From akira-i at brest-state-tech-univ.org Tue Oct 1 09:38:19 2013 From: akira-i at brest-state-tech-univ.org (Akira Imada) Date: Tue, 1 Oct 2013 17:38:19 +0400 Subject: Connectionists: Visit & join us at our conference in Belarus: Preliminary CFP - 8 months to go Message-ID: Dear Connectionists, We are organizing 7th International Conference on Neural Network and Artificial Intelligence (ICNNAI-20104) on 3-6 June 2014 in Brest, Belarus. We would highly appreciate it if you mark your calendar and plan to attend. Now we call for special session proposal (Hopefully by the end of January 2014). And we want to encourage you to submit a high quality unique original work. Submission due to regular session is to be 21 March 2014. For more in detail, please visit at http://neuro.bstu.by/icnnai-2014.html Belarus is still a land of fairly well-kept secret. In this lovely wonder land, with luck, you'll find something that could not be discovered elsewhere. Sorry if you receive this e-mail more than once. With the warmest regards. Akira Imada, Professor email: akira-i at brest-state-tech-univ.org Dept. Intelligent Information Technology Brest State Technical University Moskowskaja 267, Brest, 224017 Belarus -------------- next part -------------- An HTML attachment was scrubbed... URL: From ilya.nemenman at emory.edu Tue Oct 1 17:00:20 2013 From: ilya.nemenman at emory.edu (Nemenman, Ilya) Date: Tue, 1 Oct 2013 21:00:20 +0000 Subject: Connectionists: Faculty position in theoretical biophysics, Emory University, Department of Physics Message-ID: <2AF34C2A-278D-483E-8CB8-0BD394E9F864@emory.edu> Dear Colleagues, I am writing to bring to your attention an opening for a Faculty in Theoretical or Computational Biophysics in the Department of Physics at Emory. I would appreciate it if you could bring this to the attention of suitable candidates and share the information with colleagues or research groups who might know of qualified candidates. The position is at the assistant professor level, but senior appointments may be considered in exceptional circumstances. We are particularly interested in applicants who will benefit from and complement the ongoing research strengths at Emory in cellular and molecular biophysics, computational neuroscience, and population biology. The ad has appeared in various online and print resources, but detailed information about the position and our Department can be found at: http://www.physics.emory.edu/news/search-bpt-2013.html. We will begin reviewing the applications on December 1, 2013. Thank you in advance for your help. Please feel free to let me know if you have any questions or suggestions. With best regards, Ilya Nemenman ******************** Faculty Position in Theoretical or Computational Biophysics The Department of Physics at Emory University invites applications for a tenure-track faculty position in theoretical or computational biophysics, to begin in September 2014. The position is at the assistant professor level, but senior appointments may be considered in exceptional circumstances. We are particularly interested in applicants who will benefit from and complement the existing strengths in cellular and molecular biophysics, computational neuroscience, and population biology in the Physics and other Departments at Emory. Applicants must have a PhD in physics or a closely related field and a proven record of research accomplishment. The successful candidate will be expected to establish an independent, internationally recognized and externally funded research program, and demonstrate excellence in teaching at both undergraduate and graduate levels. To apply, submit a curriculum vitae, a research plan, and a teaching statement to search-biophysics-2013 at physics.emory.edu. Applicants should arrange for at least three letters of recommendation to be sent to the same address. To ensure full consideration, complete applications, including recommendation letters, should be received by December 1, 2013. Emory University is an Affirmative Action/Equal Opportunity employer. Women and members of underrepresented groups are particularly encouraged to apply. ________________________________ This e-mail message (including any attachments) is for the sole use of the intended recipient(s) and may contain confidential and privileged information. If the reader of this message is not the intended recipient, you are hereby notified that any dissemination, distribution or copying of this message (including any attachments) is strictly prohibited. If you have received this message in error, please contact the sender by reply e-mail message and destroy all copies of the original message (including attachments). -------------- next part -------------- An HTML attachment was scrubbed... URL: From jaakko.peltonen at aalto.fi Tue Oct 1 06:25:41 2013 From: jaakko.peltonen at aalto.fi (Peltonen Jaakko) Date: Tue, 1 Oct 2013 10:25:41 +0000 Subject: Connectionists: Call for Participation: MLSS Machine Learning Summer School, Reykjavik, April 25 - May 4, 2014 Message-ID: <34678FBC663BDC47BAD0B96BB3FF28580120D81C2A@EXMDB01.org.aalto.fi> ============================================================================== MLSS Machine Learning Summer School April 25 - May 4, 2014, Reykjavik, Iceland http://mlss2014.hiit.fi Colocated with AISTATS 2014, the Seventeenth International Conference on Artificial Intelligence and Statistics ============================================================================== The Machine Learning Summer School will take place at Reykjavik University in Reykjavik, Iceland, from April 25 to May 4, 2014. The field of machine learning is at the intersection of computer science, statistics, mathematics, and optimization. The Machine Learning Summer School (MLSS) is a great venue for graduate students, researchers, and professionals to learn about fundamental and advanced methods of machine learning, data analysis, and inference, from theory to practice. The MLSS in Reykjavik features an exciting program with talks from leading experts in the field. MLSS is colocated with the high-profile international conference AISTATS 2014, the Seventeenth International Conference on Artificial Intelligence and Statistics. The MLSS also features a poster session for students, jointly with a poster session of AISTATS. Limited travel support for students is available, see the website for details. Key Information: ---------------- URL: http://mlss2014.hiit.fi Dates: April 25 - May 4, 2014 Location: Reykjavik, Iceland Email contact: mlss at iiim.is Application system opens: 15 October Student application deadline: 15 November Admission notification by: 31 December Confirmed Speakers: ------------------- Yoshua Bengio, Universite de Montreal http://www.iro.umontreal.ca/~bengioy/yoshua_en/index.html Michael Betancourt, University College London http://www.homepages.ucl.ac.uk/~ucakmjb/ Emily B. Fox, University of Washington http://www.stat.washington.edu/~ebfox/ Mark Girolami, University College London http://www.ucl.ac.uk/statistics/people/markgirolami Thore Graepel, Microsoft Research Cambridge http://research.microsoft.com/en-us/people/thoreg/ Ralf Herbrich, Amazon http://www.herbrich.me/ Neil Lawrence, University of Sheffield http://staffwww.dcs.shef.ac.uk/people/N.Lawrence/ Iain Murray, University of Edinburgh http://homepages.inf.ed.ac.uk/imurray2/ David Silver, University College London http://www0.cs.ucl.ac.uk/staff/d.silver/web/Home.html Follow the website for more speakers! Joint Tutorial Speakers with AISTATS: ------------------------------------- Roderick Murray-Smith, University of Glasgow http://www.dcs.gla.ac.uk/~rod/ Talk title TBA Christian P. Robert, Ceremade - Universite Paris-Dauphine https://www.ceremade.dauphine.fr/~xian/ Talk title: Approximate Bayesian computation (ABC), methodology and applications Havard Rue, Norwegian University of Science and Technology http://www.ntnu.edu/employees/havard.rue Talk title: Bayesian computing with INLA Posters: ------------------ Bring along a poster! MLSS is an excellent opportunity to showcase your work. Note that it is possible to present posters alread on April 24, the day before MLSS starts: there will be a joint poster session with AISTATS on April 24, and the student poster session continues the following day. Social Events: -------------- In addition to the scientific program, a lively social program is available, with events such as a joint poster session/reception with AISTATS, an evening out, a hiking trip/walking tour, and other informal gatherings, pub excursions etc. Some events may involve a small fee. Colocated Events: ----------------- MLSS is colocated with the high-profile international conference AISTATS 2014, the Seventeenth International Conference on Artificial Intelligence and Statistics. There will be a joint poster session with AISTATS on April 24, and the student poster session continues the following day. April 25 is also an AISTATS/MLSS joint tutorial day. See http://www.aistats.org for information about AISTATS 2014. Venue: ------ The MLSS will be held in Reykjavik, the capital of Iceland, in Reykjavik University. Reykjavik and its environs offer a unique mix of culture and varied nature, from glaciers to waterfalls to geysers and thermal pools. Reykjavik is easily reachable by several airlines; travel information will be available on http://mlss2014.hiit.fi. Program Chairs: --------------- Samuel Kaski, Aalto University and University of Helsinki Jukka Corander, University of Helsinki Yee Whye Teh, University of Oxford Organizing Committee: --------------------- Deon Garrett (local organization chair), School of Computer Science, Reykjavik University and Icelandic Institute for Intelligent Machines Dorota Glowacka (sponsorship chair), University of Helsinki Antti Honkela, University of Helsinki Jaakko Peltonen (publicity and webmaster), Aalto University ============= for more information see http://mlss2014.hiit.fi =============== From smednick at ucr.edu Tue Oct 1 16:15:46 2013 From: smednick at ucr.edu (Sara C. Mednick) Date: Tue, 1 Oct 2013 13:15:46 -0700 Subject: Connectionists: Postdoctoral position in sleep, learning and memory and aging Message-ID: The Sleep and Cognition (SaC) Lab of the Department of Psychology at the University of California, Riverside is soliciting applications from psychologists and neuroscientists for a postdoctoral research position on sleep, learning and memory and aging. The researcher will work with existing and ongoing data sets related to the effect of pharmacology and sleep on memory consolidation in young and older populations. Successful candidates should have experience in sleep, pharmacology or aging research and possess a doctoral degree. Minority candidates are especially encouraged to apply. The University of California offers excellent benefits. Salary is based on research experience. The initial appointment is for 1 year with a possibility of extension. The candidate will be expected to apply for extramural funding at the appropriate time. Please send your CV, statement of research interests and the names of three references or make inquires to Sara C. Mednick smednick at ucr.edu. Thanks, Sara Mednick -- Assistant Professor University of California, Riverside Department of Psychology Sleep and Cognition Lab www.saramednick.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Tue Oct 1 18:00:55 2013 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 01 Oct 2013 15:00:55 -0700 Subject: Connectionists: NEURAL COMPUTATION - November, 2013 In-Reply-To: Message-ID: Neural Computation - Contents -- Volume 25, Number 11 - November 1, 2013 Available online for download now: http://www.mitpressjournals.org/toc/neco/25/11 Letters What Is the Limit of Redundancy Reduction With Divisive Normalization? Fabian H. Sinz, Matthias Bethge A Biological Gradient Descent for Prediction Through a Combination of STDP and Homeostatic Plasticity. Mathieu Galtier, Gilles Wainrib Formation and Regulation of Dynamic Patterns in Two-dimensional Spiking Neural Circuits with Spike-timing-dependent Plasticity John Henry Charles Palmer, Pulin Gong Encoding Binary Neural Codes in Networks of Threshold-linear Neurons Carina Curto, Anda Degeratu, and Vladimir Itskov Attention as Reward-driven Optimisation of Sensory Processing Matthew Chalk, Iain Murray, and Peggy Series Neuronal Assembly Dynamics in Supervised and Unsupervised Learning Scenarios Renan Cipriano Moioli, Phil Husbands Formal Modelling of Robot Behaviour With Learning Ryan Kirwan, Alice Miller, Bernd Porr, and Paolo di Prodi Towards Non-linear Local Reinforcement Learning Rules Through Neuroevolution Vassilis Vassiliades, Chris Christodoulou Online Learning of Single and Multi-Valued Functions with an Infinite Mixture of Linear Experts Bruno Damas, Jose Santos-Victor ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp SUBSCRIPTIONS - 2013 - VOLUME 25 - 12 ISSUES USA Others Electronic Only Student/Retired $70 $193 $65 Individual $124 $187 $115 Institution $1,035 $1,098 $926 Canada: Add 5% GST MIT Press Journals, 238 Main Street, Suite 500, Cambridge, MA 02142-9902 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ------------ From antti.honkela at hiit.fi Wed Oct 2 08:39:44 2013 From: antti.honkela at hiit.fi (Antti Honkela) Date: Wed, 02 Oct 2013 15:39:44 +0300 Subject: Connectionists: CfP: NIPS 2013 Workshop on Machine Learning Open Source Software: Towards Open Workflows Message-ID: <524C1410.1070602@hiit.fi> ********************************************************************** Call for Contributions Workshop on Machine Learning Open Source Software 2013: Towards Open Workflows http://mloss.org/workshop/nips13/ at NIPS 2013, Lake Tahoe, Nevada, United States, 10th December, 2013 ********************************************************************** The NIPS Workshop on Machine Learning Open Source Software (MLOSS) will held in Lake Tahoe (NV) on the 10th of December, 2013. The workshop is aimed at all machine learning researchers who wish to have their algorithms and implementations included as a part of the greater open source machine learning environment. Continuing the tradition of well received workshops on MLOSS at NIPS 2006, NIPS 2008 and ICML 2010, we plan to have a workshop that is a mix of invited speakers, contributed talks and discussion sessions. For 2013, we focus on workflows and pipelines. Many algorithms and tools have reached a level of maturity which allows them to be reused and integrated into larger systems. Important Dates =============== * Submission Date: October 9th, 2013 * Notification of Acceptance: October 23rd, 2013 * Workshop date: December 10th, 2013 Call for Contributions ====================== The organizing committee is currently seeking abstracts for talks at MLOSS 2013. MLOSS is a great opportunity for you to tell the community about your use, development, philosophy, or other activities related to open source software in machine learning. The committee will select several submitted abstracts for 20-minute talks. Submission Types ================ 1. Software packages This includes (but is not limited to) numeric packages (as e.g. R, Octave, Python), machine learning toolboxes and implementations of ML-algorithms, similar to the MLOSS track at JMLR (http://jmlr.org/mloss/ ). Submission format: 1 page abstract which must contain a link to the project description on mloss.org. Any bells and whistles can be put on your own project page, and of course provide this link on mloss.org. Note: Projects must adhere to a recognized Open Source License (cf. http://www.opensource.org/licenses/ ) and the source code must have been released at the time of submission. Submissions will be reviewed based on the status of the project at the time of the submission deadline. If accepted, the presentation must include a software demo. 2. Other submissions This category is open for position papers, interesting projects and ideas that may not be new software themselves, but link to machine learning and open source software. Submission format: abstract with no page limit. Please note that there will be no proceedings, i.e. the abstracts will not be published. We look forward for submissions that are novel, exciting and that appeal to the wider community. For more details see: http://mloss.org/workshop/nips13/ Please submit your contributions at https://www.easychair.org/conferences/?conf=mloss2013 Organizers ========== * Antti Honkela University of Helsinki, Helsinki Institute for Information Technology HIIT, Helsinki, Finland * Cheng Soon Ong NICTA, Victoria Research Laboratory, Melbourne, Australia From andrew.coward at anu.edu.au Wed Oct 2 10:24:07 2013 From: andrew.coward at anu.edu.au (Andrew Coward) Date: Wed, 2 Oct 2013 14:24:07 +0000 Subject: Connectionists: Towards a Theoretical Neuroscience Message-ID: <6962B1C5EA8F584CA5C090CD20F3AF0F062DD25A@HKXPRD0610MB377.apcprd06.prod.outlook.com> The book ?Towards a Theoretical Neuroscience: from Cell Chemistry to Cognition? has just been published by Springer. This book is Volume 8 in the Springer Series in Cognitive and Neural Systems. The Springer web site is http://www.springer.com/biomed/book/978-94-007-7106-2 This book provides an overview of current knowledge of human cognition, neuroanatomy, neuron physiology, and neurochemistry with extensive references to the original literature. It then goes on to describe how natural selection pressures have constrained the brain into forms in which different types of information processes are performed by major anatomical structures such as cortex, hippocampus, amygdala, basal ganglia, thalamus, hypothalamus, basal forebrain and cerebellum. More detailed anatomical structures and neurons perform more detailed information processes making up the processes performed by major structures. Neurochemical processes implement yet more detailed information processes that make up higher level processes. This hierarchy of information processing makes it possible to describe higher cognitive phenomena such as semantic, episodic, procedural, working and prospective memory and the succession of mental images called the stream of consciousness in terms of combinations of information processes in different major anatomical structures, larger combinations of more detailed information processes in more detailed structures, down to very large numbers of very detailed processes performed by neurochemistry. The book therefore bridges the gap between psychology and the physical neurosciences and makes it possible to understand complex cognitive phenomena in terms of anatomy, physiology and neurochemistry. For more information see Springer web site http://www.springer.com/biomed/book/978-94-007-7106-2 -------------- next part -------------- An HTML attachment was scrubbed... URL: From chloe-agathe.azencott at tuebingen.mpg.de Wed Oct 2 04:29:49 2013 From: chloe-agathe.azencott at tuebingen.mpg.de (=?ISO-8859-1?Q?Chlo=E9-Agathe_Azencott?=) Date: Wed, 02 Oct 2013 10:29:49 +0200 Subject: Connectionists: PhD Position: Machine learning methods for adverse drug reaction discovery Message-ID: <524BD97D.5070406@tuebingen.mpg.de> Applications are invited for an Early Stage Researcher fellowship (PhD position) of 36 months at the Centre for Computational Biology (Mines ParisTech and Institut Curie, Paris, France). This position is part of a Marie Curie Initial Training Network and the candidate should not have spent more than 12 months in France in the last 3 years. Project title: Machine learning methods for adverse drug reaction discovery. Supervisors: Prof. Dr. Jean-Philippe Vert, Prof. Dr. V?ronique Stoven, Dr. Chlo?-Agathe Azencott. Starting date: January 1st, 2014 at the latest. For details see http://mlpm.eu/positions/ For more information please contact Chlo?-Agathe Azencott (chloe-agathe.azencott at tuebingen.mpg.de). -- Chlo?-Agathe Azencott Max Planck Institutes T?bingen http://cazencott.info From cassio at idsia.ch Wed Oct 2 13:34:06 2013 From: cassio at idsia.ch (Cassio P. de Campos) Date: Wed, 2 Oct 2013 19:34:06 +0200 Subject: Connectionists: Brazilian Meeting on Bayesian Statistics - Call for papers Message-ID: ++++++++++++++++++++++++++++++++++++++++ EBEB 2014 - 12th Brazilian Meeting on Bayesian Statistics CALL FOR PAPERS (Springer Proceedings in Mathematics & Statistics) The Brazilian Meeting on Bayesian Statistics (EBEB) is in its twelfth edition. These meetings aim at strengthening the research on Bayesian methods and widening their application. They also provide an environment where Brazilian and international researchers collaborate, present their most recent developments and discuss on open problems. EBEB also allows graduate students to make contacts with experienced researchers. This year's meeting has a particular focus on discussing recent developments in the many viewpoints of Bayesian statistics, such as computational, theoretical, methodological and applied views. EBEB 2014 will take place in Atibaia, State of Sao Paulo, Brazil from March 10 to 14, in a beautiful country-side hotel (http://www.hotelfazendaatibaia.com.br/) specialized in horse riding. This is precisely one week after the famous Brazilian carnival. The venue is conveniently placed near Sao Paulo-Guarulhos international airport (40-minutes trip; the organization will coordinate means to help participants to reach the venue). For more details, please check the web page at http://www.ime.usp.br/~isbra/ebeb/. The EBEB 2014 is organized by ISBrA - the Brazilian Chapter of ISBA. EBEB 2014 invites submissions of papers on all topics related to Bayesian Statistics. We welcome submissions by authors who are new to EBEB and on new and emerging topics -- examples of topics and papers published at past EBEB meetings can be found at the meeting's web page. Full papers accepted to the proceedings will be published in a book from the series "Springer Proceedings in Mathematics & Statistics" (http://www.springer.com/series/10533). Submissions must be formatted accordingly (more details are available online) and must be written in English. Full papers (including figures and text) are limited to 10 pages in length. There are two paper submission tracks for EBEB (detailed below), even though accepted full papers appear in the proceedings regardless of their track. All accepted papers will be presented at the meeting either as contributed talks or as posters. The registration in the event of at least one author and the presentation of the work are preconditions for their publication in the proceedings. Early Submission Track: December 20, 2013: Early Full Paper Submission. January 10, 2014: Early Decision Notification (for the proceedings). July 01, 2014: Final camera-ready version. Normal Submission Track: December 20, 2013: Abstract Submission. January 10, 2014: Abstract Decision Notification (full paper mandatory in case of acceptance). January 15, 2014: Early Registration. February 10, 2014: Full Paper Submission (mandatory in case of accepted abstract). April 07, 2014: Decision Notification (for the proceedings). July 01, 2014: Final camera-ready version. More details about the two tracks and the submission procedure are available online at http://www.ime.usp.br/~isbra/ebeb/ ++++++++++++++++++++++++++++++++++++++++ (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.) From rajeev.raizada at gmail.com Wed Oct 2 15:20:52 2013 From: rajeev.raizada at gmail.com (Rajeev Raizada) Date: Wed, 2 Oct 2013 15:20:52 -0400 Subject: Connectionists: Two faculty jobs at U.Rochester: comp.neuro and systems neuro Message-ID: The Department of Brain & Cognitive Sciences at the University of Rochester is seeking applications for two tenure-track positions: one in theoretical/computational neuroscience, and one in systems neuroscience. Full info about the jobs is below. Raj --------------- Rajeev Raizada Assistant Professor Dept. of Brain & Cognitive Sciences University of Rochester Meliora Hall Rochester, NY 14627 raizada at bcs.rochester.edu http://raizadalab.org --------------- The Department of Brain and Cognitive Sciences at the University of Rochester is seeking to hire a tenure-track faculty member in the area of theoretical and computational neuroscience. We are primarily interested in candidates who employ theoretical and/or computational approaches to address fundamental questions regarding neural coding, sensory and perceptual processing, motor control, cognition, and decision-making. Candidates who demonstrate a strong interest in collaborating with experimentalists are especially encouraged to apply. The successful candidate will join a dynamic, collegial department whose focus is the study of learning and development, perception, motor control and cognition, through combined neurobiological, computational, and behavioral research (http://www.bcs.rochester.edu/index.html); she or he will also be part of a university?wide neuroscience community engaged in graduate and undergraduate education. Applicants should submit a CV, a statement of research and teaching interests, and contact information for three referees via the following website:http://www.rochester.edu/fort/bcs. Questions concerning this position can be addressed to Dr. Gregory C. DeAngelis, chair of the search committee [email: gdeangelis at cvs.rochester.edu]. Review of applications will begin on November 1, 2013. The University of Rochester is an Equal Opportunity Employer with a strong commitment to diversity, and actively encourages applications from candidates from groups underrepresented in higher education. The Department of Brain and Cognitive Sciences at the University of Rochester is seeking to hire a tenure-track faculty member in the area of systems neuroscience. We are primarily interested in candidates who employ experimental approaches to address fundamental questions regarding the neural basis of behavior. Specific areas of interest include sensory neural coding, motor control, decision-making, plasticity, learning and memory. Candidates working in both primate and non-primate model systems are encouraged to apply. The successful candidate will join a dynamic, collegial department whose focus is the study of learning and development, perception, motor control and cognition through combined neurobiological, computational, and behavioral research (http://www.bcs.rochester.edu/index.html); she or he will also be part of a university?wide neuroscience community engaged in graduate and undergraduate education. Applicants should submit a CV, a statement of research and teaching interests, and contact information for three referees via the following website: http://www.rochester.edu/fort/bcs. Questions concerning this position can be addressed to Dr. Gregory C. DeAngelis, chair of the search committee [email: gdeangelis at cvs.rochester.edu]. Review of applications will begin on November 1, 2013. The University of Rochester is an Equal Opportunity Employer with a strong commitment to diversity, and actively encourages applications from candidates from groups underrepresented in higher education. From masa-aki at atr.jp Thu Oct 3 04:14:04 2013 From: masa-aki at atr.jp (masa-aki at atr.jp) Date: Thu, 03 Oct 2013 17:14:04 +0900 Subject: Connectionists: Full-time Research Technical Staff Positions Available Message-ID: <1DCEC0108637EFmasa-aki@atr.jp> Full-time Research Technical Staff Positions Available The department of Computational Brain Imaging (CBI) at ATR has opening for a full-time research technical staff in the field of human brain imaging. The position offers the opportunity to learn experiments using four functional brain imaging methods such as fMRI, MEG, EEG, NIRS. We are looking for highly motivated applicants who help us conducting those experiments and data analysis. The mission of our department is to develop the method to analyze the human brain data. In particular, we are aiming at high-spatial and temporal resolution imaging method by integrating the multiple brain measurements to elucidate information processing among brain regions. Applicants must have a bachelor?s degree in the related field (psychology, neuroscience or computer science) and have strong motivations and ambitions to take part in experiments and data analysis related to the research above. Contact address: Department of Computational Brain Imaging ATR Neural Information Analysis Laboratories, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan E-mail: cbi-info at atr.jp Applications: Please submit the following three materials to the contact address below, either in printed or electronic form: 1. CV 2. Document (one or two pages in A4 or letter size) describing: - Summary of your previous research - Interests for research 3. Recommendation letters from one researcher *** Original documents you submit will not be returned. Work Location: Advanced Telecommunications Research Institute International (ATR) 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan Number of openings: One Employment conditions * Position: Full-time research technical staff * One year contract: Agreement is renewable according to the researcher ?s skill, work performance and qualifications. * Salary will be determined according to the company regulation based on the experience, qualifications and skills. * Standard working hour: 9:00 - 17:30, flextime available * Saturday, Sunday and public holiday off Selection process: After documentary examination, we ask for interview if needed. Starting date: After January 2014 (negotiable) Deadline for application: Opens until positions are filled. Use of personal data: All personal data received will be properly managed and only be used for the purpose of recruitment. From pedro.ortega at gmail.com Thu Oct 3 10:31:46 2013 From: pedro.ortega at gmail.com (Pedro Ortega) Date: Thu, 3 Oct 2013 10:31:46 -0400 Subject: Connectionists: Final CfP: NIPS Workshop on Planning with Information Constraints Message-ID: ***************************************************** Final Call for Contributions Workshop on Planning with Information Constraints for Control, Reinforcement Learning, Comp. Neuroscience, Robotics and Games http://www.seas.upenn.edu/~ope/workshop/ NIPS 2013, Lake Tahoe, Nevada, United States, December 9, 2013 ***************************************************** We invite submissions of papers related to the problem of planning with information constraints. Submissions in PDF should be emailed to ope at seas.upenn.edu with the subject line "NIPS 2013 Workshop Submission" no later than 9th of October 11:59 PM PDT (UTC -7 hours). Submissions should be 4-8 pages in NIPS format, with an extra page for references if necessary. Authors of the selected papers will be notified to present their work through short talks or posters presentations. ** About ** How do you make decisions when there are way more possibilities than you can analyze? How do you decide under such information constraints? Planning and decision-making with information constraints is at the heart of adaptive control, reinforcement learning, robotic path planning, experimental design, active learning, computational neuroscience and games. In most real-world problems, perfect planning is either impossible (computational intractability, lack of information, diminished control) or sometimes even undesirable (distrust, risk sensitivity, level of cooperation of the others). Recent developments have shown that a *single method*, based on the free energy functional borrowed from thermodynamics, provides a principled way of designing systems with information constraints that parallels Bayesian inference. This single method -known in the literature under various labels such as KL-control, path integral control, linearly-solvable stochastic control, information-theoretic bounded rationality- is proving itself very general and powerful as a foundation for a novel class of probabilistic planning problems. ** Organizers ** Bert J. Kappen Naftali Tishby Jan Peters David H. Wolpert Evangelos Theodorou Pedro A. Ortega -- Pedro A. Ortega web: http://www.adaptiveagents.org From thomas.j.palmeri at Vanderbilt.Edu Fri Oct 4 10:27:45 2013 From: thomas.j.palmeri at Vanderbilt.Edu (Thomas Palmeri) Date: Fri, 4 Oct 2013 09:27:45 -0500 Subject: Connectionists: postdoctoral fellowships at Vanderbilt University In-Reply-To: Message-ID: I have two open postdoctoral positions in my laboratory, one for a project on Object Categorization and Perceptual Expertise, the other for a project on Cognitive and Neural Modeling of Perceptual Decision Making and Cognitive Control. Please forward to anyone who might be interested in applying. See below. (apologies for cross-posting) -------------------------- Postdoctoral Position on Object Categorization and Perceptual Expertise Vanderbilt University Applications are being considered for a postdoctoral fellow to join an NSF-funded project on visual object categorization and the development of perceptual expertise at Vanderbilt University. Candidates will have opportunities for research combining laboratory experiments, online experiments, and computational modeling. Collaborative opportunities are possible with members of the Perceptual Expertise Network and the Temporal Dynamics of Learning Center. Applicants can hold a Ph.D. in psychology, neuroscience, computer science, mathematics, engineering, or related disciplines. Start date is negotiable. Salary will be based on NIH postdoctoral scale. Programming skills and some knowledge of Bayesian statistics are desirable. Applicants should send a cover letter with a brief research statement, a CV, and names and email addresses of three references to: Thomas Palmeri Department of Psychology Vanderbilt Vision Research Center Vanderbilt University Nashville, TN 37240 thomas.j.palmeri at vanderbilt.edu