological data and expert psychologists. The project will closely follow current knowledge on infant development and aim to reproduce behaviour as reported in the psychological literature. In particular the focus will be on three areas of core knowledge: (1) Object understanding, (2) Interaction with animate objects, and (3) Tool use. The work will be supported by collaboration with leading developmental psychologists on the project scientific advisory panel. This will produce models and mechanisms that can be implemented and tested experimentally against psychological benchmarks. The models will be validated with challenging demonstrators based on a single humanoid robotic platform (iCub). As a main outcome, the project will advance the understanding and application of intrinsic motivations in autonomous learning systems and robots. This overall goal will be achieved with the support of an International Scientific Advisory Board, consists of: Kevin O'Regan, Jacqueline Fagard, Merideth Gattis, David Whitebread, Giorgio Metta, QinetiQ and Lego. The Appointment (PDRA) – Scientific modeller Applications are invited for the post of Post-Doctoral Research Associate on this project at Aberystwyth University. The successful applicant will have a relevant background, experience of research (as demonstrated by PhD and/or publications), and proven abilities in mathematical/scientific modelling. The main tasks will involve analysing the psychological literature to develop models and experiments for testing on an iCub humanoid robot. This will be supported by another PDRA, and PhD student, who will have special responsibility for implementing the models whilst maintaining and supporting the robot. Other tasks include writing scientific documents and papers, documenting experiments and writing reports, supervising a PhD student, responsibility for day-to-day management of project needs, and collaborating with the scientific advisory panel and other researchers. Regular European travel will be involved. This post is available on a three-year fixed-term contract, funded by the EPSRC. Salary will be on the IA scale for Research Staff in the range: £32,277 - £37,384 (depending upon qualifications and experience). We expect to appoint for a start date in the first quarter of 2015.

Jan. 9, 2015

Postdoctoral and PhD positions, Personal Robotics lab, Imperial College London

by Demiris, Yiannis

Dear colleagues, two research positions (either at the postdoctoral or the PhD level) in machine learning for user-modelling and human-robot Interaction are available at the Personal Robotics Laboratory of the Department of Electrical and Electronic Engineering at Imperial College London. Successful applicants will work under the supervision of Dr Yiannis Demiris (www.demiris.info) in the context of the new EU H2020 project PAL (Personal Assistants for healthy Lifestyle, 2015-2019), which aims to develop personalised robotic systems and avatars to assist diabetic (T1DM) children and their caregivers. The PAL positions are available from 1st of March 2015 until the end of the project at the end of Feb 2019 subject to renewal. Additional PhD positions through the A*STAR-Imperial partnership programme (project “Robot Learning by Demonstration for Heterogeneous Bimanual Collaboration Tasks”), the Chinese Scholarship Council programme, and the Imperial PhD scholarship scheme, among others, are also available. For all positions, applicants should have an excellent background in mathematics, machine learning and software engineering, and should be committed to applying their research to real systems interacting with people in challenging environments. The positions offer an excellent working environment in one of the world's top research universities, in one of the most exciting cities in the world. The Department of Electrical and Electrical Engineering at Imperial was ranked as the top EE department in the UK in the recent REF 2014, while its Personal Robotics Laboratory offers an energetic, friendly intellectual environment with state of the art facilities http://www.imperial.ac.uk/PersonalRobotics For further information and links to application material: http://www.imperial.ac.uk/personalrobotics/join_us With best wishes, Yiannis ---- Dr Yiannis Demiris, FIET, FBCS, FRSS Reader (Associate Professor) in Personal Robotics, Department of Electrical and Electronic Engineering, Rm 1014, Imperial College London, South Kensington Campus, Exhibition Road, London, SW7 2BT, UK Tel: +44-(0)2075946300, FaxL +44-(0)2075946274 Personal webpage: http://www.iis.ee.ic.ac.uk/yiannis Laboratory webpage: http://www.imperial.ac.uk/PersonalRobotics - Visiting Scholar, Harvard University School of Engineering and Applied Sciences (SEAS), Maxwell Dworkin Building MD-336, 33 Oxford Street, Cambridge, MA 02138, USA