catlab.psy.vanderbilt.edu ------------------------------------------------------------ Postdoctoral Position on Cognitive and Neural Modeling Vanderbilt University Applications are being considered for a postdoctoral fellow to join an NEI-funded project on cognitive and neural modeling of perceptual decision making and cognitive control with Thomas Palmeri, Jeffrey Schall, and Gordon Logan at Vanderbilt University. Candidates have opportunities for research combining human behavioral experiments and monkey neurophysiological experiments with computational modeling. Candidates can hold a Ph.D. in psychology, neuroscience, computer science, mathematics, engineering, or related disciplines. Start date is negotiable. Salary will be based on NIH postdoctoral scale. Applicants should send a cover letter with a brief research statement, a CV, and names and email addresses of three references to: Thomas Palmeri thomas.j.palmeri at vanderbilt.edu catlab.psy.vanderbilt.edu Gordon Logan gordon.logan at vanderbilt.edu www.psy.vanderbilt.edu/faculty/logan Jeffrey Schall jeffrey.d.schall at vanderbilt.edu www.psy.vanderbilt.edu/faculty/schall/ Department of Psychology Vanderbilt Vision Research Center Vanderbilt University Nashville, TN 37240 -------------- next part -------------- An HTML attachment was scrubbed... URL: From pelillo at dsi.unive.it Mon Oct 7 11:31:29 2013 From: pelillo at dsi.unive.it (Marcello Pelillo) Date: Mon, 7 Oct 2013 17:31:29 +0200 (CEST) Subject: Connectionists: IEEE TNNLS Special Issue -- Deadline Extended Message-ID: >>>>> Deadline extended to NOVEMBER 3, 2013 <<<<< === 8< =================== CALL FOR PAPERS IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Special Issue on Learning in Non-(geo)metric Spaces Traditional machine learning and pattern recognition techniques are intimately linked to the notion of feature space. Adopting this view, each object is described in terms of a vector of numerical attributes and is therefore mapped to a point in a Euclidean (geometric) vector space so that the distances between the points reflect the observed (dis)similarities between the respective objects. This kind of representation is attractive because geometric spaces offer powerful analytical as well as computational tools that are simply not available in other representations. However, the geometric approach suffers from a major intrinsic limitation which concerns the representational power of vectorial, feature-based descriptions. In fact, there are numerous application domains where either it is not possible to find satisfactory features or they are inefficient for learning purposes. By departing from vector-space representations one is confronted with the challenging problem of dealing with (dis)similarities that do not necessarily possess the Euclidean behavior or not even obey the requirements of a metric. The lack of (geo)metric (i.e., geometric and/or metric) properties undermines the very foundations of traditional machine learning theories and algorithms, and poses totally new theoretical/computational questions and challenges that the research community is currently trying to address. The goal of the special issue is to consolidate research efforts in this area by soliciting and publishing high-quality papers which, together, will present a clear picture of the state of the art. SCOPE OF THE SPECIAL ISSUE We will encourage submissions of papers addressing theoretical, algorithmic, and practical issues related to the two fundamental questions that arise when abandoning the realm of vectorial, feature-based representations, namely: - how can one obtain suitable similarity information from data representations that are more powerful than, or simply different from, the vectorial? - how can one use similarity information in order to perform learning and classification tasks? Accordingly, topics of interest include (but are not limited to): - Embedding and embeddability - Graph spectra and spectral geometry - Indefinite and structural kernels - Game-theoretic models of pattern recognition and learning - Characterization of non-(geo)metric behavior - Foundational issues - Measures of (geo)metric violations - Learning and combining similarities - Multiple-instance learning - Applications We aim at covering a wide range of problems and perspectives, from supervised to unsupervised learning, from generative to discriminative models, and from theoretical issues to real-world applications. IMPORTANT DATES November 3, 2013 Deadline for manuscript submission <<<<< EXTENDED <<<<< April 1, 2014 Notification to authors July 1, 2014 Deadline for submission of revised manuscripts October 1, 2014 Final decision GUEST EDITORS Marcello Pelillo, Ca Foscari University, Venice, Italy (pelillo at dsi.unive.it) Edwin Hancock, University of York, UK (edwin.hancock at york.ac.uk) Xuelong Li, Chinese Academy of Sciences, China (xuelong_li at ieee.org) Vittorio Murino, Istituto Italiano di Tecnologia & University of Verona, Italy (vittorio.murino at iit.it) SUBMISSION INSTRUCTIONS 1. Read the information for authors at: http://cis.ieee.org/publications.html 2. Submit the manuscript by October 1, 2013 at the TNNLS webpage (http://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript has been submitted to the special issue on "Learning in non-(geo)metric spaces." Send also an e-mail to M. Pelillo (pelillo at dsi.unive.it) with subject TNNLS special issue submission to notify the editors of your submission. --- Marcello Pelillo, FIEEE, FIAPR Professor of Computer Science Computer Vision and Pattern Recognition Lab, Director Center for Knowledge, Interaction and Intelligent Systems (KIIS), Director DAIS Ca' Foscari University, Venice Via Torino 155, 30172 Venezia Mestre, Italy Tel: (39) 041 2348.440 Fax: (39) 041 2348.419 E-mail: marcello.pelillo at gmail.com URL: http://www.dsi.unive.it/~pelillo From william.alexander at ugent.be Mon Oct 7 07:23:37 2013 From: william.alexander at ugent.be (Will Alexander) Date: Mon, 07 Oct 2013 13:23:37 +0200 Subject: Connectionists: Postdoctoral position in computational modeling/fMRI - Ghent University Message-ID: <525299B9.2090800@ugent.be> A postdoctoral position is available in the lab of Will Alexander at Ghent University, Belgium. The position is part of a 5 year project investigating reinforcement learning and cognitive control, funded through the FWO-Flanders. The ideal candidate will have experience and interests in one or more of the following areas: 1) computational neural modeling, 2) fMRI, 3) cognitive control and 4) reinforcement learning. Individuals with experience in applying computational models to the analysis of fMRI data are especially encouraged to apply. Experience with Matlab is a plus. Depending on background and interests, the successful candidate will have the opportunity to develop computational neural models of cognitive control and decision making, as well as to contribute to the design, execution, and analysis of behavioral and fMRI experiments intended to inform and constrain new computational models. The duration of the position is initially two years, with the possibility of renewal for an additional two years The position is available from the beginning of February, 2014, although the start date is flexible. This is a full-time position with salary based on standard Belgian regulations. The successful candidate will join the Department of Experimental Psychology at Ghent University, and will have access to a research-dedicated 3T MRI scanner. To apply, send a brief statement of research interests, CV, and contact information for two references to william.alexander at ugent.be. Informal inquiries are also welcome. From michel.verleysen at uclouvain.be Sun Oct 6 05:15:40 2013 From: michel.verleysen at uclouvain.be (Michel Verleysen) Date: Sun, 6 Oct 2013 11:15:40 +0200 Subject: Connectionists: ESANN 2014: call for papers Message-ID: <000701cec274$a10de3c0$e329ab40$@uclouvain.be> *** We apologize for possible duplicates of this message sent to distribution lists. *** ESANN 2014: 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges, Belgium, 23-24-25 April 2014 http://www.esann.org/ Announcement and call for papers --------------------------------------------- ESANN 2014 builds upon a successful series of conferences organized each year since 1993. ESANN has become a major scientific event in the machine learning, computational intelligence and artificial neural networks fields over the years. The main topics are (non-exhaustive list): Statistical and mathematical aspects of learning, Feedforward models, Kernel machines, Graphical models, EM and Bayesian learning, Classification and clustering, Vector quantization and self-organizing maps, Recurrent networks and dynamical systems, Blind signal processing, Ensemble learning, Nonlinear projection and data visualization, Fuzzy neural networks, Evolutionary computation, Bio-inspired systems, Data mining, Signal processing and modelling, Approximation and identification, Feature extraction and dimension reduction, Time series forecasting, Multimodal interfaces and multichannel processing, Vision and sensory systems, Identification of non-linear dynamical systems, Biometry, Bioinformatics, Brain-computer interfaces, Neuroinformatics. See the call for papers for details. In addition to regular sessions, a number of special sessions will be organized, on selected hot topics in the machine learning, computational intelligence and artificial neural networks fields. The special sessions are: - Learning of structured and non-standard data - Learning and Modeling Big Data - Label noise in classification - Incremental learning and novelty detection methods and their applications - Advances on Weightless Neural Systems - Byte the bullet: learning on real-world computing architectures - Advances in Spiking Neural Information Processing Systems (SNIPS) See special sessions on http://www.esann.org/ for details. Deadline for submissions: November 29, 2013. Bruges is one of the most beautiful medieval towns in Europe. Designated as the "Venice of the North", the city has preserved all the charms of the medieval heritage. Its centre, which is inscribed on the Unesco World Heritage list, is in itself a real open air museum. We hope to receive your submission to ESANN 2014 and to see you in Bruges! Sincerely yours, Michel Verleysen ==================================================== Michel Verleysen Full professor - Honorary Research Director FNRS ICTEAM Institute - ELEN - Machine Learning Group Louvain School of Engineering Universit? catholique de Louvain Mail address: SST/ICTM/ELEN Maxwell Place du Levant 3, bte L5.03.02 B-1348 Louvain-la-Neuve, Belgium Phone: +32 10 47 25 51 - Fax: +32 10 47 25 98 E-mail: michel.verleysen at uclouvain.be Homepage: http://perso.uclouvain.be/michel.verleysen Institute: http://www.uclouvain.be/icteam Machine Learning Group: http://www.ucl.ac.be/mlg/ Doctoral School: http://www.uclouvain.be/doctoralschool-cil ==================================================== -------------- next part -------------- An HTML attachment was scrubbed... URL: From tomas.hromadka at gmail.com Mon Oct 7 04:57:44 2013 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Mon, 07 Oct 2013 10:57:44 +0200 Subject: Connectionists: [COSYNE2014] Abstract submission is open, Workshop pre-proposals deadline on Oct 15 Message-ID: <52527788.8030204@gmail.com> ================================================================== Computational and Systems Neuroscience (Cosyne) MAIN MEETING WORKSHOPS Feb 27 - Mar 2, 2014 Mar 3 - Mar 4, 2014 Salt Lake City, Utah Snowbird Ski Resort, Utah www.cosyne.org ================================================================== IMPORTANT DATES: Abstract submission opens: 07 Oct 2013 Abstract submission deadline: 18 Nov 2013 Workshop pre-proposal deadline: 15 Oct 2013 Workshop proposal deadline: 15 Nov 2013 The annual Cosyne meeting provides an inclusive forum for the exchange of empirical and theoretical approaches to problems in systems neuroscience, in order to understand how neural systems function. MAIN MEETING The MAIN MEETING is single-track. A set of invited talks are selected by the Executive Committee, and additional talks and posters are selected by the Program Committee, based on submitted abstracts. Cosyne topics include but are not limited to: neural coding, natural scene statistics, dendritic computation, neural basis of persistent activity, nonlinear receptive field mapping, representations of time and sequence, reward systems, decision-making, synaptic plasticity, map formation and plasticity, population coding, attention, and computation with spiking networks. This year we would like to foster increased participation from experimental groups as well as computational ones. Please circulate widely and encourage your students and postdocs to apply. WORKSHOPS The WORKSHOPS feature in-depth discussion of current topics of interest, in a small group setting. The goal is to provide an informal forum for the discussion of important research questions and challenges. Controversial issues, open problems, comparisons of competing approaches, and alternative viewpoints are encouraged. PRE-PROPOSALS: In an effort to coordinate submissions, the organizers are encouraged to submit a pre-proposal by 15 Oct 2013. Pre-proposals will be shared among submitters. Pre-proposals are requested but not required. The organizers may submit the full proposal by its deadline (15 Nov 2013). The overarching goal of all workshops should be the integration of empirical and theoretical approaches, in an environment that fosters collegial discussion and debate. Preference will be given to proposals that differ substantially in content, scope, and/or approach from workshops of recent years (examples available at www.cosyne.org). Relevant topics include, but are not limited to: sensory processing; motor planning and control; functional neural circuits; motivation, reward and decision making; learning and memory; adaptation and plasticity; neural coding; neural circuitry and network models; and methods in computational or systems neuroscience. For details on submitting (pre-)proposals please visit www.cosyne.org (Workshops). INVITED SPEAKERS: Rui Costa (Champalimaud) Catherine Dulac (Harvard) Joshua Gold (U Pennsylvania) Thomas Jessell (Columbia) John Krakauer (Johns Hopkins) Jeffrey Magee (Janelia Farm) Thomas Mrsic-Flogel (U Basel) Yael Niv (Princeton) Elad Schneidman (Weizmann) Doris Tsao (Caltech) Nachum Ulanovsky (Weizmann) When preparing an abstract, authors should be aware that not all abstracts can be accepted for the meeting, due to space constraints. Abstracts will be selected based on the clarity with which they convey the substance, significance, and originality of the work to be presented. ORGANIZING COMMITTEE: General Chairs: Marlene Cohen (U Pittsburgh) and Peter Latham (UCL) Program Chairs: Michael Long (NYU) and Stephanie Palmer (U Chicago) Workshop Chairs: Robert Froemke (NYU) and Tatyana Sharpee (Salk) Publicity Chair: Eugenia Chiappe (Champalimaud) EXECUTIVE COMMITTEE: Anne Churchland (CSHL) Zachary Mainen (Champalimaud) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) From ertekg at sabanciuniv.edu Fri Oct 4 06:51:28 2013 From: ertekg at sabanciuniv.edu (Gurdal Ertek) Date: Fri, 04 Oct 2013 13:51:28 +0300 Subject: Connectionists: free educational modules - ertek.info Message-ID: <524E9DB0.8050203@sabanciuniv.edu> Dear Colleagues and Business Professionals, Throughout the 10+ years that I have served at Sabanci University, Istanbul, Turkey, as a professor, I have created a multitude of extensive educational modules. I have also worked with my assistants and coached them as they created their own educational modules. One respected member of our Program also contributed with a module. Finally, I have assembled some copyright-free materials from the internet to create additional modules. As of today, I offer all of these modules to the Industrial Engineers, Information Systems Professionals, Business Professionals, and the whole world, FREE OF CHARGE: http://ertek.info Since each of these modules is also a virtual good that has a real monetary value, I haveused the Boxbill e-commerce interface for you to access these educational modules. You can register with your email and shop for modules of your choice (some modules are marked as being in Turkish language), just like shopping from an e-store. The difference from an e-store is that all the modules placed so far are completely free of charge, and will stay that way as long as the web site is up. In Turkey and globally, it may be hard to find technical and professional information at times. The available information may be limited, unpractical, and almost always at a cost. I hope that we can alleviate at least some of these problems through this service. I kindly invite you to share this message and the ertek.info weblink with your friends and colleagues, and contribute to the spread of the knowledge and know-how here to others. I wish you the best in everything you do, Gurdal Ertek, Ph.D., Assistant Professor, Sabanci University, Istanbul, Turkey [Alumni of Bogazici University, 2004; Georgia Tech, 2011] -------------- next part -------------- An HTML attachment was scrubbed... URL: From urundogan at gmail.com Mon Oct 7 04:24:34 2013 From: urundogan at gmail.com (urun dogan) Date: Mon, 7 Oct 2013 11:24:34 +0300 Subject: Connectionists: CFP - NIPS 2013 New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks (Reminder of Submission Deadline) Message-ID: Apologies for cross-posting. Please forward this to those who may be interested. Thank you. ========================================================================= CALL FOR PAPERS (Reminder of Submission Deadline) NIPS 2013 New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks December 10, 2013 Lake Tahoe, Nevada, USA https://sites.google.com/site/learningacross/ Submission Deadline: October 9, 2013 ========================================================================= The main objective of the workshop is to document and discuss the recent rise of new research questions on the general problem of learning across domains and tasks. This includes the main topics of transfer and multi-task learning, together with several related variants as domain adaptation and dataset bias. In the last years there has been an increasing boost of activity in these areas, many of them driven by practical applications, such as object categorization. Different solutions were studied for the considered topics, mainly separately and without a joint theoretical framework. On the other hand, most of the existing theoretical formulations model regimes that are rarely used in practice (e.g. adaptive methods that store all the source samples). This NIPS 2013 workshop will focus on closing this gap by providing an opportunity for theoreticians and practitioners to get together in one place, to share and debate over current theories and empirical results. The goal is to promote a fruitful exchange of ideas and methods between the different communities, leading to a global advancement of the field. Transfer Learning - Transfer Learning (TL) refers to the problem of retaining and applying the knowledge available for one or more source tasks, to efficiently develop an hypothesis for a new target task. Each task may contain the same (domain adaptation) or different label sets (across category transfer). A lot of the effort has been devoted to binary classification, while most interesting practical transfer problems are intrinsically multi-class and the number of classes can often increase in time. Hence, it is natural to ask: - How to formalize knowledge transfer across multi-class tasks and provide theoretical guarantees on this setting? - Can interclass transfer and incremental class learning be properly integrated? - Can learning guarantees be provided when the adaptation relies only on pre-trained source hypotheses without explicit access to the source samples, as it is often the case in real world scenarios? Multi-task Learning - Learning over multiple related tasks can outperform learning each task in isolation. This is the principal assertion of Multi-task learning (MTL) and implies that the learning process may benefit from common information shared across the tasks. In the simplest case, transfer process is symmetric and all the tasks are considered as equally related and appropriate for joint training. - What happens when this condition does not hold, e.g. how to avoid negative transfer? - Can RHKS embeddings be adequately integrated into the learning process to estimate and compare the distributions underlying the multiple tasks? - How may embedding probability distributions help learning from data clouds? - Can deep learning or multiple kernel learning help to get a step closer towards the complete automatization of multi-task learning? - How can notions from reinforcement learning such as source task selection be connected to notions from convex multi-task learning such as the task similarity matrix? Confirmed Invited Speakers - Shai Ben-David (University of Waterloo) - Massimiliano Pontil (University College London) - Fei Sha (University of Southern California) - Arthur Gretton (Gatsby Computational Neuroscience Unit) - Sinno Jialin Pan (Institute for Infocomm Research and National University of Singapore) ========================================================================= Submission: We invite submission of extended abstracts to the workshop on all topics related to transfer and multi-task learning with special interest in - New views and unifying theories on TL and MTL - Learning the task similarities/dissimilarities from the data - Sparse vs non sparse regularization in similarity learning - Domain adaptation - Dataset bias - Use of deep and reinforcement learning for TL and MTL - Large scale and online TL and MTL - Connections of multiple kernel learning to TL and MTL - Innovative applications, e.g. in computer vision or computational biology. Preference will be given to submissions which propose new principled TL and MTL methods or which are likely to generate new debate by rising general issues or suggesting directions for future work. Submissions should be no longer than 4 pages in the NIPS latex style. The extended abstract may be accompanied by an unlimited appendix and other supplementary material, with the understanding that anything beyond 4 pages may be ignored by the program committee. Topics that were recently published or presented elsewhere are allowed, provided that the extended abstract mentions this explicitly. Please send your submission by email to ml-newdirectionsinmtl at lists.tu-berlin.de Important Dates Submission deadline: October 9th, 2013 Acceptance decision: October 23th, 2013 Workshop: December 10th, 2013 Organizers Urun Dogan (Skype Labs / Microsoft) Marius Kloft (Courant Institute of Mathematical Sciences & Memorial Sloan-Kettering Cancer Center) Francesco Orabona (Toyota Technological Institute, Chicago) Tatiana Tommasi (KU Leuven) -------------- next part -------------- An HTML attachment was scrubbed... URL: From grlmc at urv.cat Sat Oct 5 05:46:53 2013 From: grlmc at urv.cat (GRLMC) Date: Sat, 5 Oct 2013 11:46:53 +0200 Subject: Connectionists: TPNC 2013: 2nd call for posters Message-ID: <156D2D9BB22541F78A4B273AB9390A6E@Carlos1> *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* ************************************************************************* The 2nd International Conference on the Theory and Practice of Natural Computing (TPNC 2013) invites authors to submit poster presentations. TPNC 2013 will be held in C?ceres (Spain) on 3-5 December, 2013. See http://grammars.grlmc.com/tpnc2013/ Poster presentations are intended to enhance informal interactions with the conference participants, at the same time permitting in-depth discussion. TOPICS Authors are encouraged to submit presentations that discuss novel work in progress on: - nature-inspired models of computation, - synthesis of nature by means of computation, - nature-inspired materials, - information processing in nature, - applications of natural computing. Posters do not need to present final research results. Work that may lead to new interesting developments is welcome. KEY DATES Submission deadline: October 20, 2013 Notification of poster acceptance or rejection: October 27, 2013 SUBMISSION Please submit a .pdf abstract through: https://www.easychair.org/conferences/?conf=tpnc2013 It should contain the title, author(s) and affiliation, and should not exceed 500 words. PRESENTATION Posters will be allocated 8 minutes each in the programme for oral presentation. Moreover, they will remain hanging during the whole conference for discussion. PUBLICATION Posters will not appear in the LNCS proceedings volume of TPNC 2013. However, they will be eligible for submission to the post-conference Soft Computing journal special issue. REGISTRATION Authors of accepted posters have to register to the conference. Their registration fare is reduced: 150 Euro (appr. one third of the fare for PhD students). From sameer at cs.umass.edu Mon Oct 7 03:21:35 2013 From: sameer at cs.umass.edu (Sameer Singh) Date: Mon, 7 Oct 2013 00:21:35 -0700 Subject: Connectionists: CFP + Deadline Extension: NIPS Workshop on Big Learning 2013 Message-ID: Big Learning 2013: Advances in Algorithms and Data Management *NIPS 2013 Workshop (http://www.biglearn.org)* Submission Deadline: *October 25th, 2013*. ORGANIZERS: - *Xinghao Pan* (Berkeley) - *Haijie Gu* (CMU) - *Joseph Gonzalez* (Berkeley) - *Sameer Singh* (UMass Amherst) - *Yucheng Low* (CMU) Submissions are solicited for a one day workshop on Monday, December 9th at Lake Tahoe, Nevada. This workshop will address algorithms, systems, and real-world problem domains related to large-scale machine learning (?Big Learning?). Big Learning has attracted intense interest, with active research spanning diverse fields. In particular, the machine learning and databases have taken distinct approaches by developing new algorithms and data management systems. This workshop will bring together experts across these diverse communities to discuss recent progress, share tools and software, identify pressing new challenges, and to exchange new ideas. Topics of interest include (but are not limited to): - *Scalable Data Systems*: Systems for large-scale parallel or distributed learning; implementations of machine learning models and algorithms in database management systems (DBMS); insights and discussions on properties (availability, scalability, correctness, etc.), strengths, and limitations of databases for Big Learning. - *Big Data*: Methods for managing large, unstructured, and/or streaming data; cleaning, visualization, interactive platforms for data understanding and interpretation; sketching and summarization techniques; sources of large datasets. - *Models & Algorithms*: Machine learning algorithms for parallel, distributed, GPGPUs, or other novel architectures; theoretical analysis; distributed online algorithms; implementation and experimental evaluation; methods for distributed fault tolerance. - *Applications of Big Learning*: Practical application studies and challenges of real-world system building; insights on end-users, common data characteristics (stream or batch); trade-offs between labeling strategies (e.g., curated or crowd-sourced). Submissions should be written as extended abstracts, no longer than 4 pages (excluding references) in the NIPS latex style. Relevant work previously presented in non-machine-learning conferences is strongly encouraged, though submitters should note this in their submission. Please refer to the website for detailed submission instructions: Guidelines -------------- next part -------------- An HTML attachment was scrubbed... URL: From Colin.Wise at uts.edu.au Mon Oct 7 20:46:42 2013 From: Colin.Wise at uts.edu.au (Colin Wise) Date: Tue, 8 Oct 2013 11:46:42 +1100 Subject: Connectionists: AAI Short Course - 'Statistical Machine Learning - an Introduction' Thursday 24 October 2013 Message-ID: <8112393AA53A9B4A9BDDA6421F26C68A014109E0D6B5@MAILBOXCLUSTER.adsroot.uts.edu.au> Dear Colleague, AAI Short Course - 'Statistical Machine Learning - an Introduction' Thursday 24 October 2013 https://shortcourses-bookings.uts.edu.au/ClientView/Schedules/ScheduleDetail.aspx?ScheduleID=1362&EventID=1175 Our AAI short course 'Statistical Machine Learning - an Introduction' may be of interest to you and or others in your organisation or network. This course introduces a range of fundamental techniques for statistical machine learning. It is offered at an introductory level and it is suitable for general audiences with only some technical background in computer programming. The course starts with recalls of probability and linear algebra and continues to cover classification, parameter estimation, linear regression, dimensionality reduction and the support vector machine. The course offers numerous examples in the Matlab programming environment. Please register here LINK An important foundation short course in the AAI series of advanced data analytic short courses - please view this short course and others here LINK We are happy to discuss at your convenience. Thank you and regards. Colin Wise Operations Manager Advanced Analytics Institute (AAI) Blackfriars Building 2, Level 1 University of Technology, Sydney (UTS) Email: Colin.Wise at uts.edu.au Tel. +61 2 9514 9267 M. 0448 916 589 AAI: www.analytics.uts.edu.au/ Reminder - AAI Short Course - Advanced Data Analytics - an Introduction - Tuesday 19 November 2013 Future short courses on Data Analytics and Big Data may be viewed at LINK AAI Education and Training Short Courses Survey - you may be interested in completing our AAI Survey at LINK AAI June 2013 Newsletter LINK AAI Email Policy - should you wish to not receive this periodic communication on Data Analytics Learning please reply to our email (to sender) with UNSUBSCRIBE in the Subject. We will delete you from our database. Thank you for your past and future support. UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any accompanying attachments may contain confidential information. If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or attachments. If you have received this message in error, please notify the sender immediately and delete this message. Any views expressed in this message are those of the individual sender, except where the sender expressly, and with authority, states them to be the views of the University of Technology Sydney. Before opening any attachments, please check them for viruses and defects. Think. Green. Do. Please consider the environment before printing this email. -------------- next part -------------- An HTML attachment was scrubbed... URL: From sabu.thampi at iiitmk.ac.in Tue Oct 8 12:23:00 2013 From: sabu.thampi at iiitmk.ac.in (Dr. Sabu M. Thampi) Date: Tue, 8 Oct 2013 21:53:00 +0530 Subject: Connectionists: International Symposium on Signal Processing and Intelligent Recognition Systems (SIRS-2014) Message-ID: -------------------------------------------------------------------------------------------------- Apologies for cross-postings! Please consider to contribute to and/or forward to the appropriate groups the following opportunity to submit and publish original scientific results to SIRS 2014. The submission deadline is November 10, 2013 -------------------------------------------------------------------------------------------------- International Symposium on Signal Processing and Intelligent Recognition Systems (SIRS-2014) March 13-15, 2014, Trivandrum, India http://www.iiitmk.ac.in/sirs/ CALL FOR PAPERS ------------------------- SIRS-2014 aims to bring together researchers from academia, industry and government and to provide an international forum for the sharing, exchange, presentation and discussion of original research results in both methodological issues and different application areas of signal processing and pattern recognition. The technical program of the Conference will include tutorials, regular technical sessions, workshops, symposiums, special sessions, demos and plenary/keynote speeches. SIRS invites submissions containing original ideas that are relevant to the scope of the Symposium. Both full research reports and work-in-progress reports are welcome. There will be both oral and poster sessions.Special sessions dedicated to the topics related to SIRS-2014 are also envisaged: researchers interested in organizing a special session are invited to contact Symposium organizers. Authors should submit their papers online. We use EDAS system for submission of papers and review process. Unregistered authors should first create an account on EDAS to log on. The manuscripts should be submitted in PDF format. Please refer submission page http://www.iiitmk.ac.in/sirs/callpaper.htmlfor more details. All accepted papers will be published as a special volume in the prestigious Advances in Intelligent and Soft Computing (Springer) Series, indexed by ISI Proceedings, DBLP, Ulrich's, EI-Compendex, SCOPUS, Zentralblatt Math, MetaPress, Springerlink etc... We welcome submissions for SIRS-2014's Technical Program in the following areas and not limited to: Acoustic and Vibration Signal Processing Adaptive Signal Processing Analog and Digital Signal Processing Audio and Speech Processing Bio-Inspired computing Biomedical Signal and Image Processing Character Recognition Coding Techniques Cognitive Radio Signal Processing Communication Signal Processing Computer Vision Data Analytics Data and Web Mining Data Fusion Applications DSP for Space Applications Fingerprint Identification Face Recognition Features Extraction and Selection Genomic Signal Processing Image and Video Processing Information Forensics and Security Intelligent Data Interpretation Intelligent Transportation Systems Knowledge-Based Decision Support Systems Machine Learning Mobile Computing and Applications Multi-classifier/Decision Systems Multidimensional Signal Processing Multimedia Language Processing Multirate and Wavelet Signal Processing Online Social Networks Pattern Recognition Sensor Signal Processing Signal Analysis Signal Processing for Security and Cryptography Signal Processing for Smart Grid Communications Statistical Signal Processing Watermarking and Information Hiding KEY DATES --------------------------- Full Paper Submission Ends:November 10, 2013 Acceptance Notification:December 15, 2013 Final paper Deadline:December 31, 2013 Author Registration Closes:January 5, 2014 Symposium: March 13 -15, 2014 Contact Us ---------------- Email: sirs2014.iiitmk at gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From fmschleif at googlemail.com Tue Oct 8 14:43:21 2013 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Tue, 8 Oct 2013 20:43:21 +0200 Subject: Connectionists: 3rd call for papers - 10th Workshop on Self-Organizing Maps 2014 -- WSOM 2014 Message-ID: [apologies for multiple posting] 10th Workshop on Self-Organizing Maps 2014 -- WSOM 2014 www.WSOM2014.de will be held in the beautiful small town Mittweida located close to the mountains Erzgebirge in Saxony/Germany. It will bring together researchers and practitioners in the field of self?organizing systems for data analysis, with a particular emphasis on self?organizing maps and learning vector quantization. WSOM 2014 is the 10th conference in a series of biannual international conferences started with WSOM'97 in Helsinki. SCOPE ? TOPICS We expect contributions related to the theoretical and methodological aspects of the self?organizing map, learning vector quantization and related fields as well as respective applications. Topics include: ? Data analysis and visualization and modelling dynamic phenomena ? Mathematical aspects including information theory and mathematical statistics ? Architectural solutions including hierarchical and growing networks, ensemble models and special metrics ? Neuro?cognitive studies that compare modelling and empirical results at different levels ? Software and hardware implementations ? Outstanding applications emphasizing special aspects of the models We also call for scientific and practice-oriented papers that describe the use of self-organizing maps with variants in different application areas including but not limited to: ? Data mining ? Pattern recognition ? Signal processing ? Knowledge management ? Time series processing ? Industrial applications ? Bioinformatics ? Biomedical applications ? Telecommunications ? Financial analysis ? Cognitive modeling ? Robotics and intelligent systems ? Image processing and vision ? Speech processing ? Language modeling ? Text and document analysis Submission of papers : November 1st 2013 Notification of provisional acceptance: December 15th 2013 Camera ready papers : January 15th 2014 Early registration (special rates) : February 15th 2014 Submissions can be done via Easychair at https://www.easychair.org/conferences/?conf=wsom2014 Accepted papers will be published in Springer's Advances in Intelligent Systems and Computing series. Further details at: www.wsom2014.de -- ------------------------------------------------------- Dr. rer. nat. Frank-Michael Schleif University of Bielefeld AG Theoretical Computer Science and Computational Intelligence CITEC - Q1-143 Universit?tsstrasse 21-23 33615 Bielefeld - email: fschleif at techfak.uni-bielefeld.de phone: +49(0)521 106 12137 fax : +49(0)521 106 12181 ------------------------------------------------------- From benoit.frenay at uclouvain.be Tue Oct 8 14:47:10 2013 From: benoit.frenay at uclouvain.be (=?ISO-8859-1?Q?Beno=EEt_Fr=E9nay?