Jan. 8, 2015

Research Topic "Metastable dynamics of neural ensembles"

by Emili Balaguer-Ballester

Research Topic "Metastable dynamics of neural ensembles" http://journal.frontiersin.org/ResearchTopic/1955 A classical view on neural computation is that it can be characterized in terms of deterministic convergence to fixed-point-type attractor states (representing, e.g., memory patterns in Hopfield 1982) or limit-cycle-like sequential transitions among states (representing e.g. motor or syntactical sequences). Is this still a valid model of how brain dynamics implements cognition? The idea that neuro-computational dynamics is more or less deterministically driven by convergence to simple attractor states has recently been challenged both empirically and by computational work. In this Research Topic of Frontiers in Systems Neuroscience we welcome experimental studies and modelling contributions addressing the question of stable vs. transient neural population dynamics, and the potential role of noise and trial-to trial variability in neural computation. Major topics are, but are not restricted to: -Attracting and meta-stable dynamics of neural ensembles, both from empirical and computational modelling perspectives. -Coding by non-stationary and transient states in neural recordings -Spontaneous cortical activity dynamics -Metastable dynamics during cognitive processing -Oscillatory emergent patterns and propagation of waves in an excitable network -Trial-to-trial variability Please see more information in http://journal.frontiersin.org/ResearchTopic/1955. Deadline is on the 31st of March. BU is a Disability Two Ticks Employer and has signed up to the Mindful Employer charter. Information about the accessibility of University buildings can be found on the BU DisabledGo webpages This email is intended only for the person to whom it is addressed and may contain confidential information. If you have received this email in error, please notify the sender and delete this email, which must not be copied, distributed or disclosed to any other person. Any views or opinions presented are solely those of the author and do not necessarily represent those of Bournemouth University or its subsidiary companies. Nor can any contract be formed on behalf of the University or its subsidiary companies via email.

Jan. 6, 2015

Special Session on Transfer Learning - International Work Conference on Artificial Neural Networks, 10-12 June, 2015

by Jorge M. Santos

Please consider to contribute to the Special Session on Transfer Learning International Work Conference on Artificial Neural Networks, 10-12 June, 2015 - http://iwann.ugr.es/2015 Transfer Learning (TL) aims to transfer knowledge acquired in one problem, the source problem, onto another problem, the target problem, dispensing with the bottom-up construction of the target model. The TL approach has gained significant interest in the Machine Learning (ML) community since it paves the way to devise intelligent learning models that can easily be tailored to many different domains of applicability. The following aspects have recently contributed to the emergence of TL: Generalization Theory: TL often produces algorithms with good generalization capability for different problems; Efficient TL algorithms: TL provides learning models that can be applied with far less computational effort than standard ML methods; Unlabeled data: TL can be advantageous since unlabeled data can have severe implications in some fields of research, such as in the biomedical field. Some examples of topics for this special session: Big Data with Deep Neural Networks; Generalization Bounds; Domain Adaptation or Covariate Shift; Algorithms for TL; New advancements in TL; Real-world applications. Deadline: 6 February 2015 Organizers Luís M. Silva, Dep. of Mathematics, University of Aveiro, Portugal - lmas(a)ua.pt Jorge M. Santos, Dep. of Mathematics, School of Engineering, Polytechnic of Porto, Portugal - jms(a)isep.ipp.pt

Jan. 6, 2015

CFP (Deadline, 1 Feb 2015): IEEE Computational Intelligence Magazine (CIM) Special Issue: “Computational Intelligence for Changing Environments"