=) Date: Tue, 08 Oct 2013 20:47:10 +0200 Subject: Connectionists: Label noise in Classification Special Session at ESANN 2014 Message-ID: <5254532E.70407@uclouvain.be> An HTML attachment was scrubbed... URL: From dayan at gatsby.ucl.ac.uk Tue Oct 8 16:09:08 2013 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Tue, 8 Oct 2013 21:09:08 +0100 Subject: Connectionists: Gatsby PhD Programme Message-ID: <20131008200908.GA20630@gatsby.ucl.ac.uk> Gatsby Computational Neuroscience Unit, University College London 4 year PhD Programme The Gatsby Unit is a centre for theoretical neuroscience and machine learning, focusing on unsupervised, semi-supervised and reinforcement learning, neural dynamics, population coding, Bayesian and nonparametric statistics, kernel methods, and applications of these to the analysis of perceptual processing, neural data, machine vision and bioinformatics. It provides a unique opportunity for a critical mass of theoreticians to interact closely with each other, and with other world-class research groups in related departments at UCL, including the Sainsbury Wellcome Centre for Neural Circuits and Behaviour, with which we will shortly share a building, and Biosciences, Computer Science, Functional Imaging, Physics, Physiology, Psychology, Neurology, Ophthalmology and Statistics, the cross-faculty Centre for Computational Statistics and Machine Learning, and also with other UK and overseas universities. The Unit has openings for exceptional PhD candidates. Applicants should have a strong analytical background, a keen interest in neuroscience and/or machine learning and a relevant first degree, for example in Computer Science, Engineering, Mathematics, Neuroscience, Physics, Psychology or Statistics. The PhD programme lasts four years, including a first year of intensive instruction in techniques and research in theoretical neuroscience and machine learning. All students are fully funded, regardless of nationality. The Unit also welcomes applications from students with pre-secured funding or who are currently soliciting other scholarship/studentships. The closing date for applications is 16th December 2013. Full details of our programme, and how to apply, are available at: http://www.gatsby.ucl.ac.uk/teaching/phd For further details of research interests please see http://www.gatsby.ucl.ac.uk/research.html and the individual faculty webpages at http://www.gatsby.ucl.ac.uk/members.html From matthew.botvinick at gmail.com Wed Oct 9 09:15:32 2013 From: matthew.botvinick at gmail.com (Matthew Botvinick) Date: Wed, 9 Oct 2013 09:15:32 -0400 Subject: Connectionists: Princeton Neuroscience Ph.D. Program Message-ID: Graduate Study in Neuroscience at Princeton University The Graduate Program in Neuroscience at Princeton University offers a unique laboratory-focused course of study, with a strong computational emphasis. Applications for entry in the Fall of 2014 are now being accepted, with a deadline of December 1. For details, including contact information, please visit our webpage at www.princeton.edu/neuroscience. Matthew Botvinick, Director of Graduate Admissions Dawn Tindall, Manager of Student Services, 609-258-9657, dtindall at princeton.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Wed Oct 9 12:25:21 2013 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 09 Oct 2013 09:25:21 -0700 Subject: Connectionists: Computational Neuroscience at UCSD In-Reply-To: Message-ID: UCSD GRADUATE PROGRAM IN COMPUTATIONAL NEUROSCIENCE http://compneuro.salk.edu http://healthsciences.ucsd.edu/education/neurograd/current-students/Pages/computational.aspx Application deadline: December 2, 2013 http://neurograd.ucsd.edu/2page.php?id=gradadm ***** The goal of the Computational Neuroscience Specialization in the Neurosciences Graduate Program at UCSD is to train researchers who are equally at home measuring large-scale brain activity, analyzing the data with advanced computational techniques, and developing new models for brain development and function. Candidates from a wide range of backgrounds are invited to apply, including Biology, Psychology, Computer Science, Physics and Mathematics. The three major themes in the training program are: 1. Neurobiology of Neural Systems: Anatomy, physiology and behavior of systems of neurons. Using modern neuroanatomical, behavioral, neuropharmacological and electrophysiological techniques. Lectures, wet laboratories and computer simulations, as well as research rotations. Major new imaging and recording techniques also will be taught, including two-photon laser scanning microscopy and functional magnetic resonance imaging (fMRI). 2. Algorithms and Realizations for the Analysis of Neuronal Data: New algorithms and techniques for analyzing data obtained from physiological recording, with an emphasis on recordings from large populations of neurons with imaging and multielectrode recording techniques. New methods for the study of co-ordinated activity, such as multi-taper spectral analysis and Independent Component Analysis (ICA). 3. Neuroinformatics, Dynamics and Control of Systems of Neurons: Theoretical aspects of single cell function and emergent properties as many neurons interact among themselves and react to sensory inputs. A synthesis of approaches from mathematics and physical sciences as well as biology will be used to explore the collective properties and nonlinear dynamics of neuronal systems, as well as issues of sensory coding and motor control. ***** Participating Faculty include: * Henry Abarbanel (Physics): Nonlinear and oscillatory dynamics; modeling central pattern generators in the lobster stomatogastric ganglion. * Thomas Albright (Salk Institute): Motion processing in primate visual cortex; linking single neurons to perception; fMRI in awake, behaving monkeys. * Darwin Berg (Neurobiology): Regulation synaptic components, assembly and localization, function and long-term stability. * Ed Callaway (Salk Institute): Neural circuits, visual perception, visual cortex Genetic tools for tracing neural pathways. * Gert Cauwenberghs (Bioengineering): Neuromorphic Engineering; analog VLSI chips; wireless recording and nanoscale instrumentation for neural systems; large-scale cortical modeling. * Sreekanth Chalasani (Salk): C. elegans: genes, networks and behavior Optical recording of olfactory processing. * Andrea Chiba (Cognitive Science): Spatial attention, associative learning, cholinergic neuromodulaiton of behavior, amygdala recordings * Todd Coleman (Bioengineering): Brain-Machine Interfaces (BMI) * Garrison Cottrell (Computer Science and Engineering): Dynamical neural network models and learning algorithms * Virginia De Sa (Cognitive Science): Computational basis of perception and learning; multi-sensory integration and contextual influences * Mark Ellisman (Neurosciences, School of Medicine): High resolution electron and light microscopy; anatomical reconstructions. * Fred Gage (Salk Institute): Neurogenesis and models of the hippocampus; neuronal diversity, neural stem cells. * Timothy Gentner (Psychology): Birdsong learning. Neuroethology of vocal communication and audition * Robert Hecht-Nielsen (Electrical and Computer Engineering): Neural computation and the functional organization of the cerebral cortex. * Steve Hillyard (Neurosciences): EEG, perception, attention, memory, Event related potentilas, SSVEP * Harvey Karten (Neurosciences, School of Medicine): Anatomical, physiological and computational studies of the retina and optic tectum of birds and squirrels * David Kleinfeld (Physics): Active sensation in rats; properties of neuronal assemblies; optical imaging of large-scale activity. * William Kristan (Neurobiology): Computational Neuroethology; functional and developmental studies of the leech nervous system, including studies of the bending reflex and locomotion. * Scott Makeig (Institute for Neural Computation): Analysis of cognitive event-related brain dynamics and fMRI using time-frequency and Independent Component Analysis * Javier Movellan (Institute for Neural Computation): Sensory fusion and learning algorithms for continuous stochastic systems * Howard Poizner (Institute for Neural Computation): Motor systems; arm reaching; Parkinson's Disease. * Mikhael Rabinovich (Institute for Nonlinear Science): Dynamical systems analysis of the stomatogastric ganglion of the lobster and the antenna lobe of insects * Pamela Reinagel (Biology): Sensory and neural coding; natural scene statistics; recordings from the visual system of cats and rodents. * John Reynolds (Salk): Visual attention, cortex, psychophysics, neurophysiology, neural modeling * Massimo Scanziani (Biology): Neural circuits in the somotosensory cortex; physiology of synaptic transmission; inhibitory mechanisms. * Terrence Sejnowski (Salk Institute/Neurobiology): Computational models and physiological studies of synaptic, neuronal and network function. * Tanya Sharpee (Salk): Statistical physics and information theory approaches to sensory processing in natural auditory and visual environments. * Gabe Silva (Bioengineering): Cellular neural engineering * Nicholas Spitzer (Neurobiology): Regulation of ionic channels and neurotransmitters in developing neurons and neural function. * Charles Stevens (Salk Institute): Synaptic physiology; theoretical models of neuroanatomical scaling. * Roger Tsien (Chemistry): Second messenger systems in neurons; development of new optical and MRI probes of neuron function, including calcium indicators and caged neurotransmitters * Jing Wang (Biology): Representation of olfactory information in the nervous system of Drosophila * Ruth Williams (Mathematics): Probabilistic analysis of stochastic systems and continuous learning algorithms * Angela Yu (Cognitive Science): Sensory processing, attentional selection, perceptual decision-making, sensorimotor integration, learning, and adaptation. ***** On-line applications: http://neurograd.ucsd.edu/2page.php?id=gradadm The deadline for completed application materials, including letters of recommendation, is December 2, 2013. ***** From yevgeny.seldin at gmail.com Thu Oct 10 06:57:11 2013 From: yevgeny.seldin at gmail.com (Yevgeny Seldin) Date: Thu, 10 Oct 2013 20:57:11 +1000 Subject: Connectionists: Deadline Extension: Resource-Efficient Machine Learning, NIPS-2013 workshop Message-ID: <52568807.6000006@gmail.com> CALL FOR ABSTRACTS AND OPEN PROBLEMS Resource-Efficient Machine Learning NIPS-2013 Workshop Tuesday, December 10, 2013 Lake Tahoe, Nevada, US https://sites.google.com/site/resefml2013 ---------------------------------------------- We invite submission of abstracts and open problems to Resource-Efficient Machine Learning NIPS-2013 workshop. IMPORTANT DATES *New Submission Deadline:* October 23. *Notification of Acceptance:* November 6. More details are provided below. ----------------------------------------------- Abstract Resource efficiency is key for making ideas practical. It is crucial in many tasks, ranging from large-scale learning ("big data'') to small-scale mobile devices. Understanding resource efficiency is also important for understanding biological systems, from individual cells to complex learning systems, such as the human brain. The goal of this workshop is to improve our fundamental theoretical understanding and link between various applications of learning under constraints on the resources, such as computation, observations, communication, and memory. While the founding fathers of machine learning were mainly concerned with characterizing the sample complexity of learning (the observations resource) [VC74] it now gets realized that fundamental understanding of other resource requirements, such as computation, communication, and memory is equally important for further progress [BB11]. The problem of resource-efficient learning is multidimensional and we already see some parts of this puzzle being assembled. One question is the interplay between the requirements on different resources. Can we use more of one resource to save on a different resource? For example, the dependence between computation and observations requirements was studied in [SSS08,SSST12,SSB12]. Another question is online learning under various budget constraints [AKKS12,BKS13,CKS04,DSSS05,CBG06]. One example that Badanidiyuru et al. provide is dynamic pricing with limited supply, where we have a limited number of items to sell and on each successful sale transaction we lose one item. A related question of online learning under constraints on information acquisition was studied in [SBCA13], where the constraints could be computational or monetary. Yet another direction is adaptation of algorithms to the complexity of operation environment. Such adaptation can allow resource consumption to reflect the hardness of a situation being faced. An example of such adaptation in multiarmed bandits with side information was given in [SAL+11]. Another way of adaptation is interpolation between stochastic and adversarial environments. At the moment there are two prevailing formalisms for modeling the environment, stochastic and adversarial (also known as ``the average case'' and ``the worst case''). But in reality the environment is often neither stochastic, nor adversarial, but something in between. It is, therefore, crucial to understand the intermediate regime. First steps in this direction were done in [BS12]. And, of course, one of the flagman problems nowadays is ``big data'', where the constraint shifts from the number of observations to computation. We strongly believe that there are deep connections between problems at various scales and with various resource constraints and there are basic principles of learning under resource constraints that are yet to be discovered. We invite researchers to share their practical challenges and theoretical insights on this problem. Study of resource-efficient learning also require design of resource-dependent performance measures. In the past, algorithms were compared in terms of predictive accuracy (classification errors, AUC, F-measures, NDCG, etc.), yet there is a need to evaluate them with additional metrics related to resources, such as memory, CPU time, and even power. For example, reward per computational operation. This theme will also be discussed at the workshop. References: [AKKS12] Kareem Amin, Michael Kearns, Peter Key and Anton Schwaighofer. Budget Optimization for Sponsored Search: Censored Learning in MDPs. UAI 2012. [BB11] Leon Bottou and Olivier Bousquet. The trade-offs of large scale learning. In Suvrit Sra, Sebastian Nowozin, and Stephen J. Wright, editors, Optimization for Machine Learning. MIT Press, 2011. [BKS13] Ashwinkumar Badanidiyuru, Robert Kleinberg and Aleksandrs Slivkins. Bandits with Knapsacks. FOCS, 2013. [BS12] Sebastien Bubeck and Aleksandrs Slivkins. The best of both worlds: stochastic and adversarial bandits. COLT, 2012. [CBG06] Nicol? Cesa-Bianchi and Claudio Gentile. Tracking the best hyperplane with a simple budget perceptron. COLT 2006. [CKS04] Koby Crammer, Jaz Kandola and Yoram Singer. Online Classification on a Budget. NIPS 2003. [DSSS05] Ofer Dekel, Shai Shalev-shwartz and Yoram Singer. The Forgetron: A kernel-based perceptron on a fixed budget. NIPS 2004. [SAL+11] Yevgeny Seldin, Peter Auer, Fran?ois Laviolette, John Shawe-Taylor, and Ronald Ortner. PAC-Bayesian Analysis of Contextual Bandits. NIPS, 2011. [SBCA13] Yevgeny Seldin, Peter Bartlett, Koby Crammer, and Yasin Abbasi-Yadkori. Prediction with Limited Advice and Multiarmed Bandits with Paid Observations. 2013. [SSB12] Shai Shalev-Shwartz and Aharon Birnbaum. Learning halfspaces with the zero-one loss: Time-accuracy trade-offs. NIPS, 2012. [SSS08] Shai Shalev-Shwartz and Nathan Srebro. SVM Optimization: Inverse Dependence on Training Set Size. ICML, 2008. [SSST12] Shai Shalev-Shwartz, Ohad Shamir, and Eran Tromer. Using more data to speed-up training time. AISTATS, 2012. [VC74] Vladimir N. Vapnik and Alexey Ya. Chervonenkis. Theory of pattern recognition. Nauka, Moscow (in Russian), 1974. German translation: W.N.Wapnik, A.Ya.Tschervonenkis (1979), Theorie der Zeichenerkennug, Akademia, Berlin. Call for Sponsors Your logo could be here.... If you are interested to sponsor this event, please, contact yevgeny.seldin at gmail. Call for Contributions We invite submission of *abstracts and open problems* to the workshop. Abstracts and open problems should be at most 4 pages long in the NIPS format . Appendices are allowed, but the organizers reserve the right to evaluate the submissions based on the first 4 pages only. Submissions should be NOT anonymous. Selected abstracts and open problems will be presented as talks or posters during the workshop. Contributions should be emailed to yevgeny.seldin at gmail. IMPORTANT DATES *Submission Deadline:* October 23. *Notification of Acceptance:* November 6. EVALUATION CRITERIA * Theory and application-oriented contributions are equally welcome. * All submissions should emphasize relevance to the workshop subject. * Submission of previously published work or work under review is allowed, in particular NIPS-2013 submissions. However, for oral presentations preference will be given to novel work or work that was not yet presented elsewhere (for example, recent journal publications or NIPS posters). All double submissions must be clearly declared as such! Invited Speakers (tentative) Alexandrs Slivkins , Microsoft Research Michael Mahoney , Stanford Organizers Yevgeny Seldin , Queensland University of Technology and UC Berkeley Koby Crammer , The Technion Yasin Abbasi-Yadkori , Queensland University of Technology and UC Berkeley Ralf Herbrich , Amazon Peter Bartlett , UC Berkeley and Queensland University of Technology Schedule TBA -------------- next part -------------- An HTML attachment was scrubbed... URL: From fmschleif at googlemail.com Wed Oct 9 13:31:18 2013 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Wed, 9 Oct 2013 19:31:18 +0200 Subject: Connectionists: 2nd Call for papers - Special Session on 'Learning of structured and non-standard data' at ESANN 2014 Message-ID: [Apologies if you receive multiple copies of this CFP] Call for Papers - Special Session on 'Learning of structured and non-standard data' 23-25 April 2014, Bruges, Belgium http://www.dice.ucl.ac.be/esann AIMS AND SCOPE Today real life data are often given not in the form of vectorial data but in various formats often without an underlying metric space. Prominent examples are network structured data e.g. from social or communication networks, tree structured data used to represent hierarchical documents or collections thereof. Also the simple relation between objects e.g. by means of score data found in sequence alignments or rating information as obtained in collaborative filtering approaches is of this type. The recent technological developments, also in the context of big data, allow the generation of very complex data sets. Challenges are now in the effective processing of these data, in the light of the pure amount, but also to keep the obtained model informative for subsequent analysis. These data are also often given without an explicit vector space, point relations can be asymmetric, metric properties may not be valid and the available information if often sparse in different representations. Computational intelligence methods have the potential to be used to pre-process, model and to analyze such complex data but new strategies are needed. A very effective way is to employ explicit or implicit knowledge about the data, or the analysis task and to learn an appropriate model from available training data. In other cases the knowledge is used in the design of adaptive analysis algorithms to generate the desired meta information out of the data. Such knowledge may be available by means of appropriate (bio-)physical models, data specific distance measures, auxiliary information associated with the data. or dedicated processing strategies for non-metric data employing infinite kernels or dissimilarity learning approaches. Also novel data encoding techniques and projection methods, employing concepts from randomization algorithm, have been used to obtain compact descriptions of these complex data sets or to identify relevant information. Examples of such data analysis problems are e.g. in the analysis of biological or social networks with a large number of measurements and complex data relations. TOPICS We encourage submission of papers on novel methods for structured data, dissimilarity learning, non-standard data analysis and non-metric data processing by means of computational intelligence and machine learning approaches, including but not limited to: - data analysis and pattern recognition approaches for structured data - dissimilarity learning - methods employing ex- and implicit data knowledge for non-standard data - representation and modeling of heterogeneous, high-dimensional, multi-modal (structured) and/or non-standard data - approaches in the line of matrix completion, collaborative filtering, reduction techniques for non-standard data - large scale network analysis IMPORTANT DATES Paper submission deadline : 29 November 2013 Notification of acceptance : 31 January 2014 Deadline for final papers : 21 February 2014 The ESANN 2014 conference : 23-25 April 2014 SPECIAL SESSION ORGANIZERS: Frank-Michael Schleif, University of Appl. Sc. Mittweida, Germany and University of Birmingham, Birmingham, UK Thomas Villmann, University of Appl. Sc. Mittweida, Germany Peter Tino, University of Birmingham, Birmingham, UK From t.nowotny at sussex.ac.uk Thu Oct 10 10:32:26 2013 From: t.nowotny at sussex.ac.uk (Thomas Nowotny) Date: Thu, 10 Oct 2013 15:32:26 +0100 Subject: Connectionists: New 4 year PhD program in Neuroscience at the University of Sussex Message-ID: <5256BA7A.30006@sussex.ac.uk> 4-year PhD Programme in Neuroscience The aim of the Sussex Neuroscience 4-Year PhD Programme is to provide a broader research training in Neuroscience than is possible in a traditional 3-year PhD. We also encourage interdisciplinarity by making it possible for students with a background in psychological or physical sciences to transition to Neuroscience. Students will spend the first year completing intensive courses and up to three rotations in laboratories participating in the Programme. Topics available include molecular & cellular biology, neurophysiology, learning, behavioural and cognitive neuroscience, psychology, development, sensory systems, computational neuroscience, functional imaging, neurodegeneration and translational neuroscience. Students will be selected on the basis of their potential to tackle and solve difficult intellectual and experimental challenges. Previous training in quantitative disciplines (e.g. physics, mathematics, computer science), biological sciences (e.g. biology, medicine, bioengineering), psychology or related fields is important. The Programme is administered by Sussex Neuroscience, a community of about 50 research groups with diverse interests covering all major areas of contemporary Neuroscience (http://www.sussex.ac.uk/sussexneuroscience/). Tuition fees and stipends will be ensured for successful applicants of all nationalities for a period of 4 years. The application deadline is January 13th, 2014. For further information and potential projects, see:http://www.sussex.ac.uk/sussexneuroscience/study/4yearphd Further information on eligibility, entrance requirements and application procedures are available here. For further information you can also contact Ruth Staras (r.staras at sussex.ac.uk) or Leon Lagnado (l.lagnado at sussex.ac.uk). -- Prof. Thomas Nowotny CCNR, Sussex Neuroscience Phone: +44-1273-678593 Engineering and Informatics Fax: +44-1273-877873 University of Sussex Falmer, Brighton BN1 9QJ http://sussex.ac.uk/informatics/tnowotny From christopher.honey at gmail.com Thu Oct 10 13:22:22 2013 From: christopher.honey at gmail.com (Christopher Honey) Date: Thu, 10 Oct 2013 13:22:22 -0400 Subject: Connectionists: Postdoctoral Position in Computational Cognitive Neuroscience at the University of Toronto Message-ID: *Postdoctoral Position in Computational Cognitive Neuroscience* Department of Psychology, University of Toronto A postdoctoral position is available in the lab of Christopher Honey at the University of Toronto. This is a new lab, established to study large-scale systems properties of the human brain. Research topics include: regulation of inter-regional communication; temporal integration and memory in hierarchical circuits; the neural basis of situation models. The primary research tools are neuroimaging (fMRI & DWI), electrocorticography (ECoG) and computational modeling. There is opportunity for collaborating with clinical researchers, especially in the domains of epilepsy and dementia. The ideal candidate will have a strong quantitative background, experience running cognitive neuroscience experiments and proficiency in MATLAB/Python/R. The lab will be located downtown in Toronto, which is a liveable and cosmopolitan city with a vibrant academic and biomedical community. The post will provide local and international opportunities for collaborating and conferencing. This is a full-time position with benefits. The initial appointment will be for one year, renewable to four, and the start date is flexible from March 2014 onward. Applicants should email a CV, brief research statement, relevant publications, and contact details for two academic references to: choney at princeton.edu More information and prior papers are available at www.princeton.edu/~choney/ . -------------- next part -------------- An HTML attachment was scrubbed... URL: From brian.mingus at colorado.edu Thu Oct 10 11:54:15 2013 From: brian.mingus at colorado.edu (Brian J Mingus) Date: Thu, 10 Oct 2013 09:54:15 -0600 Subject: Connectionists: Connectionists digests will now be sent weekly Message-ID: Hi all, I have received a number of complaints that monthly digests are not frequent enough, resulting in stale postings. Therefore, I have changed the settings so that digests will be sent weekly. Please let me know if you are not receiving digests, or if any other complications arise. The mailman settings are rather complicated. Thanks, Brian https://www.linkedin.com/profile/view?id=74878589 -------------- next part -------------- An HTML attachment was scrubbed... URL: From rish at us.ibm.com Thu Oct 10 13:35:49 2013 From: rish at us.ibm.com (Irina Rish) Date: Thu, 10 Oct 2013 13:35:49 -0400 Subject: Connectionists: CFP: Deadline Extended: MLINI-2013: 3rd Workshop on Machine Learning and Interpretation in Neuroimaging at NIPS-2013 Message-ID: MLINI-2013: 3rd Workshop on Machine Learning and Interpretation in Neuroimaging at NIPS-2013 https://sites.google.com/site/mlininips2013/ December 9-10, 2013, Lake Tahoe, Nevada, United States Submission deadline: October 18th, 2013 Workshop Overview: ----------------------- MLINI is a two day workshop on the topic of machine learning approaches in neuroscience and neuroimaging. The goal of the workshop is to pinpoint the most pressing issues and common challenges across the fields, and to sketch future directions and open questions in the light of novel methodology. The workshop aims at providing a forum that joins machine learning, neuroscience, psychology and psychiatry community, and should facilitate formulating and discussing the issues at their interface.? Motivated by two previous workshops, MLINI ?11 and MLINI?12, we will center this workshop around invited talks, and two panel discussions. Triggered by these discussions, this year we plan to adapt the workshop topics to a less traditional scope that investigates the role of machine learning in neuroimaging of both animals and humans, as well as in behavioral models and psychology. Open questions and possible topics for contribution will be structured around the following 4 main topics: - Machine learning and pattern analysis methodology in neuroimaging - Functional networks and dynamical models of the brain - Multi-modal analysis of? mental state inference from imaging and/or behavioral data - Linking machine learning, neuroimaging and neuroscience Workshop Format: -------------------------- In this two-day workshop we will explore perspectives and novel methodology at the interface of Machine Learning, Inference, Neuroimaging and Neuroscience. We aim to bring researchers from machine learning and neuroscience community together, in order to discuss open questions, identify the core points for a number of the controversial issues, and eventually propose approaches to solving those issues. Each session will be opened by 2-3 invited talks, and an in depth discussion. This will be followed by original contributions. Original contributions will also be presented and discussed during a poster session. The workshop will end with a panel discussion, during which we will address specific questions, and invited speakers will open each segment with a brief presentation of their opinion. Paper Submission: -------------------------- We seek for submission of original (previously unpublished) research papers. The length of the?submitted papers?should not exceed 8 pages?in Springer format,??excluding the references (LaTeX2e style ?files?are available on the workshop page). Submission of previously published work is possible as well, but the authors are required to mention this explicitly. Previously published work can be presented at the workshop, but will not be included into the workshop proceedings (which are considered peer-reviewed publications of novel contributions). ?Moreover, the authors are welcome to present their novel work but choose to opt out of the workshop proceedings in case they have alternative publication plans. Important dates: -------------------------- - ?October 11, 2013 - paper submission - ?October 26, 2012? -? notification of acceptance/rejection - ?December 9-10, 2013 - ?Workshop in Lake Tahoe, Nevada US, following the NIPS conference Organizing Committee: -------------------------- Guillermo Cecchi (IBM T.J. Watson Research Center) Kai-min Kevin Chang (Language Technologies Institute, Carnegie Mellon University) Georg?Langs?