by Dr Amir Hussain

CALL FOR PAPERS (Deadline: 1 Feb 2015) - With advance apologies for any cross postings! IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE (CIM) (http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=10207) SPECIAL ISSUE (Nov 2015) ON "Computational Intelligence for Changing Environments" (http://www.cs.stir.ac.uk/~ahu/IEEE-CIM-CICE2015.pdf) AIMS AND SCOPE: Over the past decade or so, computational intelligence techniques have been highly successful for solving big data challenges in changing environments. In particular, there has been growing interest in so called biologically inspired learning (BIL), which refers to a wide range of learning techniques, motivated by biology, that try to mimic specific biological functions or behaviors. Examples include the hierarchy of the brain neocortex and neural circuits, which have resulted in biologically-inspired features for encoding, deep neural networks for classification, and spiking neural networks for general modelling. To ensure that these models are generalizable to unseen data, it is common to assume that the training and test data are independently sampled from an identical distribution, known as the sample i.i.d. assumption. In dynamic and non- stationary environments, the distribution of data changes over time, resulting in the phenomenon of ‘concept drift’ (also known as population drift or concept shift), which is a generalization of covariance shift in statistics. Over the last five years, transfer learning and multitask learning have been used to tackle this problem. Fundamental analyses using probably approximately correct (PAC) and Rademacher complexity frameworks have explained why appropriate incorporation of context and concept drift can improve generalizability in changing environments. It is possible to use human-level processing power to tackle concept drift in changing environments. Concept drift is a real-world problem, usually associated with online and concept learning, where the relationships between input data and target variables dynamically change over time. Traditional learning schemes do not adequately address this issue, either because they are offline or because they avoid dynamic learning. However, BIL seems to possess properties that would be helpful for solving concept drift problems in changing environments. Intuitively, the human capacity to deal with concept drift is innate to cognitive processes, and the learning problems susceptible to concept drift seem to share some of the dynamic demands placed on plastic neural areas in the brain. Using improved biological models in neural networks can provide insight into cognitive computational phenomena. However, a main outstanding issue in using computational intelligence for changing environments and domain adaptation is how to build complex networks, or how networks should be connected to the features, samples, and distribution drifts. Manual design and building of these networks are beyond current human capabilities. Recently, computational intelligence methods has been used to address concept drift in changing environments, with promising results. A Hebbian learning model has been used to handle random, as well as correlated, concept drift. Neural networks have been used for concept drift detection, and the influence of latent variables on concept drift in a neural network has been studied. In another study, a timing-dependent synapse model has been applied to concept drift. These works mainly apply biologically-plausible computational models to concept drift problems. Although these results are still in their infancy, they open up new possibilities to achieve brain-like intelligence for solving concept drift problems in changing environments. Taking the current state of research in computational intelligence for changing environments into account, the objective of this special issue is to collate this research to help unify the concepts and terminology of computational intelligence in changing environments, and to survey state-of-the-art computational intelligence methodologies and the key techniques investigated to date. Therefore, this special issue invites submissions on the most recent developments in computational intelligence for changing environments, algorithms and architectures, theoretical foundations, and representations, & their application to real-world problems. We also welcome timely surveys & review papers. TOPICS OF INTEREST include (but are not limited to): • Computational intelligence methodologies and implementation for changing environments •Transfer learning, Multitask learning, Domain adaption •Incremental Learning architectures, Unsupervised and semi-supervised learning architectures •Incremental Knowledge augmentation, Representation learning and disentangling •Incremental Adaptive Neuro-fuzzy systems •Incremental and single-pass data mining •Incremental Neural Clustering & Regression •Incremental Adaptive decision systems •Incremental Feature selection and reduction •Incremental Constructive Learning •Novelty detection in Incremental learning SUBMISSION PROCESS The maximum length for the manuscript is typically 25 pages in single column format with double-spacing, including figures and references. Authors should specify in the first page of their manuscripts the corresponding author’s contact and up to 5 keywords. Submission should be made via: https://easychair.org/conferences/?conf=ieeecimcdbil2015 IMPORTANT (REVISED) DATES (for November 2015 Issue) 1st Feb, 2015: Submission of Manuscripts 15th April, 2015: Notification of Review Results 15th May, 2015: Submission of Revised Manuscripts 15th June, 2015: Submission of Final Manuscripts GUEST EDITORS Professor Amir Hussain, University of Stirling, Stirling FK9 4LA, Scotland, UK Email: ahu(a)cs.stir.ac.uk http://cs.stir.ac.uk/~ahu/ Professor Dacheng Tao, University of Technology, Sydney, 235 Jones Street, Ultimo, NSW 2007, Australia Email: dacheng.tao(a)uts.edu.au Professor Jonathan Wu University of Windsor, 401 Sunset Avenue, Windsor, ON, Canada Email: jwu(a)uwindsor.ca Professor Dongbin Zhao Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China E-mail: dongbin.zhao(a)gmail.com ----- A PDF copy of the CFP is attached with this email for forwarding to interested colleagues. It is also available for download from: http://www.cs.stir.ac.uk/~ahu/IEEE-CIM-CICE2015.pdf For more information on the IEEE CIM, see: http://cis.ieee.org/ieee-computational-intelligence-magazine.html -- The University of Stirling has been ranked in the top 12 of UK universities for graduate employment*. 94% of our 2012 graduates were in work and/or further study within six months of graduation. *The Telegraph The University of Stirling is a charity registered in Scotland, number SC 011159.