(Medical University of Vienna, CSAIL, MIT) Brian Murphy?(Machine Learning Department, Carngie Mellon University) Irina?Rish?(IBM T.J. Watson Research Center) -------------- next part -------------- An HTML attachment was scrubbed... URL: From mzachariou at cs.ucy.ac.cy Thu Oct 10 12:56:56 2013 From: mzachariou at cs.ucy.ac.cy (Margarita Zachariou) Date: Thu, 10 Oct 2013 19:56:56 +0300 Subject: Connectionists: =?windows-1252?q?Computational_Neuroscience_Socia?= =?windows-1252?q?l_=96_SfN_2013?= Message-ID: <5256DC58.3020401@cs.ucy.ac.cy> Dear all, Join us for this year's Computational Neuroscience Social at the Society for Neuroscience meeting in San Diego. This is a purely social and networking event to celebrate the thriving field of computational neuroscience. Reunite with old friends, make new ones, mingle with some of the top researchers in the field, and find out all about upcoming conferences, summer schools, professional opportunities, and much more. Everybody is welcome! *Special Guests:* Gy?rgy Buzs?ki, Carmen Canavier, Alain Destexhe, Michele Giugliano, Eugene Izhikevich, Abigail Morrison, Panayiota Poirazi, John Rinzel, Terrence Sejnowski, Yulia Timofeeva, Misha Tsodyks. *Date: *Tuesday, November 12, 6:45-8:45 PM *Location:* San Diego Marriott Marquis: Marriott 3 *Info:* http://www.sfn.org/annual-meeting/neuroscience-2013/abstracts-and-sessions/sfn-sponsored-socials Hope to see you all there! Margarita Zachariou. -- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Dr Margarita Zachariou DIDAKTOR Research Fellow Department of Computer Science University of Cyprus http://www.cs.ucy.ac.cy/~mzachar/ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -------------- next part -------------- An HTML attachment was scrubbed... URL: From peortega at dcc.uchile.cl Thu Oct 10 18:32:43 2013 From: peortega at dcc.uchile.cl (Pedro Ortega) Date: Thu, 10 Oct 2013 18:32:43 -0400 Subject: Connectionists: Extended Deadline for Submissions (Oct 16) - NIPS Workshop on Planning with Information Constraints Message-ID: ======================================================= CfP - EXTENDED DEADLINE: Oct 16, 2013 Workshop on Planning with Information Constraints for Control, Reinforcement Learning, Comp. Neuroscience, Robotics and Games http://www.seas.upenn.edu/~ope/workshop/ NIPS 2013, Lake Tahoe, Nevada, United States, December 9, 2013 ======================================================= We have extended our deadline for contributions to October 16, 2013. Submissions in PDF should be emailed to ope at seas.upenn.edu with the subject line "NIPS 2013 Workshop Submission" no later than October 16, 2013. Submissions should be 4-8 pages in NIPS format, with an extra page for references if necessary. Authors of the selected papers will be notified to present their work through short talks or posters presentations. ** About ** How do you make decisions when there are way more possibilities than you can analyze? How do you decide under such information constraints? Planning and decision-making with information constraints is at the heart of adaptive control, reinforcement learning, robotic path planning, experimental design, active learning, computational neuroscience and games. In most real-world problems, perfect planning is either impossible (computational intractability, lack of information, diminished control) or sometimes even undesirable (distrust, risk sensitivity, level of cooperation of the others). Recent developments have shown that a *single method*, based on the free energy functional borrowed from thermodynamics, provides a principled way of designing systems with information constraints that parallels Bayesian inference. This single method -known in the literature under various labels such as KL-control, path integral control, linearly-solvable stochastic control, information-theoretic bounded rationality- is proving itself very general and powerful as a foundation for a novel class of probabilistic planning problems. ** Organizers ** Bert J. Kappen Naftali Tishby Jan Peters David H. Wolpert Evangelos Theodorou Pedro A. Ortega From janla at dtu.dk Fri Oct 11 08:35:58 2013 From: janla at dtu.dk (Jan Larsen) Date: Fri, 11 Oct 2013 12:35:58 +0000 Subject: Connectionists: Call for papers - 4th International Workshop on Cognitive Information Processing Message-ID: CIP2014 CALL FOR PAPERS http://cip2014.conwiz.dk Schedule Special session proposal: December 1, 2013 Submission of full paper: January 15, 2014 Notification of acceptance: March 5, 2014 Camera-ready paper: April 5, 2014 Advance registration before: April 5, 2014 Following the success of three previous editions, the 4th International Workshop on Cognitive Information Processing (CIP2014) aims at bringing together researchers from the machine learning, cognitive engineering, human-machine interaction, pattern recognition, statistical signal processing in an effort to promote and encourage cross-fertilization of ideas and tools. CIP 2014 will take place May 26-28 2014 at the Bella Sky Hotel, Copenhagen, Denmark. The workshop will feature keynote addresses and technical presentations, oral and poster, all of which will be included in the workshop proceedings. Papers are solicited for the following areas in theory and applications: Theory Areas * Machine learning theory and algorithms * Cognitive principles for machine architectures and training * Adaptive and sparsity-aware learning * Cognitive psychology modeling * Machine understanding and human-machine interaction * Cognitive dynamic systems * Cognitive fuzzy methods and techniques * Cognitive approaches to decision making and game theory * Collaborative sensing * Algorithms and Tools for Large-Scale Machine Learning Application Areas * Sound and audio systems * Datamining, textmining, * Sentiment analysis * Social networks, social science * Medicine, neuroimaging, bioinformatics, * Energy and smart grids, advanced manufacturing, * Robotics, artificial vision, * Engineering systems, industrial processes, * Economy and finance * Cognitive communications: Modulation, networks, dynamic spectrum management and personalization * Cognitive radar and sonar: Detection, estimation, tracking and target identification Special Sessions Special sessions are solicited in the same areas. Please suggest the topic and 3-5 potential speakers to Program Chair Jan Larsen (cip2014-programchair.conwiz.dk) before December 1, 2013. Student Paper Prize A prize of 500.00 EUR will recognize the best contribution whose first author is a graduate student. The award will be presented during the conference and consists of a honorarium (to be divided equally between all student authors of the paper), and a certificate for each such author. The award will be selected by a subcommittee of the program committee and based on the quality, originality, and clarity of the submission. Paper submission Prospective authors are invited to submit a double column paper of up to six pages. Accepted papers will be published in an online proceedings available to workshop registrants. The proceedings will further be published by an internationally recognized publishing house. We are seeking collaboration with IEEE Xplore. For more information and paper submission visit http://cip2014.conwiz.dk You are very welcome to share this call for paper with relevant lists and individuals. Best regards, General Chair, Professor Lars Kai Hansen, DTU Compute, Technical University of Denmark, Denmark Vice Chair, Professor S?ren Holdt Jensen, Department of Electronic Systems, Aalborg University, Denmark Program Chair, Associate Professor Jan Larsen, DTU Compute, Technical University of Denmark, Denmark -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: cip2014_cfp.pdf Type: application/pdf Size: 311359 bytes Desc: cip2014_cfp.pdf URL: From conradt at tum.de Mon Oct 14 04:52:08 2013 From: conradt at tum.de (=?iso-8859-1?Q?J=F6rg_Conradt?=) Date: Mon, 14 Oct 2013 08:52:08 +0000 Subject: Connectionists: BCCN Sparks Workshop Announcement: Neuroengineering the Brain Message-ID: <60e75165-c417-4880-aa11-8139c95b1685@BADWLRZ-SWHBT2.ads.mwn.de> Dear Colleagues, we cordially invite you to the BCCN Sparks Workshop Neuroengineering the Brain: from Neuroscience to Robotics ... and back taking place December 2-4, 2013 near Munich, Germany. The workshop brings together leading researchers in the border areas between computational neuroscience and systems engineering with a focus on robotics, to discuss currently available neuromorphic computing approaches applicable in future technical systems. Detailed information: http://www.sparks2013.de Attendance is limited; please register on the web pages as soon as possible if you want to attend. Seats will be allocated on first-come-first-served basis. We are very much looking forward to your participation! The workshop organizing team Jorg Conradt, Gordon Cheng, Stefan Ehrlich, Susanne Schneider -- J?rg Conradt Prof. of Neuroscientific System Theory www.nst.ei.tum.de Cluster "Cognition for Technical Systems" www.cotesys.org Institute of Automatic Control Engineering www.lsr.ei.tum.de Technische Universit?t M?nchen, Karlstr. 45, 80333 Munich, Germany Tel: +49 89 289-26902, Fax: +49 89 289-26901, E-mail: conradt at tum.de -------------- next part -------------- An HTML attachment was scrubbed... URL: From grlmc at urv.cat Sat Oct 12 06:14:41 2013 From: grlmc at urv.cat (GRLMC) Date: Sat, 12 Oct 2013 12:14:41 +0200 Subject: Connectionists: LATA 2014: extended submission deadline 21 October Message-ID: *To be removed from our mailing list, please respond to this message with UNSUBSCRIBE in the subject line* ---------------------------------------------------------------------------- ***** SUBMISSION DEADLINE EXTENDED: October 21 ***** ---------------------------------------------------------------------------- ************************************************************************* 8th INTERNATIONAL CONFERENCE ON LANGUAGE AND AUTOMATA THEORY AND APPLICATIONS LATA 2014 Madrid, Spain March 10-14, 2014 Organized by: Research Group on Implementation of Language-Driven Software and Applications (ILSA) Complutense University of Madrid Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University http://grammars.grlmc.com/lata2014/ ********************************************************************* AIMS: LATA is a yearly conference on theoretical computer science and its applications. Following the tradition of the diverse PhD training events in the field developed at Rovira i Virgili University in Tarragona since 2002, LATA 2014 will reserve significant room for young scholars at the beginning of their career. It will aim at attracting contributions from both classical theory fields and application areas (bioinformatics, language technology, artificial intelligence, etc.). VENUE: LATA 2014 will take place in Madrid, the capital of Spain. The venue will be the School of Informatics of Complutense University. SCOPE: Topics of either theoretical or applied interest include, but are not limited to: algebraic language theory algorithms for semi-structured data mining algorithms on automata and words automata and logic automata for system analysis and programme verification automata, concurrency and Petri nets automatic structures cellular automata codes combinatorics on words compilers computability computational complexity data and image compression decidability issues on words and languages descriptional complexity DNA and other models of bio-inspired computing digital libraries and document engineering foundations of finite state technology foundations of XML fuzzy and rough languages grammars (Chomsky hierarchy, contextual, unification, categorial, etc.) grammatical inference and algorithmic learning graphs and graph transformation language varieties and semigroups language-based cryptography language-theoretic foundations of artificial intelligence and artificial life natural language and speech automatic processing parallel and regulated rewriting parsing patterns power series quantum, chemical and optical computing semantics string and combinatorial issues in computational biology and bioinformatics string processing algorithms symbolic dynamics symbolic neural networks term rewriting transducers trees, tree languages and tree automata weighted automata STRUCTURE: LATA 2014 will consist of: invited talks invited tutorials peer-reviewed contributions INVITED SPEAKERS: Javier Esparza (Munich Tech, DE), On Trees and Fixed Point Equations (tutorial) Leslie A. Goldberg (Oxford, UK), The Complexity of Approximate Counting Oscar H. Ibarra (Santa Barbara, US), Some Computability and Complexity Problems Concerning FAs, PDAs, and Counter Machines Sanjeev Khanna (Philadelphia, US), tba Helmut Seidl (Munich Tech, DE), Interprocedural Information Flow Analysis of XML Processors PROGRAMME COMMITTEE: Dana Angluin (Yale, US) Eugene Asarin (Paris Diderot, FR) Jos Baeten (Amsterdam, NL) Christel Baier (Dresden, DE) Jan Bergstra (Amsterdam, NL) Jin-Yi Cai (Madison, US) Marek Chrobak (Riverside, US) Andrea Corradini (Pisa, IT) Mariangiola Dezani (Turin, IT) Ding-Zhu Du (Dallas, US) Michael R. Fellows (Darwin, AU) J?rg Flum (Freiburg, DE) Nissim Francez (Technion, IL) J?rgen Giesl (Aachen, DE) Annegret Habel (Oldenburg, DE) Kazuo Iwama (Kyoto, JP) Sampath Kannan (Philadelphia, US) Ming-Yang Kao (Northwestern, US) Deepak Kapur (Albuquerque, US) Joost-Pieter Katoen (Aachen, DE) S. Rao Kosaraju (Johns Hopkins, US) Evangelos Kranakis (Carleton, CA) Gad M. Landau (Haifa, IL) Andrzej Lingas (Lund, SE) Jack Lutz (Iowa State, US) Ian Mackie (?cole Polytechnique, FR) Carlos Mart?n-Vide (Tarragona, ES, chair) Giancarlo Mauri (Milan, IT) Faron G. Moller (Swansea, UK) Paliath Narendran (Albany, US) Enno Ohlebusch (Ulm, DE) Helmut Prodinger (Stellenbosch, ZA) Jean-Fran?ois Raskin (Brussels, BE) Wolfgang Reisig (Humboldt Berlin, DE) Marco Roveri (Bruno Kessler, Trento, IT) Micha?l Rusinowitch (LORIA, Nancy, FR) Yasubumi Sakakibara (Keio, JP) Davide Sangiorgi (Bologna, IT) Colin Stirling (Edinburgh, UK) Jianwen Su (Santa Barbara, US) Jean-Pierre Talpin (IRISA, Rennes, FR) Andrzej Tarlecki (Warsaw, PL) Rick Thomas (Leicester, UK) Sophie Tison (Lille, FR) Rob van Glabbeek (NICTA, Sydney, AU) Helmut Veith (Vienna Tech, AT) ORGANIZING COMMITTEE: Adrian Horia Dediu (Tarragona) Ana Fern?ndez-Pampill?n (Madrid) Carlos Mart?n-Vide (Tarragona, co-chair) Antonio Sarasa (Madrid) Jos?-Luis Sierra (Madrid, co-chair) Bianca Truthe (Magdeburg) Florentina Lilica Voicu (Tarragona) SUBMISSIONS: Authors are invited to submit non-anonymized papers in English presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (including eventual appendices) and should be formatted according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0). Submissions have to be uploaded to: https://www.easychair.org/conferences/?conf=lata2014 PUBLICATIONS: A volume of proceedings published by Springer in the LNCS series will be available by the time of the conference. A special issue of a major journal will be later published containing peer-reviewed extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation. REGISTRATION: The period for registration is open from July 15, 2013 to March 10, 2014. The registration form can be found at: http://grammars.grlmc.com/lata2014/Registration.php DEADLINES: Paper submission: October 21, 2013 (23:59 CET) ? EXTENDED ? Notification of paper acceptance or rejection: November 25, 2013 Final version of the paper for the LNCS proceedings: December 2, 2013 Early registration: December 9, 2013 Late registration: February 24, 2014 Starting of the conference: March 10, 2014 End of the conference: March 14, 2014 Submission to the post-conference journal special issue: June 14, 2014 QUESTIONS AND FURTHER INFORMATION: florentinalilica.voicu at urv.cat POSTAL ADDRESS: LATA 2014 Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University Av. Catalunya, 35 43002 Tarragona, Spain Phone: +34 977 559 543 Fax: +34 977 558 386 ACKNOWLEDGEMENTS: Departament d?Economia i Coneixement, Generalitat de Catalunya Universidad Complutense de Madrid Universitat Rovira i Virgili From info.cognition at plymouth.ac.uk Mon Oct 14 07:49:24 2013 From: info.cognition at plymouth.ac.uk (Info Cognition (General Enquiries)) Date: Mon, 14 Oct 2013 11:49:24 +0000 Subject: Connectionists: 26 PhD studentships - CogNovo Message-ID: <6173FEB6C6EE9840A9253B8C57EC19D2B84E@TIS105.uopnet.plymouth.ac.uk> APOLOGIES FOR ANY CROSS-POSTING! 14 Marie-Curie funded Research Fellowships and 12 Plymouth University funded PhD studentships are available for positions in the Marie Curie Initial training Network "CogNovo" www.cognovo.eu New projects have now been posted: http://www.cognovo.eu/projects2/ Marie Curie Early Career Research Fellowships (PhD): 14 positions Cognition Institute | Plymouth University Closing date for applications: 12 noon, 30 November 2013 Fixed term 36 months, starting 1st April 2014 The CogNovo project is offering fourteen early career research fellowships. CogNovo is an Innovative Doctoral Programme funded by the EU Marie Curie initiative and Plymouth University to foster research in the emerging field of Cognitive Innovation. CogNovo offers transdisciplinary research training that combines scientific studies of the neural correlates and mechanisms of creativity, with investigations into the role of creativity in human cognition, and their application in sustainable technological and social innovation. Selected candidates will be registered for a comprehensive PhD programme that includes specialised research on specific topics, as well as training workshops covering experimental methods, cognitive neuroscience, computational modelling, humanities and human values, experimental psychology, creative arts, cognitive robotics and entrepreneurship. CogNovo also offers secondment opportunities to academic and commercial partners across the world. Candidates should apply for specific projects, indicating their top 3 choices. For further details of CogNovo and the research projects available, please see: www.cognovo.eu. Application forms are available for download from the website. Eligibility: Marie Curie funding is intended to promote mobility of early career researchers within the research community; candidates must: a) have received a degree (Bachelor or Master's) that qualifies them for PhD training (project-specific educational prerequisites vary and are indicated in the project web-pages), b) should not have undertaken more than 4 years of fulltime research subsequent to that degree, and c) should not have been resident within the UK for more than 12 months within the 3 years prior to 1 April 2014. For a full description of the eligibility conditions see: http://ec.europa.eu/research/mariecurieactions/ An excellent 1st degree, good verbal and written communication skills in English, and an interest in multi-disciplinary research are essential. Specific educational prerequisites vary and are indicated in the project web-pages. More information on individual projects can be found on the CogNovo Projects Page. Salary: from ?35,000, including living and mobility allowance. Applicants should send a completed application form along with a covering letter detailing their suitability for the studentship, C.V. and 2 academic references to Catherine Johnson, Faculty of Science and Technology Research Office, Room A425, Portland Square, Plymouth PL4 8AA or e-mail catherine.johnson at plymouth.ac.uk. Plymouth University Research Studentships (PhD): 12 positions Cognition Institute | Plymouth University Closing date for applications: 12 noon, 30 November 2013 Fixed term 36 months, starting 1st April 2014 Twelve University-funded PhD positions are available on the CogNovo project. CogNovo is an Innovative Doctoral Programme funded by the EU Marie Curie initiative and Plymouth University to foster research in the emerging field of Cognitive Innovation. CogNovo offers transdisciplinary research training that combines scientific studies of the neural correlates and mechanisms of creativity, with investigations into the role of creativity in human cognition, and their application in sustainable technological and social innovation. Selected candidates will be registered for a comprehensive PhD programme that includes specialised research on specific topics, as well as training workshops covering experimental methods, cognitive neuroscience, computational modelling, humanities and human values, experimental psychology, creative arts, cognitive robotics and entrepreneurship. CogNovo also offers secondment possibilities to academic and commercial partners across the world. Candidates should apply for specific projects, indicating their top 3 choices. For further details of CogNovo and the research projects available, please see: www.cognovo.eu. Application forms are available for download from the website. Eligibility: An excellent 1st degree, good verbal and written communication skills in English, and an interest in multi-disciplinary research are essential. Specific educational prerequisites vary and are indicated in the project web-pages. More information on individual projects can be found on the CogNovo Projects Page. These positions are open to all UK and EU citizens with appropriate qualifications. Applicants who are normally required to pay overseas fees may also apply, but will have to cover the difference between the Home/EU and the overseas tuition fee rates (approximately ?9,790 per annum). For more details on university studentships, please visit www.plymouth.ac.uk/postgraduate. University studentships include full Home/EU tuition fees plus a stipend of ?13, 726 per annum. Submitting an application: Applicants should send a completed application form along with a covering letter detailing their suitability for the studentship, C.V. and 2 academic references to Catherine Johnson, Faculty of Science and Technology Research Office, Room A425, Portland Square, Plymouth PL4 8AA or e-mail catherine.johnson at plymouth.ac.uk. Shortlisted candidates will be invited for interview in January/February 2014. We regret that we may not be able to respond to all applications. Applicants who have not received an offer of a place by March 2014 should consider their application has been unsuccessful on this occasion. Dr Lucy Davies Cognition Institute Room A222, Portland Square Ext: 84920 Website: http://www1.plymouth.ac.uk/research/cognition/Pages/default.aspx Like us on Facebook: http://www.facebook.com/PlymCogInst Follow us on Twitter: https://twitter.com/PlymCogInst YouTube Channel: http://www.youtube.com/user/PlymouthCognition?feature=watch ________________________________ [http://www.plymouth.ac.uk/images/email_footer.gif] This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form. From conradt at tum.de Mon Oct 14 09:51:25 2013 From: conradt at tum.de (=?iso-8859-1?Q?J=F6rg_Conradt?=) Date: Mon, 14 Oct 2013 13:51:25 +0000 Subject: Connectionists: PostDoc opportunity in Distributed Neural Computation / Spatial Representation / Robotics at TU Munich Message-ID: Dear colleagues, the research group on Neuroscientific System Theory (NST) at Technische Universit?t Munich (TUM) invites applications for a PostDoc in the EU FET project "GRIDMAP: from brains to technical implementation" The project investigates the formation of grid cells in rodents and possible translations to unsupervised parallel processing computer architectures. The focus of the NST research group at TUM is on theoretical modeling and on distributed (robot based) implementations of processing algorithms. The ideal candidate has prior knowledge about neuronal spatial representations and a strong commitment/interest in (neuronal) parallel computing architectures, such as the SpiNNaker computing system. The position is available immediately with flexible start date. In exceptional cases applications for a PhD position will also be considered. Project consortium: Edvard Moser, Trondheim; Richard Morris, Edinburgh; Alessandro Treves, Trieste, J?rg Conradt, Munich The GRIDMAP project allows frequent exchange visits to the labs involved and provides further funding for conference travel. EU FET Project web pages: http://www.ntnu.edu/kavli/gridmap Research information about other projects at NST: http://www.nst.ei.tum.de/research/NST http://www.lsr.ei.tum.de/open-positions/other-open-positions/postdoc-neuroscience-and-robotics/ Please send **concise** applications, including a 10-lines motivation, CV, and publication list, by email to Jorg Conradt: conradt at tum.de Please forward to interested colleagues! Thank you! J?rg Conradt -- J?rg Conradt Prof. of Neuroscientific System Theory www.nst.ei.tum.de Cluster "Cognition for Technical Systems" www.cotesys.org Institute of Automatic Control Engineering www.lsr.ei.tum.de Technische Universit?t M?nchen, Karlstr. 45, 80333 Munich, Germany Tel: +49 89 289-26902, Fax: +49 89 289-26901, E-mail: conradt at tum.de -------------- next part -------------- An HTML attachment was scrubbed... URL: From brainresearch at hanmail.net Sat Oct 12 02:00:44 2013 From: brainresearch at hanmail.net (Soo-Young Lee) Date: Sat, 12 Oct 2013 15:00:44 +0900 (KST) Subject: Connectionists: PostDoc and Research Professor Positions at Computational NeuroSystems Lab and Brain Science Research Center, KAIST Message-ID: <20131012150044.HM.b000000000Dr4u8@brainresearch.wwl1406.hanmail.net> An HTML attachment was scrubbed... URL: From irodero at cac.rutgers.edu Sun Oct 13 00:14:46 2013 From: irodero at cac.rutgers.edu (Ivan Rodero) Date: Sun, 13 Oct 2013 00:14:46 -0400 Subject: Connectionists: CiSE Extreme Data - Call for Papers In-Reply-To: <828ECB55-3292-4D46-9F21-A4C18EF2F712@rutgers.edu> References: <51EC7783-DCAD-4364-B1DC-576C726BAA31@rutgers.edu> <828ECB55-3292-4D46-9F21-A4C18EF2F712@rutgers.edu> Message-ID: <5F86C42F-E15F-49FC-9AA3-FBBCA55BA44D@rutgers.edu> ------------------------------------------------------------------------------------------------------ Please accept our apologies if you receive multiple copies of this CFP! ------------------------------------------------------------------------------------------------------ Call for Papers Computing in Science & Engineering Extreme Data Submissions due: March 2014 Estimated Publication date: November 2014 The current era of extreme data culled from a range of diverse data sources, ranging from extreme scale simulations to instruments, experiments, and pervasive sensors and systems, has the potential for revolutionizing science, engineering, and society in general. However, the expanding distribution and dynamism of the data, increasing data heterogeneity and uncertainty about its quality and availability, as well as the growing costs (time and energy) associated with transporting and processing this data, requires new paradigms and practices in data management and analytics, as well as supporting software stacks before this potential can be realized. The goal of this special issue of CiSE is to explore the fundamental challenges ? as well as the state of the art in solutions ? of extreme data. From innovative algorithmic formulations to implementation frameworks and software stacks, what can accelerate insights from extreme data? End-to-end application workflows and relevant experiences with real applications are of particular interest. Published by the IEEE Computer Society and the American Institute of Physics, CiSE magazine features the latest computational science and engineering research in an accessible format, along with departments covering news and analysis, CSE in education, and emerging technologies. We strongly encourage submissions that include multimedia, data, and community content, which will be featured on the IEEE Computer Society website along with the accepted papers. For more information please see http://www.computer.org/portal/web/computingnow/cscfp4 Questions? Contact guest editors Manish Parashar, Rutgers University (parashar at rutgers.edu) or George K. Thiruvathukal, Loyola University Chicago (gkt at cs.luc.edu). Submission Guidelines Authors are asked to submit high-quality original work that has neither appeared in nor is under consideration by other journals. All submissions will be peer-reviewed following standard journal practices. Manuscripts based on previously published conference papers must be extended substantially to include at least 30 percent new material. Manuscripts should be written in the active voice, should be no longer than 7,200 words (counting each standard figure and table as 250 words), and should follow the style and presentation guidelines of CiSE (see www.computer.org/cise/author for details). Please submit your article using the online manuscript submission service at https://mc.manuscriptcentral.com/cs-ieee. When uploading your article, select the appropriate special-issue title under the category "Manuscript Type." Also include complete contact information for all authors. If you have any questions about submitting your article, contact the peer review coordinator at cise at computer.org. ============================================================= Ivan Rodero, Ph.D. Rutgers Discovery Informatics Institute (RDI2) NSF Center for Cloud and Autonomic Computing (CAC) Department of Electrical and Computer Engineering Rutgers, The State University of New Jersey Office: CoRE Bldg, Rm 625 94 Brett Road, Piscataway, NJ 08854-8058 Phone: (732) 993-8837 Fax: (732) 445-0593 Email: irodero at rutgers dot edu WWW: http://nsfcac.rutgers.edu/people/irodero ============================================================= -------------- next part -------------- An HTML attachment was scrubbed... URL: From irodero at cac.rutgers.edu Mon Oct 14 09:38:42 2013 From: irodero at cac.rutgers.edu (Ivan Rodero) Date: Mon, 14 Oct 2013 09:38:42 -0400 Subject: Connectionists: IEEE TCSC Award for Excellence in Scalable Computing -- Call for Nominations In-Reply-To: <2E3B7E33-6D9E-441E-A993-784AC5560153@rutgers.edu> References: <51EC7783-DCAD-4364-B1DC-576C726BAA31@rutgers.edu> <828ECB55-3292-4D46-9F21-A4C18EF2F712@rutgers.edu> <2E3B7E33-6D9E-441E-A993-784AC5560153@rutgers.edu> Message-ID: <5A66C314-2267-4708-B8C6-A7CBC1414CF0@rutgers.edu> ------------------------------------------------------------------------------------------------------ Please accept our apologies if you receive multiple copies of this CFN! ------------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------ The 2014 IEEE TCSC Award for Excellence in Scalable Computing A Call for Nominations ------------------------------------------------------------------------------------------ The IEEE TCSC Award for Excellence in Scalable Computing is awarded by the IEEE Technical Committee on Scalable Computing (TCSC) for significant and sustained contributions to scalable computing coupled with an outstanding record of high quality and high impact research. The award consists of a plaque and an honorarium of $1000. During 2008-2011, this honour was presented as the IEEE TCSC Medal for Excellence, and has since been renamed to the IEEE TCSC Award for Excellence. The past recipients of this IEEE award are: Professor Jack Dongarra (University of Tennessee, USA) in 2008, Professor Rajkumar Buyya (University of Melbourne, Australia) in 2009, Professor William Gropp (University of Illinois at Urbana-Champaign, USA) in 2010, Professor Albert Zomaya (University of Sydney, Australia) in 2011, Professor David Abramson (Monash University, Australia) in 2012, and Professor Marc Snir (Argonne National Laboratory, USA) in 2013. More details of the award can be found at the IEEE TCSC website: https://www.ieeetcsc.org/awards/award_for_excellence Nominations: A candidate may be nominated by colleagues/TCSC members or may nominate him/her-self. An individual can nominate at most one candidate for this award. The candidate must be an IEEE, IEEE CS, and TCSC member in good standing. Nomination must be submitted online (https://www.easychair.org/conferences/?conf=tcscexcellence2013). A nomination application (as a single PDF file) should contain the following details: 1. Professional Employment Affiliations: List the nominee's current professional affiliations and titles. 2. Citation: Give a brief citation (thirty words or less) precisely stating the most salient reason(s) why the nominee is qualified for the award. 3. Technical Contributions: Describe the nominee's technical achievements as well as significance and impact. (Max 2 page length) 4. TCSC Contribution: Describe the candidate?s service and specific contributions to TCSC and its community activities. (Max 2 page length) 5. Endorsers: Each nomination must be supported by letter from three at least endorsers. An endorser can endorse only one candidate for this award. The endorsers will be required to comment on the nominee's technical contributions as well as service to the TCSC and its community. It is nominator's responsibility to ensure that endorsement letters are submitted on/before the application deadline. Important Dates: Nomination Deadline: January 07, 2014 Results Notification: February 01, 2014 Award Selection Committee: The award selection committee will consist of past winners, leaders in the field, as well as members of the TCSC Executive Committee. The selection committee member cannot be a nominator or endorser. Award Presentation Note: The award will presented at the 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid 2014) to be held in Chicago, USA, from May 26-29, 2014. The winner should be available to receive the award in person and present an award acceptance speech, scheduled as a keynote talk at the CCGrid 2014 conference. For more information about the conference please see http://datasys.cs.iit.edu/events/CCGrid2014/. Chairs: Manish Parashar, Rutgers, The State University of New Jersey, USA (Email: parashar at rutgers dot edu) Beniamino Di Martino, Second University of Naples, Italy (Email: beniamino.dimartino at unina dot it) Selection Committee: David Abramson Monash University, Australia William Gropp, University of Illinois, USA Hai Jin, Huazhong University of Science and Technology, China Dieter Kranzlmueller Ludwig-Maximilians University (LMU), Germany Satoshi Matsuoka, Tokyo Institute of Technology, Japan Marc Snir, Argonne National Laboratory, USA Mateo Valero, UPC, Spain ============================================================= Ivan Rodero, Ph.D. Rutgers Discovery Informatics Institute (RDI2) NSF Center for Cloud and Autonomic Computing (CAC) Department of Electrical and Computer Engineering Rutgers, The State University of New Jersey Office: CoRE Bldg, Rm 625 94 Brett Road, Piscataway, NJ 08854-8058 Phone: (732) 993-8837 Fax: (732) 445-0593 Email: irodero at rutgers dot edu WWW: http://nsfcac.rutgers.edu/people/irodero ============================================================= -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Mon Oct 14 13:33:33 2013 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 14 Oct 2013 13:33:33 -0400 Subject: Connectionists: Workshop on parallel computation at SFN 2013 meeting Message-ID: <525C2AED.6070108@yale.edu> A few seats are still available for the workshop "Using the Neuroscience Gateway Portal for Parallel Simulations" which will be held from 9 AM to Noon on Saturday, Nov. 9, in downtown San Diego, CA, just a few blocks from the convention center. However, the registration deadline is Friday, Oct. 25, so you should act quickly if you're interested in learning how to use this free high performance computing resource. The Neuroscience Gateway Portal (NSG) http://www.nsgportal.org/ is designed for neuroscientists who need to use HPC resources for large modeling projects. It simplifies every aspect of the process, from applying for CPU time to uploading your model, launching and monotoring jobs, and downloading results. The NSG already has several parallel simulators installed, including Brian, MOOSE, NEST, NEURON, PGENESIS and PyNN. See http://www.neuron.yale.edu/neuron/static/courses/nsg2013/nsg2013.html for further details and the registration form. --Ted From ted.carnevale at yale.edu Tue Oct 15 10:43:53 2013 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 15 Oct 2013 10:43:53 -0400 Subject: Connectionists: NEURON course at SFN 2013 meeting Message-ID: <525D54A9.2070900@yale.edu> A few seats are still available for the course "Using NEURON to Model Cells and Networks" which will be held from 9 AM to 5 PM on Friday, Nov. 8, in downtown San Diego, CA, just a few blocks from the convention center. However, the registration deadline is Friday, Oct. 25, so you should act quickly if you want to sign up for this course. The course presents the principles and practical strategies for building and using models of cells and networks with NEURON. Among the topics to be covered are * Efficient design and implementation of models with NEURON's GUI and the hoc and Python programming languages. * Parallelizing models of cells and networks. * Expanding NEURON's repertoire of biophysical mechanisms. * Databases for empirically-based modeling. In addition, this year's course will introduce the latest enhancement to NEURON's multiscale modeling capabilities: RxD for reaction- diffusion modeling. For further details and the registration form see http://www.neuron.yale.edu/neuron/static/courses/sd2013/sd2013.html --Ted From ghio.alessandro at gmail.com Tue Oct 15 05:28:33 2013 From: ghio.alessandro at gmail.com (Alessandro Ghio) Date: Tue, 15 Oct 2013 11:28:33 +0200 Subject: Connectionists: "Byte the bullet: learning on real-world computing architectures" - ESANN 2014 Special Session Call for Papers Message-ID: <4BF26DFA-A1E6-4EA6-8387-7B38E160C1CD@gmail.com> *** Apologies for cross posting *** ESANN 2014 Special Session - "Byte the bullet: learning on real-world computing architectures" - CALL FOR PAPERS European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2014). 23-25 April 2014, Bruges, Belgium - http://www.esann.org Submissions are invited for next year ESANN Special Session "Byte the bullet: learning on real-world computing architectures". Organizers: Davide Anguita, Alessandro Ghio, Luca Oneto University of Genoa (Italy) ESANN 2014 Special Session "Byte the bullet: learning on real-world computing architectures" webpage: http://btb.smartlab.ws TOPICS In this special session, we would like to encourage submissions related to the development and the application of fast, effective, reliable techniques, which consider possibilities, potentialities and constraints of real-world computing architectures as basic cornerstones and motivations. This list includes (despite not being limited to): Bit-based models (e.g. bit-base reformulations, Weightless Neural Networks) & their applications (e.g. sensor networks) Learning on dedicated (e.g. GPU, FPGA) and unconventional (e.g. quantum computing systems) architectures Linear & sub-linear ML algorithms for High-Performance Computing Learning on large, distributed and cloud architectures. Note that: Theoretical, practical and applicative works are all welcome The relevance with reference to the Special Session topics should be emphasized by the authors in their submissions. ABSTRACT Fast, effective, reliable models: these are the desiderata of every theorist and practitioner. Machine Learning (ML) algorithms, proposed in the last decades, proved to be effective and reliable in solving complex real-world problems. A huge amount of work has been spent to properly reformulate or revise these techniques, which are usually designed without taking into account the destination computing architecture, in order to make them run as fast as possible. This effort is often motivated by application-specific requirements, such as the need to accelerate the learning process with dedicated/distributed hardware (e.g. cloud computing) or to foster energy-sparing requirements of applications based on mobile standalone devices (e.g. smartphones, sensor networks). Contemplating the destination computing architecture influences overall performance, but can also be exploited for implementation benefits: it is the case of quantum computing, and of recent advances in ML showing how the generalization capability of learnt models can take advantage of computational constraints in learning. SUBMISSION & IMPORTANT DATES We kindly invite you to submit a paper to this special session. Each paper will undergo to a peer reviewing process for its acceptance. Paper submission should be done exclusively through the ESANN portal following the instructions provided in: (http://www.elen.ucl.ac.be/esann/index.php?pg=submission). Paper submission deadline : 29 November 2013 Notification of acceptance : 31 January 2014 Deadline for final papers : 21 February 2014 ESANN 2014 conference : 23-25 April 2014 NOTES You can find details about the special session at http://btb.smartlab.ws. If you have any questions concerning the special session, please do not hesitate to contact us via email to: btb at smartlab.ws More information about the Conference Program, accommodation facilities and registration fees is available on the ESANN website www.esann.org --- Dr. Alessandro Ghio, Ph.D. DITEN - University of Genoa Via Opera Pia 11a, I-16145 Genoa (Italy) T. +39-(0)10-3532192 F. +39-(0)10-3532897 @ Alessandro.Ghio at smartlab.ws W http://smartlab.ws/ --- -------------- next part -------------- An HTML attachment was scrubbed... URL: From wegall at nsi.edu Tue Oct 15 12:10:42 2013 From: wegall at nsi.edu (W. Einar Gall) Date: Tue, 15 Oct 2013 09:10:42 -0700 Subject: Connectionists: The Neurosciences Institute Event on Friday, November 8, 2013 Message-ID: Good Morning, As many of you know, The Brain Corporation and The Neurosciences Institute will be co-sponsoring an event "The Neurosciences Institute: Past, Present and Future" on Friday, November 8, 2013. Below are the list of speakers (in alphabetical order) and a schedule. We hope that you will be able to attend. An R.S.V.P. is preferred so that we can ensure that there is enough food, space, and parking for everyone particularly at the reception. Please send an e-mail to meeting at nsi.edu. Thank you and we look forward to seeing you. ................................................................... The Neurosciences Institute: Past, Present, and Future Friday, November 8, 2013 Noon - 7 pm The Auditorium at 10640 John Jay Hopkins Drive, San Diego, CA 92121 This gathering will have a scientific program featuring presentations of current work by former Fellows of The Neurosciences Institute to celebrate thirty years of scientific impact. Confirmed speakers (in alphabetical order) include: Bernard Baars "Multiple Sources of Conscious Odor Integration and Propagation in Olfactory Cortex" Jeffrey Krichmar "Brain-Based Devices: Then and Now" Douglas Nitz "The Parietal Cortex as a Cognitive Map" Aniruddh Patel "The Evolutionary Neuroscience of Musical Rhythm Perception: Was Darwin Wrong?" Daniele Piomelli "So Many Lipids, So Little Time! A Journey in the Physiology and Pharmacologyof Lipid-mediated Signaling" Andrew Schwartz "Toward a High-Performance Brain-Computer Interface" Schedule: 12 noon - 1 pm Informal lunch 1 pm - 3 pm Presentations 3 pm - 3:30 pm Break 3:30 pm - 5:30 pm Presentations 5:30 pm - 7 pm Reception For additional information, please email meeting at nsi.edu or call 858-626-2000. This meeting is co-sponsored by Brain Corporation (Eugene Izhikevich, CEO) and The Neurosciences Institute. From jason at cs.jhu.edu Wed Oct 16 23:57:32 2013 From: jason at cs.jhu.edu (Jason Eisner) Date: Wed, 16 Oct 2013 23:57:32 -0400 Subject: Connectionists: Johns Hopkins University Jobs: Research Scientists and Postdocs Message-ID: The Human Language Technology Center of Excellence (HLTCOE) at Johns Hopkins University is hiring research scientists and postdocs. The HLTCOE already has a very strong group of researchers and is growing rapidly: http://hltcoe.jhu.edu/people/ Candidates interested in applying machine learning to NLP and speech processing should apply. http://hltcoe.jhu.edu The full advertisement is below. Best, Jason ------------------------------------------------------------ The Human Language Technology Center of Excellence (HLTCOE) at Johns Hopkins University seeks to hire outstanding junior and senior researchers in all areas of speech and language processing. Positions include research scientist and postdoc. The HLTCOE, located near Johns Hopkins? beautiful Homewood campus in Baltimore, Maryland, conducts long-term research on fundamental challenges that are critical for real-world problems. Its researchers publish widely. Applicants must hold a PhD in computer science, linguistics, electrical engineering, or a closely related field. Candidates should have a strong background in one or more of these areas: - *Natural Language Processing and Understanding:* Information extraction, knowledge distillation, semantics, sentiment, parsing, morphology, including low-resource languages - *Machine Translation:* Low-resource languages, large-scale training, phrase-based and syntax-based approaches - *Speech Processing:* Robust speech recognition and speaker identification (multiple languages, genres, and channels, limited resources), speech retrieval, language identification - *Machine Learning:* Large-scale learning, transfer learning, semi-supervised learning, data mining* * *Research Scientists* Research scientists are charged with setting the agenda for a program, working with other members of the HLTCOE research team to pursue the organization?s cutting-edge research goals, publishing results in academic conferences, and (optionally) working with or directly advising students and teaching University courses. *Senior applicants *should be an experienced researcher with a track record of high-quality publications, and should also have significant experience in project management and a demonstrated ability in building HLT systems. Senior applicants should have experience equivalent to the level of associate professor or 6+ years in industrial research. Applications will be considered on a rolling basis. *Junior applicants *should have a strong record of publication, and demonstrated research experience. Applicants should have experience equivalent to those applying to assistant professor positions, or 1-5 years in industry. Submit applications by January 3, 2014 for full consideration, however, applications will be accepted until positions have been filled. *Post-Docs* Recent PhD graduates may be considered for postdoctoral positions, which last from 1-2 years. Post-docs will be mentored by research scientists. Applications should be submitted here: https://academicjobsonline.org/ajo/jobs/2911 Email: hltcoe-hiring at jhu.edu WWW: http://hltcoe.jhu.edu *Note: U.S. Citizenship and security clearance are required for most positions; the HLTCOE will seek a clearance for those who do not already have one.* -------------- next part -------------- An HTML attachment was scrubbed... URL: From bengioy at iro.umontreal.ca Tue Oct 15 21:33:49 2013 From: bengioy at iro.umontreal.ca (Yoshua Bengio) Date: Tue, 15 Oct 2013 21:33:49 -0400 Subject: Connectionists: ICLR 2014 (International Conference on Learning Representations) In-Reply-To: <4732B2C0-42AB-4041-98FA-9D5D890FCDEE@iro.umontreal.ca> References: <4732B2C0-42AB-4041-98FA-9D5D890FCDEE@iro.umontreal.ca> Message-ID: Call For Papers for ICLR'2014 [Apologies for multiple copies due to cross-posting. Please forward to colleagues who might be interested] ----------------------------------------------------------------------------------------------------- 2nd International Conference on Learning Representations (ICLR2014) ----------------------------------------------------------------------------------------------------- Website: https://sites.google.com/site/representationlearning2014/ Submission deadline (for initial arXiv submission): December 20th 2013 Held at the: Rimrock Resort Hotel, Banff, Canada on April 14th-16th 2014 Overview ------------- It is well understood that the performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. The rapidly developing field of representation learning is concerned with questions surrounding how we can best learn meaningful and useful representations of data. We take a broad view of the field, and include in it topics such as deep learning and feature learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization. Despite the importance of representation learning to machine learning and to application areas such as vision, speech, audio and NLP, there is currently no common venue for researchers who share a common interest in this topic. The goal of ICLR is to help fill this void and following the success of the 1st ICLR conference in May 2013, we present a second edition of the conference. A non-exhaustive list of relevant topics: - unsupervised representation learning - supervised representation learning - metric learning and kernel learning - dimensionality expansion, sparse modeling - hierarchical models - optimization for representation learning - implementation issues, parallelization, software platforms, hardware - applications in vision, audio, speech, and natural language processing, robotics and neuroscience. - other applications ICLR2014's Two Submission Tracks: ----------------------------------------------------- ICLR2014 has two publication tracks: Conference Track: These papers are reviewed as standard conference papers. Papers should be between 6-9 pages in length. Accepted papers will be presented at the main conference as either an oral or poster presentation and will be included in the official ICLR2014 proceedings. A subset of accepted conference track papers will be selected to participate in a JMLR special topics issue on the subject of Representation Learning. Authors of the selected papers will be given an opportunity to extend their original submissions with supplementary material. Workshop Track: Papers submitted to this track are ideally 2-3 pages long and describe late-breaking developments. This track is meant to carry on the tradition of the former Snowbird Learning Workshop. These papers are considered as workshop papers (and can be published elsewhere). They will be lightly reviewed by ICLR reviewers. ICLR2014 Submission Instructions: --------------------------------------------------- (1) Authors should post their submissions (both conference and workshop tracks) on arXiv: http://arxiv.org (2) Once the arXiv paper is publicly visible (there can be an approx. 30 hour delay), authors should go to the openreview ICLR2014 website: http://openreview.net/iclr2014 to submit to either the conference track or the workshop track. To register on the openreview ICLR2014 website, the submitting author requires a google account. Both tracks will use the NIPS format (style files available here: http://nips.cc/PaperInformation/StyleFiles). Submission deadline (for initial arXiv submission): December 20th 2013 Notes: i. Regarding the conference submission's 6-9 page limits, these are really meant as guidelines and will not be strictly enforced. For example, figures should not be shrunk to illegible size to fit within the page limit. However, in order to ensure a reasonable workload for our reviewers, papers that go beyond the 9 pages should be formatted to include a 9 page submission and a separate supplementary material submission that will be optionally reviewed. If the paper is selected for the JMLR special topic issue, this supplementary material can be incorporated into the final journal version. ii. Workshop track submissions should be formatted as a short paper, with introduction, problem statement, brief explanation of solution, figure(s) and references. They should not merely be abstracts. iii. Paper revisions will be permitted in response to reviewer comments (see "An Open Reviewing Paradigm" section below). An Open Reviewing Paradigm: -------------------------------------------- Following the success achieved last year with openreview.net, ICLR2014 will use an open publication and reviewing model that proceeds as follows: - After the authors have posted their submissions on arXiv, the ICLR program committee designates anonymous reviewers as usual. - The submitted reviews are published without the name of the reviewer, but with an indication that they are the designated reviews. Anyone can write and publish comments on the paper (non anonymously). Anyone can ask the program chairs for permission to become an anonymous designated reviewer (open bidding). The program chairs have ultimate control over the publication of each anonymous review. Open commenters will have to use their real name, linked with their Google Scholar profile. - Authors can post comments in response to reviews and comments. They can revise the paper as many times as they want, possibly citing some of the reviews. - By Feb 22nd 2014, the ICLR program committee will consider all submitted papers, comments, and reviews and will decide which papers are to be presented at the conference as oral or poster. Although papers can be modified after that date, there is no guarantee that the modifications will be taken into account by the committee. - Papers that are not accepted for publication in the proceedings will be considered non-archival, and could be submitted elsewhere (modified or not), although the ICLR site will maintain the reviews, the comments, and the links to the arXiv versions. +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Invited Speakers ------------------------ To be announced. General Chairs --------------------- Yoshua Bengio, Universit? de Montreal Yann LeCun, New York University Program Chairs ----------------------- Aaron Courville, Universit? de Montreal Rob Fergus, New York University Brian Kingsbury, IBM Research Contact ----------- The organizers can be contacted at: iclr2014.programchairs at gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From erik at oist.jp Wed Oct 16 04:36:12 2013 From: erik at oist.jp (Erik De Schutter) Date: Wed, 16 Oct 2013 17:36:12 +0900 Subject: Connectionists: Call for proposals to host the annual Computational Neuroscience (CNS) Meeting in 2016 Message-ID: <1A244F9B-1CF0-4B5D-87C9-4BFF54A4C359@oist.jp> After the record breaking CNS*2013 meeting in Paris, France OCNS (http://www.cnsorg.org) requests proposals from candidate local organizers to organize the CNS meeting in 2016 in in a location outside of Europe. For the first time we offer the option of having the meeting outside of North America, though North American proposals are also quite welcome. Groups or individuals interested in organizing the CNS*20156 meeting should submit a proposal with consideration of the extensive on-line information (http://www.cnsorg.org/cns-2016-local-organizer) and using the on-line templates provided as a guide. The OCNS board members will select/discuss the different proposals, contact the potential local organizers for more information if necessary and come to a timely agreement between OCNS and potential local organizers. Proposals should be emailed to the OCNS president at president at cnsorg.org no later than December 15, 2013. Decisions are expected to be conveyed to potential organizers begin of 2014. Erik De Schutter OCNS President From antonior at ffclrp.usp.br Wed Oct 16 22:37:05 2013 From: antonior at ffclrp.usp.br (Antonio C. Roque) Date: Wed, 16 Oct 2013 23:37:05 -0300 Subject: Connectionists: Postdoctoral opportunities in Mathematics and Neuroscience at the University of Sao Paulo, Brazil Message-ID: Please announce these postdoc opportunities at the University of Sao Paulo in Brazil: Postdoctoral opportunities in Mathematics and Neuroscience at the University of Sao Paulo, Brazil The recently established Research, Innovation and Dissemination Center for Neuromathematics (NeuroMat), hosted by the University of S?o Paulo, Brazil, and funded by FAPESP (S?o Paulo Research Foundation) is offering several postdoctoral fellowships for recent PhDs with outstanding research potential. Candidates are sought that fit one of the profiles below (or a combination): * A strong background in probability theory with emphasis on stochastic processes or alternatively in statistics with emphasis on statistical model selection. Previous knowledge of rigorous statistical mechanics, random graphs or stochastic modeling in biosciences will be favorably considered. * A solid background in systems neuroscience, programming skills, experience of imaging and/or EEG acquisition and analysis and strong interest in interdisciplinary research. The initial appointments are for two years, with a possible extension to up to four years conditional on research progress. Salary is competitive at international level and fellows benefit from extra funds for travel and research expenses, plus limited support for relocation expenses. Application instructions are found at http://neuromat.numec.prp.usp.br/postdoc. -- Dr. Antonio C. Roque Professor Associado Departamento de Fisica FFCLRP, Universidade de Sao Paulo 14040-901 Ribeirao Preto-SP Brazil - Brasil E-mails: antonior at ffclrp.usp.br aroquesilva at gmail.com URL: www.sisne.org Tels: +55 16 3602-3768 (sala/office); +55 16 3602-3859 (lab) FAX: +55 16 3602-4887 -------------- next part -------------- An HTML attachment was scrubbed... URL: From guestrin at cs.washington.edu Thu Oct 17 12:59:53 2013 From: guestrin at cs.washington.edu (Carlos Guestrin) Date: Thu, 17 Oct 2013 09:59:53 -0700 Subject: Connectionists: University of Washington: Joint Faculty Positions in Statistics and Computer Science & Engineering Message-ID: Dear Colleagues, I would like to bring this faculty search to your attention. Recent hires at UW in the area of machine learning, as well as a new PhD track on Big Data and a new NSF IGERT have given momentum to a growing effort and commitment to build a core expertise in this area. The goal of these positions is to continue to strengthen the bridge between the highly-ranked Statistics and Computer Science & Engineering Departments at UW. The positions are open-rank, with appointments as Assistant Professor, Associate Professor, or Professor commensurate with the candidate?s qualifications. Please forward this email as appropriate. Thank you, Carlos Guestrin Amazon Professor of Machine Learning University of Washington =========================================================== ** Joint Faculty Positions in Statistics and Computer Science & Engineering ** The Provost of the University of Washington has launched a major effort focused on Data-Driven Discovery, with a commitment to hire several new faculty in this area. In support of this effort, we are seeking candidates for one open-rank tenured or tenure-track faculty position jointly in the Department of Computer Science & Engineering and the Department of Statistics at the University of Washington. This position will be a full-time joint appointment in both departments with precise percentages as appropriate for the candidate. The new faculty will also participate in the UW eScience Institute. We encourage applications from exceptional candidates at the intersection of computer science and statistics, with a particular focus on machine learning and large-scale statistical analysis. We expect candidates to have a strong commitment to both research and teaching. The joint position will be primarily focused on hires at the Assistant Professor or Associate Professor levels although individuals at senior ranks with exceptional credentials may be considered. Applicants must have earned a PhD, or foreign equivalent, by the date of appointment. All University of Washington faculty engage in teaching, research and service. The CSE and Stat departments are located less than 5 minutes apart on the Seattle campus, enabling cross department collaborations and initiatives. The Seattle area is particularly attractive given the presence of significant industrial research laboratories, a vibrant technology-driven entrepreneurial community, and spectacular natural beauty. * Application Instructions Please apply online at https://statcse.cs.washington.edu/apply with a letter of application, a complete curriculum vitae, a statement of research and teaching interests, and the names of at least four references. The review of applications will start on November 15, 2013, and those received by January 15, 2014, will be given priority consideration. Open positions are contingent on funding. The University of Washington was awarded an Alfred P. Sloan Award for Faculty Career Flexibility in 2006. In addition, the University of Washington is a recipient of a National Science Foundation ADVANCE Institutional Transformation Award to increase the participation of women in academic science and engineering careers. We are building a culturally diverse faculty and encourage applications from women and minority candidates. The University of Washington is an affirmative action, equal opportunity employer. -------------- next part -------------- An HTML attachment was scrubbed... URL: From mike at mwcole.com Thu Oct 17 16:13:45 2013 From: mike at mwcole.com (Michael W. Cole) Date: Thu, 17 Oct 2013 13:13:45 -0700 Subject: Connectionists: Two postdoctoral positions in cognitive neuroscience (neuroimaging and/or modeling) Message-ID: Two post-doctoral positions available: Human neuroimaging and/or computational modeling focusing on brain connectivity dynamics and cognitive control (human intelligence) We seek two post-doctoral fellows to work on studies using functional MRI (fMRI) and/or computational modeling of brain connectivity dynamics investigating cognitive control. We are especially interested in investigating neural mechanisms of highly adaptive cognition ? such as the human ability to rapidly learn new tasks from instructions. Human neuroimaging studies will focus on identifying local (within-region) and global (multi-network) connectivity mechanisms facilitating first-trial task learning and other forms of highly flexible cognition (e.g., involving lateral prefrontal cortex). This will primarily involve functional connectivity analyses using fMRI (during rest and task). Computational modeling will involve biologically realistic neuronal network models implementing first-trial learning and other forms of highly flexible cognition in order to test the plausibility of proposed mechanisms ? and expanding computers into a computational realm currently only occupied by humans (i.e., creating artificial intelligence by investigating natural intelligence). Further, computational modeling will involve application of statistical techniques to find ways to detect newly identified mechanisms using neuroimaging, in order to test predictions made by the models. The positions will be at Rutgers University in Newark, NJ (13 miles from New York City, NY) and located in a newly renovated laboratory space in the Center for Molecular and Behavioral Neuroscience (CMBN), in the same building as the new Rutgers University Brain Imaging Center. Preferred attributes of candidates: 1) Strong computer programming skills; 2) Strong statistical analysis skills; 3) Excellent writing (and general communication) skills; 4) A consistent passion for learning and making discoveries in neuroscience (or related fields); 5) Expertise (a PhD) in behavioral, neuroimaging, and/or computational modeling research. For more information on the lab's research visit http://www.mwcole.net Start date is flexible, but is anticipated to be between January and September 2014. The deadline for applying is December 1, 2013. If interested send your CV and a cover letter with an overview of your background and career goals, along with names and emails of potential recommenders to mwcole at mwcole.net (Also note if you will be at the Society for Neuroscience meeting in November for a possible interview.) http://www.mwcole.net/openpositions/postdoc2014.html -------------- next part -------------- An HTML attachment was scrubbed... URL: From y-inoue at hi.is.uec.ac.jp Fri Oct 18 06:57:36 2013 From: y-inoue at hi.is.uec.ac.jp (Yasuyuki Inoue) Date: Fri, 18 Oct 2013 19:57:36 +0900 Subject: Connectionists: CFP Neural Networks: Special Issue on Communication and Brain Message-ID: <52611420.8030100@hi.is.uec.ac.jp> Dear Colleagues, We cordially invite you to submit a paper to the Special Issue on Communication and Brain of Neural Network journal. The submission deadline is January 10, 2014. Please visit the following site for details. http://www.journals.elsevier.com/neural-networks/call-for-papers/communication-brain-emergent-functions/ Sincerely, Yutaka Sakaguchi Guest Editor of Special Issue on "Communication and Brain", Neural Networks === Aim and Scope The variety of functions of the brain is realized by the communications among information processing units at multiple levels. First, a network of single neurons forms a rich non-linear dynamical system. Second, interaction between different functional modules (or cell assemblies) is a basic structure for achieving perceptual, cognitive and motor functions. Third, communication between different individuals (or brains) enables cooperative and social functions. Considering the complex nature of the communicationswithin and between brains, their understanding necessitates multidisciplinary approaches, such as mathematics, computational theory, psychophysics, physiology and brain imaging. Integration of these approaches can lead to the comprehension of the principle of brain information processing and its application to practical matters. The aim of this special issue is to foster a new research field of communication by integrating advances in the theoretical and experimental studies, including mathematical theory, computer models, psychophysical and neurophysiological experiments, and conceptual proposals. Results of collaborative studies between theoretical and experimental researchers are especially welcome. Topics include: - Functions of chaotic dynamical system - Dynamic cell assemblies - Synchronization and de-synchronization of neural activity and EEG patterns - Behavioral synchronization; Social synchronization - Interactions between bottom-up and top-down signal streams - Dynamics of functional differentiation - Emergence of grammar/rules in communication, and - Self-organization of social roles This special issue invites concise submissions, but longer papers that capture the essence of communication will also be considered. Topical reviews as well as original results are welcome. Manuscripts should be submitted from http://ees.elsevier.com/neunet For any inquiry, please contact nncb2014 at hi.is.uec.ac.jp From glotin at univ-tln.fr Fri Oct 18 10:40:28 2013 From: glotin at univ-tln.fr (Herve Glotin) Date: Fri, 18 Oct 2013 16:40:28 +0200 Subject: Connectionists: NIPS4B (Neural Info. Processing for Bioacoustics Wkp, joint to NIPS) Message-ID: Last call for papers for NIPS4B 2013 - Apologies for multiple copies. Please forward to colleagues who might be interested -------------------------------------------------------------------------------- 1st Neural Information Processing for Bioacoustics wkp / joint to NIPS 2013 -------------------------------------------------------------------------------- Nevada, december 10th, joint to NIPS https://sabiod.org/nips4b * Submission deadline (extended abstract of 1 page): October 23th 2013 * Acceptance decisions: October 30th * Camera ready paper due (NIPS format): November 23th - Objectives : Bioacoustic data science aims at analyzing and modeling animal sounds for neuroethology / biodiversity assessment. Given the complexity of the collected data along with the different taxonomies and species and environmental contexts, it requires original approaches. The increased expectations from bioacoustic research have been coincident with a dramatic increase in the spatial, temporal and spectral scales of acoustic data collection efforts. One of the most promising strategies concerns neural information processing and advanced machine learning. Some representative data for representation processing / classification validation are given on the nips4b web site, including two challenges : * Bird classification challenge : http://sabiod.org/nips4b/challenge1.html, ends 20th nov. (also on Kaggle) * Whale song analysis challenge : http://sabiod.org/nips4b/challenge2.html, ends 20th nov. * Biosonar session (non restrictive topic) : http://sabiod.org/nips4b/neurosonar.html Topic of interest includes: * Multilabel learning * Semi-supervised classification * Structuration of animal sound (insect / bird / mammals / ...) * Passive acoustic tracking * Learning to sing (model of),... Chairs -------- Yann LeCun, New-York Univ. Stephane Mallat, Ecole Normale Superieur, Paris Herve Glotin, Inst. Univ. de France & Toulon Univ. Thierry Arti?res, Pierre et Marie Curie Univ., Paris Ofer Tchernichovski, Hunter College, New-York Xanadu Halkias, Toulon Univ. -------- Contact: nips4b at gmail.com -- Herve' Glotin, Pr. Institut Univ. de France (IUF) & Univ. Toulon (UTLN) Head of information DYNamics & Integration (DYNI @ UMR CNRS LSIS) http://glotin.univ-tln.fr glotin at univ-tln.fr From agostino.gibaldi at unige.it Fri Oct 18 13:32:37 2013 From: agostino.gibaldi at unige.it (Agostino Gibaldi) Date: Fri, 18 Oct 2013 19:32:37 +0200 Subject: Connectionists: =?iso-8859-15?q?Special_Issue_on_=22Emerging_Spat?