Jan. 6, 2015

MBL Methods in Computational Neuroscience Course 2015: applications due March 5

by Mark Goldman

Applications are open for the Methods in Computational Neuroscience course at the Marine Biology Laboratory in Woods Hole, MA. The course will run from July 29 to August 26, 2014, and the online application form can be found at: http://ws2.mbl.edu/studentapp/studentapp.asp?CourseID=MCN. The course application deadline is March 5. The course covers a range of topics in computational neuroscience including neuronal biophysics, neural coding & information processing, circuit dynamics, learning & memory, motor control, and cognitive processing & disease. In addition, numerous tutorials and problem sets will cover a broad range of computational and mathematical modeling methods. The course strongly emphasizes the collaboration between theory and experiment in solving neuroscience problems, and lectures will be given by a mixture of theorists and experimentalists. The final weeks of the course are primarily reserved for development and work on projects that students design in collaboration with the resident faculty. Further information can be found on the MCN website: http://www.mbl.edu/mcn/ 2015 Course Directors: Michale Fee, MIT Mark Goldman, UC Davis 2015 Confirmed Faculty: Larry Abbott, Columbia University Steve Baccus, Stanford University William Bialek, Princeton University Dmitri Chklovskii, HHMI Janelia Farm Peter Dayan, University College London Bard Ermentrout, University of Pittsburgh Adrienne Fairhall, University of Washington Ila Fiete, UT Austin Loren Frank, UCSF Michael Frank, Brown University Surya Ganguli, Stanford University John Huguenard, Stanford University David Kleinfeld, UC San Diego Nancy Kopell, Boston University John Lisman, Brandeis University Eve Marder, Brandeis University Bartlett Mel, University of Southern California Jonathan Pillow, Princeton University Terry Sejnowski, Salk Institute Michael Shadlen, Columbia University Josh Shaevitz, Princeton University Sara Solla, Northwestern University Haim Sompolinsky, Hebrew University David Tank, Princeton University Josh Tenenbaum, MIT Xiao-Jing Wang, NYU Daniel Wolpert, Cambridge University Ryohei Yasuda, Duke University

Jan. 6, 2015

CNS*2015 Call for Workshop Proposals - Deadline Approaching

by Farzan Nadim

CNS 2015 Prague July 1823, 2015: Call for Workshops DEADLINE APPROACHING We are requesting proposals for workshops from the international community of computational neuroscientists. Proposals from all levels of faculty as well as advanced postdoctoral fellows are welcome. This is a great opportunity to organize a small meeting with just a few of the headaches of actually organizing it. Workshop proposal submission instructions for CNS 2015 The last two days (July 22-23) of the 24th annual CNS meeting will be devoted to workshops, in which computationally related neuroscience topics can be presented and discussed. Workshops can be anywhere between one half to two days in duration. Usually several speakers are invited to introduce a unifying theme, but ample time for discussion should also be planned. Submit workshop proposals to: workshops(a)cnsorg.org. The Past Meetings page gives access to archives of workshops held at previous CNS meetings. The proposal should be submitted as a Word or pdf file and MUST include the following sections: 1. Workshop Title 2. Organizers (list primary organizer first; include affiliations and emails) 3. One or two days (2 sessions per day) 4. Number of expected speakers 5. Brief Description (~150 words; if possible, say why this is significant or timely) 6. Speakers (mark expected or confirmed) Also please note the following rules which were approved by the OCNS Board on July 15, 2013: Each individual can be the organizer or co-organizer on only one workshop. The number of confirmed speakers is a criterion for accepting the proposal. Overlapping proposals may be asked to be combined. If the organizers do not wish to combine the proposals, only one of the proposals may be accepted. Workshops submitted before January 15, 2015 will be given priority in acceptance. Workshop proposals arriving after January 15, 2015 will be evaluated based on remaining space for additional workshops. No further workshop acceptances will be anticipated after May 15, 2015. Registration: Workshop registration will occur through the OCNS registration web site for CNS 2015. All workshop participants, including speakers must register. Each workshop is eligible to receive registration waivers for 2 speakers. Travel awards: a limited number of Travel Awards will be available for postdoctoral researchers to lead and be included as speakers. Exceptionally starting assistant professors may also be given consideration. These Travel Awards will be variable depending on distance traveled. Please indicate which speakers you would like to be considered for this mechanism but take into account that there will be less travel awards than workshops. Springer Computational Neuroscience Book Series: Some of the workshops may be published by the Springer Series in Computational Neuroscience. Workshop organizers interested in this mechanism should submit a book proposal to Simina Calin (Simina.calin(a)springer.com) and indicate in the workshop proposal their interest in publishing a book. Logistics: Rooms, AV equipment, snacks and beverages during breaks will be provided by OCNS to the workshop organizers.

Jan. 5, 2015