= =?iso-8859-15?q?ial_Competences=3A_From_Machine_Perception_to_Sensorimoto?= =?iso-8859-15?q?r_Intelligence=22?= Message-ID: <526170B5.9010501@unige.it> Please accept our apologies if you receive multiple copies of this CFP! ===================================================================================== *CALL FOR PAPERS* ************************************************************************************* Robotics and Autonomous Systems Journal Special Issue on /*"Emerging Spatial Competences: From Machine Perception to Sensorimotor Intelligence" */ ===================================================================================== *IMPORTANT DATES* - January 31, 2014: Paper submission deadline - March 31, 2014: Notification of paper acceptance - April 30, 2014: Camera ready paper submission - Late Spring 2014: Expected publication date ===================================================================================== *AIMS AND OBJECTIVES* Following the recent evolution of robotics and AI in different fields of application, the increasing complexity of the *actions *that an artificial agent needs to perform, is directly dependent on the complexity of the *sensory information * that it can acquire and *interpret*, i.e. *perceive*. >From this point of view, an efficient and internal representation of the sensory information is at the base of a robot to develop a *human-like capability *of interaction with the surrounding environment. Particularly, in the space at a *reachable distance*, not only visual and auditory, but also tactile and proprioceptive information rise to be relevant to gain a comprehensive spatial cognition. This information, coming from different senses, can be in principle integrated and used to experience an awareness of the environment both to actively interact with it, and to calibrate the interaction itself. Besides, the early sensory and sensorimotor mechanisms, that at a first glance may appear simple processes, are grounded on highly structured and complex algorithms that are far from being understood and modeled. By exploiting an early synergy between *sensing modules* and *motor control*, the loop between action and perception comes to be not just closed at system level, but shortened at an inner one. This would allow not only the emergence of *spatial competences* but also their *continuous adaptation* to changes in the environment or in the body, which could modify its interactions with the world. The aim of this special issue is to survey a state of the art of methodologies, concepts, algorithms and techniques that would serve as bricks on which to build and develop artificial agents with such a spatial competence; perceptual and cognitive understanding of space should emerge from sensorimotor exercise. The *action-perception loop* has never been so close! ===================================================================================== *PAPER SUBMISSION* We invite original contributions that provide novel solutions to address the relevant topics including but not limited to: - Theoretical or practical aspects of machine sensing (for computer vision, robot audition, artificial touch, etc.) - Multisensory data fusion, processing, learning and integration - Computational neural modeling - Embodied robotics: perception, cognition, and behaviors - Machine learning for sensorimotor control and intelligence - Neural networks: models, theories, learning algorithms and applications - Engineering application of sensorimotor intelligence to pattern recognition, computer vision, speech recognition, human-robot interactions. As a follow-up of the IJCNN 2013 special session, we invite in particular the special session participants to submit profoundly extended versions of their conference submission to go through a new peer review process, together with contributions not published in the conference proceedings. Papers should be typeset according to the format instructions for the Robotics and Autonomous Systems Journal, available on the Elsevier web site (http://www.elsevier.com/journals/robotics-and-autonomous-systems/0921-8890/guide-for-authors). ===================================================================================== *GUEST EDITORS* _Agostino Gibaldi_, agostino.gibaldi at unige.it Department of Informatics, Bioengineering, Robotics and System Engineering University of Genoa, Italy Advanced Research Center on Electronic Systems (ARCES) University of Bologna, Italy _Silvio P. Sabatini_, silvio.sabatini at unige.it Department of Informatics, Bioengineering, Robotics and System Engineering University of Genoa, Italy _Sylvain Argentieri_, sylvain.argentieri at upmc.fr Institute for Intelligent Systems and Robotics (ISIR) Universit? Pierre et Marie Curie, Paris, France _Zhengping Ji_, jizhengp at gmail.com Advanced Image Research Laboratory (AIRL) Samsung, Pasadena, CA, U.S.A -------------- next part -------------- A non-text attachment was scrubbed... Name: RAS Special Issue on ESC.pdf Type: application/pdf Size: 46878 bytes Desc: not available URL: From irodero at cac.rutgers.edu Fri Oct 18 17:31:16 2013 From: irodero at cac.rutgers.edu (Ivan Rodero) Date: Fri, 18 Oct 2013 17:31:16 -0400 Subject: Connectionists: CiSE Extreme Data - Call for Papers In-Reply-To: <5F86C42F-E15F-49FC-9AA3-FBBCA55BA44D@rutgers.edu> References: <51EC7783-DCAD-4364-B1DC-576C726BAA31@rutgers.edu> <828ECB55-3292-4D46-9F21-A4C18EF2F712@rutgers.edu> <5F86C42F-E15F-49FC-9AA3-FBBCA55BA44D@rutgers.edu> Message-ID: Please accept our apologies for the confusion with the dates in our former email, and for any inconvenience this may have caused. Please note that the submission due date was NOT correct in the previous CFP. The submission due date has been updated to December 1st, 2013. Thank you for your patience, and we do apologize again for the inconvenience. On Oct 13, 2013, at 12:14 AM, Ivan Rodero wrote: > ------------------------------------------------------------------------------------------------------ > > Please accept our apologies if you receive multiple copies of this CFP! > > ------------------------------------------------------------------------------------------------------ > > Call for Papers > > Computing in Science & Engineering > > Extreme Data > > Submissions due: March 2014 > Estimated Publication date: November 2014 > > The current era of extreme data culled from a range of diverse data sources, ranging from extreme scale simulations to instruments, experiments, and pervasive sensors and systems, has the potential for revolutionizing science, engineering, and society in general. However, the expanding distribution and dynamism of the data, increasing data heterogeneity and uncertainty about its quality and availability, as well as the growing costs (time and energy) associated with transporting and processing this data, requires new paradigms and practices in data management and analytics, as well as supporting software stacks before this potential can be realized. > > The goal of this special issue of CiSE is to explore the fundamental challenges ? as well as the state of the art in solutions ? of extreme data. From innovative algorithmic formulations to implementation frameworks and software stacks, what can accelerate insights from extreme data? End-to-end application workflows and relevant experiences with real applications are of particular interest. > > Published by the IEEE Computer Society and the American Institute of Physics, CiSE magazine features the latest computational science and engineering research in an accessible format, along with departments covering news and analysis, CSE in education, and emerging technologies. > > We strongly encourage submissions that include multimedia, data, and community content, which will be featured on the IEEE Computer Society website along with the accepted papers. > > For more information please see http://www.computer.org/portal/web/computingnow/cscfp4 > > Questions? > > Contact guest editors Manish Parashar, Rutgers University (parashar at rutgers.edu) or George K. Thiruvathukal, Loyola University Chicago (gkt at cs.luc.edu). > > Submission Guidelines > > Authors are asked to submit high-quality original work that has neither appeared in nor is under consideration by other journals. All submissions will be peer-reviewed following standard journal practices. Manuscripts based on previously published conference papers must be extended substantially to include at least 30 percent new material. Manuscripts should be written in the active voice, should be no longer than 7,200 words (counting each standard figure and table as 250 words), and should follow the style and presentation guidelines of CiSE (see www.computer.org/cise/author for details). > > Please submit your article using the online manuscript submission service at https://mc.manuscriptcentral.com/cs-ieee. When uploading your article, select the appropriate special-issue title under the category "Manuscript Type." Also include complete contact information for all authors. If you have any questions about submitting your article, contact the peer review coordinator at cise at computer.org. > > > ============================================================= > Ivan Rodero, Ph.D. > Rutgers Discovery Informatics Institute (RDI2) > NSF Center for Cloud and Autonomic Computing (CAC) > Department of Electrical and Computer Engineering > Rutgers, The State University of New Jersey > Office: CoRE Bldg, Rm 625 > 94 Brett Road, Piscataway, NJ 08854-8058 > Phone: (732) 993-8837 > Fax: (732) 445-0593 > Email: irodero at rutgers dot edu > WWW: http://nsfcac.rutgers.edu/people/irodero > ============================================================= ============================================================= Ivan Rodero, Ph.D. Rutgers Discovery Informatics Institute (RDI2) NSF Center for Cloud and Autonomic Computing (CAC) Department of Electrical and Computer Engineering Rutgers, The State University of New Jersey Office: CoRE Bldg, Rm 625 94 Brett Road, Piscataway, NJ 08854-8058 Phone: (732) 993-8837 Fax: (732) 445-0593 Email: irodero at rutgers dot edu WWW: http://nsfcac.rutgers.edu/people/irodero ============================================================= -------------- next part -------------- An HTML attachment was scrubbed... URL: From sala038 at aucklanduni.ac.nz Sun Oct 20 19:35:11 2013 From: sala038 at aucklanduni.ac.nz (shafiq burki) Date: Mon, 21 Oct 2013 12:35:11 +1300 Subject: Connectionists: CFP: PAKDD 3rd workshop on "Biologically Inspired Techniques for Data Mining (BDM'14) Message-ID: Call For Papers: PAKDD 3rd workshop on "Biologically Inspired Techniques for Data Mining (BDM'14) ********************************** Apologies for Multiple postings.... (deadline: 15, January 2014) *********************************************************** ++++++++++++++++++++++++++++++++++++++++++ To submit your paper use the following link: Web site: https://conference.fos.auckland.ac.nz/bdm/bdm14/index.html Submission page: https://www.easychair.org/conferences/?conf=bdm14 ++++++++++++++++++++++++++++++++++++++ PAKDD 3rd workshop on "Biologically Inspired Techniques for Data Mining (BDM'14)", is to be held in conjunction with 18th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'14 ), 13-16 May, 2014, Tainan, Taiwan. PAKDD is one of the major conferences in knowledge discovery and data mining. The workshop calls for high quality research papers outlining current research, literature surveys, theoretical and empirical studies, and other relevant work including but not limited to the following areas: 1. Particle Swarm Optimization (PSO) PSO based clustering PSO based classification PSO based outlier detection PSO based feature selection 2. Ant Colony Optimization (ACO) ACO based clustering ACO based classification ACO based outlier detection ACO based feature selection ACO based rules mining ACO based sequential patterns mining 3. Artificial Neural Networks (ANN) ANN based pattern matching and discovery Classification rules discovery using ANN Forecasting and prediction analysis using ANN 4. Genetic Algorithms (GAs) Clustering, classification and parameter tuning using GAs GAs based feature extraction and selection Learning Classifier Systems 5. Artificial Immune System(AIS) AIS for intrusion detection AIS for data clustering AIS for decision support system 6. Fuzzy Systems (FS) and biologically inspired techniques Fuzzy clustering Fuzzy classification Fuzzy Association rules discovery 7. Bee Colony Optimization (BCO) BCO for pattern matching Clustering using BCO 8. Evolutionary Neural Nets, Evolutionary SVMs, and Evolutionary Decision Trees 9. Computational Intelligence in Recommender System ++++++++++++++++++++++++++++++++++++++++++ To submit your paper use the following link: https://www.easychair.org/conferences/?conf=bdm14 ++++++++++++++++++++++++++++++++++++++ For more information please contact: Dr. Shafiq Alam, University of Auckland, New Zealand. sala038 at aucklanduni.ac.nz -------------- next part -------------- An HTML attachment was scrubbed... URL: From bwyble at gmail.com Mon Oct 21 10:09:51 2013 From: bwyble at gmail.com (Brad Wyble) Date: Mon, 21 Oct 2013 10:09:51 -0400 Subject: Connectionists: PhD position available in Experimental/Computational neuroscience at Penn State University Message-ID: Dear colleagues and students, My apologies if you receive multiple notices for this position! Candidates are invited to apply for Ph.D candidacy in the laboratory of Brad Wyble in the Department of Psychology at Penn State University?s main campus in State College, PA. Applicants should ideally have significant computer programming skills (i.e. two or more years of experience programming in C, MatLab, Python, or equivalent) and a background in psychology, neuroscience, cognitive science, physics or biology. Fluency in English is also required. The research focus of our lab is to understand the neural mechanisms underlying visual attention and the encoding of information into memory with a specific emphasis on understanding the interaction of the two. Our research involves a joint effort in computational modelling and experimental work using a variety of methods (e.g. behavioral, electrophysiological, eye-tracking). More detail about specific projects can be found at http://wyblelab.com/research. In addition to these projects, there are opportunities to develop artificial vision applications with partners in Penn State's Applied Research lab. There are also ongoing collaborations with partners studying Traumatic Brain Injury and the underlying causes of autism. Penn State main campus offers a diverse array of resources for conducting research such as the SLEIC neuroimaging center: http://www.imaging.psu.edu/. There is also a diverse set of research interests both within the psychology department, and across the campus (e.g. Engineering: http://www.esm.psu.edu/wiki/research:cne:start; Neuroscience: http://www.huck.psu.edu/research/neurosciences, http://cbbc.psu.edu/; Social: http://www.ssri.psu.edu/) Interested applicants should apply to the Psychology department at http://psych.la.psu.edu/graduate/howToApply.html and should note that the deadline for applications is December 1st. Best regards, -- Brad Wyble Assistant Professor Psychology Department Penn State University http://wyblelab.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From Colin.Wise at uts.edu.au Mon Oct 21 18:46:19 2013 From: Colin.Wise at uts.edu.au (Colin Wise) Date: Tue, 22 Oct 2013 09:46:19 +1100 Subject: Connectionists: AAI Short Course - 'Behaviour Analytics - an Introduction' - Wednesday 6 November 2013 Message-ID: <8112393AA53A9B4A9BDDA6421F26C68A0158DD495F41@MAILBOXCLUSTER.adsroot.uts.edu.au> Dear Colleague, AAI Short Course - 'Behaviour Analytics - an Introduction' - Wednesday 6 November 2013 https://shortcourses-bookings.uts.edu.au/Clientview/Schedules/ScheduleDetail.aspx?ScheduleID=1392&EventID=1185 Our AAI short course 'Behaviour Analytics - an Introduction' may be of interest to you and or others in your organisation or network. Complex behaviours are widely seen on the internet, business, social and online networks, and multi-agent systems. In fact, behaviour is a concept with stronger semantic meaning than the so-called data for recording and representing business activities, impacts and dynamics. Therefore, an in-depth understanding of complex behaviours has been increasingly recognised as a crucial means for disclosing interior driving forces, causes and impact on businesses in handling many challenging issues. This forms the need and emergence of behaviour analytics, i.e. understanding behaviours from the computing perspective. In this short course, we present an overview of behaviour analytics and discuss complex behaviour interactions and relationships, complex behaviour representation, behavioural feature construction, behaviour impact and utility analysis, behaviour pattern analysis, exceptional behaviour analysis, negative behaviour analysis, behaviour interaction and evolution. Please register here LINK An important foundation short course in the AAI series of advanced data analytic short courses - please view this short course and others here LINK We are happy to discuss at your convenience. Thank you and regards. Colin Wise Operations Manager Advanced Analytics Institute (AAI) Blackfriars Building 2, Level 1 University of Technology, Sydney (UTS) Email: Colin.Wise at uts.edu.au Tel. +61 2 9514 9267 M. 0448 916 589 AAI: www.analytics.uts.edu.au/ Reminder - AAI Short Course - Advanced Data Analytics - an Introduction - Tuesday 19 November 2013 Future short courses on Data Analytics and Big Data may be viewed at LINK AAI Education and Training Short Courses Survey - you may be interested in completing our AAI Survey at LINK AAI September 2013 Newsletter LINK AAI Email Policy - should you wish to not receive this periodic communication on Data Analytics Learning please reply to our email (to sender) with UNSUBSCRIBE in the Subject. We will delete you from our database. Thank you for your past and future support. UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any accompanying attachments may contain confidential information. If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or attachments. If you have received this message in error, please notify the sender immediately and delete this message. Any views expressed in this message are those of the individual sender, except where the sender expressly, and with authority, states them to be the views of the University of Technology Sydney. Before opening any attachments, please check them for viruses and defects. Think. Green. Do. Please consider the environment before printing this email. -------------- next part -------------- An HTML attachment was scrubbed... URL: From tom_griffiths at berkeley.edu Mon Oct 21 14:27:41 2013 From: tom_griffiths at berkeley.edu (Tom Griffiths) Date: Mon, 21 Oct 2013 11:27:41 -0700 Subject: Connectionists: Assistant Professor position in higher level cognition at the University of California, Berkeley Message-ID: Dear connectionists (et al.), The Department of Psychology at UC Berkeley is hiring at the Assistant Professor level, looking for somebody who specializes in studying higher level cognition (broadly construed). Researchers with computational interests are encouraged to apply. The full advertisement appears below. Note that the deadline is November 18. Best wishes, Tom. -- The Department of Psychology is seeking to fill a tenure-track assistant professor faculty position, with an anticipated start date of July 1, 2014. We are interested in candidates with exceptional promise conducting research in the area of higher-level cognition, broadly construed. Research interests may include but are not limited to language, learning, reasoning, decision-making, concepts, high-level perception, attention, skill acquisition, and memory. Use or development of new experimental or computational methods is highly desirable. This position will be based in the Cognition, Brain, and Behavior area of the department. Ph.D. or equivalent is required by date of hire. The department is committed to addressing the family needs of faculty, including dual career couples and single parents, and is interested in candidates who will contribute to diversity and equal opportunity in higher education through their teaching, research, and service. To apply, please go to the following link: http://aprecruit.berkeley.edu/apply/JPF00201. Applicants should submit a cover letter, curriculum vitae, research statement, summary of teaching experience and interests, and up to five reprints or preprints. Applicants should also arrange for the online submission of three letters of recommendation. All letters will be treated as confidential per University of California policy and California state law. Please refer potential referees, including when letters are provided via a third party (i.e., dossier service or career center), to the UC Berkeley statement of confidentiality (http://apo.chance.berkeley.edu/evalltr.html) prior to submitting their letters. Applications must be received by November 18, 2013. Please direct questions to psychsearch at berkeley.edu, and include ?Higher-Level Cognition Search? in the subject line. For information about potential relocation to Berkeley, or career needs of accompanying partners and spouses, please visit the CALcierge office website at http://calcierge.berkeley.edu. The University of California is an Equal Opportunity/Affirmative Action Employer. -- Tom Griffiths Associate Professor, Psychology and Cognitive Science Director, Institute of Cognitive and Brain Sciences University of California, Berkeley http://cocosci.berkeley.edu/tom/ From Jean-Philippe.Vert at mines-paristech.fr Mon Oct 21 19:09:16 2013 From: Jean-Philippe.Vert at mines-paristech.fr (Jean-Philippe Vert) Date: Tue, 22 Oct 2013 01:09:16 +0200 Subject: Connectionists: *Deadline extension Oct 24* - NIPS 2013 workshop on Machine Learning in Computational Biology Message-ID: <0E6A5ADE-513F-481A-A0DF-A335118B2DFC@mines-paristech.fr> NIPS 2013 workshop on Machine Learning in Computational Biology ---------- Call for contributions Workshop on Machine Learning in Computational Biology http://www.mlcb.org A workshop at the Twenty-Seventh Annual Conference on Neural Information Processing Systems (NIPS 2013) Lake Tahoe, Nevada, USA, December 10, 2013. Important dates: Oct 24, 2013 : Deadline for submission of extended abstracts Nov 4, 2013: Acceptance notification Dec 10, 2013: Workshop date WORKSHOP DESCRIPTION The field of computational biology has seen dramatic growth over the past few years, in terms of newly available data, new scientific questions and new challenges for learning and inference. In particular, biological data is often relationally structured and highly diverse, and thus requires combining multiple weak evidence from heterogeneous sources. These sources include sequenced genomes of a variety of organisms, gene expression data from multiple technologies, protein sequence and 3D structural data, protein interaction data, gene ontology and pathway databases, genetic variation data (such as SNPs), high-content phenotypic screening data, and an enormous amount of text data in the biological and medical literature. New types of scientific and clinical problems require novel supervised and unsupervised learning approaches that can use these growing resources. Furthermore, next generation sequencing technologies are yielding terabyte scale data sets that require novel algorithmic solutions. The workshop will host presentations of emerging problems and machine learning techniques in computational biology. We encourage contributions describing either progress on new bioinformatics problems or work on established problems using methods that are substantially different from standard approaches. Kernel methods, graphical models, semi-supervised approaches, feature selection and other techniques applied to relevant bioinformatics problems would all be appropriate for the workshop. SUBMISSION INSTRUCTIONS Researchers interested in contributing should upload an extended abstract of 4 pages in PDF format to the MLCB submission web site http://www.easychair.org/conferences/?conf=mlcb2013 by Oct 24, 2013, 11:59pm (time zone of your choice). No special style is required. Authors may use the NIPS style file, but are also free to use other styles as long as they use standard font size (11 pt) and margins (1 in). *Submissions should be suitably anonymized and meet the requirements for double-blind reviewing.* All submissions will be anonymously peer reviewed and will be evaluated on the basis of their technical content. A strong submission to the workshop typically presents a new learning method that yields new biological insights, or applies an existing learning method to a new biological problem. However, submissions that improve upon existing methods for solving previously studied problems will also be considered. Examples of research presented in previous years can be found online at http://www.mlcb.org/nipscompbio/previous/. The workshop allows submissions of papers that are under review or have been recently published in a conference or a journal. This is done to encourage presentation of mature research projects that are interesting to the community. The authors should clearly state any overlapping published work at time of submission. INVITED SPEAKERS Jonathan Pritchard (Stanford) Samuel Kaski (HIIT) ORGANIZERS Anna Goldenberg (University of Toronto) Sara Mostafavi (Stanford) Oliver Stegle (EMBL) Jean-Philippe Vert (Mines ParisTech, Institut Curie) -------------- next part -------------- An HTML attachment was scrubbed... URL: From miguel.nicolau at ucd.ie Tue Oct 22 09:14:40 2013 From: miguel.nicolau at ucd.ie (Miguel Nicolau) Date: Tue, 22 Oct 2013 14:14:40 +0100 Subject: Connectionists: EuroGP 2014: Third CFP (DEADLINE 1st NOVEMBER 2013) Message-ID: (apologies for cross-posting) ***************************************************************************** EuroGP 2014, 17th European Conference on Genetic Programming 23-25 April 2014, Granada, Spain www.evostar.org THIRD CALL FOR PAPERS *** PLEASE NOTE CHANGE OF LOCATION *** ***************************************************************************** (CFP download: www.evostar.org/flyer/EuroGP2014Flyer.pdf) SUBMISSION DEADLINE: 1 November 2013 EuroGP is the premier annual conference on Genetic Programming, attracting participants from all over the world. High quality papers describing new original research are sought on topics strongly related to the evolution of computer programs, ranging from theoretical work to innovative applications. Topics include but are not limited to: * Innovative applications of GP * Theoretical developments * GP performance and behaviour * Fitness landscape analysis of GP * Algorithms, representations and operators * Real-world applications * Evolutionary design * Evolutionary robotics * Tree-based GP and Linear GP * Graph-based GP and Grammar-based GP * Evolvable hardware * Self-reproducing programs * Multi-population GP * Multi-objective GP * Fast/Parallel GP * Probabilistic GP * Evolution of automata or machine * Software Engineering and GP * Object-oriented GP * Hybrid architectures including GP * Coevolution in GP * Modularity in GP * Semantics in GP * Unconventional evolvable computation * Automatic software maintenance * Evolutionary inductive programming In 2013, the EuroGP acceptance rate was 49% (38% for oral presentations). Accepted papers will be included in the proceedings published by Springer Verlag in the Lecture Notes in Computer Science (LNCS) series. The papers which receive the best reviews will be nominated for the Best Paper Award. EuroGP 2014 will take place in Granada, Spain, and will be co-located within the EvoStar event with four related conferences: EvoBIO, EvoCOP, EvoMUSART, and EvoApplications. Submission Details Submissions must be original and not published elsewhere. They will be peer reviewed by at least three members of the program committee. The reviewing process will be double-blind, so please omit information about the authors in the submitted paper. Submit your manuscript in Springer LNCS format. Page limit: 12 pages. The authors of accepted papers will have to improve their paper on the basis of the reviewers? comments and will be asked to send a camera ready version of their manuscripts. At least one author of each accepted work has to register for the conference, attend the conference and present the work. Submission page: myreview.csregistry.org/eurogp14 Website: www.evostar.org/cfpEuroGP.html Facebook: fb.com/evostarconf Twitter: twitter.com/Evostar2014 LinkedIn: www.linkedin.com/groups/EVOstar-1908983 EuroGP programme chairs Miguel Nicolau, University College Dublin, Ireland Krzysztof Krawiec, Poznan University of Technology, Poland From cookie at ucsd.edu Tue Oct 22 12:25:06 2013 From: cookie at ucsd.edu (Santamaria, Cookie) Date: Tue, 22 Oct 2013 16:25:06 +0000 Subject: Connectionists: 2nd Winter Q-Bio Mtg in HAWAII Feb. 2014 ***Abstract submission deadline NOV. 5, 2013*** In-Reply-To: <20672B9D-10D1-42F1-914A-F4D807546FE7@ucsd.edu> References: <20672B9D-10D1-42F1-914A-F4D807546FE7@ucsd.edu> Message-ID: THE SECOND ANNUAL WINTER Q-BIO MEETING Quantitative Biology on the Hawaiian Islands February 17-20, 2014 http://w-qbio.org/ The Winter q-bio meeting brings together scientists and engineers who are interested in all areas of q-bio. The venue for 2014 is the Hilton Waikoloa Village, which is located on the Kohala Coast of Hawaii's Big Island. The resort lets you experience breathtaking tropical gardens, abundant wildlife, award-winning dining, world-class shopping, art and culture, and an array of activities. The Island of Hawaii is the youngest and biggest in the Hawaiian chain, providing a vast canvas of environments to discover--home of one of the world's most active volcanoes (Kilauea), the most massive mountain in the world (Maunaloa), and the largest park in the state (Hawaii Volcanoes National Park). As requested by participants at the last meeting, a number of selected contributed talks will be interspersed with the invited talks during the plenary morning sessions (in addition to the contributed talks in the breakout sessions). SPONSORED BY: UC San Diego BioCircuits Institute and the San Diego Center for Systems Biology The University of Hawaii at Manoa UC San Diego Divisions of Biological Sciences, Physical Sciences, and Engineering The Office of Naval Research 2014 CONFIRMED SPEAKERS: Naama Barkai, The Weizmann Institute of Science Sangeeta Bhatia Massachusetts Institute of Technology Hana El-Samad, University of California, San Francisco Zev Gartner, University of California, San Francisco Taekjip Ha, University of Illinois Shigeru Kondo, Osaka University Arthur Lander, University of California, Irvine Andrew Murray, Harvard University Steve Quake, Stanford University Petra Schwille, Max Planck Institute Christina Smolke, Stanford University Aleksandra Walczak, Laboratoire de Physique Th?orique CONFERENCE ORGANIZERS: Kevin Bennett, University of Hawaii at Manoa William Ditto, University of Hawaii at Manoa Hana El-Samad, University of California, San Francisco Jeff Hasty, University of California, San Diego Alexander Hoffmann, University of California, San Diego Galit Lahav, Harvard University Eva-Maria Schoetz-Collins, University of California, San Diego Chao Tang, Peking University Lev Tsimring, University of California, San Diego ***REGISTRATION NOW OPEN*** Registration fee covers conference venue, registration reception, banquet, coffee & snacks. EARLY BIRD REGISTRATION ($500/$425 Student) DEADLINE: December 1, 2013 REGULAR REGISTRATION ($600/$525 Student) DEADLINE: January 31, 2014 LATE REGISTRATION ($675/$600 Student) After January 31, 2014 REGISTER NOW: http://w-qbio.org/ HOTEL: A block of rooms has been reserved for registered conference participants at a negotiated rate of $199 per night at the Hilton Waikoloa Village. The rooms will be available soon on a first-come, first-served basis, so book early! CONTRIBUTED TALKS: If you wish to present your work at the conference, either as an oral talk or a poster, you must submit an abstract through the conference website by the November 5th deadline. Abstract guidelines and submission information at: http://w-qbio.org/abstracts/ ABSTRACT DEADLINE: November 5, 2013 Abstract guidelines and submission information at: http://w-qbio.org/abstracts/ Questions should be emailed to: coordinator at w-qbio.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From z.kourtzi at bham.ac.uk Tue Oct 22 18:06:44 2013 From: z.kourtzi at bham.ac.uk (Zoe Kourtzi) Date: Tue, 22 Oct 2013 23:06:44 +0100 Subject: Connectionists: lab manager position, Univ of Cambridge Message-ID: A lab manager position is available to work with Andrew Welchman and Zoe Kourtzi at the Department of Psychology, University of Cambridge, UK. The lab focuses on understanding the neural basis of human perception and adaptive behaviours using a combination of behavioral, computational and brain imaging techniques (fMRI, TMS, EEG). The team consists of an international and interdisciplinary mix of students and post-docs who use specialist equipment (display devices, eye trackers, brain imaging equipment). The successful candidate will provide hardware (i.e. configuring IT equipment and experimental hardware) and software support (i.e. developing software for stimulus generation and data analysis) as well as some administrative support (e.g. ordering equipment, organizing data bases and data storage, writing reports). The lab manager will be involved in all aspects of the lab life (i.e. conducting research projects in collaboration with lab members, organizing conferences and workshops, attending seminars and lab meetings). A bachelor's (or higher) degree in computer science, engineering, neuroscience, psychology, math or other related field is required. Strong computer programming skills (especially MATLAB, C++, OpenGL) and organizational skills are required. Research experience in cognitive and or computational neuroscience would be preferable, but not required. For informal inquiries, please send CV and a brief statement of background skills and interests to zoe at kourtzi.com From mjose.escobar at gmail.com Wed Oct 23 08:38:23 2013 From: mjose.escobar at gmail.com (Maria Jose Escobar) Date: Wed, 23 Oct 2013 09:38:23 -0300 Subject: Connectionists: Tenure-track Academic Position Message-ID: Tenure-track Academic Position ------------------------------ Job Description *Academic profile: ELECTRONIC BIOENGINEERING* The Department of Electronic Engineering, Universidad T?cnica Federico Santa Mar?a (UTFSM), offers a full-time tenure-track academic position, to strengthen multidisciplinary research lines in Electronic Bioengineering. The successful applicant will be asked to sign a performance agreement defining the specific goals to be achieved in teaching and research during a trial period of three years. If the assessment of the attainment of the goals specified in the aforementioned agreement receives positive evaluations, the candidate will be offered a permanent position in the Department of Electronic Engineering. *Position requirements* 1)Possession of a doctoral degree in Electronic Engineering, or similar, with demonstrable results in the creation of knowledge, through patents or publications in ISI indexed journals. 2)Experience in application to and management of research projects. 3)Willingness to teach in graduate programs and at undergraduate level (theoretical and experimental). 4)Willingness to participate in training programs aimed at the use of modern educational methodologies and in the planning of the engineering education curriculum. 5)Applicants not fluent in Spanish should show willingness to acquire as soon as possible sufficient proficiency to be able to teach and to interact with students. The trajectory and expertise of the candidate is expected to strengthen multidisciplinary research lines in Electronic Bioengineering, such any of the following areas: ?Modeling and analysis of biological systems ?Instrumentation associated with bioelectric signals, ?Digital signal processing and biomedical imaging. Additionally, it is desirable that the candidate complements and strengthens new lines of research in the Department of Electronic Engineering, such as voice and human hearing, biomedical acoustics, computational neuroscience, biological vision and ambulatory monitoring of biomedical signals, human computer interaction, cognitive feedback and statistical analysis. More information about the Department of Electronic Engineering, UTFSM, and the related research projects can be found at: http://www.elo.utfsm.cl ; http://www.elo.utfsm.cl/~bioelo/ . Additional General information on the University and on Valparaiso can be found in http://www.oai.utfsm.cl/en/usm/ ------------------------------ To Apply *Documentation required* 1. Curriculum Vitae. 2. Proposal for personal academic development, including research and teaching. 3. Recommendation letters from (at least, two) academics. One of the referees should be the Ph.D. Thesis advisor. 4. Copy of most relevant publications. 5. Certificates of diplomas and degrees. *Important Dates* Application Deadline: November 30, 2013 *Submission of Application* Additional information can be requested by e-mail to Dr. Juan I. Yuz ( juan.yuz at usm.cl) cc: concursos.elo at usm.cl, convenio.doctorados at usm.cl Applications should be sent in electronic format to: concursos.elo at usm.cl, cc: postulaciones.rrhh at usm.cl, juan.yuz at usm.cl The subject of the message should include the *Position Code 13-01-57*. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ala at csc.kth.se Wed Oct 23 14:58:12 2013 From: ala at csc.kth.se (Anders Lansner) Date: Wed, 23 Oct 2013 20:58:12 +0200 Subject: Connectionists: Assistant Professor in Applied Computer Science/Neuroinformatics at KTH Message-ID: <003a01ced021$df5ff8b0$9e1fea10$@csc.kth.se> School of Computer Science at KTH (Royal institute of Technology) has announced an OPEN ASSISTANT PROFESSOR POSITION in Applied computer science with specialization in Neuroinformatics. The assignments involve research and teaching in particular as a part of the Computational biology research group at School of Computer Science and Communication, KTH, as well as to foster and participate in collaboration with experimental brain research groups, nationally and internationally. Distribution between research and teaching is negotiable but the percentage of teaching will not be more than 25%. For more information please see http://www.kth.se/en/om/work-at-kth/vacancies/assistant-professor-in-applied -computer-science-with-specialization-in-neuroinformatics-1.423956 ****************************************** Anders Lansner Professor in Computer Science, Computational biology School of Computer Science and Communication Stockholm University and Royal Institute of Technology (KTH) ala at kth.se, +46-70-2166122 -------------- next part -------------- An HTML attachment was scrubbed... URL: From ahirose at ee.t.u-tokyo.ac.jp Thu Oct 24 00:51:14 2013 From: ahirose at ee.t.u-tokyo.ac.jp (Akira Hirose) Date: Thu, 24 Oct 2013 13:51:14 +0900 Subject: Connectionists: CFP: Complex-Valued Neural Networks Special Session in WCCI/IJCNN 2014 Beijing Message-ID: <5268A742.1010004@ee.t.u-tokyo.ac.jp> Call For Papers: ================================================== Complex-Valued Neural Networks Special Session in WCCI/IJCNN 2014 Beijing ================================================== http://www.eagle.tamut.edu/faculty/igor/IJCNN_CVNN_Special_Session_Title.htm Paper submission deadline: December 20, 2013 http://www.ieee-wcci2014.org/ Scope: Complex-valued neural networks (CVNNs) exhibit very desirable characteristics in their learning, self-organizing, and processing dynamics. They are perfectly suited to deal with complex amplitude, composed of amplitude and phase, which is one of the core concepts in physical systems dealing with electromagnetic, light, sonic/ultrasonic, and quantum waves (electron and superconducting waves). This, together with the widespread use of analytic signals, gives them a critical advantage in practical applications in diverse fields of engineering, where signals are routinely analyzed and processed in time/space, frequency, and phase domains. CVNNs are closely related also to brain dynamics, e.g., in the analysis of theta rhythm in Hippocampus where the phase shift plays an important role in place cell firing. In addition, broad-sense CVNNs such as quaternion and Clifford neural networks, as well as kernel and reservoir approaches, underpin unique new directions in color-information treatment, robotics and control. From djaeger at emory.edu Fri Oct 25 16:42:18 2013 From: djaeger at emory.edu (Jaeger, Dieter) Date: Fri, 25 Oct 2013 20:42:18 +0000 Subject: Connectionists: Postdoctoral Position in Cerebellar Modeling Message-ID: <5A5A0407AFA3CE489A16D5CF16661836BE50D845@e14mbx11n.Enterprise.emory.net> A postdoctoral position in the area of biological neuron modeling in the cerebellar nuclei is available in the lab of Dieter Jaeger at Emory University (Atlanta, USA). The project is tightly integrated with an experimental project of recording multiple cerebellar neurons in behaving mice in the lab of Detlef Heck in Memphis (TN, USA) and aims to reproduce recorded cerebellar nuclei activity in compartmental simulations. It is funded by an NIH CRCNS award. Simulations are based on a published model of cerebellar nuclei neurons (Steuber, V., N. W. Schultheiss, et al. (2011) "Determinants of synaptic integration and heterogeneity in rebound firing explored with data driven models of deep cerebellar nucleus cells." JCNS 30: 633-658; Steuber, V. and D. Jaeger (2013). "Modeling the generation of output by the cerebellar nuclei." Neural Networks 47(0): 112-119.). For productive engagement in this project the candidate must have previous experience in compartmental modeling using Neuron or Genesis simulators as well as be proficient in using Matlab. The position is available immediately. Compensation is based on posted NIH NRSA levels. Interested candidates please email djaeger at emory.edu with a C.V. a brief statement of research interests, and the name of two references. Pre-application questions are also welcome. -- Dieter Jaeger Professor Department of Biology, Emory University 1510 Clifton Rd., Atlanta, GA 30322 404 727 8139, e-mail: djaeger at emory.edu http://www.biology.emory.edu/research/Jaeger ________________________________ This e-mail message (including any attachments) is for the sole use of the intended recipient(s) and may contain confidential and privileged information. If the reader of this message is not the intended recipient, you are hereby notified that any dissemination, distribution or copying of this message (including any attachments) is strictly prohibited. If you have received this message in error, please contact the sender by reply e-mail message and destroy all copies of the original message (including attachments). -------------- next part -------------- An HTML attachment was scrubbed... URL: From gluck at pavlov.rutgers.edu Sat Oct 26 09:34:46 2013 From: gluck at pavlov.rutgers.edu (Mark Gluck) Date: Sat, 26 Oct 2013 09:34:46 -0400 Subject: Connectionists: POSTDOCTORAL & PHD PROGRAM OPENINGS: Cognition, Aging, & Brain Health in African-Americans (Deadline December 15, 2013) Message-ID: <8E799451-8E4C-4E2E-A13E-44BF53DDF122@pavlov.rutgers.edu> Please re-post and/or forward to potential applicants: POSTDOCTORAL AND GRADUATE/PHD POSITION AT RUTGERS UNIVERSITY - NEWARK Cognition, Aging, & Brain Health in African-Americans Start dates: Postdoctoral Fellowships: January, 2014 or Summer/fall 2014. Graduate/PhD Program in Behavioral and Neural Sciences: August, 2014 DEADLINES FOR BOTH: December 15, 2013 (or sooner if possible) FOR THE POSTDOCTORAL FELLOW: We seek someone who either has a PhD, or will be finishing their PhD in the coming year for a two to three-year postdoctoral fellowships to work on research projects relating to cognition, aging, and brain health in the African-American community. The research is based at the Center for Neuroscience at Rutgers University-Newark, within the lab of Mark Gluck, Ph.D., and is part of the university's broader African-American Brain Health Initiative. For more information, see http://www.brainhealth.rutgers.edu In partnership with local Newark churches and other community and city organizations, we are combining educational programs on brain health and cognitive vitality in the African-American community with observational and interventional research studies on "Pathways to Healthy Brain Aging in African-Americans." Related studies focus of neurological disorders (especially Parkinson's disease, Depression, and Alzheimer's disease) in African-American seniors. We are especially interested in the interactions between biological markers and life-style variables (including sleep, diet, exercise, and fitness) on cognitive and emotional changes across the lifespan in the African-American community. A series of exercise and dance intervention studies are planned in collaboration with the Rutgers Department of Exercise Science. Rutgers-Newark located in downtown Newark, New Jersey, just outside (about 13 miles from) Manhattan/New York City. There is easy access via several forms of publication transportation between Newark and NYC, as well as most major cities in New Jersey. Rutgers University is the State University of New Jersey with several campuses and two medical schools. Postdoctoral Candidates must: 1. Have (or soon graduate with) a PhD in Psychology, Nursing, Geriatrics, Social Work, Exercise Science or related fields with a strong background in (a) experimental behavioral research, (b) strong writing skills, and (c) statistical data analysis skills (please document all three in your cover letter). 2. Have prior experience, familiarity, and sensitivity to minority health issues and working with the African-American community. More information on our lab and related research, educational, and global health programs is at http://www.gluck.edu Informal letters of inquiry are encouraged as soon as possible, especially for those who might not be done their PhD until summer 2014. Full applications should include a CV and cover letter with overview of background and career goals, addressing both criteria noted above, along with names and emails of potential recommenders and be emailed to gluck at pavlov.rutgers.edu. FOR GRADUATE/PHD PROGRAM: We also seek strong graduate students to work on our studies of "Cognition, Aging, & Brain Health in African-Americans" as part of their thesis research leading towards a PhD in Neuroscience. SPECIAL MINORITY FELLOWSHIP NOTICE: Rutgers-Newark has additional minority graduate fellowships funded by the NIH through the Minority Biomedical Research Support Program. If you are eligible for such a program, please contact me at gluck at pavlov.rutgers.edu. From the NIH grant each doctoral student in the MRBS Program receives, initially, an annual salary of $28,456, full tuition remission, a $1,000 research allowance, and defrayment of all expenses associated with attending one scientific conference annually. Additional information on our MBRS program can be found at: http://www.newark.rutgers.edu/news/three-decades-success-r-ns-minority-biomedical-research-support-program http://catalogs.rutgers.edu/generated/nwk-grad_current/pg10.html The goal of the Graduate Program in Behavioral and Neural Sciences (BNS) at Rutgers University-Newark is to provide training across all areas of neuroscience as well as to provide intensive instruction within one area of focus so that graduates will be prepared for careers as academicians, educators and research scientists. Students are fully funded by the graduate program (not by individual faculty) for five years with a stipend, tuition and comprehensive health insurance. The BNS curriculum offers a wide range of courses that provide both breadth and depth. The program has only a few required courses but many electives so that students may tailor coursework to their individual backgrounds and needs. Students are primarily trained to conduct independent research and to present and discuss their results orally and in written form. Students also gain experience in undergraduate and graduate teaching and mentoring. The recent integration into Rutgers of the former UMDNJ Medical School provides our students with additional clinically-relevant training opportunities. The campus of the BNS program is located in Newark, New Jersey, 13 miles from Manhattan, New York City, with extensive public transportation links between the two. For more information, and links to faculty profiles and related resources, see: http://www.neuroscience.newark.rutgers.edu Additional information on our brain imaging center can be found at http://rubic.rutgers.edu The admissions link can be reached directly at: http://www.bns.rutgers.edu The deadline for applications is December 15, 2013 and interviews of the top candidates will take place mid/late February, 2014. Late applications may be considered on a case by case basis. Applicants to the BNS program who are interested in working on African-American Brain Health research should contact me directly as well at gluck at pavlov.rutgers.edu. - Mark Gluck ___________________________________ Dr. Mark A. Gluck, Professor Director, Rutgers Memory Disorders Project Center for Molecular and Behavioral Neuroscience Rutgers University 197 University Ave. Newark, New Jersey 07102 Web: http://www.gluck.edu Email: gluck at pavlov.rutgers.edu Ph: (973) 353-3298 -------------- next part -------------- An HTML attachment was scrubbed... URL: From mattia at iss.infn.it Thu Oct 24 04:03:47 2013 From: mattia at iss.infn.it (Maurizio Mattia) Date: Thu, 24 Oct 2013 10:03:47 +0200 Subject: Connectionists: Two postdoctoral positions: modeling and analysis of slow-wave oscillations Message-ID: <002b01ced08f$91565ce0$b40316a0$@infn.it> Applications are invited for two two-year postdoctoral positions at the Italian Institute of Health (Istituto Superiore di Sanit?, ISS) in Rome to collaborate with Dr. Maurizio Mattia. The positions are funded by the project CORTICONIC from FP7 of European Commission (www.corticonic.org), and one of them will be co-supervised with Prof. Paolo Del Giudice (project PI for ISS). The project aims to identify the multi-scale organization of the cortex by analyzing and modeling the generation and propagation of slow oscillations during sleep and anesthesia. The postdoctoral researchers will develop models of cortical fields of interconnected pools of spiking neurons to reproduce slow-wave oscillations with propagation modes and variability comparable to the one observed in in vivo experiments on rodents. This will allow to infer more general features of the nervous tissue as an excitable medium and will inspire theory-driven innovative strategies for electrophysiological data analysis to perform in close collaboration with the laboratory of Prof. Maria-Victoria Sanchez-Vives in Barcelona. The ideal applicants have a strong background in Physics or Applied Mathematics, with experience in modeling biological systems and in analyzing experimental data. Programming friendliness with MATLAB (or similar) is desirable. The contracts will start from the beginning of 2014 for full-time positions with salary based on standard Italian regulations for 3rd level researcher. The successful candidates will spend two years in ISS enjoying the awesome marvels of our Eternal City, and joining a growing group of researchers in theoretical neuroscience (neural.iss.infn.it) enriched by collaborations with theoretical physicists and neurophysiologists working on primates and humans at the nearby 'Sapienza' University of Rome. To apply, send a brief statement of research interests, CV, and contact information for two references to maurizio.mattia at iss.it and paolo.delgiudice at iss.infn.it. Informal inquiries are also welcome. _______________________ Maurizio Mattia, PhD Complex Systems Modeling Sect., Technologies and Health Dept., phone : +39 06 49902513 Istituto Superiore di Sanit? fax : +39 06 49902137 v.le Regina Elena, 299 e-mail: maurizio.mattia at iss.it 00161 Roma, Italy web : http://neural.iss.infn.it From hiro at brain.riken.jp Mon Oct 28 01:35:49 2013 From: hiro at brain.riken.jp (hiroyuki nakahara) Date: Mon, 28 Oct 2013 14:35:49 +0900 Subject: Connectionists: Postdoctoral researcher positions available, Laboratory for Integrated Theoretical Neuroscience at RIKEN Brain Science Institute, Japan Message-ID: <20131028143549.8B66.25DAB7C8@brain.riken.jp> Dear colleagues, Applications are invited for opening positions for postdoctoral scientists to work at the Laboratory for Integrated Theoretical Neuroscience (Lab Head: Hiro Nakahara), RIKEN Brain Science Institute. Our laboratory?s long-term research goal is to understand the computational principles that underlie the way neural systems realize adaptive decision-making and associated learning. We work on two main areas, decision making and neural coding, using computational approaches and conducting human fMRI experiments. In this way, we build computational and mathematical models and analyze behavioral, neurophysiological, and imaging data, often closely combined with experimental investigations. (Find details about our laboratory on our website: http://www.itn.brain.riken.jp). We are seeking enthusiastic and well-qualified postdoctoral fellows to join our research activities in any of the following topics. (This job advert is on http://www.brain.riken.go.jp/en/careers/20131021_h_! nakahara_r.html). 1) Human fMRI experiments: We study value-based (reward-based) decision-making and learning as well as social decision-making and learning. We welcome candidates who want to investigate the underlying neural and cognitive processes with respect to key computations such as model-based analysis (e.g., reinforcement learning and Bayesian frameworks). We are also interested in the techniques of neural decoding and connectivity analysis, combined with model-based analyses, and extending our research into the domain of computational psychiatry. 2) Modeling studies: We build computational and mathematical models for understanding the neural, cognitive, and computational processes of value-based and social decision-making. We are interested, for example, in integrating reinforcement learning with state representational learning and in investigating the relationship of model-free and model-based reinforcement learning in neural circuits. Circuit-wise, we are interested in the basal ganglia-related circuit, including dopamine neuron functions and in relation to prefrontal areas and other subcortical areas (e.g., the lateral habenula, amygdala, and neuromodulator circuits). 3) Neural coding studies: We analyze neural data, particularly fMRI and neurophysiological data, often developing new methods of analysis. We address to the underlying neural mechanisms for decision-making and, more generally, contribute to understanding neural coding: computation and coding realized by the collective activity and interactions of neurons. With respect to fMRI data, we plan to advance model-based analysis, for instance, in combination with developing methods for neural decoding and connectivity analysis. As for neurophysiological data (e.g., via collaboration with experimental laboratories using animal experiments), we are analyzing dopamine neural activity from behaving monkey experiments, based on new theories of reinforcement learning, and are also planning to analyze large-scale simultaneous recording of neural activities from behaving rat experiments, with the aim of answering how neural interactions give rise to reinforcement and representational learni! ng. Applicants should have, or be expecting to receive, a Ph.D., and have research interest and background in the area of (or related to) research described above. Please send your application to itninfo at brain.riken.jp; for what to be sent as the application materials, please refer to http://www.brain.riken.go.jp/en/careers/20131021_h_nakahara_r.html. Application review will begin immediately and continue until the position is filled. Start date is flexible, but an early starting time is preferred. Informal inquiry should also be sent to itninfo at brain.riken.jp. Best wishes, Hiro Hiroyuki Nakahara, Ph.D. Laboratory for Integrated Theoretical Neuroscience RIKEN Brain Science Institute http://www.itn.brain.riken.jp -- hiroyuki nakahara http://www.itn.brain.riken.jp From conradt at tum.de Mon Oct 28 03:13:16 2013 From: conradt at tum.de (=?iso-8859-1?Q?J=F6rg_Conradt?=) Date: Mon, 28 Oct 2013 07:13:16 +0000 Subject: Connectionists: reminder, Sparks Workshop Announcement: Neuroengineering the Brain Message-ID: Dear Connectionists members, -- reminder -- we cordially invite you to the NNCN Sparks Workshop Neuroengineering the Brain: from Neuroscience to Robotics ... and back taking place December 2-4, 2013 near Munich, Germany. The workshop brings together leading researchers in the border areas between computational neuroscience and systems engineering with a focus on robotics, to discuss currently available neuromorphic computing approaches applicable in future technical systems. Detailed information: http://www.sparks2013.de Attendance is limited; please register on the web pages as soon as possible if you want to attend. Seats will be allocated on first-come-first-served basis. We are very much looking forward to your participation! The workshop organizing team Jorg Conradt, Gordon Cheng, Stefan Ehrlich, Susanne Schneider -- J?rg Conradt Prof. of Neuroscientific System Theory www.nst.ei.tum.de Cluster "Cognition for Technical Systems" www.cotesys.org Institute of Automatic Control Engineering www.lsr.ei.tum.de Technische Universit?t M?nchen, Karlstr. 45, 80333 Munich, Germany Tel: +49 89 289-26902, Fax: +49 89 289-26901, E-mail: conradt at tum.de -------------- next part -------------- An HTML attachment was scrubbed... URL: From lvdmaaten at gmail.com Mon Oct 28 05:59:38 2013 From: lvdmaaten at gmail.com (Laurens van der Maaten) Date: Mon, 28 Oct 2013 10:59:38 +0100 Subject: Connectionists: CfP Neurocomputing Special Issue on Visual Analytics using Multidimensional Projections Message-ID: ---- Neurocomputing special issue on Visual Analytics using Multidimensional Projections ---- ---- Extended submission deadline: DECEMBER 1ST, 2013 ---- Following the successful workshop on Visual Analytics using Multidimensional Projections (VAMP) at EuroVis 2013 (http://homepage.tudelft.nl/19j49/eurovis2013/), we solicit submissions to a special issue of the Neurocomputing journal on Visual Analytics using Multidimensional Projections (VAMP). Submissions are due December 1st, 2013 via the Neurocomputing submission system (please select "SI: VAMP 2013" when you reach the ?Article Type? step in the submission process). Each paper will be reviewed by experts from both Machine Learning and Visualization communities. Dimensionality reduction is an active area in machine learning. New techniques have been proposed for more than 50 years, for instance, principal component analysis, classical scaling, isomap, probabilistic latent trait models, stochastic neighbor embedding, and neighborhood retrieval visualization. These techniques facilitate the visualization of high-dimensional data by representing data instances as points in a two-dimensional space in such a way that similar instances are modeled by nearby points and dissimilar instances are modeled by distant points. Although many papers on these so-called ?embedding? techniques are published every year, which all aim to improve visual representations of high-dimensional data, it appears that these techniques have not gained popularity in the information-visualization community due to the inherent complexity of their interpretation. At the cross-section of information visualization, machine learning, and graph drawing, the special issue intends to focus on issues that embedding techniques should address to bridge the gap with the information-visualization community. A non-exhaustive list of such issues is given below: ? Stability: Nonlinear embedding techniques are more efficient at preserving similarities than linear ones. However, non-linearities generate local optima as a result of which different initializations lead to different representations of the same data. The differences between these embeddings of the same data create confusion for the analyst, who is unable to grasp the common facts across the different visualizations. How can we design efficient and stable nonlinear embeddings? ? Embedding of dynamic data: Embedding usually projects all the data at once; when new data arrive, how can we embed these data without modifying the current embedding too much? ? Multiple methods: Each embedding algorithm necessarily comes with its own set of built-in underlying assumptions, and knowledge of these assumptions is often helpful in making sense of the visual output. How can we design black-box visualization methods that demand less understanding of underlying assumptions from the side of the analyst? ? Evaluation and subjectivity: Visual interpretation is inherently subjective. How can we help analysts to verify whether an eye-catching pattern is real/essential or whether it just happens to be an artifact? ? Inference and interactions: Nonlinear embedding techniques produce points clouds in which the axes have no meaning and pairwise distances are approximations which may have many artifacts. What kinds of analytical tasks can be performed with such embeddings? How can we better convey the meaning of the embeddings to analysts? ? Feedback: The human eye is excellent at visual analysis, and can identify regularities and anomalous data even without having to define an algorithm. How can we make use of this ability to enhance the predictive performance of machine learning and embedding techniques? ? Input data: Currently, the input data in embedding techniques typically comprises high-dimensional feature vectors or pairwise distance between objects. However, this is not always the kind of data that analysts encounter in practice. How can embeddings be constructed based on partial similarity rankings, associations or co-occurences of objects, heterogeneous data, data with missing values, relations between objects, structured objects, etc.? ? Optimizing embeddings for visual analysis: nonlinear embeddings are found by optimizing mathematical goodness-of-fit measures. Instead of using off-the-shelf embedding methods, can the measures and methods be designed so that the optimized embeddings will be good for carrying out concrete low-level or high-level analysis tasks from the visualization? The special issue aims to attract contributions on these or related topics. In case of any questions about this special issue, please contact the guest editors: Laurens van der Maaten and Micha?l Aupetit . -------------- next part -------------- An HTML attachment was scrubbed... URL: From pascal.fua at epfl.ch Mon Oct 28 08:45:53 2013 From: pascal.fua at epfl.ch (Pascal Fua) Date: Mon, 28 Oct 2013 13:45:53 +0100 Subject: Connectionists: Faculty Positions in Computer Science at EPFL Message-ID: <526E5C81.8060508@epfl.ch> The School of Computer and Communication Sciences at EPFL invites applications for faculty positions in computer and communication sciences. We are seeking candidates for positions at the tenure-track assistant professor or tenured senior professor levels. Successful candidates will develop an independent and creative research program, participate in both undergraduate and graduate teaching, and supervise PhD students. Candidates from all areas of computer science will be considered, but preference will be given to candidates in the fields of cyber-physical risk management, data analytics, machine learning, security and privacy. EPFL, in Lausanne, Switzerland, is a dynamic science and engineering university ranked among the top research institutions in Europe. It offers a rich international environment with English as its common language, as well as competitive salaries, significant start-up resources, and outstanding research infrastructure. To apply, please follow the application procedure at https://academicjobsonline.org/ajo/jobs/3050 The following documents are requested in PDF format: curriculum vitae including publication list, brief statements of research and teaching interests, names and addresses (including e-mail) of 3 references for junior positions and 6 for senior positions. Screening will start on December 1, 2013. Further questions can be addressed to : Prof. Willy Zwaenepoel Chairman of the recruiting committee School of Computer and Communication Sciences EPFL CH-1015 Lausanne recruiting.ic at epfl.ch For additional information on EPFL, please consult http://www.epfl.ch or http://ic.epfl.ch From i.bojak at reading.ac.uk Mon Oct 28 13:46:24 2013 From: i.bojak at reading.ac.uk (Ingo Bojak) Date: Mon, 28 Oct 2013 17:46:24 +0000 Subject: Connectionists: Reminder: Advances in Neural Population Models and Their Networks Message-ID: <48CB3D20-994E-4F46-9603-24F43F155F6F@reading.ac.uk> Dear colleagues, May we remind you of the Open Thematic Series ("special issue") in the Springer open access journal EPJ Nonlinear Biomedical Physics: Advances in Neural Population Models and Their Networks This special issue arises from two CNS*13 workshops ("Advances in Neural Mass Modelling" and "Full Brain Network Dynamics - Modelling, Analyses, Experiments", respectively), but welcomes topical submissions from all. Deadline for submissions is 15 November 2013, and will not be moved. The full announcement can be found here as PDF, but is also reproduced below. If you have any questions please feel free to contact us via i.bojak at reading.ac.uk. As (guest) editors, we look forward to receiving your contributions to what promises to be an exciting special issue. Best wishes, Ingo Bojak, Stephan van Gils and Sid Visser Full announcement Neural population models (NPMs) describe the overall behaviour of large ensembles of neurons. Various names have been used for this general approach according to mathematical and conceptual detail: neural mass models, mean field models, neural field models, cortical field theory, etc. Since not all neurons are modelled individually, a distinct advantage of these lumped models is the reduction in dimensionality of both the parameter and variable space, which reduces computation time and makes possible sophisticated mathematical analyses of the model?s behaviour as well as their application to experimental data. Nevertheless, NPMs retain their biological interpretability, allowing researchers to investigate a wide range of brain function in health and disease, as well as the effects of drugs and other extraneous influences. Current non-invasive neuroimaging methods such as EEG, fMRI and MEG measure in various ways the activity of sizable groups of neurons, making their data a natural target for NPMs. Furthermore, thanks to the speed with which NPMs can be evaluated one can computationally match the ability of these modalities to record the activity of entire brains. In combination with rapid experimental progress in determining the large scale connectivity (the connectome), this is leading to novel NPM-based methods for the modelling of partial or even full brain networks. Typically such models are characterized by time delays via signal propagation along connecting fibres with NPMs as network nodes. They promise to make NPMs the tool of choice for neuroimaging analysis in the future. Topics of interest for this thematic series include but are not limited to the following advances in neural population modelling: ? the inclusion of neural mechanisms such as spike rate adaptation or bursting ? the effects of higher order statistics on the dynamics ? the formal and/or computational correspondence between microscopic and macroscopic models ? adapting models for different regions of the brain ? describing pathologies and drug effects ? the development of new analytic tools for these systems ? determining the effects of connectivity on dynamics ? building partial and full brain networks ? studying large scale brain dynamics in health and disease ? addressing cognition through associated brain processes Authors are cordially invited to submit original research papers on novel techniques, theoretical analyses and simulations, as well as applications to experiment and data analysis, of recent developments in neural population models and their networks. Submission Instructions Before submission, authors should carefully read over the ?Instructions for Authors?, which are located at http://www.epjnonlinearbiomedphys.com/authors/instructions. Prospective authors should submit an electronic copy of their complete manuscript through the SpringerOpen submission system at http://www.epjnonlinearbiomedphys.com/manuscript according to the submission schedule. They should choose the section ?Systems Neurosciences and Integrative Brain Research? and then choose the subsection ?Thematic series: Advances in Neural Population Models and Their Networks?. In addition, they should specify the manuscript as a submission to the ?Thematic series on Advances in Neural Population Models and Their Networks? in the cover letter. Submission Schedule Manuscript due: November 15, 2013 Guest Editors Ingo Bojak, School of Systems Engineering, University of Reading, UK and Donders Centre for Neuroscience, Radboud University Nijmegen (Medical Centre), The Netherlands Stephan A. van Gils, Applied Mathematics, University of Twente, The Netherlands Sid Visser, School of Mathematical Sciences, University of Nottingham, UK For any queries please contact Ingo Bojak, i.bojak at reading.ac.uk. -------------- next part -------------- An HTML attachment was scrubbed... URL: From i.bojak at reading.ac.uk Mon Oct 28 15:28:17 2013 From: i.bojak at reading.ac.uk (Ingo Bojak) Date: Mon, 28 Oct 2013 19:28:17 +0000 Subject: Connectionists: 3 year Postdoc in Neural Population Model Data Assimilation, Reading, UK Message-ID: <59E6B035-CAF5-4090-9D4F-F758890DD097@reading.ac.uk> Postdoctoral Fellow in Neural Population Model Data Assimilation School of Systems Engineering, School of Meteorology and Center for Integrative Neuroscience and Neurodynamics University of Reading, UK Closing date: 21 November 2013 Reference number: RS13077 Interviews: 28 November 2013 Start date: 1 December 2013, or as soon as possible thereafter Post type: full-time, fixed term for 3 years Payscale: ?27,854 to ?36,298 per annum You will play a pivotal role in an exciting interdisciplinary collaboration between the School of Systems Engineering (Prof Ingo Bojak), the School of Meteorology (Prof Peter Jan van Leeuwen) and the Center for Integrative Neuroscience and Neurodynamics (CINN, Prof Douglas Saddy) at the University of Reading. Together we will bring world-leading Data Assimilation techniques, developed in particular for weather forecasting, to bear on computational neuroscience by demonstrating that spontaneous and task-driven neuroimaging data (EEG and fMRI BOLD) can be described, understood and forecast in terms of highly realistic and complex models comprising a large number of neural masses distributed over a cortical discretization mesh. You will have: ? Prior research experience in at least one of the following fields: Data Assimilation, Computational Neuroscience or Computational Neuroimaging Analysis ? Excellent skills in applied mathematics, scientific programming, scientific methods and research presentation ? A PhD in a relevant field, excellent scientific publication(s) and a track record of producing useful software (preferably C/C++ and Fortran 90) ? Enthusiasm for an interdisciplinary project focused on neuroscience, a winning, creative personality and the drive to push technical boundaries together with our team For further particulars, please click here. Informal questions are welcomed by Prof Ingo Bojak (Project Leader, Neural Population Models), Prof Peter Jan van Leeuwen (Project Co-Leader, Data Assimilation) and Prof Douglas Saddy (Project Co-Leader, Neuroimaging). To apply click here on the "Apply online" button. Alternatively, if you wish to apply using a hardcopy form please email recruitment at reading.ac.uk or contact Human Resources, University of Reading, Whiteknights, PO Box 217, Reading RG6 6AH or Telephone +44(0)118 378 6771 (voicemail). Please quote the relevant reference number RS13077. We value a diverse workforce and welcome applications from all sections of the community. -------------- next part -------------- An HTML attachment was scrubbed... URL: From pierre.kornprobst at inria.fr Tue Oct 29 03:54:07 2013 From: pierre.kornprobst at inria.fr (Pierre Kornprobst) Date: Tue, 29 Oct 2013 08:54:07 +0100 Subject: Connectionists: Postdoctoral position in computational neuroscience at INRIA, France Message-ID: Postdoctoral position in computational neuroscience at INRIA, France: From real retinas to a virtual retina (Bruno Cessac and Pierre Kornprobst, team Neuromathcomp) *** Context : Our understanding on how the retina works has progressively known a paradigm change : whereas retina was up to recently viewed as a relatively simple organ (acting roughly like a camera), it is now admitted by the scientific community that ? eyes are smarter than scientists believed ? [Gollisch-Meister, 2010]. The retina is able to perform such clever tasks as detecting differential motion or anticipating motion. These wonderful properties are largely due to the sophisticated retina structure in terms of cells differentiation as well as connectivity. This results in a complex dynamical system where the response to visual inputs is encoded in a collective way by neurons dynamics. The ? output ? of the retina, a sequence of action potentials or spike train emitted by ganglion cells, is transmitted to the visual cortex via the optic nerve (constituted by the axons of the ganglion cells). In this way, the retina is able to ? encode ? a visual scene in the form of spike trains. How to decipher this collective code is an open problem. The Multi-Electrode Array (MEA) technique allows scientists to register spike trains in order to analyze their statistical properties and to extract potential generic laws giving keys to decipher the code on the one hand; on the other hand, techniques such as two-photons imaging or calcium imaging provide more and more detailed information about the retina circuitry and dynamics. This opens up several scientific challenges : on the theoretical side, building new mathematical models allowing to relate the retina circuitry and dynamics to spike trains statistics as a response to a visual scene ; on the applied side, creating software that mimics retina functioning with potential applications in the domain of fundamental research (simulating virtual retinas instead of performing experiments on animals) and therapy (e.g. analyzing the effect of drugs on retina functions, in silico). *** Project : The project we propose is at the corner between these two aspects. The goal is to develop a new hybrid retina simulator, emulating the outer retina. On the theoretical side, the project will use statistical methods developed in our team to perform spike train analysis [1,2] from experiments done by our partners (Evelyne Sernagor from NewCastle University and Luca Berdondini from IIT Genova), in order to construct a virtual layer of Amacrine and Ganglion cells emulating realistic spike statistics, instead of replicating the detailed laminar connectivity of the retina. For this, generic neural network models studied in our team will be used. These models neglect the detailed biological description of neurons, but take into account anatomical constraints such as connectivity and reproduce collective statistics of RGCs types in response to specific stimuli. On the applied side, this layer will be integrated to the Virtual Retina software developed in our team [3]. This postdoc is part of the RenVision European project. It is funded by the European Union FP7 FET (Future Emerging technology) proactive program: Neuro-Bio-Inspired Systems Call 9 Objective 9.11. This highly interdisciplinary project aims at understanding and modeling the biological processing of visual information in the retina and exploiting this new knowledge to build retina-inspired artificial visual processing systems. RENVISION website: https://www.renvision-fp7.eu *** Profile : The work is highly interdisciplinary, and applicants must have strong mathematical and computational skills. Preferred educational background is a PhD in Computational Neuroscience. Previous experience with neural population coding and C++ programming skills is required. Applicants should email a CV, brief research statement, relevant publications, and contact details for two academic references to: bruno.cessac at inria.fr and pierre.kornprobst at inria.fr. Bruno Cessac website: http://www-sop.inria.fr/members/Bruno.Cessac Pierre Kornprobst website: http://www-sop.inria.fr/members/Pierre.Kornprobst *** Laboratory: The INRIA team Neuromathcomp is working in the fields of mathematical and computational neuroscience, and biological vision modeling with applications to artificial vision. We are involved in several European research projects. The group is located in Sophia-Antipolis between Nice and Cannes on the French Riviera. INRIA is the only French public research body fully dedicated to computational sciences. Combining computer sciences with mathematics, INRIA?s 3,500 researchers strive to invent the digital technologies of the future. Educated at leading international universities, they creatively integrate basic research with applied research and dedicate themselves to solving real problems, collaborating with the main players in public and private research in France and abroad and transferring the fruits of their work to innovative companies. The researchers at INRIA published over 4,450 articles in 2012. They are behind over 250 active patents and 112 start-ups. The 180 project teams are distributed in eight research centers located throughout France. Neuromathcomp website: http://www-sop.inria.fr/neuromathcomp INRIA website: http://www.inria.fr *** Starting date: January 2014, on the basis of a competitive application. The position is open now until filled. *** Contract duration: 2 years (1 year probation) *** Net salary: 2140 euros/month *** Related references: [1] B. Cessac and A. Palacios, Spike train statistics from empirical facts to theory: the case of the retina, In Mathematical Problems in Computational Biology and Biomedicine, F. Cazals and P. Kornprobst, Springer (2013) [2] J.C. Vasquez, A. Palacios, O. Marre, M.J. Berry II, B. Cessac, Gibbs distribution analysis of temporal correlation structure on multicell spike trains from retina ganglion cells, J. Physiol. Paris, 106(3-4), pp. 120-127 (2012) [3] A. Wohrer and P. Kornprobst. Virtual Retina: A biological retina model and simulator, with contrast gain control, Journal of Computational Neuroscience, 26(2), pp. 219-249 (2009) -------------- next part -------------- An HTML attachment was scrubbed... URL: From fmschleif at googlemail.com Tue Oct 29 16:02:20 2013 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Tue, 29 Oct 2013 21:02:20 +0100 Subject: Connectionists: WSOM 2013 - deadline extension - strict deadline: 15th November 2013 Message-ID: +++ PLEASE, APOLOGIZE MULTIPLE COPIES +++ Dear colleagues, due to several requests we decided to extend the deadline for WSOM 2014. Now, the STRICT last deadline is: 15th November 2013 ! Please follow the the submission guidlines provided at the conference homepage www.WSOM2014.de Details of the original call are also given below. We are looking forward to welcome you in Mittweida. With best regards, Frank-Michael Schleif WSOM Program Chair -- 10th Workshop on Self-Organizing Maps 2014 -- WSOM 2014 www.WSOM2014.de will be held in the beautiful small town Mittweida located close to the mountains Erzgebirge in Saxony/Germany. It will bring together researchers and practitioners in the field of self?organizing systems for data analysis, with a particular emphasis on self?organizing maps and learning vector quantization. WSOM 2014 is the 10th conference in a series of biannual international conferences started with WSOM'97 in Helsinki. SCOPE ? TOPICS We expect contributions related to the theoretical and methodological aspects of the self?organizing map, learning vector quantization and related fields as well as respective applications. Topics include: ? Data analysis and visualization and modelling dynamic phenomena ? Mathematical aspects including information theory and mathematical statistics ? Architectural solutions including hierarchical and growing networks, ensemble models and special metrics ? Neuro?cognitive studies that compare modelling and empirical results at different levels ? Software and hardware implementations ? Outstanding applications emphasizing special aspects of the models We also call for scientific and practice-oriented papers that describe the use of self-organizing maps with variants in different application areas including but not limited to: ? Data mining ? Pattern recognition ? Signal processing ? Knowledge management ? Time series processing ? Industrial applications ? Bioinformatics ? Biomedical applications ? Telecommunications ? Financial analysis ? Cognitive modeling ? Robotics and intelligent systems ? Image processing and vision ? Speech processing ? Language modeling ? Text and document analysis Submission of papers : November 15th 2013 Notification of provisional acceptance: December 15th 2013 Camera ready papers : January 15th 2014 Early registration (special rates) : February 15th 2014 Submissions can be done via Easychair at https://www.easychair.org/conferences/?conf=wsom2014 Accepted papers will be published in Springer's Advances in Intelligent Systems and Computing series. Further details at: www.wsom2014.de From Aaron.Clauset at colorado.edu Tue Oct 29 17:35:46 2013 From: Aaron.Clauset at colorado.edu (Aaron Clauset) Date: Tue, 29 Oct 2013 15:35:46 -0600 Subject: Connectionists: Assistant Professor position in machine learning + optimization at University of Colorado Boulder Message-ID: <3261149F-F6A1-4FCB-8CA9-D38A27C94BAD@colorado.edu> Dear all, The Department of Computer Science at University of Colorado Boulder is hiring this year at the Assistant Professor level, looking for someone who works at the intersection of machine learning and numerical optimization. A summary advertisement appears below, along with a direct link to the application site, which contains the full ad. The deadline is December 1, 2013. Sincerely, Aaron Clauset ------ > The Department of Computer Science (CS) at the University of Colorado Boulder seeks outstanding candidates for a tenure-track position with expertise in both machine learning and optimization. The opening is targeted at the level of Assistant Professor, although exceptional senior candidates at higher ranks may be considered. > > We seek candidates whose primary research areas lie at the intersection of machine learning and numerical optimization, and whose research addresses challenges in theory, algorithms, implementation, and application of problems in optimization and machine learning. Candidates should demonstrate excellence in both research and teaching, have a strong interest in interdisciplinary collaboration, and aim to lead a highly visible, externally funded research program. > > To apply, please go to the following link: > https://www.jobsatcu.com/postings/73978 ------ Aaron Clauset Assistant Professor Computer Science Department, University of Colorado, Boulder, and External Faculty, Santa Fe Institute http://structureandstrangeness.com/ aaron.clauset at colorado.edu @aaronclauset From ASAHTan at ntu.edu.sg Thu Oct 31 01:51:18 2013 From: ASAHTan at ntu.edu.sg (Tan Ah Hwee (Assoc Prof)) Date: Thu, 31 Oct 2013 05:51:18 +0000 Subject: Connectionists: FW: Call for Papers - WCCI 2014 Special Session on Towards Human-Like Intelligence Message-ID: Call for Papers World Congress on Computational Intelligence (WCCI) 2014 Special Session on Towards Human-Like Intelligence (THLI) The WCCI 2014 Special Session on Towards Human-Like Intelligence (THLI) is organized by the IEEE Computational Intelligence Society (CIS) Task Force on Towards Human-Like Intelligence (http://www.mini.pw.edu.pl/~mandziuk/cis_tf_thli/). It is one of a series of events, following the success of 2013 IEEE Symposium on Computational Intelligence for Human-Like Intelligence (CIHLI) as part of Symposium Series on Computational Intelligence (SSCI 2013) held in Singapore from 16 to 19 April 2013 and will be followed by 2014 IEEE Symposium on Computational Intelligence for Human-Like Intelligence as part of SSCI 2014 to be held in Orlando, USA from 9 to 12 December 2014. The main goal of this special session is to promote and advance research activities related to achieving all facets of human-like intelligence, including learning, reasoning, problem solving, intuition, creativity, insight, emotion, motivation, curiosity, and imagination. The organizers encourage submission of papers describing interdisciplinary research, development, and applications of various Computational Intelligence paradigms, including neural networks, fuzzy logic, genetic algorithms, memetic computing, machine learning, and statistical techniques, towards creating human-like behavior, performance and characteristics. Topics of Interests The special session welcomes all papers related to accomplishing human-like intelligence by artificial and/or biologically-inspired systems, models, and algorithms. The topics of interests include but are not limited to: * Models and architectures for human-like intelligence * Cognitively-plausible architectures and systems * Biologically-inspired cognitive models * Knowledge representation, learning and reasoning * Emulating intuition, creativity, insight, curiosity, personality and imagination * Chunk-based representations and the use of geometrical properties in problem solving * High level cognition * Motivation in autonomous behavior * Emotion in human intelligence * Machine consciousness * Autonomous learning, active learning * Transfer learning and multi-task learning Important Dates December 20, 2013 Paper submission deadline March 15, 2014 Author notification of acceptance April 15, 2014 Deadline for receipt of final manuscript Information for Authors 1) Information on the format and templates for papers can be found here: http://www.ieee-wcci2014.org/Paper%20Submission.htm 2) Papers should be submitted via the IJCNN 2014 paper submission site: http://ieee-cis.org/conferences/ijcnn2014/upload.php3) Select the Special Session name in the Main Research topic dropdown list 3) Fill out the input fields, upload the PDF file of your paper and finalize your submission by the deadline of December 20, 2013 Special Session Organizers Ah-Hwee Tan School of Computer Engineering, Nanyang Technological University, Singapore Jacek Ma?dziuk Faculty of Mathematics and Information Science, Warsaw University of Technology, Poland W?odzis?aw Duch Faculty of Physics, Astronomy and Informatics, Nicolaus Copernicus University, Poland ________________________________ CONFIDENTIALITY:This email is intended solely for the person(s) named and may be confidential and/or privileged.If you are not the intended recipient,please delete it,notify us and do not copy,use,or disclose its contents. Towards a sustainable earth:Print only when necessary.Thank you. -------------- next part -------------- An HTML attachment was scrubbed... URL: From nilton at eiiris.tut.ac.jp Tue Oct 29 23:00:33 2013 From: nilton at eiiris.tut.ac.jp (Nilton Kamiji) Date: Wed, 30 Oct 2013 12:00:33 +0900 Subject: Connectionists: RAST for Neuroscience 2013, San Diego, Nov. 9 - 13 Message-ID: Dear all, Apologies if you have received multiple copies. I am please to announce the Related Abstract Search Tool (RAST) for Neuroscience 2013 (SfN2013)! The RAST was developed by the former Laboratory for Neuroinformatics at RIKEN Brain Science Institute. The lab has been closed, but I'm glad the tool could have been made available this year again! The RAST for Neuroscience 2013 (SfN2013) can be accessed at http://ras.ni.brain.riken.jp/SfN2013/ For mobile devices such as iPad,iPhone,and Android based tablets and smartphones, a web application is available at: http://ras.ni.brain.riken.jp/SfN2013/mobile/htdocs Since this is a web application, all you need is a web browser. The RAST allows you to search not only by providing keyword(s), but also by selecting one or multiple abstracts which you are interested in to search for its related abstracts. This feature may provide results focused on the user's interest. That is, abstracts related to a single abstract by means of document similarity may belong to a different research topic. However, abstracts mutually similar to multiple selected abstracts have higher chance in belonging to the similar topic. RAST also suggests possible candidates of keywords by automatically extracting major words from the list of related abstracts. You can also use these words to refine your search. Moreover, not all related abstracts will contain the provided keyword(s). These abstracts cannot be searched by the ordinary keyword search, and thus we call them "Hidden treasure". You can create a list by clicking on Add to Cart button at each abstract, where abstracts will be sorted by date and time. You can also print the list with or without the abstract body from your Printing Cart. You can restore your "Printing Cart" by saving the ID which is displayed on the top right corner. Try and find your "hidden treasures" with RAST! A quick guide is shown on the top page, and a detailed guide can be accessed by clicking on "How to use". Any comments or questions are very welcomed at: ras at ni.brain.riken.jp Shiro Usui ------------------------------------------- Shiro USUI, Ph.D usui at eiiris.tut.ac.jp EIIRIS, ToyohashiTech.(Toyohashi Univ.Tech) Hibarigaoka, Tempaku, Toyohashi 441-8580 Japan Tel:+81-532-81-5154 Cel:+81-90-7175-0861 http://www.eiiris.tut.ac.jp ------------------------------------------- INCF Japan-node (NIJC) RIKEN BSI Hirosawa, Wako, Saitama 351-0198 Japan usuishiro at riken.jp Tel:+81-48-467-6454 Cel:+81-90-7175-0861 http://www.neuroinf.jp ------------------------------------------- From miguel.nicolau at ucd.ie Wed Oct 30 16:16:20 2013 From: miguel.nicolau at ucd.ie (Miguel Nicolau) Date: Wed, 30 Oct 2013 20:16:20 +0000 Subject: Connectionists: EuroGP 2014: Final CFP (Deadline extension: 11th NOVEMBER 2013) Message-ID: (apologies for cross-posting) ***************************************************************************** EuroGP 2014, 17th European Conference on Genetic Programming 23-25 April 2014, Granada, Spain www.evostar.org FINAL CALL FOR PAPERS ***************************************************************************** (CFP download: www.evostar.org/flyer/EuroGP2014Flyer.pdf) SUBMISSION DEADLINE: 11th November 2013 EuroGP is the premier annual conference on Genetic Programming, attracting participants from all over the world. High quality papers describing new original research are sought on topics strongly related to the evolution of computer programs, ranging from theoretical work to innovative applications. Topics include but are not limited to: * Innovative applications of GP * Theoretical developments * GP performance and behaviour * Fitness landscape analysis of GP * Algorithms, representations and operators * Real-world applications * Evolutionary design * Evolutionary robotics * Tree-based GP and Linear GP * Graph-based GP and Grammar-based GP * Evolvable hardware * Self-reproducing programs * Multi-population GP * Multi-objective GP * Fast/Parallel GP * Probabilistic GP * Evolution of automata or machine * Software Engineering and GP * Object-oriented GP * Hybrid architectures including GP * Coevolution in GP * Modularity in GP * Semantics in GP * Unconventional evolvable computation * Automatic software maintenance * Evolutionary inductive programming In 2013, the EuroGP acceptance rate was 49% (38% for oral presentations). Accepted papers will be included in the proceedings published by Springer Verlag in the Lecture Notes in Computer Science (LNCS) series. The papers which receive the best reviews will be nominated for the Best Paper Award. EuroGP 2014 will take place in Granada, Spain, and will be co-located within the EvoStar event with four related conferences: EvoBIO, EvoCOP, EvoMUSART, and EvoApplications. Submission Details Submissions must be original and not published elsewhere. They will be peer reviewed by at least three members of the program committee. The reviewing process will be double-blind, so please omit information about the authors in the submitted paper. Submit your manuscript in Springer LNCS format. Page limit: 12 pages. The authors of accepted papers will have to improve their paper on the basis of the reviewers? comments and will be asked to send a camera ready version of their manuscripts. At least one author of each accepted work has to register for the conference, attend the conference and present the work. Submission page: myreview.csregistry.org/eurogp14 Website: www.evostar.org/cfpEuroGP.html Facebook: fb.com/evostarconf Twitter: twitter.com/Evostar2014 LinkedIn: www.linkedin.com/groups/EVOstar-1908983 EuroGP programme chairs Miguel Nicolau, University College Dublin, Ireland Krzysztof Krawiec, Poznan University of Technology, Poland From Colin.Wise at uts.edu.au Thu Oct 31 00:55:24 2013 From: Colin.Wise at uts.edu.au (Colin Wise) Date: Thu, 31 Oct 2013 15:55:24 +1100 Subject: Connectionists: REMINDER - AAI Short Course - 'Behaviour Analytics - an Introduction' - Wednesday 6 November 2013 Message-ID: <8112393AA53A9B4A9BDDA6421F26C68A016E459D213F@MAILBOXCLUSTER.adsroot.uts.edu.au> Dear Colleague, REMINDER - AAI Short Course - 'Behaviour Analytics - an Introduction' - Wednesday 6 November 2013 https://shortcourses-bookings.uts.edu.au/Clientview/Schedules/ScheduleDetail.aspx?ScheduleID=1392&EventID=1185 Our AAI short course 'Behaviour Analytics - an Introduction' may be of interest to you and or others in your organisation or network. Complex behaviours are widely seen on the internet, business, social and online networks, and multi-agent systems. In fact, behaviour is a concept with stronger semantic meaning than the so-called data for recording and representing business activities, impacts and dynamics. Therefore, an in-depth understanding of complex behaviours has been increasingly recognised as a crucial means for disclosing interior driving forces, causes and impact on businesses in handling many challenging issues. This forms the need and emergence of behaviour analytics, i.e. understanding behaviours from the computing perspective. In this short course, we present an overview of behaviour analytics and discuss complex behaviour interactions and relationships, complex behaviour representation, behavioural feature construction, behaviour impact and utility analysis, behaviour pattern analysis, exceptional behaviour analysis, negative behaviour analysis, behaviour interaction and evolution. Please register here LINK An important foundation short course in the AAI series of advanced data analytic short courses - please view this short course and others here LINK We are happy to discuss at your convenience. Thank you and regards. Colin Wise Operations Manager Advanced Analytics Institute (AAI) Blackfriars Building 2, Level 1 University of Technology, Sydney (UTS) Email: Colin.Wise at uts.edu.au Tel. +61 2 9514 9267 M. 0448 916 589 AAI: www.analytics.uts.edu.au/ Reminder - AAI Short Course - Advanced Data Analytics - an Introduction - Tuesday 19 November 2013 Future short courses on Data Analytics and Big Data may be viewed at LINK AAI Education and Training Short Courses Survey - you may be interested in completing our AAI Survey at LINK AAI September 2013 Newsletter LINK AAI Email Policy - should you wish to not receive this periodic communication on Data Analytics Learning please reply to our email (to sender) with UNSUBSCRIBE in the Subject. We will delete you from our database. Thank you for your past and future support. UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any accompanying attachments may contain confidential information. If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or attachments. If you have received this message in error, please notify the sender immediately and delete this message. Any views expressed in this message are those of the individual sender, except where the sender expressly, and with authority, states them to be the views of the University of Technology Sydney. Before opening any attachments, please check them for viruses and defects. Think. Green. Do. Please consider the environment before printing this email. -------------- next part -------------- An HTML attachment was scrubbed... URL: From wilson.rosa at gmail.com Thu Oct 31 14:03:08 2013 From: wilson.rosa at gmail.com (Wilson de Oliveira) Date: Thu, 31 Oct 2013 16:03:08 -0200 Subject: Connectionists: Advances on Weightless Neural Systems Message-ID: ESAN 2014 - Special Session on Advances on Weightless Neural Systems: Mimicking biological neurons by focusing on the decoding performed by the dendritic trees is a different and attractive alternative to the integrate-and-fire McCullogh-Pitts neuron stylisation. RAM-based or boolean neurons and weightless systems have been studied and applied in a wide spectrum of situations. The ESANN 2009 Special Session on Weightless Neural Systems played an important role in providing incentive to this area, resulting in the development of interesting applications and theoretical results. In particular, the theoretical aspects, first presented at that session, enabled the application of weightless systems to an ample set of new domains, ranging from natural language processing to game playing, including memory transfer and biomedical applications. This session invites original contributions on theoretical and practical aspects of weightless neural systems, at all levels of abstraction. For more information: https://www.elen.ucl.ac.be/esann/ Wilson de Oliveira UFRPE-DEInfo http://www.cin.ufpe.br/~wrdo If we knew what it was we were doing, it would not be called research, would it?. Einstein -------------- next part -------------- An HTML attachment was scrubbed... URL: