From tpolk at umich.edu Thu Sep 3 15:09:36 2009 From: tpolk at umich.edu (Thad Polk) Date: Thu, 3 Sep 2009 15:09:36 -0400 (EDT) Subject: Connectionists: Post-doc position in reinforcement learning & cognitive architecture Message-ID: As part of a recently funded NSF project, we are looking for a postdoctoral fellow to do research on extending reinforcement learning ideas into an architecture for building long-lived agents. A number of research issues including learning good representations and models, using internal rewards, control of internal as well as external actions, abstraction of actions into skills, and the use of episodic and semantic memories within reinforcement learning are in the scope of the project. A mix of empirical and theoretical work is called for in the project which funds Satinder Singh, John Laird, Richard Lewis and Thad Polk, all at the University of Michigan. The ideal candidate would have done a thesis on a reinforcement learning topic. If you are interested in applying for such a position, please send a CV to baveja at umich.edu (please don't spam the whole mailing list). The position is available immediately. Regards, Thad Polk ---------------------------------------------------- Thad A. Polk, Ph.D. Email: tpolk at umich.edu Associate Professor & Phone: (734) 647-6982 Arthur F. Thurnau Professor Fax: (734) 763-7480 Depts of Psychology & EECS University of Michigan Ann Arbor, MI 48109-1109 http://sitemaker.umich.edu/tpolk_lab ---------------------------------------------------- From dglanzma at mail.nih.gov Thu Sep 3 12:15:03 2009 From: dglanzma at mail.nih.gov (Glanzman, Dennis (NIH/NIMH) [E]) Date: Thu, 3 Sep 2009 12:15:03 -0400 Subject: Connectionists: Final Call For Posters -- Dynamical Neuroscience Satellite Symposium -- Dynamical Disease In-Reply-To: Message-ID: <87A69598824B3D4EBF14080B3F0906BE092D7673@NIHMLBX12.nih.gov> This is the final call for posters for the 17th Annual Dynamical Neuroscience Satellite Symposium - "Dynamical Disease" (Preceding the 39th Annual Meeting of the Society for Neuroscience) Thursday and Friday, October 15-16, 2009 The Buckingham Ballroom of the Allerton Hotel, 701 North Michigan Avenue, Chicago, Illinois The concept of dynamical diseases has been in existence for over 30 years, with numerous re-views drawing attention to disorders that are characterized by the recurrence of certain symptoms, or exhibit oscillations that appear in the intensity of an ongoing nervous system disease. Neuropsychiatric and neurological diseases exhibiting periodicity or cyclicity include Bipolar Disorder, Schizophrenia, Seasonal Affective Disorder, Klein-Levin Syndrome, Sleep Disorders, Binging, Epilepsy, Multiple Sclerosis, Jet-Lag and Headache. The time course of the disorders can range from seconds and minutes to months and years. This symposium will examine a number of dynamical disorders of the nervous system, with the aim of providing an overarching perspective into potential underlying mechanisms, detection, prevention and treatment strategy. Confirmed Speakers: Markus Dahlem, Uri Eden, Bard Ermentrout, Leon Glass, Isabela Granic, Suzanne Haber, Nancy Kopell, Marc Lewis, Alfred Lewy, Haim Sompolinsky, Peter Tass, Jonathan Victor and Miles Whittington Keynote Address: Winner of the 2nd Annual Swartz Prize in Computational Neuroscience Symposium Organizers: Nicholas Schiff, Weill Cornell Medical Center, and Dennis Glanzman, NIMH/NIH Registration: http://neuro.dgimeetingsupport.com/ To Submit a Poster (Deadline September 18, 2009): http://neuro.dgimeetingsupport.com/Call_For_Posters.aspx For programmatic information, please contact: Dennis Glanzman > National Institute of Mental Health Telephone: (301) 443-1576 For logistics information, please contact: Nakia Wilson > The Dixon Group Telephone: (877) 772-9111 -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090903/62057338/attachment-0001.html From wic-office at wi-consortium.org Fri Sep 4 22:06:33 2009 From: wic-office at wi-consortium.org (wic-office@wi-consortium.org) Date: 5 Sep 2009 11:06:33 +0900 Subject: Connectionists: AMT-BI'09 Call for Posters/Participation Message-ID: <20090905020633.3529.qmail@earth.azu.com> [Apologies if you receive this more than once] #################################################################### Active Media Technology 2009 & Brain Informatics 2009 CALL FOR POSTERS and CALL FOR PARTICIPATION #################################################################### 2009 International Conference on Active Media Technology (AMT 2009) 2009 International Conference on Brain Informatics (BI 2009) October 22-24, 2009, Beijing, China Homepage: http://www.wici-lab.org/amtbi09/ Mirror page: http://www.iwici.org/amtbi09/ Co-organized by Web Intelligence Consortium (WIC) and IEEE Task Force on Brain Informatics (IEEE TF-BI) ------------------------------------------------ On-line registration (and more information) at http://www.wici-lab.org/amtbi09/ Posters Due: *** 30 September 2009 *** Special discount (or free) registration is available for students and poster session presenters ************************************************ You are invited to join Active Media Technology 2009 and Brain Informatics 2009. Active Media Technology is a new area of intelligent information technology and computer science that emphasizes the proactive, seamless roles of interfaces and systems as well as new media in all aspects of digital life. An AMT based system offers services to enable the rapid design, implementation and support of customized solutions. Brain Informatics has recently emerged as an interdisciplinary research field that focuses on studying the mechanisms underlying the human information processing system (HIPS). BI lies in the interplay between the studies of human brain and the research of informatics. The two conferences will have a joint opening, keynote, reception, and banquet. Attendees only need to register for one conference and can attend keynotes, sessions, workshop, posters across the two conferences. ============================ ***** Call for Posters ***** ============================ AMT-BI'09 also welcomes Posters submissions. AMT-BI'09 Posters session will provide researchers and practitioners in active media technology and brain informatics an exciting and highly interactive way to explore new ideas and results. All areas of the AMT/BI conference are of interest to the Posters and Demos. The proposal of a poster must include the following information: - Authors (name, affiliation, email, address, phone and fax) - The corresponding author with her/his email address - Title - Keywords - The category of the submission (AMT or BI) The proposals of posters must be submitted online at the conference websites. The deadline for proposals submission is *** 30 September 2009 ***. Special discount (or free) registration is available for students and poster session presenters AMT-BI 2009 Keynote Speakers ============================ Using Neural Imaging to Inform the Instruction of Mathematics Professor John Anderson Department of Psychology, Carnegie Mellon University http://act-r.psy.cmu.edu/people/ja/ Distributed Human-Machine Systems: Progress and Prospects Dr. Jeffrey M. Bradshaw Florida Institute for Human and Machine Cognition (IHMC) http://www.ihmc.us/users/jbradshaw Large Scale Reasoning on the Semantic Web: what to do when success is becoming a problem Professor Frank van Harmelen AI Department, Vrije Universiteit Amsterdam http://www.cs.vu.nl/~frankh How Midazolam Can Help Us Understand Human Memory: 3 Illustrations and a Proposal for a New Methodology Professor Lynne Reder Department of Psychology, Carnegie Mellon University http://memory.psy.cmu.edu/ Research on Brain-like Computer Professor Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology, Chinese Academy of Sciences http://www.intsci.ac.cn/en/shizz/ A Framework for Machine Learning with Ambiguous Objects Professor Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University, China http://cs.nju.edu.cn/zhouzh/ AMT-BI 2009 Special Sessions ============================ In addition to sessions for presenting accepted papers, we have the following special sessions: Special Session on Information Processing Meets Brain Sciences -------------------------------------------------------------- Data Compression and Data Selection in Human Vision Zhaoping Li (University College London, UK) Do Brain Networks Correlate with Intelligence? Tianzi Jiang (Institute of Automation, Chinese Academy of Sciences, China) How Were Intelligence and Language Created in Human Brain Setsuo Ohsuga (University of Tokyo, Japan) Affective Learning with an EEG Approach Bin Hu (Birmingham City University, UK, and Lanzhou Unviersity, China) Some Web Intelligence Oriented Brain Informatics Studies Yulin Qin (Beijing University of Technology, China, and Carnegie Mellon University, USA) Special Session on Conversational Informatics --------------------------------------------- Implementing a Multi-user Tour Guide system with an Embodied Conversational Agent Aleksandra Cerekovic, Hsuan-Huang Huang, Takuya Furukawa, Yuji Yamaoka, Igor Pandzic, Toyoaki Nishida, and Yukiko Nakano Actively Adaptive Agent for Human-Agent Collaborative Task Yong Xu, Yoshimasa Ohmoto, Kazuhiro Ueda, Takanori Komatsu, Takeshi Okadome, Koji Kamei, Shogo Okada, Yasuyuki Sumi, and Toyoaki Nishida Low-Overhead 3D Items Drawing Engine for Communicating Situated Knowledge Loic Merckel and Toyoaki Nishida A Method to Detect Lies in Free Communication using Diverse Nonverbal Information: Towards an Attentive Agent Yoshimasa Ohmoto, Kazuhiro Ueda, and Takehiko Ohno An Integrative Agent Model for Adaptive Human-Aware Presentation of Information During Demanding Tasks Andy van der Mee, Nataliya Mogles, and Jan Treur Special Session on Human-Web Interaction ---------------------------------------- Consumer Decision Making in Knowledge-Based Recommendation Monika Mandl, Alexander Felfernig, and Monika Schubert Incremental Learning of Triadic PLSA for Collaborative Filtering Hu Wu and Yongji Wang Interactive Storyboard: Animated Story Creation on Touch Interfaces Kun Yu, Hao Wang, Chang Liu, and Jianwei Niu Comparative Evaluation of Reliabilities on Semantic Search Functions: Auto-complete and Entity-centric Unified Search Hanmin Jung, Mi-Kyoung Lee, Beom-Jong You, and Do-Wan Kim Integrated Recommender Systems Based on Ontology and Usage Mining Liang Wei AMT-BI 2009 Workshop ==================== WICI Workshop/Posters on Web Intelligence Meets Brain Informatics Conference Site =============== The conference will take place at the Grand Gongda Jianguo Hotel (Beijing Gongda Jianguo Fandian - 4-stars hotel) is located inside Beijing University of Technology within close proximity of the central business district and only a five-minute walk from the 2008 Beijing Olympic badminton and eurythmics venue. We will give a special discount price for BI-AMT'09 attendees. (400 RMB/1 single room, 450 RMB/1 double room (2 persons use), including Tax, Breakfast, etc.) The hotel reservation information is available at the AMT-BI'09 homepages. ----------------- Co-sponsored by Beijing University of Technology (BJUT) Chinese Society of Radiology National Natural Science Foundation of China (NSFC) State Administration of Foreign Experts Affairs, PRC Shanghai Psytech Electronic Technology Co. Ltd Shenzhen Hanix United, Inc. Beijing Branch Beijing JinShangQi Net System Integration Co. Ltd Springer Lecture Notes in Computer Science (LNCS/LNAI) *** Contact Information *** Email: Jia Hu hujia0601 at gmail.com Jiajin Huang hjj at emails.bjut.edu.cn From hamid at isys.uni-klu.ac.at Fri Sep 4 11:41:56 2009 From: hamid at isys.uni-klu.ac.at (Hamid Bouchachia) Date: Fri, 04 Sep 2009 17:41:56 +0200 Subject: Connectionists: Special Issue on Incremental Learning: Call for Contribution Message-ID: <4AA13544.2040203@isys.uni-klu.ac.at> =============================== C A L L F O R C O N T R I B U T I O N =============================== ------------------------------------------------------- Special Issue of the Neurocomputing Journal (Elsevier) on Adaptive Incremental Learning in Neural Networks ------------------------------------------------------- Guest Editors Hamid Bouchachia, University of Klagenfurt, Austria (hamid at isys.uni-klu.ac.at) Nadia Nedjah, State University of Rio de Janeiro, Brazil (nadia at eng.uerj.br) -------- Scope -------- Adaptation plays a central role in dynamically changing systems. It is about the ability of the system to ?responsively? self-adjust upon change in the surrounding environment. Like in living creatures that have evolved over millions of years developing ecological systems due to their self-adaptation and fitness capacity to the dynamic environment, systems undergo similar cycle to improve or at least do not weaken their performance when internal or external changes take place. Internal change bears on the physical structure of the system (the building blocks: hardware and/or software components). External change originates from the environment due to the reciprocal action and interaction. These two classes of change shed light on the research avenues towards smart adaptive systems. The state of the art draws the picture of challenges that such systems need to face before they come reality. A sustainable effort is necessary to develop intelligent hardware on one level and concepts and algorithms on the other level. The former level concerns various analog and digital accommodations encompassing self-healing, self-testing, reconfiguration and many other aspects of system development and maintenance. The latter level is concerned with developing algorithms, concepts and techniques which can rely on metaphors of nature and which are inspired from biological and cognitive plausibility. To face the different types of change, systems must self-adapt their structure and self-adjust their controlling parameters over time as changes are sensed. A fundamental issue is the notion of ?self? which refers to the capability of the systems to act and react on their own. It covers all stages of the system?s working and maintenance cycle starting from online self-monitoring to self-growing and self-organizing. Relying on the two-fold plausibility which is the basis for many computational models, neural networks can be encountered in various real-world dynamical and non-stationary systems that require continuous update over time. There exit many neural models that are theoretically based on incremental (i.e., online, sequential) learning addressing in particular the notions of self-growing and self-organizing. However, their strength in practical situations that involve online adaptation is not as efficient as desirable. The present special issue aims at presenting the latest advances of neural adaptive models and their application in various dynamic environments. The special issue is intended for a wide audience including neural network scientists as well as mathematicians, physicists, engineers, computer scientists, biologists, economists and social scientists. The special issue will cover various topics of neural networks related to the self-organization, self-monitoring and self-growing concepts. It also aims at presenting a coherent view of these issues and a thorough discussion about the future research avenues. A sample of the targeted topics, which is suggestive rather than exhaustive, includes: Theories and Algorithms - Self growing neural networks - Online adaptive and life-long learning - Constructive learning - Plasticity and stability in neural networks - Forgetting and Unlearning in neural networks - Incremental adaptive neuro-fuzzy systems - Incremental and single-pass data mining - Incremental neural classification systems - Incremental neural clustering - Incremental neural regression - Adaptation in changing environments - Concept drift in incremental learning systems - Self-monitoring in incremental learning systems - Incremental diagnostics - Novelty detection in incremental learning - Time series prediction with neural networks - Incremental feature selection and reduction - Adaptive decision systems - Methodologies of self-organization - Neural algorithms for self-organization - Perception and evolution in learning systems Applications : Adaptivity and learning in - Smart systems - Ambient / ubiquitous environments - Distributed intelligence - Intelligent agent technology - Robotics - Game theory - Industrial applications - Internet applications - E-commerce, etc ----------- Schedule ----------- Submission due date: December 15th , 2009 First acceptance notification: February 20th , 2010 Revised manuscripts due: April 15th , 2010 Final acceptance notification: June 15th , 2010 Final version due: July 15th , 2010 Intended publication date: 3rd/4th quarter, 2010 ----------- Submission ----------- Manuscripts should be submitted to the Special Issue of Neurocomputing on Adaptive Incremental Learning in Neural Networks following the formatting guidelines of the journal at: http://www.elsevier.com/wps/find/journaldescription.cws_home/505628/authorinstructions. The manuscripts must be submitted through the online submission system of the journal http://ees.elsevier.com/neucom/. Please choose article type "SI: Incremental Learning" when submitting your manuscript. From esann at uclouvain.be Sun Sep 6 12:43:04 2009 From: esann at uclouvain.be (esann) Date: Sun, 6 Sep 2009 18:43:04 +0200 Subject: Connectionists: ESANN'2010 call for papers Message-ID: <003601ca2f11$1aebc910$50c35b30$@be> ESANN 2010 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges (Belgium) - April 28-29-30, 2010 Announcement and call for papers =================================================== The call for papers for the ESANN'2010 conference is now available at the following URL: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We make all possible efforts to avoid sending multiple copies of this call for papers; however we apologize if you receive this e-mail twice, despite our precautions. ***** Deadline for submission of papers: November 25, 2009 ***** You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2010 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). The conference is technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society, the IEEE Region 8, the IEEE Benelux Section (sponsors to be confirmed). Scope and topics ---------------- Since its first happening in 1993, ESANN has become a reference for researchers on fundamentals and theoretical aspects of artificial neural networks, computational intelligence, machine learning and related topics. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2010 conference will follow this tradition, while adapting its scope to the new developments in the field. The ESANN conferences cover artificial neural networks, machine learning, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered. The following is a non-exhaustive list of machine learning, computational intelligence and artificial neural networks topics covered during the ESANN conferences: THEORY and MODELS Statistical and mathematical aspects of learning Feedforward models Kernel machines Graphical models, EM and Bayesian learning 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 INFORMATION PROCESSING and APPLICATIONS Data mining Signal processing and modeling Approximation and identification Classification and clustering Feature extraction and dimension reduction Time series forecasting Multimodal interfaces and multichannel processing Adaptive control Vision and sensory systems Biometry Bioinformatics Brain-computer interfaces Neuroinformatics Papers will be presented orally (single track) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. It is important to mention that the topics of a paper decide if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors must indicate their preference for oral or poster presentation when submitting their paper. Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organized in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all levels of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Proceedings and journal special issue ------------------------------------- The proceedings will include all communications presented to the conference (tutorials, oral and posters), and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). Call for contributions ---------------------- Prospective authors are invited to submit their contributions before November 25, 2009. The electronic submission procedure is described on the ESANN portal http://www.dice.ucl.ac.be/esann/. Authors must also commit themselves that they will register to the conference and present the paper in case of acceptation of their submission (one paper per registrant). Authors of accepted papers will have to register before February 28, 2010; they will benefit from the advance registration fee. The ESANN conference applies a strict policy about the presentation of accepted papers during the conference: authors of accepted papers who do not show up at the conference will be blacklisted for future ESANN conferences, and the lists will be communicated to other conference organizers. Deadlines --------- Submission of papers 25 November 2009 Notification of acceptance 18 January 2010 ESANN conference 28-30 April 2010 Conference secretariat ---------------------- ESANN'2010 d-side conference services phone: + 32 2 730 06 11 24 av. L. Mommaerts Fax: + 32 2 730 06 00 B - 1140 Evere (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee (to be confirmed) ---------------------------- Fran?ois Blayo Ipseite (CH) Gianluca Bontempi Univ. Libre Bruxelles (B) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Mia Loccufier Univ. Gent (B) Bernard Manderick Vrije Univ. Brussel (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Louis Wehenkel Univ. Li?ge (B) Scientific committee (to be confirmed) -------------------- Fabio Aiolli Univ. degli Studi di Padov (I) Cecilio Angulo Univ. Polit. de Catalunya (E) Miguel Atencia Univ. Malaga (E) Michael Biehl University of Groningen (NL) Martin Bogdan Univ. T?bingen (D) Luc Boullart Ghent University (B) Herv? Bourlard IDIAP Martigny (CH) Antonio Braga Federal University of Minas Gerais (Brazil) Joan Cabestany Univ. Polit. de Catalunya (E) Colin Campbell Bristol University (UK) St?phane Canu Inst. Nat. Sciences App. (F) Valentina Colla Scuola Sup. Sant'Anna Pisa (I) Nigel Crook Oxford University (UK) Holk Cruse Universit?t Bielefeld (D) Tijl De Bie University of Bristol (UK) Massimo De Gregorio Istituto di Cibernetica-CNR (I) Dante Del Corso Politecnico di Torino (I) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton NXP Semiconductors (USA) Richard Duro Univ. Coruna (E) Andr? Elisseef IBM Research (CH) Deniz Erdogmus Oregon Health & Science University (USA) Anibal Figueiras-Vidal Univ. Carlos III Madrid (E) Jean-Claude Fort Universit? Paul Sabatier Toulouse (F) Felipe M. G. Fran?a Universidade Federal do Rio de Janeiro (Brazil) Leonardo Franco Univ. Malaga (E) Damien Fran?ois Universit? catholique de Louvain (B) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Gu?rin-Dugu? IMAG Grenoble (F) Barbara Hammer Clausthal Univ. of Technology (D) Martin Hasler EPFL Lausanne (CH) Verena Heidrich-Meisner Ruhr-Univ. Bochum (D) Tom Heskes Univ. Nijmegen (NL) Katerina Hlavackova-Schindler Austrian Acad. of Sciences (A) Christian Igel Ruhr-Univ. Bochum (D) Jose Jerez Univ. Malaga (E) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinki Univ. of Technology (FIN) Samuel Kaski Helsinki Univ. Tech. (FIN) Stefanos Kollias National Tech. Univ. Athens (GR) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Priscila M. V. Lima Universidade Federal do Rio de Janeiro (Brazil) Paulo Lisboa Liverpool John Moores University (UK) Erzsebet Merenyi Rice Univ. (USA) David Meunier University of Cambridge (UK) Anke Meyer-B?se Florida State university (USA) Jean-Pierre Nadal Ecole Normale Sup?rieure Paris (F) Erkki Oja Helsinki Univ. of Technology (FIN) Tjeerd olde Scheper Oxford Brookes University (UK) Georges Otte Dr. Guislain Institute (B) Gilles Pag?s Univ. Paris 6 (F) Thomas Parisini Univ. Trieste (I) H?l?ne Paugam-Moisy Universit? Lumi?re Lyon 2 (F) Kristiaan Pelckmans K. U. Leuven (B) Alberto Prieto Universitad de Granada (E) Didier Puzenat Univ. Antilles-Guyane (F) Leonardo Reyneri Politecnico di Torino (I) Jean-Pierre Rospars INRA Versailles (F) Fabrice Rossi Telecom ParisTech (F) David Saad Aston Univ. (UK) Francisco Sandoval Univ.Malaga (E) Jose Santos Reyes Univ. Coruna (E) Craig Saunders Univ.Southampton (UK) Frank-Michael Schleif Univ. Leipzig (Germany) Benjamin Schrauwen Univ. Gent (B) Udo Seiffert Fraunhofer-Institute IFF Magdeburg (D) Bernard Sendhoff Honda Research Institute Europe (D) Alessandro Sperduti Universit? degli Studi di Padova (I) Jochen Steil Univ. Bielefeld (D) John Stonham Brunel University (UK) Johan Suykens K. U. Leuven (B) John Taylor King?s College London (UK) Peter Tino University of Birmingham (UK) Claude Touzet Univ. Provence (F) Thiago Turchetti Maia Fed.Univ.Minas Gerais (Brazil) Marc Van Hulle KUL Leuven (B) Alfredo Vellido Polytechnic University of Catalonia (E) Pablo Verdes Novartis Phrama (CH) David Verstraeten Univ. Gent (B) Thomas Villmann Univ. Apllied Sciences Mittweida (D) Heiko Wersing Honda Research Institute Europe (D) Axel Wism?ller University of Rochester, New York (USA) Bart Wyns Ghent University (B) Michalis Zervakis Technical Univ. Crete (GR) ======================================================== ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews, registrations: Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at uclouvain.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at uclouvain.be ======================================================== From juergen at idsia.ch Mon Sep 7 05:09:57 2009 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Mon, 7 Sep 2009 11:09:57 +0200 Subject: Connectionists: Review: Reservoir computing & recurrent neural networks / unsupervised RNN / IDSIA PhD fellowships In-Reply-To: References: <4A96A16F.5060607@jacobs-university.de> Message-ID: Thanks for this survey! Please allow me to point to a few selected earlier papers (below) on unsupervised training procedures for recurrent neural networks (RNN) - in this new terminology you might call them reservoirs. We like to think these were pretty much the first unsupervised RNN. Please tell us if you know of earlier ones, also for the upcoming RNN book http://www.idsia.ch/~juergen/rnnbook.html Note also the connection to the hot topic of unsupervised deep nets with many layers - RNN are deep by nature. IDSIA is still offering a few PhD fellowships along these lines: http://www.idsia.ch/~juergen/sinergia2008.html http://www.idsia.ch/~juergen/eu2009.html Cheers, Juergen http://www.idsia.ch/~juergen/whatsnew.html 4. M. Klapper-Rybicka, N. N. Schraudolph, J. Schmidhuber. Unsupervised Learning in LSTM Recurrent Neural Networks. In G. Dorffner, H. Bischof, K. Hornik, eds., Proc. ICANN'01, Vienna, LNCS 2130, pages 684-691, Springer, 2001. 3. S. Hochreiter and J. Schmidhuber. Flat Minima. Neural Computation, 9(1):1-42, 1997. (Uses the FMS algorithm to find simple, low-complexity RNN among the many RNN that can solve a given task - another type of unsupervised learning, although some would file this under "regularizers for RNN".) 2. J. Schmidhuber. Learning unambiguous reduced sequence descriptions. In J. E. Moody, S. J. Hanson, and R. P. Lippman, editors, NIPS'4, p 291-298. San Mateo, CA: Morgan Kaufmann, 1992. (Unsupervised compact sequence encoding to facilitate subsequent supervised learning.) 1. J. Schmidhuber. Learning complex, extended sequences using the principle of history compression. Neural Computation, 4(2):234-242, 1992. (Uses self-prediction to compactly encode sequences in unsupervised fashion. This facilitates subsequent supervised learning.) On Aug 27, 2009, at 5:08 PM, Mantas Lukosevicius wrote: > A comprehensive survey article "Reservoir computing approaches to > recurrent neural network training" has been published in Computer > Science Review by M. Lukosevicius and H. Jaeger. > Preprint: > http://www.faculty.jacobs-university.de/hjaeger/pubs/2261_LukoseviciusJaeger09.pdf > Article: > http://dx.doi.org/10.1016/j.cosrev.2009.03.005 -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090907/7d48c60d/attachment.html From P.J.Lisboa at ljmu.ac.uk Mon Sep 7 13:04:32 2009 From: P.J.Lisboa at ljmu.ac.uk (Lisboa, Paulo) Date: Mon, 7 Sep 2009 18:04:32 +0100 Subject: Connectionists: Special Session at ESANN 20108: Computational Intelligence in Biomedicine Message-ID: <0F6C80385A691C4BB21E749DDC9A1E92011E1205@exch5.jmu.ac.uk> *** 1st CFP (with apologies for cross-posting)*** SPECIAL SESSION: Computational Intelligence in Biomedicine ************** As part of ESANN 2010 ************** The 18th European Symposium on Artificial Neural Networks, 28-30 April 2010, Bruges, Belgium Organizers: Paulo J.G. Lisboa (Liverpool John Moores University, U.K.), Alfredo Vellido (Tech. Univ. Catalunya, Spain), Jos? D. Mart?n (University of Valencia, Spain) THE SESSION IN BRIEF: Computational Intelligence techniques (including, broadly, neural networks, connectionist systems, genetic algorithms, evolutionary programming, fuzzy systems, and hybrid intelligent systems, according to the scope provided by the IEEE-CIS) have made significant inroads over the last two decades in the area of biomedical applications. This is both as beacons of evidence-based medicine and as robust building blocks of medical decision support systems. Systems based on Computational Intelligence techniques should have an important role in defining the methodologies for the next generation of healthcare delivery technologies. This is expected to follow the 4P (personalized, predictive, preventive and participatory) agenda, which demands greater personalization to the needs of the individual patient, a focus on preventive medicine with the support of predictive approaches, as well as greater emphasis on pro-active involvement by the patient at the point of healthcare delivery. This special session aims to be of interest to CI practioners (with a strong focus on Machine Learning) working in the area of biomedicine, but also to those biomedicine researchers that have made CI techniques their tools of choice. The sinergy between both worlds should guarantee that leading-edge techniques become known to medical practitioners and that CI research in biomedicine complies with the real-world requirements of the field. The main topics of interest, any of them based on Computational Intelligence, Machine Learning and otherwise AI-related techniques, include (but are indeed not necessarily limited to): * Methodologies with a focus on model interpretation (including, for instance, visualization, feature selection and extraction, graphs, and rules). * Structured methodologies for multi-modal data (data fusion combining different modalities, e.g.: molecular biomarkers, histology, imaging, electrophysiological measurements and clinical signs). * Methodologies for the analysis of functional and spectral signal and imaging data. * Survival analysis. * Methodologies for computer-based medical decision support and treatment planning. * Current and planned clinical applications. * Methodologies of mining and knowledge discovery applied to medical data. * Pharmaceutical research. All contributions are meant to strike a reasonable balance between theoretical novelty and the originality and appropriateness of the biomedical application. Further information on the web (forthcoming): http://www.dice.ucl.ac.be/esann/index.php?pg=specsess ***** IMPORTANT DATES ***** Submission deadline: 25th of November, 2009. Notification to authors: 18th of January, 2010. Camera-ready papers due: 22nd of February, 2010. CONTACTS: ========= Alfredo Vellido, PhD Department of Computing Languages and Systems. Technical University of Catalonia Barcelona, Spain Tel.: +34 93 4137796. Fax: +34 93 4137833 email: avellido at lsi.upc.edu Paulo J.G. Lisboa, PhD School of Computing and Mathematical Sciences. Liverpool John Moores University Liverpool, United Kingdom Tel.: +44 151 2312225. Fax: +44 151 2074594 email: P.J.Lisboa at ljmu.ac.uk Jos? D. Mart?n, PhD Department of Electronic Engineering. University of Valencia. Valencia, Spain Tel.: +34 96 3544022. Fax: +34 96 3544353 email: jose.d.martin at uv.es From vcu at cs.stir.ac.uk Tue Sep 8 08:24:54 2009 From: vcu at cs.stir.ac.uk (Cutsuridis, Vassilis) Date: Tue, 8 Sep 2009 15:24:54 +0300 Subject: Connectionists: 2 papers on hippocampus, microcircuits and associative memory Message-ID: <1B115D7453BE48A6973CBBDEFEC5304A@Zeus> Cutsuridis V, Cobb S, Graham BP. (2009). Encoding and retrieval in a model of the hippocampal CA1 microcircuit. Hippocampus, in press The article can be found in http://www.cs.stir.ac.uk/~vcu/papers/CutCobGra2009Hippo.pdf Its NEURON source code can be found in http://senselab.med.yale.edu/modeldb/ShowModel.asp?model=123815 ABSTRACT It has been proposed that the hippocampal theta rhythm (4-7 Hz) can contribute to memory formation by separating encoding (storage) and retrieval of memories into different functional half-cycles (Hasselmo et al. (2002) Neural Comput 14:793-817). We investigate, via computer simulations, the biophysical mechanisms by which storage and recall of spatio-temporal input patterns are achieved by the CA1 microcircuitry. A model of the CA1 microcircuit is presented that uses biophysical representations of the major cell types, including pyramidal (P) cells and four types of inhibitory interneurons: basket (B) cells, axo-axonic (AA) cells, bistratified (BS) cells and oriens lacunosum-moleculare (OLM) cells. Inputs to the network come from the entorhinal cortex (EC), the CA3 Schaffer collaterals and medial septum. The EC input provides the sensory information, whereas all other inputs provide context and timing information. Septal input provides timing information for phasing storage and recall. Storage is accomplished via a local STDP mediated hetero-association of the EC input pattern and the incoming CA3 input pattern on the CA1 pyramidal cell target synapses. The model simulates the timing of firing of different hippocampal cell types relative to the theta rhythm in anesthetized animals and proposes experimentally confirmed functional roles for the different classes of inhibitory interneurons in the storage and recall cycles (Klausberger et al., (2003, 2004) Nature 421:844-848, Nat Neurosci 7:41-47). Measures of recall performance of new and previously stored input patterns in the presence or absence of various inhibitory interneurons are employed to quantitatively test the performance of our model. Finally, the mean recall quality of the CA1 microcircuit is tested as the number of stored patterns is increased. KEYWORDS: CA1 microcircuit model; storage and recall; pyramidal cell; basket cell; bistratified cell; OLM cell; axo-axonic cell; STDP --------------------------------------------- Cutsuridis V, Wennekers T. (2009). Hippocampus, microcircuits, and associative memory. Neural Networks, in press The article can be found in http://www.cs.stir.ac.uk/~vcu/papers/CutWenNN2009.pdf ABSTRACT The hippocampus is one of the most widely studied brain region. One of its functional roles is the storage and recall of declarative memories. Recent hippocampus research has yielded a wealth of data on network architecture, cell types, the anatomy and membrane properties of pyramidal cells and interneurons, and synaptic plasticity. Understanding the functional roles of different families of hippocampal neurons in information processing, synaptic plasticity and network oscillations poses a great challenge but also promises deep insight into one of the major brain systems. Computational and mathematical models play an instrumental role in exploring such functions. In this paper, we provide an overview of abstract and biophysical models of associative memory with particular emphasis on the operations performed by the diverse (inter)neurons in encoding and retrieval of memories in the hippocampus. KEYWORDS: Hippocampus; Microcircuit; Associative memory; Hebb; STDP; Interneurons; Rhythms -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090908/61ef2c8a/attachment-0001.html From fhamker at uni-muenster.de Tue Sep 8 05:29:25 2009 From: fhamker at uni-muenster.de (Fred Hamker) Date: Tue, 8 Sep 2009 11:29:25 +0200 Subject: Connectionists: Post-Doc or PhD Position for Cognitive Computational Neuroscience Message-ID: <0AB24647-C3D2-4A65-AE60-942067AA77C3@uni-muenster.de> Post-Doc or PhD Position for Cognitive Computational Neuroscience A Post-Doc or PhD position is available at the Technical University of Chemnitz in the Department of Computer Science. The position is for three years, starting immediately. The research position is part of the research network ?Neuro-cognitive mechanisms of conscious and unconscious visual perception? (http://www.uniulm.de/unbewusst/index.htm ). The goal in our project is to elucidate the role of reentrant processing for visual masking and stimulus encoding. Subliminal perception is typically investigated using masked stimuli. Previous priming experiments of the partners in the network have demonstrated various effects of subliminal perception that altogether suggest unconscious stimulus processing to a significant degree, even when stimuli are masked. In previous computational work we have established a framework of attentive visual perception by means of reentrant processing (Hamker, 2005; Hamker, 2007), which has been used as a theoretical basis for the design of experimental studies of the partner groups in the network. We intend to extend this framework to include mechanisms of visual masking with a particular focus on reentrant processing based on previous work of learning receptive fields (Wiltschut & Hamker, 2009). This computational work complements the experimental studies of the Haynes, Ansorge and Mattler groups and also relates to the work of other partner projects. We will provide a description of the neural stimulus trace of masked stimuli that will be important for the interpretation of the experimental results obtained in other groups of the network. See http://www.tu-chemnitz.de/informatik/KI/veroe.php for references. The canditate should have prior experience in developing neurocomputational systems, particularly with respect to data in the neurosciences and psychology. Experience in interdisciplinary projects or own experimental studies is welcome. Good programming experience is essential. The salary is according to German standards (E 13 TV-L). The university is an equal opportunity employer. Women are encouraged to apply. Disabled applicants will receive priority in case they have equal qualifications. Chemnitz is the third-largest city of the state of Saxony and close to scenic mountains. Major cities nearby are Leipzig and Dresden with a rich tradition of music and culture. Applications should be sent by email (preferebly in PDF format) to (fred.hamker at informatik.tu-chemnitz.de ) as soon as possible. Applications will be considered until the position is filled. -------------------- Prof. Dr. Fred H Hamker Artificial Intelligence Department of Computer Science Technical University Chemnitz Strasse der Nationen 62 D - 09107 Chemnitz Germany Tel: +49 (0)371 531-37875 Fax: +49 (0)371 531-25739 email: fred.hamker at informatik.tu-chemnitz.de www: http://www.tu-chemnitz.de/informatik/KI/ From terry at salk.edu Tue Sep 8 20:09:10 2009 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 08 Sep 2009 17:09:10 -0700 Subject: Connectionists: NEURAL COMPUTATION - October, 2009 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 21, Number 10 - October 1, 2009 ARTICLES Experience-Induced Neural Circuits That Achieve High Capacity Vitaly Feldman and Leslie G. Valiant Operant Matching as a Nash Equilibrium of an Intertemporal Game Yonatan Loewenstein, Drazen Prelec, and H. Sebastian Seung LETTERS Stimulus-Dependent Correlations and Population Codes Kresimir Josic, Eric Shea-Brown, Brent Doiron, and Jaime de la Rocha Receptive Field Self-Organization in a Model of the Fine Structure in V1 Cortical Columns Jorg Lucke A Dynamic Causal Model of the Coupling between Pulse Stimulation and Neural Activity Veronique Lefebvre, Ying Zheng, Christopher Martin, Ian Devonshire, Samuel Harris, and John Mayhew A Neurocomputational Model for Cocaine Addiction Amir Dezfouli, Payam Piray, Mohammad Mahdi Keramati, Hamed Ekhtiari, Caro Lucas, and Azarakhsh Mokri Sequential Monte Carlo Point-Process Estimation of Kinematics from Neural Spiking Activity for Brai-Machine Interfaces Yiwen Wang, Antonio R. C. Paiva, Jose C. Principe, and Justin C. Sanchez Correlation between Eigenvalue Spectra and Dynamics of Neural Networks Qingguo Zhou, Tao Jin, and Hong Zhao Distance Learning in Discriminative Vector Quantization Petra Schneider, Michael Biehl, and Barbara Hammer An Integral Upper Bound for Neural-Network Approximation Paul C. Kainen and Vera Kurkova ----- ON-LINE - http://www.mitpressjournals.org/loi/neco SUBSCRIPTIONS - 2009 - VOLUME 21 - 12 ISSUES USA/Canada Others Electronic only Student/Retired $60 $123 $54 Individual $110 $173 $99 Institution $849 $912 $756 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 http://mitpressjournals.org/neuralcomp ----- From moritzgw at tuebingen.mpg.de Wed Sep 9 13:06:53 2009 From: moritzgw at tuebingen.mpg.de (Moritz Grosse-Wentrup) Date: Wed, 09 Sep 2009 19:06:53 +0200 Subject: Connectionists: Call for Contributions: NIPS 2009 Workshop on Connectivity Inference in Neuroimaging Message-ID: <4AA7E0AD.2040200@tuebingen.mpg.de> ---------------------- CALL FOR CONTRIBUTIONS ---------------------- *NIPS 2009 WORKSHOP ON CONNECTIVITY INFERENCE IN NEUROIMAGING* *Webpage* http://cini2009.kyb.tuebingen.mpg.de *Workshop description* Over the past decade, brain connectivity has become a central theme in the neuroimaging community. At the same time, causal inference has recently emerged as a major research topic in machine learning. Even though the two research questions are closely related, interactions between the neuroimaging and machine-learning communities have been limited. The aim of this workshop is to initiate productive interactions between neuroimaging and machine learning by introducing the workshop audience to the different concepts of connectivity/causal inference employed in each of the communities. Special emphasis is placed on discussing commonalities as well as distinctions between various approaches in the context of neuroimaging. Due to the increasing relevance of brain connectivity for analyzing mental states, we also highly welcome contributions discussing applications of brain connectivity measures to real-world problems such as brain-computer interfacing or mental state monitoring. *Topics* We solicit contributions on new approaches to connectivity and/or causal inference for neuroimaging data as well as on applications of connectivity inference to real-world problems. Contributions might address, but are not limited to, the following topics: * Effective connectivity & causal inference o Dynamic causal modelling o Granger causality o Structural equation models o Causal Bayesian networks o Non-Gaussian linear causal models o Causal additive noise models * Functional connectivity o Canonical correlation analysis o Phase-locking o Imaginary coherence o Independent component analysis * Applications of brain connectivity to real-world problems o Brain-computer interfaces o Mental state monitoring *Invited speakers* * Jean Daunizeau, University of Zurich & University College London * Rainer Goebel, Maastricht University * Scott Makeig, University of California San Diego *Workshop format* CINI 2009 is a one-day workshop at the Twenty-Third Annual Conference on Neural Information Processing Systems (NIPS 2009). Besides three invited talks, in which the audience will be introduced to current approaches for inferring connectivity in neuroimaging data, there will be several contributed talks and an evening poster session. Special emphasis will be placed on a balanced contribution of talks from the neuroimaging and machine learning communities. To foster interaction between communities, approximately 50% of workshop time is reserved for discussions. *Key dates* * Extended abstract submission deadline: October 9th, 2009, 5 pm (PT) * Notification of acceptance: October 23rd, 2009 * Workshop: December 11th or 12th, 2009 *Submission instructions* Please submit extended abstracts (maximum two pages) in either pdf or doc format through the CINI 2009 submission site at https://cmt.research.microsoft.com/CINI2009/. Upon notification of acceptance, authors will also be notified whether their contribution has been accepted as a contributed talk or poster. *Workshop location* Westin Resort and Spa / Hilton Whistler Resort and Spa Whistler, B.C., Canada *Organization committee* * Moritz Grosse-Wentrup (primary contact), MPI for Biological Cybernetics, Tuebingen * Uta Noppeney, MPI for Biological Cybernetics, Tuebingen * Karl Friston, University College London * Bernhard Schoelkopf, MPI for Biological Cybernetics, Tuebingen *Program committee* * Olivier David, Institut National de la Sante et de la Recherche Medicale, Grenoble * Justin Dauwels, Massachusetts Institute of Technology, Cambridge * Michael Eichler, Maastricht University * Jeremy Hill, Max Planck Institute for Biological Cybernetics, Tuebingen * Guido Nolte, Fraunhofer FIRST, Berlin * Will Penny, University College London * Alard Roebroeck, Maastricht University * Klaas Enno Stephan, University of Zurich * Ryota Tomioka, University of Tokyo * Pedro Valdes-Sosa, Cuban Neuroscience Center, Havana From announce at ccnconference.org Fri Sep 11 16:02:55 2009 From: announce at ccnconference.org (ccnc-announce) Date: Fri, 11 Sep 2009 14:02:55 -0600 Subject: Connectionists: CCNC 2009: Call for Fellowship Applicants Message-ID: <200909111402.55633.announce@ccnconference.org> ~ CCNC 2009 --- CALL FOR FELLOWSHIP APPLICANTS ~ The CCNC organizing committee is pleased to announce the availability of a limited number of $500 fellowship awards to early-career computational cognitive neuroscience researchers and potential researchers. Eligible candidates should be undergraduates, graduate students, or post-docs. It is anticipated that approximately ten (10) stipends will be awarded. Criteria to be used in selection will include (in approximate order of weighting): * Financial need: e.g., student status, specific hardship, etc. * Membership in a group underrepresented in science: e.g., African-American, Hispanic, Native American ancestry; female gender * Distance to be traveled: Transoceanic vs. North America * Participating author: e.g., are you a sole presenter, first author, auxiliary author on a poster? Interested applicants should send an email to the conference administrator no later than midnight Friday September 25, 2009: Thomas E. Hazy, MD thazy at colorado.edu Your email should include your career status and address all of the selection criteria listed above. Please also include the name and contact info of a faculty reference who is familiar with your career status, academic work and/or research interests and can corroborate your application if asked. An overview of CCNC 2009 is provided below. ---------------------------------------------------------------------------- 4th CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE www.ccnconference.org To be held in conjunction with the 2009 Annual Meeting of the Psychonomic Society at the Sheraton Boston Hotel in Boston, MA. CCN CONFERENCE DATES: Wed-Thu November 18 & 19, 2009 All three of our previous meetings have been a great success, two as satellites to Society for Neuroscience Annual Meeting (2005, 2007) and in 2006 with Psychonomics. Attendance has ranged from 115-250. ____________________________________________________________________________ * DEADLINE FOR SUBMISSION OF ABSTRACTS: CLOSED A limited number of late posters may be accepted on a space available basis. Abstracts can be submitted online via the website: www.ccnconference.org. * Online registration is available at the conference website: www.ccnconference.org. As in past years, there are two categories of submissions: -Poster only -Poster, plus short talk (15 min) to highlight the poster Abstracts should be limited to 250 words. Women and underrepresented minorities are especially encouraged to apply. Reviewing of posters will be inclusive and only to ensure appropriateness to the meeting. Short talks will be selected on the basis of research quality, relevance to conference theme, and expected accessibility in a talk format. Abstracts not selected for short talks will still be accepted as posters as long as they meet appropriateness criteria. * NOTIFICATION OF POSTER ACCEPTANCE: September 7, 2009 * CONTRIBUTED SHORT TALK SELECTION: September 7, 2009 __________________________________________________________________________ Program: * 2009 Keynote Speakers: Neil Burgess, University College London Josh Tenenbaum, MIT * Three symposia, each including a mixture of modelers and non-modelers and focused on a common theme or issue: ** Top-Down Mechanisms of Visual Attention Moderator: Steven Bressler, Florida Atlantic University ** Our Vision for the Word: Modeling Orthographic Processing Moderators: Carol Whitney, University of Maryland, College Park Jonathan Grainger, CNRS, France ** Context, Memory, and the Brain Moderators: Michael Hasselmo, Boston University Ken Norman, Princeton University * Approximately 12 short talks will be chosen featuring selected posters. * Poster sessions * We plan to award a limited number of competitive travel fellowships for students -- look for a notice by late summer. We especially encourage applications from members of underrepresented minorities. * Registration fees: $175 ($75 for students). ____________________________________________________________________________ 2009 Planning Committee: Suzanna Becker, McMaster University Carlos Brody, Princeton University Nathaniel Daw, New York University Michael Hasselmo, Boston University David Noelle, University of California, Merced Ken Norman, Princeton University Maximilian Riesenhuber, Georgetown University Ex officio: Randall O'Reilly, University of Colorado, Boulder Jonathan Cohen, Princeton University Executive Organizer: Thomas Hazy, University of Colorado, Boulder For more information and to sign up for the mailing list visit: www.ccnconference.org From marcus.hutter at gmx.net Sat Sep 12 06:35:13 2009 From: marcus.hutter at gmx.net (Marcus Hutter) Date: Sat, 12 Sep 2009 20:35:13 +1000 Subject: Connectionists: AGI-10 CFP Message-ID: <042e01ca3394$bc0ebfa0$3cd6cb96@crl174ml1s> Hi, We're pleased to announce the Third Conference on Artificial General Intelligence, hosted by Juergen Schmidhuber in Lugano, Switzerland, March 5-8 2010. Continuing the mission of the highly successful First and Second AGI Conferences, AGI-10 will gather an international group of leading academic and industry researchers involved in serious scientific and engineering work aimed directly toward the goal of artificial general intelligence. This is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of results and discussion of ideas, we accelerate our progress toward our common goal. The preliminary Call for Papers is here: http://agi-conf.org/2010/call-for-papers This is the first AGI conference to be held outside the US and we are looking forward to a lively mixture of perspectives. Lugano is a beautiful locale and we are sure it will be an inspiring place to collaborate on creating the future of AGI! Yours, Marcus Hutter Conference Chair From ahu at cs.stir.ac.uk Sat Sep 12 07:54:03 2009 From: ahu at cs.stir.ac.uk (Dr. Amir Hussain) Date: Sat, 12 Sep 2009 12:54:03 +0100 (BST) Subject: Connectionists: Table of Contents Alert: "Cognitive Computation" (Springer, NY, USA) - Vol. 1, Issue 3, Sep 2009 Message-ID: <11277.78.148.91.236.1252756443.squirrel@www.cs.stir.ac.uk> Dear Colleagues: (with advance apologies for any cross-postings) We are delighted to announce the publication of the third (quarterly) Issue (Sep 2009) of Springer's exciting new multi-disciplinary journal in the neurosciences: "Cognitive Computation" - www.springer.com/12559 The list of published articles (Table of Contents) can be found at the end of this message. You will also be pleased to know that ALL (full) articles in Cognitive Computation are FREELY AVAILABLE for access/download through December 31, 2009. Please ask your library to subscribe for 2010 and beyond! The full listing of Issue 3 (Sep 2009) can be viewed here: http://springerlink.com/content/m224t1178m77/?p=61f9d0eb786e434783d7e55414ff013f&pi=0 The full listing of the Inaugural Issue 1 (March 2009) can be viewed here (which includes invited authoritative reviews by leading researchers in their areas - including keynote papers from London University's John Taylor, Igor Aleksander and Stanford University's James McClelland, and invited papers from Kevin Gurney, Ron Sun, Pentti Haikonen, Geoff Underwood, Claudius Gross, Anil Seth and Tom Ziemke): http://www.springerlink.com/content/w2826455k852/?p=603724902f224ec4ab2a0e52213f8d3e&pi=0 The full listing of Issue 2 (June 2009) can be viewed here (which includes invited reviews and original research contributions from leading researchers, including Rodney Douglas, Giacomo Indiveri, Jurgen Schmidhuber, Thomas Wennekers, Pentti Kanerva and Friedemann Pulvermuller): http://www.springerlink.com/content/n6134575mg14/?p=0ae0e58e2b8444c48fc62261e6b6a13f&pi=0 Other 'Online First' published articles not yet in a print issue can be viewed here: http://www.springerlink.com/content/121361/?Content+Status=Accepted For further information and to sign up for electronic "Table of Contents alerts" please visit the Cognitive Computation homepage: http://www.springer.com/biomed/neuroscience/journal/12559 Finally, we would like to invite you to submit short or regular papers describing original research or timely review of important areas - our aim is to peer review all papers within approximately SIX WEEKS of receipt. We also welcome relevant proposals for Special Issues. With our very best wishes for all aspiring readers and authors of Cognitive Computation, Amir Hussain, PhD (Editor-in-Chief: Cognitive Computation) Igor Aleksander, PhD (Honorary Editor-in-Chief: Cognitive Computation) John Taylor, PhD (Chair, Advisory Board: Cognitive Computation) -------------------------------------------------------------------------------------------- Table of Contents: Springer's Cognitive Computation, Vol.1, No.3, Sep 2009 -------------------------------------------------------------------------------------------- (Full listing of Articles, in PDF, is available here: http://springerlink.com/content/m224t1178m77/?p=61f9d0eb786e434783d7e55414ff013f&pi=0 ) Articles Actor-Critic Learning for Platform-Independent Robot Navigation David Muse and Stefan Wermter http://www.springerlink.com/content/83xk7n24hh7n8273 A Cognitive Computation Fallacy? Cognition, Computations and Panpsychism John Mark Bishop http://www.springerlink.com/content/uq06742357143589 Multiple Model-Based Control Using Finite Controlled Markov Chains Enso Ikonen and Kaddour Najim http://www.springerlink.com/content/c40m1227215311k8 A Consequence of Failed Sequential Learning: A Computational Account of Developmental Amnesia Qi Zhang http://www.springerlink.com/content/l74pm0r430m72633 Biometric Recognition Performing in a Bioinspired System Joan F?bregas and Marcos Faundez-Zanuy http://www.springerlink.com/content/14n81k768426r137 The Perceptual and Cognitive Role of Visual and Auditory Channels in Conveying Emotional Information Anna Esposito http://www.springerlink.com/content/m028u137vh4132nq -- Dr. Amir Hussain Dept. of Computing Science & Mathematics, University of Stirling Stirling FK9 4LA, Scotland, UK Tel/Fax: (++44) (0)1786-467437 / (0)1786-464551 Email: ahu at cs.stir.ac.uk http://www.cs.stir.ac.uk/~ahu/ -- Academic Excellence at the Heart of Scotland. The University of Stirling is a charity registered in Scotland, number SC 011159. From pmt6sbc at maths.leeds.ac.uk Sat Sep 12 23:05:21 2009 From: pmt6sbc at maths.leeds.ac.uk (S Barry Cooper) Date: Sun, 13 Sep 2009 04:05:21 +0100 (BST) Subject: Connectionists: 2012 - THE ALAN TURING YEAR Message-ID: 2012 - THE ALAN TURING YEAR: June 23, 2012, is the Centenary of Alan Turing's birth. During his relatively brief life, Turing made a unique impact on the history of computing, computer science, artificial intelligence, developmental biology, and the mathematical theory of computability. 2012 will be a year-long celebration of Turing's life and scientific impact, with a number of major events taking place throughout the year. Most of these will be linked to places with special significance in Turings life, such as Cambridge, Manchester and Bletchley Park. If you would like to be included in the Turing Centenary email list, please go to: http://www.turingcentenary.eu/ and enter your email address in the panel provided. __________________________________________________________________________ ALAN TURING YEAR http://www.turingcentenary.eu _________________ Prof S Barry Cooper Tel: UK: (0113) 343 5165, Int: +44 113 343 5165 School of Mathematics Fax: UK: (0113) 343 5090, Int: +44 113 3435090 University of Leeds Email: pmt6sbc at leeds.ac.uk, Mobile: 07590602104 Leeds LS2 9JT Home tel: (0113) 278 2586, Int: +44 113 2782586 U.K. WWW: http://www.amsta.leeds.ac.uk/~pmt6sbc __________________________________________________________________________ From knorman at Princeton.EDU Sun Sep 13 22:43:00 2009 From: knorman at Princeton.EDU (Kenneth Norman) Date: Sun, 13 Sep 2009 22:43:00 -0400 Subject: Connectionists: Postdoc and Research Assistant: Memory Modeling and Multivariate fMRI/EEG Data Analysis Message-ID: <852AE5F5-EFCB-4450-BA55-C44B5FB53691@princeton.edu> dear connectionist colleagues, i have openings for a postdoc and a research assistant in my lab at princeton -- the advertisements are appended below. if you know of anyone in your lab (or elsewhere) who might be suitable for either position, i would be grateful if you could forward the advertisement along to them. best wishes ken ============== postdoc ad ================= Postdoctoral Research Associate, Computational Memory Lab, Princeton Neuroscience Institute and Department of Psychology, Princeton University. The Princeton Computational Memory Lab, led by Professor Ken Norman, is seeking a postdoctoral research associate to work on NIH-funded studies of cortical and hippocampal learning mechanisms. The lab uses both computational models and neuroimaging data (fMRI and EEG) to study learning and memory. To test our models? detailed predictions, we use multivariate neuroimaging analysis methods that allow us to decode what information is represented in the brain and how these representations change over time. The goal of this specific project is to explore how competition between neural representations (e.g., during memory retrieval) affects learning. The postdoctoral researcher will help to build computational models of competition- dependent learning processes. They will also develop and run experiments that use highly sensitive pattern classifier algorithms, applied to fMRI and EEG data, to track the extent to which memories compete on a trial-by-trial basis. This neural readout of the competing memories can be used to test the model?s predictions about how competition drives learning. In addition to this competition- dependent learning project, the postdoctoral researcher will be given the opportunity to participate in other lab research endeavors, and they will be expected to make a strong contribution to the lab?s efforts to improve and validate neuroimaging analysis methods. For more information on our lab, see http://compmem.princeton.edu. Essential qualifications for this position include: a Ph.D. in Psychology, Neuroscience, Cognitive Science, Computer Science, Engineering, or other related field; a strong publication record of original research in cognitive neuroscience; prior experience with using fMRI or EEG to study cognitive processes; and fluency in at least one programming language (e.g., Matlab, Python, C/C++). The position will provide training in computational methods, but we prefer applicants who already have some experience with computational modeling/or and multivariate methods for neuroimaging data analysis. The Norman lab is part of a highly collaborative network of labs at Princeton that are using computational methods to enrich neuroscience theory and data analysis, ranging from the Botvinick, Brody, Cohen, Hasson, and Niv labs in the Princeton Neuroscience Institute, to the Blei, Daubechies, and Ramadge research groups in Computer Science, Math, and Engineering. Questions can be addressed to Professor Ken Norman, knorman at princeton.edu. Review of applications will continue until the position is filled. To apply, please visit the website https://jobs.princeton.edu (requisition #0900383), create an online application. Applications should include a cover letter, a CV, one or two representative publications and a list of at least two potential referees. Princeton University is an equal opportunity employer and complies with applicable EEO and affirmative action regulations. For general application information and how to self-identify, see http://www.princeton.edu/dof/policies/forms/newappoint_reclassif/PSoftSelfID.pdf . ============= research assistant ad ================= Research Specialist, Computational Memory Lab, Princeton Neuroscience Institute and Department of Psychology, Princeton University. The Princeton Computational Memory Lab, led by Professor Ken Norman, is seeking a full-time research specialist to work on NIH-funded studies of cortical and hippocampal learning mechanisms. The lab uses both computational models and neuroimaging data (fMRI and EEG) to study learning and memory. To test our models? detailed predictions, we use multivariate neuroimaging analysis methods that allow us to decode what information is represented in the brain and how these representations change over time (see http://compmem.princeton.edu for more information on our lab?s research). The successful candidate will assist with all aspects of our lab?s research, including developing materials, programming experiments, recruiting participants, collecting and analyzing fMRI and EEG data, and miscellaneous research support (literature searches, manuscript and grant preparation, general lab duties). A major part of the research specialist?s duties will be assisting with the development, testing, and dissemination (via open-source software) of new methods for analyzing neuroimaging data. Essential qualifications for this position include: A bachelor?s degree in Psychology, Cognitive Science, Neuroscience, Computer Science, Engineering, Math, or other related field; demonstrated interest or research experience in cognitive neuroscience; fluency in at least one programming language (e.g., Matlab, Python, C/C++); and an organized, independent, and efficient work ethic. Preferred (but not essential) qualifications include prior experience with neuroimaging data analysis (fMRI and/or EEG) and a working knowledge of modern machine learning methods (e.g., pattern classification algorithms). This position is ideal for candidates who are planning to attend graduate school and want additional research experience. Questions about the position can be addressed to Professor Ken Norman, knorman at princeton.edu . Review of applications will continue until the position is filled. To apply, please visit the website https://jobs.princeton.edu (requisition #0900381), create an online application. Applications should include a cover letter, a CV, and a list of at least two potential referees. Princeton University is an equal opportunity employer and complies with applicable EEO and affirmative action regulations. For general application information and how to self-identify, see http://www.princeton.edu/dof/policies/forms/newappoint_reclassif/PSoftSelfID.pdf . ===================================================== Ken Norman Associate Professor Department of Psychology and Princeton Neuroscience Institute Princeton University http://compmem.princeton.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090913/1407fb35/attachment.html From mcclelland at stanford.edu Mon Sep 14 03:23:29 2009 From: mcclelland at stanford.edu (Jay McClelland) Date: Mon, 14 Sep 2009 00:23:29 -0700 Subject: Connectionists: Faculty Position in Psychology at Stanford Message-ID: <4AADEF71.7070504@stanford.edu> The following opening is open to a wide range of applicants. I would like to specifically encourage applicants who combine computational and experimental approaches to any of the content topics listed. Jay McClelland ------------------------------------------------------------- STANFORD UNIVERSITY PSYCHOLOGY DEPARTMENT plans to create a tenure-track appointment at the Assistant Professor level in Cognitive Psychology, to begin in the academic year 2010-11. All areas of cognitive psychology will be considered, including, but not limited to, memory, thinking, language, attention, decision-making, cognitive neuroscience, and computational/mathematical models of cognition. The appointee will be expected to teach courses at both the graduate and undergraduate levels. All applicants should provide a curriculum vitae (including bibliography), a brief statement of research interests, copies of their most representative scholarly papers, and three letters of reference. The deadline for applications is October 31, 2009. Please apply through AcademicJobsOnline.org. Stanford University is an equal opportunity employer and is committed to increasing the diversity of its faculty. It welcomes nominations of, and applications from, women and members of minority groups, as well as others who would bring additional dimensions to the university's research and teaching missions. From jose at psychology.rutgers.edu Mon Sep 14 19:54:44 2009 From: jose at psychology.rutgers.edu (Stephen Jose hanson) Date: Mon, 14 Sep 2009 19:54:44 -0400 Subject: Connectionists: New Papers for Computational Neuroimaging and Neuroscience Message-ID: <1252972484.10651.98.camel@max> >From the RUMBA Lab Rutgers University Mind Brain Analysis Three new papers for Computational Neuroimaging and Neuroscience Hanson SJ, Gagliardi AD, and Hanson C. (2009) Solving the brain synchrony eigenvalue problem: conservation of temporal dynamics (fMRI) over subjects doing the same task. Journal of computational neuroscience. Aug;27(1):103-14. This paper describes a new method for extracting synchronous temporal dynamics across subjects doing passive viewing task such as a movie while they are being brain scanned. ".... This general question can be framed in a dynamical systems context and further be posed as an eigenvalue problem about the conservation of synchrony across all brains simultaneously. We show that solving the problem results in a non-arbitrary measure of temporal dynamics across brains that scales over any number of subjects, stabilizes with increasing sample size, and varies systematically across tasks and stimulus conditions." PDF here: http://sites.google.com/site/rumbalab/publications-1/papers/2009 Poldrack, R., Halchenko Y., and Hanson, S.J. (in press). Decoding the large-scale structure of brain function by classifying mental states across individuals, Psychological Science. "...Using a variety of classifier techniques, we achieved cross-validated classification accuracy of 80% across individuals (chance = 13%). Using a neural network classifier, we recovered a low-dimensional representation common to all the cognitive-perceptual tasks in our data set, and we used an ontology of cognitive processes to determine the cognitive concepts most related to each dimension. These results revealed a small set of large-scale networks that map cognitive processes across a highly diverse set of mental tasks, suggesting a novel way to characterize the neural basis of cognition." PDF here: http://sites.google.com/site/rumbalab/publications-1/papers/in-press Ramsey, J. D., Hanson, S. J., Hanson, C., Halchenko, Y. O., Poldrack, R. A., and Glymour, C. (2009). Six problems for causal inference from fmri. NeuroImage. "...To find actual effective connectivity relations, search methods must accommodate indirect measurements of nonlinear time series dependencies, feedback, multiple subjects possibly varying in identified regions of interest, and unknown possible location-dependent variations in BOLD response delays. We describe combinations of procedures that under these conditions find feed-forward sub-structure characteristic of a group of subjects. The method is illustrated with an empirical data set and confirmed with simulations of time series of non-linear, randomly generated, effective connectivities, with feedback, subject to random differences of BOLD delays, with regions of interest missing at random for some subjects, measured with noise approximating the signal to noise ratio of the empirical data." PDF here: http://sites.google.com/site/rumbalab/publications-1/papers/in-press -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090914/819fdec8/attachment-0001.html From rjolivet at pharma.uzh.ch Wed Sep 16 06:21:03 2009 From: rjolivet at pharma.uzh.ch (Renaud Jolivet) Date: Wed, 16 Sep 2009 12:21:03 +0200 Subject: Connectionists: New paper: modeling neuron-astrocyte interactions Message-ID: <4AB0BC0F.1000400@pharma.uzh.ch> Dear colleagues, I would like to draw your attention to a paper we recently published modeling the exchange of metabolites between neuron and astrocytes and providing a new method for evaluating the brain's energy budget. The paper is available at http://frontiersin.org/neuroenergetics/paper/10.3389/neuro.14/004.2009/ Jolivet R, Magistretti PJ, Weber B. Deciphering neuron-glia compartmentalization in cortical energy metabolism. Front. Neuroenerg. 1:4. doi:10.3389/neuro.14.004.2009 Energy demand is an important constraint on neural signaling. Several methods have been proposed to assess the energy budget of the brain based on a bottom-up approach in which the energy demand of individual biophysical processes are first estimated independently and then summed up to compute the brain's total energy budget. In this paper, we address this question using a novel approach that makes use of published datasets that reported average cerebral glucose and oxygen utilization in humans and rodents during different activation states. Our approach allows us [1] to decipher neuron-glia compartmentalization in energy metabolism and [2] to compute a precise state-dependent energy budget for the brain. Our results suggest that glycolysis occurs for a significant part in astrocytes whereas most of the oxygen is utilized in neurons. As a consequence, a transfer of glucose-derived metabolites from glial cells to neurons has to take place. Furthermore, we find that the amplitude of this transfer is correlated to the activity level of the brain and to the oxidative activity in astrocytes. Our method allows for a straightforward assessment of the brain's energy budget from macroscopic measurements with minimal underlying assumptions. Best regards, Renaud Jolivet -- Dr Renaud Jolivet Roche Research Fellow University of Zurich Institute of Pharmacology & Toxicology University Hospital Z?rich Nuclear Medicine R?mistrasse 100 CH-8091 Z?rich Tel: +41 76 437 9798 rjolivet at pharma.uzh.ch http://www.pharma.uzh.ch/research/functionalimaging/members/jolivet.html From welling at ics.uci.edu Wed Sep 16 11:23:54 2009 From: welling at ics.uci.edu (Max Welling) Date: Wed, 16 Sep 2009 08:23:54 -0700 Subject: Connectionists: Postdoctoral position available in machine learning (UCI & Caltech) In-Reply-To: References: Message-ID: Department of Computer Science Post Doctoral Scholar Position University of California, Irvine The Department of Computer Science at UC Irvine has a postdoctoral position available in the area of machine learning and computational vision. The position is part of a collaboration between Professor Max Welling?s research group at UCI (department of Computer Science) and Professor Pietro Perona?s research group at Caltech (department of engineering). The postdoc is expected to spend at least one day a week at Caltech on average. Responsibilities will include the development of new algorithms for learning hierarchical models for visual object categories. The approach will focus on the following three aspects of this problem: I) developing probabilistic models for visual object categories in image data, II) developing learning algorithms that can automatically grow in complexity in response to new data, III) developing efficient learning and inference algorithms that scale to large datasets. Applicants must have earned a Ph.D. in Computer Science, Electrical Engineering, Applied Mathematics, Statistics, Physics or a closely-related discipline. The salary range for these positions will be between $45,000 and $60,000 annually, commensurate with training and experience. The earliest date for appointment will be October 1, 2009. The appointments will each initially be for a one-year period with extensions to additional years possible subject to availability of funding. Interested applicants should apply electronically to Max Welling at welling.max at gmail.com with a subject line containing ?application for postdoctoral position.? Applicants should include a list of publications, a CurriculumVitae and the names of three references in their electronic application (no letters required at this stage). Applicants who are unable to apply electronically should send their application by mail to: Max Welling Department of Computer Science 3019 Donald Bren Hall Donald Bren School of Information and Computer Sciences University of California, Irvine CA 92697-3435 The University of California, Irvine is an equal opportunity employer committed to excellence through diversity. -- Max Welling Professor of Computer Science and Statistics Donald Bren School of Information & Computer Science University of California Irvine Bren Hall 4028 phone: 949-824 8169 fax: 949-824 4056 email: welling at ics.uci.edu Irvine, CA 92697-3425 USA URL: www.ics.uci.edu/~welling/ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090916/ab27d67b/attachment.html From giulio.sandini at iit.it Wed Sep 16 18:27:36 2009 From: giulio.sandini at iit.it (Giulio Sandini) Date: Thu, 17 Sep 2009 00:27:36 +0200 Subject: Connectionists: PhD positions at IIT - Robotics, Brain and Cognitive Science Message-ID: <001d01ca371c$e4932160$adb96420$@sandini@iit.it> PhD Course: Robotics, Cognition and Interaction Technologies ? XXV Cycle Research Themes Proposed by the Department of Robotics, Brain and Cognitive Sciences Eight PhD positions are available at the Robotics, Brain and Cognitive Sciences Department (RBCS) of the Italian Institute of Technology (IIT) within the Doctoral Course ?Robotics, Cognition and Interaction Technologies?. The Robotics, Brain and Cognitive Science department directed by Professor Giulio Sandini, is a multidisciplinary community of scientists sharing research interests and contributing jointly to the emerging field of human centered research and technologies with a focus on learning and development and, in general, on the dynamics of knowledge acquisition and update in the framework of goal directed actions. Among the Senior Scientists coordinating RBCS research activities are Franco Bertora (Brain Imaging), Luciano Fadiga (Brain Machine Interface), Giorgio Metta (Cognitive Robotics), Pietro Morasso (Motor Learning and Robot Rehabilitation), Concetta Morrone (Visuo-haptic Perception), Stefano Panzeri (Brain Signal Analysis), Thierry Pozzo (Physiology of Action and Perception),. Collaborations with international research centers and industries is carried out throught formalized projects and teaching-oriented international networks. RBCS is the home of the iCub humanoid robot (www.icub.org). More information about RBCS research: http://www.iit.it/en/robotics-brain-and-cognitive-sciences.html Within the department?s Research Agenda, proposals for PhD fellowships are accepted with reference to three main streams: 1. Humanoid Robotics and Cognition (themes 3.1 to 3.7): The themes under this heading group the research activities targeting the humanoid platforms of the lab among which iCub (the platform of the RobotCub project www.robotcub.org) and ?James? (a one-arm humanoid build to investigate manipulation and object affordance). The research themes proposed are examples of the planned activities in areas such as cognitive systems, sensorimotor coordination, advanced materials for actuation, sensing and scaffolding. - Theme 3.1: Composite materials design for biocompatible robotic structural elements. - Theme 3.2: Finite element analysis and CAD design of robotic components made from variable stiffness composite materials - Theme 3.3: Learning body dynamics in humans and robots - Theme 3.4: Manipulation and Learning in Humanoid Robots - Theme 3.5: Reaching and Moving in the Peripersonal Space for a Humanoid Robots - Theme 3.6: Neuromorphic sensors for humanoid robots - Theme 3.7: Event-driven vision for robot control 2. Human Behavior, Perception and Biomechanics (themes 3.8 to 3.12): The themes under this heading group the research activities targeting the study of how humans learn, perceive and act. This year?s focus is on multimodal sensory integration, the control of redundant degree of freedom and a new topic addressing the neural correlates of biological motion inference. - Theme 3.8: Measuring the human body - Theme 3.9: Action and task representation in human and robot learning - Theme 3.10: Action and Perception coupling - Theme 3.11: Modular control of natural motor behaviour - Theme 3.12: Psychophysical study of unimodal perception and multimodal integration 3. Brain Machine Interface, (themes 3.13 and 3.14): The themes under this heading will contribute to the multidisciplinary BMI project developed at IIT aiming at 'reading' the brain to understand and extract motor signals which may be used to the development of innovative prosthetic devices. - Theme 3.13: Information theoretic extraction of muscle synergies - Theme 3.14: Nano-scaffolds with on-design tunable properties for tissue engineering Short abstract and scientist in charge of the research themes proposed are included below and are to be considered as indications of this year?s priorities. Research projects within the same areas are welcome and will be also considered. Interested applicants should read the procedure described below and/or refer to the IIT?s website (www.iit.it) to download instructions for application and/or contact directly the scientists in charge for more information regarding the individual research plans. Submission procedure in short Application letters and the required accompanying documents as detailed in the call for applications (http://www.iit.it/media/call/ciclo25_iit_bando_en.doc) should be prepared following the outline of Annex B (application form) and be sent within September, 25th 2009 to Magnifico Rettore dell?Universit? degli Studi di Genova. Besides completing the application form (Annex B) you must provide the following documents: ? Curriculum vitae et studiorum dated and signed ? A photocopy of a valid identity document; ? Title and synthetic description of dissertation (also on cd-rom); ? A list of exams with the grades; ? At least one letter (and not more than three) of presentation of the candidate signed by a university lecturer or an expert in the subject; ? A signed research project concerning one or more of the research themes described above you intend to apply (maximum 10 pages); ? A statement of actual knowledge of the English language; foreign nationals may also state their knowledge of the Italian language; ? Any other qualifications relative to the subject areas of the research dealt with in the course, papers shall not be more than 10 pages long. On the envelope you should indicate the name of the course (Robotics, Cognition an Interaction Technologies) and the number of the research theme you are applying as described above. Application letters and the required documents can be delivered 1. by mail Applications can be sent using a registered letter. The envelope must include in the header the following wording: ?Concorso per ammissione al XXIV ciclo del Dottorato di Ricerca? Doctoral Course: Robotics, Cognition and Interaction Technologies and has to be addressed as follows: Magnifico Rettore dell?Universit? degli Studi di Genova Servizio Alta Formazione e Ordinamenti Didattici Via Balbi 5 16126 ? Genova Italy 2. by hand Letters can be handed personally to the following office (opening time: 9:00 ? 12:00, Monday to Friday; extra opening on Tuesday and Wednesday from 14:30 to 16:00): Universit? degli Studi di Genova Servizio Alta Formazione e Ordinamenti Didattici Via Bensa 1 - 2nd floor 16124 Genova Italy For any further information regarding the application procedure please contact: Ms Anastasia Bruzzone Doctoral School UNIGE-IIT Fondazione Istituto Italiano di Tecnologia Via Morego, 30 - 16163 Genova Tel. +39 010 71781472 Fax. +39 010 7170817 Email: anastasia.bruzzone at iit.it RESEARCH TOPICS PROPOSED BY RBCS Department STREAM 1: Humanoid Robotics and Cognition Theme 3.1: Composite materials design for biocompatible robotic structural elements. Tutors: Dr. Davide Ricci, Dr. Alberto Barone This Ph.D. thesis proposal originates from the collaboration of the IIT Robotic, Brain and Cognitive Sciences Department with the IIT Nanobiotechnology Facility. An essential task that needs to be addressed in the realization of robotic prosthetic devices is the coupling of structural elements of artificial limbs with bone tissue. Many pre-clinical and also clinical reports demonstrate that poor scaffold design and inadequate tissue culture conditions are currently the major problems in bone tissue engineering that may prevent its successful applications. To overcome these limitations, novel structural biomaterials and better bio-reactor processes are needed, capable of sustaining and guiding bone tissue precursors generation and differentation. Within this project, we will pursue the integration of bio-hybrid synthetic techniques, nanotechnologies and advanced material processing technologies to obtain three-dimensional scaffolds able to guide and control tissue growth, differentiation and proliferation. Requirements: Potential candidates should have basic background in one or more of the following fields: materials science, polymer science, biomechanics For further details concerning the research project, please contact: davide.ricci at iit.it alberto.barone at iit.it Theme 3.2: Finite element analysis and CAD design of robotic components made from variable stiffness composite materials Tutor: Prof. Giorgio Metta A traditional robot is made of mechanical parts that are assembled with screws, bearings, levers, gears and other components to obtain the desired functionality. An emerging trend in robot design relies instead on deriving the required functionality directly from the materials properties. Two approaches can be envisaged: either by appropriately combining functional materials with different properties via methods similar to the "shape deposition manufacturing" (Kutkosky et al. 1989) or by locally modifying a composite material properties changing the density and nature of fillers. To this end, CAD and FE simulations are essential tools to choose the appropriate materials and shape for the robot components. The goal of this project is the design of a robot hand for the iCub ( http://www.robotcub.org) that includes variable stiffness mechanics, sensorization (proprioceptive and tactile), wiring and tendon driven actuation. Appropriate controllers are also required to match and exploit natural compliance but also to compensate for e.g. backlash. The reference task will be manipulation. The ideal candidate would have a background in mechanical engineering or related disciplines, and in particular, skills in finite element analysis/modelling, robotics, and more in general in the use of polymers in mechanical design. On the other hand, IIT will provide a fully equipped machine shop with CNC and rapid prototyping machines both on polymers and metal. The successful candidate is expected to work in a team and contribute substantially to the design of a future release of the iCub. Requirements: physics, mechanical or material engineering, For further details concerning the research project, please contact: giorgio.metta at iit.it Theme 3.3: Learning body dynamics in humans and robots Tutor: Dr. Francesco Nori Humans exhibit a broad repertoire of motor capabilities far beyond the capabilities of modern robots. Remarkably, there is strong evidence that these capabilities are strongly linked to human adaptability to novel dynamical contexts (J.R. Lackner and P. Dizio, 1994) (R. Shadmehr and F.A. Mussa-Ivaldi, 1994) (J. Konczak et al., 1995). Related neurophysiological experiments suggest that this adaptability can be the result of a modular organization of the central nervous system which forms forward and inverse dynamical representations by means of multiple modules. The final goal of this research project will be to enhance a ?state of the art? humanoid robot (http://www.icub.org) with a ?beyond the state of the art? adaptive dynamical controller. The project should focus on the robot ability to develop, learn and adapt a multisensory representation of its own body dynamics and of the surrounding dynamical environment, possibly exploiting the generalization potentialities behind a modular representation. Requirements: engineering background, confidence with dynamical system analysis, (optional) machine learning, adaptive control For further details concerning the research project, please contact: francesco.nori at iit.it and giorgio.metta at iit.it Theme 3.4: Manipulation and Learning in Humanoid Robots Tutor: Dr. Lorenzo Natale Object manipulation is a key ability for robots. However current robots are very poor at manipulating objects in dynamical or unmodeled environments. Unfortunately this situation is quite common in practical scenarios and seriously hampers the possibility to employ robots outside industries or research laboratories. In this project we will study the role of haptic information (touch, proprioception and force) for manipulation. The goals of the project are two: i) to implement control strategies for grasping and manipulating objects and ii) to investigate how to use the sensory information originating from the manipulation of objects (haptic but also visual or auditory) for learning about objects and the environment. The project will be carried out working on the robot iCub. The iCub is a 53 degree of freedom humanoid robot equipped with dexterous arms and hands (respectively 7 and 9 degrees of freedom). We have recently added torque sensing on the arm and realized tactile sensors to be mounted on the hand and the arm of the robot. We seek candidates with a strong background in computer science and engineering that are interested in studying perception and learning in artificial systems. Backgrounds of electronics and mechanics are not required, but the candidates should have a strong motivation to work on robotic systems. For further details concerning the research project, please contact: lorenzo.natale at iit.it and giorgio.metta at iit.it Theme 3.5: Reaching and Moving in the Peripersonal Space for a Humanoid Robots Tutor: Prof. Giorgio Metta, Prof. Luciano Fadiga Tantalizing evidence from neuroscience is showing that the control of reaching in humans and animals is correlated with the activation of several neural pathways, where touch, proprioception, and vision are intertwined with motor information in a multisensory representation of the space around the body (Fogassi, Gallese, di Pellegrino, Fadiga, et al. 1992). The goal of this PhD program is to model these multiple neural pathways in the form of a working controller for a humanoid robot. The robot in question is the iCub which is equipped with vision, proprioception and soon with a distributed sensorized skin. We will study how this multisensory representation can be acquired through learning and development during the interaction of the robot with the environment. We will formulate models that are in agreement with neuroscience (Rizzolatti, Fadiga, Fogassi, Gallese, 1997). We are seeking candidates with a strong motivation to implement biologically sound models in a humanoid robot, with a background in engineering or related disciplines, programming skills, and some machine learning or computer vision experience. The successful candidate is expected to work in a team and integrate with the existing development tools and methods. Requirements: engineering or computer science background, some experience in one of more of the following disciplines: machine learning, computer vision, control systems, neuroscience. For further details concerning the research project, please contact: giorgio.metta at iit.it or luciano.fadiga at iit.it Theme 3.6: Neuromorphic sensors for humanoid robots Tutor: Dr. Chiara Bartolozzi Biological sensory systems outperform conventional digital systems in almost all aspects of perception tasks, where the system must process noisy and ambiguous stimuli to produce appropriate behavioral responses. The goal of this project is to introduce in the field of robotic vision the principles of biological sensory systems design. Specifically we aim at combining the design of novel data-driven biologically inspired sensory devices with the development of new asynchronous event-driven computational paradigms, with structure and morphology that are matched to the requirements of the robots body and its application domain. The candidate shall work on testing of existing asynchronous vision sensors and on the design of new sensors, using analog real-time low-power VLSI neuromorphic circuits. The candidate will participate in the whole project development by also interacting with researchers developing supporting data-driven asynchronous computational paradigms for machine-vision methodologies, and participating to the testing of the developed vision system performance on advanced humanoid robotic platforms. Requirements: Applicants should have a strong interest in bio-inspired hardware engineering, fundamental notions of microelectronics and background in neuroscience. For further details concerning the research project, please contact: chiara.bartolozzi at iit.it Theme 3.7: Event-driven vision for robot control Tutor: Drs. Giorgio Metta, Chiara Bartolozzi, R. Benosman The goal of this project is to develop asynchronous event-driven computational paradigms for designing visual systems based on data-driven biologically inspired sensory devices providing spike-based outputs. Such sensors respond with spiking events to relative variations of contrast in their field of view. This approach reduces redundancies and produces a sparse image coding. The generated data are spatiotemporal volumes which size and information depend only on the dynamic content of observed scenes. The real-time asynchronous output nature of the sensors ensures precise timing information and low latency, yet requiring a much lower bandwidth used by frame-based image sensors of equivalent time resolution. The high temporal precision is crucial for real-time interaction with the environment and is especially suitable for tasks requiring fast evaluation of dynamic scenes, involving real time interaction with the environment. At the same time, the nature of the sensor's output requires a radically new framework of data-driven asynchronous computational paradigms for vision. The candidate will work on the development of event-driven algorithms for the visual system of a humanoid robot, the iCub, starting from stereo vision and binocular vergence control to end up with recognition and control of the robot?s own hands dynamics, with the final goal of objects dexterous manipulation. Requirements: Ideal candidates have a strong background in robotics or computer vision; candidates with background in neuroscience are also welcome. They should have potential for excellent research and the capability to collaborate within an interdisciplinary research group with people from all these disciplines. They should be highly motivated to use robotics for tackling fundamental issues in bio inspired perception. For further details concerning the research project, please contact: giorgio.metta at iit.it chiara.bartolozzi at iit.it STREAM 2: Human Behavior, Perception and Biomechanics Theme 3.8: Measuring the human body Tutor: Prof. Luciano Fadiga This ambitious project aims at overpass traditional limitations in precisely measure cinematic, physiological and neuro-vegetative parameters during the normal behavior in healthy subjects. Among the to-be-explored possibilities: occlusion-immune dynamic tracking of body parts, miniaturized eye-motion detectors, measurements of tactile stimulation by determining the modifications of epidermal-dermal electric impedance, multi-technique simultaneous determination of vegetative states (skin resistance, thermal imaging, pupil diameter, changes in prosodic tonality, etc.). The Ph.D. thesis work will be devoted to setup new techniques, to build specifically dedicated hardware and software, to build a normative database during different kind of motor activities, as well as inter-individual interaction and communication. Requirements: Background in electronics and computer science is a must. For further details concerning the research project, please contact: luciano.fadiga at iit.it Theme 3.9: Action and task representation in human and robot learning Tutor: Prof. Pietro Morasso, Dr. Lorenzo Masia In recent years it has become clear that purposive action, in humans and humanoid robots, requires the bi-directional interaction among the brain, the body, and the environment. This has important implications at the computational level, in the sense that task-critical computations must not necessarily be totally centralized in the ?brain? but can be distributed to the implicit dynamics of the body and the environment, thus implementing what is known as ?morphological computation?. However, most research in this area has been focused on robot locomotion (passive dynamic walking or running) or insect flying. The purpose of the thesis instead is to focus on motor learning, while interacting in a haptic and visual way with dynamical processes that emulate an artificial environment generated by means of robotic devices. A variety of robotic platforms will be used to create human robot interaction: monomanual and bimanual tasks involving proximal and distal arm will be implemented using different control scheme and robotic devices. Experiments on human learning will be analyzed in such a way to provide useful insight for the organization of robot learning paradigms. Requirements: Backgrounds in computer sciences, robotics, automatic control, behavioural neurosciences are required. For further details concerning the research project, please contact: pietro.morasso at iit.it, lorenzo.masia at iit.it Theme 3.10: Action and Perception coupling Tutor: Prof. Thierry Pozzo The idea that observation can activate motor representation that do not result from observer past executions (i.e., without sensory and motor signal resulting from actual execution, as in the case of new motor abilities), opens innovative learning methods for humans and robots. Ph.D. thesis work will involve students in the fields of motor control (3D kinematic analysis, optimization control) and robotic (machine learning ). The aim is twofold: 1) To study biological motion recognition using non invasive brain activity measurements (TMS, EEG,FMRi), EOG and psychophysics, making the hypothesis of online action simulation at observation. Moreover the loci of internal models of action will be investigated: TMS will be used to induce virtual lesions of different cortical areas (STS, superior parietal lobule ) during the motion display and the potential effect on the end point estimation in order a) to verify the true role of parietal cortex in the inverse model elaboration, b) to quantify the effect on estimation accuracy and, c) to detail the circuitry of the action to perception matching system. 2) to implement the experimental results performed on human in robot for learning by imitating human movements. For instance the perceived action of a teacher can be mapped onto a set of existing primitives inside the robot. Requirements: Backgrounds in computer sciences, robotic or behavioural neurosciences are required. For further details concerning the research project, please contact: thierry.pozzo at iit.it Theme 3.11: Modular control of natural motor behaviour Tutor: Dr. Thierry Pozzo The research project will be performed on the basis of previous results obtained during an original paradigm developed to study both equilibrium and spatial components of a complex multijoint goal oriented task (Pozzo et al. 2002, Berret et. Al 2009). A number of interesting questions arise when considering together the control of equilibrium and arm trajectory formation. For example: 1) What are the control laws governing a multijoint reaching movements (requiring a high degree of equilibrium control and numerous DoF)? 2) How are integrated equilibrium component with finger manipulating activities performed with distal body parts? 3) Is there a macroscopic representation (motor primitives) at spinal and/or supraspinal level of such components and can they be combined like building blocks to perform this task in different mechanical contexts and to adapt to task changes (velocity, postural stability, lack of gravity, initial sensory state..). These questions will be investigated by using EMG analysis, 3D motion capture and TMS in addition to computational approaches in line with the idea that invariant characteristics of motor behavior reflects optimality criteria used by the CNS to select of the best motor strategy among all possibilities. Requirements: Backgrounds in computer sciences, robotic or behavioural neurosciences are required. For further details concerning the research project, please contact: thierry.pozzo at iit.it Theme 3.12: Psychophysical study of unimodal perception and multimodal integration Tutor: Dr. Monica Gori As no single information-processing system can perceive optimally under all conditions, integration of multiple sources of sensory information makes perception more robust. Many recent studies have demonstrated the capacity of human observers to integrate information across various senses in a statistically optimal (sometimes termed ?Bayesian?) fashion, where greater weight is given to the sense carrying the more reliable information under any particular condition. Importantly, performance in the multimodal condition is always better than in either single modality. The work done in our research group is related to the study of unimodal perception and multimodal integration of different kinds of signals to understand the rules that govern and modulate sensory fusion. This knowledge is fundamental to deepen our understanding of brain processing and will be important to reproduce human abilities in artificial systems. One PhD student will be involved in psychophysical experiments related to this research theme with the goal of understanding the rules that govern multisensory fusion. He will be required to study human perception with psychophysical techniques. Within the many aspects that will be studied we can cite the analysis of dynamic signals (e.g. visual, tactile and haptic) and the development of multisensory fusion (e.g. visual-haptic, visual-audio, audio-haptic) in children of different ages (as in Gori et.al.2008). All these studies will be extended to people with different disabilities. Requirements: Backgrounds in experimental psychology, neuroscience and basic programming skills (in particular Matlab) are required. For further details concerning the research project, please contact: monica.gori at iit.it STREAM 3: Brain Machine Interface Theme 3.13: Information theoretic extraction of muscle synergies Tutor: Dr. Stefano Panzeri In this 4-year-long PhD project, we aim at determining the patterns of muscle activation that best describe, using the minimal number of variables, many different types of complex movements which underlie the execution of tasks involving both reaching objects and maintaining equilibrium [1]. The project will be jointly supervised by Prof. Stefano Panzeri and Prof. Thierry Pozzo. The student will analyze electromyographic recordings of large numbers of muscles spread throughout the subject?s body by using and adapting to this particular purpose advanced techniques arising from the theory of communication [2]. The student will also help with data collection and the refinement of the experiment design. Requirements: The ideal candidate will have a degree in a numerate discipline (engineering, physics or mathematics), a multidisciplinary attitude, and a very keen interest in applying mathematical concepts to understanding biological processes. A good understanding of information theory is a plus. For further details concerning the research project, please contact: stefano.panzeri at iit.it Theme 3.14: Nano-scaffolds with on-design tunable properties for tissue engineering Tutor: Dr. Davide Ricci In the past years, great progress has been made in understanding the essential requirements that have to be satisfied by synthetic materials to be used as scaffolds for tissue engineering. Presently, there is an ever increasing request for materials whose morphological, elastic and bioactive properties may be tuned on demand to investigate their effect on growth and differentiation of specific cell lines. The aim is to create highly efficient tree-dimensional interfaces between biological and artificial systems, allowing the development of innovative prosthetic devices. This ambitious goal may be pursued by a bottom-up approach in the design and assembly of appropriate nano-materials, such as carbon nanotubes and electrospun polymers, thus giving rise to a new generation of cellular scaffolds Requirements: Potential candidates should have basic background in one or more of the following fields: bioengineering, materials science, physics, chemistry For further details concerning the research project, please contact: davide.ricci at iit.it -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090916/0f355a5e/attachment-0001.html From airoldi at fas.harvard.edu Thu Sep 17 00:12:13 2009 From: airoldi at fas.harvard.edu (Edoardo Airoldi) Date: Thu, 17 Sep 2009 00:12:13 -0400 Subject: Connectionists: CFP :: NIPS 09 workshop on Analyzing Networks and Learning with Graphs References: <13CBC6DB-F992-4F89-A17C-FF4D7A0B63DE@FAS.HARVARD.EDU> Message-ID: <72D6638A-BB4D-4C13-A86D-60E272879379@fas.harvard.edu> -- Apologies if you receive multiple copies of this announcement -- -- Please forward to anyone who might be interested -- ##################################################################### CALL FOR PAPERS Analyzing Networks and Learning with Graphs a workshop in conjunction with 23nd Annual Conference on Neural Information Processing Systems (NIPS 2009) December 11 or 12, 2009 (exact date TBD) Whistler, BC, Canada http://snap.stanford.edu/nipsgraphs2009/ Deadline for Submissions: Friday, October 30, 2009 Notification of Decision: Monday, November 9, 2009 ##################################################################### Overview: --------- Recent research in machine learning and statistics has seen the proliferation of computational methods for analyzing networks and learning with graphs. These methods support progress in many application areas, including the social sciences, biology, medicine, neuroscience, physics, finance, and economics. The primary goal of the workshop is to actively promote a concerted effort to address statistical, methodological and computational issues that arise when modeling and analyzing large collection of data that are largely represented as static and/or dynamic graphs. To this end, we aim at bringing together researchers from applied disciplines such as sociology, economics, medicine and biology, together with researchers from more theoretical disciplines such as mathematics and physics, within our community of statisticians and computer scientists. Different communities use diverse ideas and mathematical tools; our goal is to to foster cross-disciplinary collaborations and intellectual exchange. Presentations will include novel graph models, the application of established models to new domains, theoretical and computational issues, limitations of current graph methods and directions for future research. Online Submissions: ------------------- We welcome the following types of papers: 1. Research papers that introduce new models or apply established models to novel domains, 2. Research papers that explore theoretical and computational issues, or 3. Position papers that discuss shortcomings and desiderata of current approaches, or propose new directions for future research. All submissions will be peer-reviewed; exceptional work will be considered for oral presentation. We encourage authors to emphasize the role of learning and its relevance to the application domains at hand. In addition, we hope to identify current successes in the area, and will therefore consider papers that apply previously proposed models to novel domains and data sets. Submissions should be 4-to-8 pages long, and adhere to NIPS format (http://nips.cc/PaperInformation/StyleFiles). Please email your submissions to: nipsgraphs2009 at gmail.com Deadline for Submissions: Friday, October 30, 2009 Notification of Decision: Friday, November 6 2009 Workshop Format: ---------------- This is a one-day workshop. The program will feature invited talks, poster sessions, poster spotlights, and a panel discussion. All submissions will be peer-reviewed; exceptional work will be considered for oral presentation. More details about the program will be announced soon. Organizers: ----------- Edo Airoldi, Harvard University Jure Leskovec, Stanford University Jon Kleinberg, Cornell University Josh Tenenbaum, MIT Thank you, we look forward to receiving your submissions! Edo, Jure, Jon & Josh From shivani at MIT.EDU Thu Sep 17 11:47:25 2009 From: shivani at MIT.EDU (Shivani Agarwal) Date: Thu, 17 Sep 2009 11:47:25 -0400 (EDT) Subject: Connectionists: CFP: NIPS 2009 Workshop - Advances in Ranking Message-ID: ************************************************************************ CALL FOR PAPERS ---- Advances in Ranking ---- Workshop at the 23rd Annual Conference on Neural Information Processing Systems (NIPS 2009) http://web.mit.edu/shivani/www/Ranking-NIPS-09/ -- Submission Deadline: October 23, 2009 -- ************************************************************************ [ Apologies for multiple postings ] OVERVIEW -------- Ranking problems are increasingly recognized as a new class of statistical learning problems that are distinct from the classical learning problems of classification and regression. Such problems arise in a wide variety of domains: in information retrieval, one wants to rank documents according to relevance to a query; in natural language processing, one wants to rank alternative parses or translations of a sentence; in collaborative filtering, one wants to rank items according to a user's likes and dislikes; in computational biology, one wants to rank genes according to relevance to a disease. Consequently, there has been much interest in ranking in recent years, with a variety of methods being developed and a whole host of new applications being discovered. This workshop aims to bring together researchers interested in the area to share their perspectives, identify persisting challenges as well as opportunities for meaningful dialogue and collaboration, and to discuss possible directions for further advances and applications in the future. One of the primary goals of the workshop will be to reach out to a broad audience. To this end, we will have talks on topics ranging from more statistically/mathematically oriented approaches to ranking, to newer application areas. A second goal will be to bring to the fore a range of questions that are currently being debated within the community, for example via a panel discussion between experts in the field. Overall, the workshop will aim to provide a forum that showcases recent advances in ranking to the broader community, facilitates open debate on some of the questions in this area, and helps catalyze further interest among those new to the topic. FORMAT ------ This is a one-day workshop that will follow the 23rd Annual Conference on Neural Information Processing Systems (NIPS 2009). The workshop will consist of two 3-hour sessions. There will be 2-4 invited talks by experts in the area, and 5-8 short talks. Depending on interest and submissions, we may also have a short poster/demo session. There will be time at the end of each talk/session for questions and discussion. We also intend to have a panel discussion that will be moderated by the organizers and that will bring together leading figures from both academia and industry for discussion and debate. Keynote Lecture --------------- * Persi Diaconis, Stanford University (Tentative) Invited Talks ------------- * Ralf Herbrich, Microsoft Research Cambridge * Lek-Heng Lim, University of California, Berkeley Contributed Talks ----------------- These will be based on submissions of short papers. See below for details. CALL FOR PAPERS --------------- We invite submissions of short papers addressing all aspects of ranking in machine learning, data mining, and statistics, as well as related application areas. These include for example: * algorithms for ranking * mathematical/statistical analyses of ranking * relationships between ranking and other problems * applications of ranking in information retrieval, natural language processing, collaborative filtering, computational biology, computer vision, and other areas * benchmark data sets for ranking * challenges in applying or analyzing ranking methods We also welcome papers on ranking that do not fit into one of the above categories, as well as papers that describe work in progress. Please note that papers that have previously appeared (or have been accepted for publication) in a journal or at a conference or workshop, or that are being submitted to another workshop, are not appropriate for this workshop. All papers presented at the workshop will be made available as electronic proceedings. A print version will be distributed at the workshop. Submission Instructions ----------------------- Submissions should be upto 4 pages in length using NIPS style files (available at http://web.mit.edu/shivani/www/Ranking-NIPS-09/StyleFiles/), and should include the title, authors' names, postal and email addresses, and a brief abstract. Email submissions (in pdf or ps format only) to shivani at mit.edu with subject line "Workshop Paper Submission". The deadline for submissions is Friday October 23, 5:00 pm EDT. Submissions will be reviewed by the program committee and authors will be notified of acceptance/rejection decisions by Wednesday November 11. Final versions of accepted papers will be due on Wednesday November 18. Please note that one author of each accepted paper must be available to present the paper at the workshop. IMPORTANT DATES --------------- First call for papers -- September 15, 2009 Paper submission deadline -- October 23, 2009 (5:00 pm EDT) Notification of decisions -- November 11, 2009 Final papers due -- November 18, 2009 Workshop -- December 11, 2009 ORGANIZERS ---------- * Shivani Agarwal, MIT * Chris J.C. Burges, Microsoft Research * Koby Crammer, The Technion CONTACT ------- Please direct any questions to shivani at mit.edu. ************************************************************************ From feldman at ICSI.Berkeley.EDU Fri Sep 18 11:29:32 2009 From: feldman at ICSI.Berkeley.EDU (Jerry Feldman) Date: Fri, 18 Sep 2009 08:29:32 -0700 Subject: Connectionists: Utility, neural codes Message-ID: <4AB3A75C.5030105@icsi.berkeley.edu> There is a new survey article *Ecological expected utility and the mythical neural code* now available on SpringerLink *http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s11571-009-9090-4 *This is a nice hyper-linked version. The abstract is: Neural spikes are an evolutionarily ancient innovation that remains nature?s unique mechanism for rapid, long distance information transfer. It is now known that neural spikes sub serve a wide variety of functions and essentially all of the basic questions about the communication role of spikes have been answered. Current efforts focus on the neural communication of probabilities and utility values involved in decision making. Significant progress is being made, but many framing issues remain. One basic problem is that the metaphor of a neural code suggests a communication network rather than a recurrent computational system like the real brain. We propose studying the various manifestations of neural spike signaling as adaptations that optimize a utility function called ecological expected utility. If you can't get access, you could ask me for a preprint. ** From byronyu at stanford.edu Mon Sep 21 12:19:55 2009 From: byronyu at stanford.edu (Byron Yu) Date: Mon, 21 Sep 2009 09:19:55 -0700 (PDT) Subject: Connectionists: Announcing Cosyne 2010 Message-ID: ================================================================= Computational and Systems Neuroscience (Cosyne) MAIN MEETING 25 - 28 Feb, 2010 Salt Lake City, Utah WORKSHOPS 1 - 2 Mar, 2010 Snowbird Ski Resort, Utah http://cosyne.org ABSTRACT SUBMISSION OPENS: 20 Oct 2009 ABSTRACT SUBMISSION DEADLINE: 20 Nov 2009 ================================================================= Cosyne is an annual meeting providing an inclusive forum for the exchange of experimental and theoretical approaches to problems in systems neuroscience. The meeting is expected to draw over 500 researchers from a wide variety of disciplines. The MAIN MEETING is organized in a single track, and consists of both oral and poster sessions. Some oral presentations are invited (see below), while others are selected based on short submitted abstracts. Poster presentations are also selected from the submitted abstracts. The WORKSHOPS are held in 6-10 parallel sessions, allowing for more in-depth discussion of specialized topics. CONFIRMED INVITED SPEAKERS: - Keynote: Clay Reid (Harvard Medical School) - Tirin Moore (Stanford University) - Jackie Schiller (Technion) - Eve Marder (Brandeis University) - Michael Platt (Duke University) - Daphne Bavelier (University of Rochester) - John Lisman (Brandeis University) - Tony Zador (Cold Spring Harbor Laboratories) - Adrienne Fairhall (University of Washington) - Howard Berg (Harvard University) Cosyne 2010 will include a special symposium in honour of Horace Barlow, featuring talks by: - Honorary Lecturer: Horace Barlow (Cambridge University) - Geoff Hinton (University of Toronto) - Bill Geisler (University of Texas) - David Field (Cornell University) EXECUTIVE COMMITTEE: - Tony Zador (Cold Spring Harbor Laboratory) - Alex Pouget (University of Rochester) - Zach Mainen (Instituto Gulbenkian de Ciencia) ORGANIZING COMMITTEE: - General Chair: Maneesh Sahani (University College London) - Program Chairs: Anne Churchland (University of Washington) and Bartlett Mel (University of Southern California) - Workshop Chairs: Adam Kohn (Yeshiva University) and Mark Laubach (Yale University) - Communications Chair: Byron Yu (Stanford University and CMU) ADVISORY BOARD: - Matteo Carandini (University College London) - Eero Simoncelli (New York University) - Peter Dayan (University College London) - Steven Lisberger (UC San Francisco) - Karel Svoboda (Howard Hughes Medical Institute) From pascal.fua at epfl.ch Mon Sep 21 07:13:06 2009 From: pascal.fua at epfl.ch (Pascal Fua) Date: Mon, 21 Sep 2009 13:13:06 +0200 Subject: Connectionists: PhD Candidate Positions in Computer Vision at EPFL Message-ID: <4AB75FC2.2060602@epfl.ch> EPFL's Computer Vision laboratory (http://cvlab.epfl.ch) has openings for PhD candidates interested in modeling the shape and connectivity of neurons from light and electron microscope images. The ultimate goal of this line of research is to better understand neural circuitry and brain function. For more details about our research activities in this area, see http://cvlab.epfl.ch/research/medical/neurons/. For practical information about EPFL's doctoral program and life in Lausanne, see http://acide.epfl.ch/webdav/site/acide/shared/phdguide.pdf. Education: Masters degree in Computer Science or related field with experience in the areas of Computer Vision or Medical Image Processing. A strong background in Mathematics is desirable. Applying: 1. Apply to our doctoral program, as explained under http://phd.epfl.ch/page55508.html. 2. Specify in the application form that you are interested by Prof. Fua's CVLab. There is no need to contact Prof. Fua directly as your application will be forwarded to him. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From pascal.fua at epfl.ch Mon Sep 21 07:13:26 2009 From: pascal.fua at epfl.ch (Pascal Fua) Date: Mon, 21 Sep 2009 13:13:26 +0200 Subject: Connectionists: Post-Doctoral Position in Computer Vision at EPFL Message-ID: <4AB75FD6.7070201@epfl.ch> EPFL's Computer Vision Laboratory (http://cvlab.epfl.ch/) has an opening for a post-doctoral fellow in the field of perception. The position is initially offered for 12 months and can be extended for up to 4 years. Description: The Computer Vision Laboratory is involved in modeling the shape and connectivity of neurons from light and electron microscope images. The ultimate goal of this line of research is to better understand neural circuitry and brain function. For more details about our research activities in this area, see http://cvlab.epfl.ch/research/medical/neurons/. Position: The Computer Vision laboratory offers a creative international environment, a possibility to conduct competitive research on a global scale, and involvement in teaching. There will be ample opportunities to cooperate with some of the best groups in Europe and the USA. EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers away from the city of Geneva. Salaries are in the range CHF 70000 to 80000 per year, the precise amount to be determined by EPFL's department of human resources. Education: Applicants are expected to have finished, or be about to finish their Ph.D. degrees, to have a strong background in the area of Computer Vision and/or Medical Image Processing, and to have a track record of publications in top conferences and journals. Strong programming skills (C or C++) are a plus. French language skills are not required, English is mandatory. Application: Applications must be sent by email to Prof. P. Fua (pascal.fua at epfl.ch). They must contain a statement of interest, a CV, a list of publications, and the names of three references. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From antonior at ffclrp.usp.br Mon Sep 21 13:50:57 2009 From: antonior at ffclrp.usp.br (Antonio Carlos Roque da Silva Filho) Date: Mon, 21 Sep 2009 14:50:57 -0300 Subject: Connectionists: LASCON 2010: Third Latin American School on Computational Neuroscience (final call for applications) Message-ID: <200909211450.AA1209925818@srv1.ffclrp.usp.br> **** Apologies for cross-posting **** 3rd Latin American School on Computational Neuroscience - LASCON 2010 January 17 - February 9, 2010, Ribeirao Preto, Brazil http://neuron.ffclrp.usp.br/LASCON FINAL CALL FOR APPLICATIONS Dear Colleagues, Following the success of the previous two editions of LASCON (Latin American School on Computational Neuroscience), held in 2006 and 2008, I am pleased to announce the 3rd LASCON, which will take place between January 17th and February 9th 2010 in Ribeirao Preto, Brazil. LASCON aims at introducing advanced undergraduate and graduate students to the use of computational and mathematical methods for modeling neurons and neuronal circuits. These models will be ilustrated with the use of programs like neuroConstruct, GENESIS, NEURON, XPPAUT and Matlab. The school will last for 24 days, and will consist of theoretical lectures and hands on tutorials given by the lecturers and computational exercises made by the students. Students also will have to work on individual research projects, which they will present orally at the end of the school. Lectures and tutorials will be organized into three tracks: Track 1: Realistic neural modeling; Track 2: Simplified neural modeling and phase-plane methods of analysis; Track 3: Plasticity and Learning The following researchers will be in charge of lectures and tutorials: Alessandro Treves Arnd Roth Avrama Blackwell David Beeman Gennady Cymbalyuk Reynaldo Pinto Volker Steuber William Lytton There will also be some invited lecturers and tutors (mostly former LASCON students) who will help students and lecturers during the school. The number of students is limited to 22 and applications should be made electronically via the application form in the school's web page (http://neuron.ffclrp.usp.br/LASCON). Applicants are also requested to submit a detailed CV (in English) and to provide two letters of recommendation. Costs for accommodation and meals will be covered by the school organization. In the selection procedure, priority will be given to Latin-American students, but students from other parts of the world are encouraged to apply as well. The application deadline has been postponed (due to requests) to October 2nd 2009. I am looking forward to see you in Ribeirao Preto. Best regards, A. Roque, LASCON Organizer Antonio Roque Departamento de Fisica e Matematica FFCLRP, Universidade de Sao Paulo 14040-901 Ribeirao Preto-SP Brazil - Brasil Tels: +55 16 3602-3768 (office); +55 16 3602-3859 (lab) FAX: +55 16 3602-4887 E-mails: antonior at neuron.ffclrp.usp.br antonior at ffclrp.usp.br URL: http://neuron.ffclrp.usp.br ________________________________________________________________ Sent via the WebMail system at srv1.ffclrp.usp.br From arthur.gretton at googlemail.com Mon Sep 21 15:23:37 2009 From: arthur.gretton at googlemail.com (arthur gretton) Date: Mon, 21 Sep 2009 15:23:37 -0400 Subject: Connectionists: Call for Contributions: NIPS 2009 Workshop on Temporal Segmentation Message-ID: <6ab54c960909211223l49ed39abueb7f15d5fdbe57f1@mail.gmail.com> Call for NIPS 2009 Workshop on "Temporal Segmentation: perspectives from statistics, machine learning, and signal processing." Submissions are solicited for the workshop to be held on December 11th/ 12th 2009 at this year's NIPS workshop session in Whistler, Canada. The workshop will focus on temporal segmentation of signals. This encompasses retrospective multiple change-point estimation, online change-point detection, as well as anomaly detection and fault isolation. The workshop is meant to be broadly interdisciplinary, representing an opportunity to cross-fertilize ideas from different backgrounds and to explore current open topics in temporal segmentation. Submissions are not constrained regarding the applications in which temporal segmentation is of interest: these can include speaker/audio processing, financial time series, video, motion capture, bioinformatics, network intrusion detection, etc. Presentations on closely related topics such as sequential decision making, temporal classification, structured prediction with temporal/spatial constraints, are also encouraged. Submissions may focus on theoretical, methodological, and computational aspects of temporal segmentation. Accepted submissions will be presented either as talks or during the workshop poster session, depending on the proposals. The deadline for submission will be October 23th 2009 and notifications will be sent out by November 2nd 2009. The submission should be at most four pages long in NIPS format, and should be sent to "temposegment.nips09 at gmail.com". The program committee consists of the workshop organizers and the invited speakers. Current workshop information including the list of invited speakers together with a preliminary schedule may be found at: http://www.tsi.enst.fr/~zharchao/nips09/nips09.html as well as other important information. Your Workshop Organizers, Stephane Canu Olivier Cappe Arthur Gretton Zaid Harchaoui (primary organizer) Alain Rakotomamonjy Jean-Philippe Vert From jean-pascal.pfister at eng.cam.ac.uk Wed Sep 23 09:29:29 2009 From: jean-pascal.pfister at eng.cam.ac.uk (Jean-Pascal Pfister) Date: Wed, 23 Sep 2009 14:29:29 +0100 Subject: Connectionists: Call for abstract: NIPS 2009 workshop on normative electrophysiology Message-ID: ------------------------------- CALL FOR ABSTRACT ------------------------------- *NIPS 2009 WORKSHOP ON NORMATIVE ELECTROPHYSIOLOGY* We are now soliciting abstracts (see format below) for the NIPS 2009 Workshop on : Normative Electrophysiology: explaining cellular properties of neurons from first principles. Authors of accepted abstracts will be entitled to present a poster during the workshop. *Webpage* http://blg.eng.cam.ac.uk/t/bin/view/Public/Lengyel/EventNips09 *Key dates* - abstract submission deadline: October 15th, 2009 - Notification of acceptance: October 30th, 2009 - Workshop: December 11th, 2009 *Workshop description* In the past decades, computational neuroscience has seen a burgeoning of normative approaches. These studies made significant advances in formulating formal theories of optimality, and optimal computations, identifying relevant physical and computational constraints under which those computations need to be implemented, developing analytical methods and numerical algorithms to solve the resulting constrained optimization problems, and relating these solutions to biological substrates. However, only a relatively small fraction of these studies attempted to make specific predictions about, and thus interpret in normative terms, the cellular-level electrophysiological properties of individual neurons or synapses. Small in numbers it may be, the potential impact of this particular line of research cannot be ignored as such theories may provide a way to bridge the gap between the cellular-molecular and the systems-level branches of neuroscience by connecting low-level properties of the nervous system to its high-level functions. Our workshop aims to highlight and discuss recent work in this field. Since much of the theoretical background in this field has been adopted from information theory, machine learning, and related fields, we expect that not only experimental and computational neuroscientists, but also machine learning researchers will be interested in the general topic and the specific talks. *Speakers* - Sophie Den?ve, ?cole Normale Sup?rieure - Adrienne Fairhall, U Washington - M?t? Lengyel, U Cambridge - Jean-Pascal Pfister, U Cambridge - Tatyana Sharpee, Salk Institute - Taro Toyoizumi, Columbia U *Workshop location* Westin Resort and Spa / Hilton Whistler Resort and Spa Whistler, B.C., Canada *Submission instructions* Please submit abstracts (maximum 300 words) in plain text format by email directly to jean-pascal.pfister at eng.cam.ac.uk with the mention "Normative Electrophysiology". *Organizers* Jean-Pascal Pfister (primary contact) Computational and Biological Learning Lab Department of Engineering University of Cambridge Trumpington Street, Cambridge CB2 1PZ United Kingdom tel: +44 (0)1223 748 506 fax: +44 (0)1223 332 662 e-mail: jean-pascal.pfister at eng.cam.ac.uk M?t? Lengyel Computational and Biological Learning Lab Department of Engineering University of Cambridge Trumpington Street, Cambridge CB2 1PZ United Kingdom tel: +44 (0)1223 748 532 fax: +44 (0)1223 332 662 e-mail: m.lengyel at eng.cam.ac.uk -- Jean-Pascal Pfister, PhD Computational and Biological Learning Lab Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ, UK tel: +44 (0)1223 748 506, fax: +44 (0)1223 332 662 email: jean-pascal.pfister at eng.cam.ac.uk http://www.eng.cam.ac.uk/~jptp2/ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090923/475bb803/attachment-0001.html From kirsch at bccn.uni-freiburg.de Mon Sep 21 09:55:05 2009 From: kirsch at bccn.uni-freiburg.de (Janina Kirsch) Date: Mon, 21 Sep 2009 15:55:05 +0200 Subject: Connectionists: Position for a Junior Scientist (Research Associate) in Neurophysiology, University of Freiburg Message-ID: <6EA2180A5AB348D6910C8FF3D27C86F2@janina> % apologies for multiple postings % Junior Scientist Position (Research Associate) at the Laboratory for Biomicrotechnology, Dept. of Microsystems Engineering, Faculty of Engineering University of Freiburg, Freiburg The Laboratory for Biomicrotechnology ( Prof. Ulrich Egert) offers a junior scientist position ( A13, up to 4 years) for a biologist with expertise on electrophysiology, cell culture of neuronal networks, neurophysiology in acute brain slices and/or Ca-imaging. We are interested in the mechanisms and structures underlying the activity dynamics in neuronal networks and the processing of neuronal activity within the network. In joint projects with computational neuroscientists we investigate how the biological neuronal networks process incoming stimuli, what determines intrinsic activity, how pathological dynamics arise and how to contain them. To address these questions we use acute brain slices, cell cultures and animal models with a variety of techniques. A central technology is extracellular recording the neuronal activity with microelectrode arrays to analyze the spatio-temporal structure of activity. Recordings with these arrays are combined with paired intracellular recordings, calcium imaging, microstimulation and advanced data analyses. New technical and analysis tools are developed as needed in collaborations with microsystems engineers. This work is embedded in the Bernstein Center for Computational Neuroscience Freiburg (BCCN Freiburg) and the new Bernstein Focus Neurotechnology - Freiburg/Tuebingen. The successful candidate is expected to contribute to the teaching and training program of these iniatives. Candidates should have outstanding academic records and an interest in translational neuroscience and neurotechnology. The position is open immediately until filled. For further information, please contact Prof. Ulrich Egert (Head of laboratory) or Dr. Janina Kirsch (Coordinator for the Teaching & Training Programs). -- Dr. Janina Kirsch -- Coordinator for the Teaching & Training Programs Bernstein Center Freiburg Albert-Ludwig University of Freiburg Hansastr. 9a D - 79104 Freiburg Germany Phone: +49 (0) 761 203-9575 Fax: +49 (0) 761 203-9559 Email: kirsch @bcf.uni-freiburg.de Web: www.bcf.uni-freiburg.de -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090921/212af83b/attachment-0001.html From celiasmith at uwaterloo.ca Wed Sep 23 09:52:11 2009 From: celiasmith at uwaterloo.ca (Chris Eliasmith) Date: Wed, 23 Sep 2009 09:52:11 -0400 Subject: Connectionists: Two tenure track positions Message-ID: <4ABA280B.6070007@uwaterloo.ca> Feel free to contact me if you would like any additional information on these positions. Posted by: Chris Eliasmith (celiasmith at uwaterloo.ca) Director, CTN ------------------------------------------- Tenure Track Positions in Theoretical and Systems Neuroscience The Department of Biology at the University of Waterloo, in conjunction with the Centre for Theoretical Neuroscience (CTN), is seeking two Faculty at the Assistant or Associate Professor level in the area of Neuroscience. Applicants involved in the measurement and/or modeling of neural circuits and systems (systems neuroscience) are especially encouraged to apply. Applicants, both experimental or theoretical in approach, should demonstrate the linkage of their program to the Department of Biology and the CTN. One successful applicant will be invited to apply for a Tier II Canada Research Chair. Duties of the successful applicants will include research, teaching at the undergraduate and graduate levels in the Department of Biology, and graduate student supervision. Applicants must have a Ph.D., relevant postdoctoral experience with a strong indication of independent productivity, and be prepared to establish active research programs. Applicants should send their curriculum vitae, the names of three individuals willing to furnish letters of reference, and a brief outline of their future research and teaching direction to: Dr. David R. Rose, Professor and Chair, Department of Biology, University of Waterloo, Waterloo, Ontario, N2L 3G1, CANADA. This information may also be sent to the Biology Chair's Secretary: Mrs. Gini Kennings at: givan at scimail.uwaterloo.ca Review of applications will commence November 1, 2009, but applications will be accepted until the positions are filled. Anticipated starting date is on or after July 1, 2010. http://www.biology.uwaterloo.ca/ http://ctn.uwaterloo.ca/ From drwuusc at gmail.com Wed Sep 23 14:00:09 2009 From: drwuusc at gmail.com (Dongrui Wu) Date: Wed, 23 Sep 2009 11:00:09 -0700 Subject: Connectionists: Postdoc position in Augmented Cognition and psychophysiological cognitive assessment applications, University of Southern California, Los Angeles Message-ID: A Postdoctoral Associate for research in Augmented Cognition and psychophysiological cognitive assessment applications is being sought at for a joined collaborative position between the University of Southern California?s Institute for Creative Technologies (USC/ICT), the Army Research Labs (ARL); Quantum Applied Science & Research (QUASAR). USC/ICT?s Laboratory for Virtual Reality, Psychology, and Social Neuroscience is directed by Thomas D. Parsons, PhD. The lab is engaged in a broad program of research on the brain mechanisms that underlie neurocognitive functioning and emotion regulation in persons throughout the life course. We make use of Virtual and Augmented Reality to study associations between the essential neural correlates of cognitive functioning and emotion regulation to assess the mechanisms of brain-behavior relations. The Army Research Laboratory is undertaking an ambitious effort to translate the wealth of non-medical, human-system integration (HSI)?supporting neuroscience into the Army. The HSI relationship includes interactions and interfaces among humans and such entities as machines, communications systems, network entities, knowledge bases, and advanced decision systems. QUASAR is a world leader in non-invasive biomedical instrumentation. Our work builds on our revolutionary bioelectric sensors integrated with precision hardware and robust algorithms to produce systems that evaluate cognitive and physiological states for medical, military, and consumer applications. The research effort will focus on developing physiologic gauges designed to infer users? cognitive and physical readiness states from non-invasive sensor data in controlled lab and virtual-reality environments as well as real-world simulations. The postdoc will be involved in various research aspects of technology development, including experimental design, hardware integration, data collection and analysis, and algorithm optimization. Working at USC/ICT, the postdoc will integrate QUASAR?s advanced physiological monitoring sensors with a battery of USC/ICT?s simulation and training programs. The associate will collect physiological data and develop gauges for classification of cognitive and physical states during various behavioral paradigms, including learning, military training, neurocognitive evaluation. Work will involve occasional travel to ARL in Maryland. The ideal candidate will be experienced with collecting and analyzing electrophysiological signals from human subjects (including EEG/ECG/EMG). Experience in programming languages (Matlab, python, C/C++, Maya, 3dsMax, Gamebryo, Ogre, Delta3d, Source Game Engine), as well as knowledge of machine learning algorithms are desirable. We are seeking a reliable team-player with good oral and written communication skills who is capable of independent work in a multi-disciplinary team. Our new team member will be a self-driven individual who is meticulous and dedicated to professional excellence, and highly motivated to seek new creative solutions to QUASAR and USC/ICT?s cutting-edge projects. Applicants should have a PhD in biomedical engineering, neuroscience, cognitive psychology, or a related field. US citizenship required. If you feel you skills match our requirements, please email us your CV at: tparsons at ict.usc.edu *Job Location Information:* Institute for Creative Technologies 13274 Fiji Way, Marina del Rey, CA. 90292-4019 -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090923/567826ef/attachment.html From sumitb at microsoft.com Wed Sep 23 13:08:35 2009 From: sumitb at microsoft.com (Sumit Basu) Date: Wed, 23 Sep 2009 17:08:35 +0000 Subject: Connectionists: Call for Abstracts: NIPS 2009 Workshop on Analysis and Design of Algorithms for Interactive Machine Learning Message-ID: [note to moderator: the previous version never came through; thus the resend] --------------------------------------------------------------------------------------------------------------------- ADA-IML'09: Workshop on Analysis and Design of Algorithms for Interactive Machine Learning at NIPS 2009 12/11 or 12/12, TBD http://research.microsoft.com/~sumitb/adaiml09 ***Deadline for abstract submission: Friday, October 30, 5pm PST*** --------------------------------------------------------------------------------------------------------------------- INTRODUCTION AND GOALS OF THE WORKSHOP The traditional role of the human operator in machine learning problems is that of a batch labeler, whose work is done before the learning even begins. However, there is an important class of problems in which the human is interacting directly with the learning algorithm as it learns. Canonical problem scenarios which fall into this space include active learning, interactive clustering, query by selection, learning to rank, and others. Such problems are characterized by three main factors: 1. the algorithm requires input from the human during training, in the form of labels, feedback, parameter guidance, etc. 2. the user cannot express an explicit loss function to optimize, either because it is impractical to label a large training set or because they can only express implicit preferences. 3. the stopping criterion is performance that's "good enough" in the eyes of the user. The goal of this workshop is to focus on the machine learning techniques that apply to these problems, both in terms of surveying the major paradigms and sharing information about new work in this area. Through a combination of invited talks, discussions, and posters, we hope to gain a better understanding of the available algorithms and best practices for this space, as well as their inherent limitations. ? CALL FOR ABSTRACTS We invite all researchers interested in presenting at the workshop to submit a one-page abstract of their work. The presentation format will be a spotlight summary talk along with a poster session later in the afternoon. We encourage presentations on new, developing ideas, as well as previously published work the authors would like to discuss in this forum. Feel free to email us if you are concerned about whether your work is appropriate for the workshop. Note that there will not be formal proceedings for the workshop, so authors need not be concerned about publishing work they present here at a later venue. Please send your submissions (as PDF) by email to sumitb at microsoft dot com with the subject line "ADA-IML'09 Abstract: [submission title]" ***Deadline for submission: Friday, October 30, 5pm PST*** INVITED SPEAKERS We have a number of invited speakers who will be presenting at the workshop. -Jerry Zhu (University of Wisconsin, Madison) -Jure Leskovec?(Stanford) -Carlos Guestrin (CMU) -Rich Carauna (Microsoft Research) SCHEDULE Morning (7:30-10:30) ? I. Introduction (0.5 hr) II. Invited Talks (2 talks - 1.0 hr) III. Poster preview talks (1.0 hr) IV.?Developing a Syllabus/Bibliography for Interactive Machine Learning (30 mins)* Afternoon (3:30-6:30) V. Invited Talks (2 talks - 1 hr) VI. Poster Session (1.5 hrs) VII. Open Problems, Challenges, and Opportunities (30 mins) *Note that the syllabus-in-progress will be left on the board so that ?participants may continue to contribute to it during the poster ?session, final discussion, etc. ORGANIZERS Sumit Basu (sumitb at microsoft dot com) and Ashish Kapoor (akapoor at microsoft dot com) From jns9 at cornell.edu Wed Sep 23 16:36:39 2009 From: jns9 at cornell.edu (Jascha Sohl-Dickstein) Date: Wed, 23 Sep 2009 13:36:39 -0700 Subject: Connectionists: learning, partition functions, and probability flow Message-ID: Dear Colleagues, It is my pleasure to draw your attention to a recent pre/e-print describing a new technique for parameter estimation in probabilistic models with intractable partition functions. http://arxiv.org/abs/0906.4779 Minimum Probability Flow Learning. Jascha Sohl-Dickstein, Peter Battaglino, Michael R DeWeese. Learning in probabilistic models is often severely hampered by the general intractability of the normalization factor and its derivatives. Here we propose a new learning technique that obviates the need to compute an intractable normalization factor or sample from the equilibrium distribution of the model. This is achieved by establishing dynamics that would transform the observed data distribution into the model distribution, and then setting as the objective the minimization of the initial flow of probability away from the data distribution. Score matching, minimum velocity learning, and certain forms of contrastive divergence are shown to be special cases of this learning technique. We demonstrate the application of minimum probability flow learning to parameter estimation in Ising models, deep belief networks, multivariate Gaussian distributions and a continuous model with a highly general energy function defined as a power series. In the Ising model case, minimum probability flow learning outperforms current state of the art techniques by approximately two orders of magnitude in learning time, with comparable error in the recovered parameters. It is our hope that this technique will alleviate existing restrictions on the classes of probabilistic models that are practical for use. - arXiv (2009) vol. cs.LG Best, Jascha Sohl-Dickstein(, Peter Battaglino, Michael R DeWeese) From odobez at idiap.ch Wed Sep 23 16:07:17 2009 From: odobez at idiap.ch (Jean-Marc Odobez) Date: Wed, 23 Sep 2009 22:07:17 +0200 Subject: Connectionists: Doctoral and postdoctoral positions in multimodal processing and robotics at Idiap Research Institute Message-ID: <4ABA7FF5.5060407@idiap.ch> ---------------------------------------------------- Doctoral and postdoctoral positions in multimodal processing and robotics at Idiap Research Institute ---------------------------------------------------- The IDIAP Research Institute (www.idiap.ch), associated with EPFL (Swiss Federal Institute of Technology, Lausanne) seeks qualified candidates for one doctoral and one postdoctoral research position in computer vision, audio processing, and machine learning for multimodal interaction in robots. Both positions are available immediately. The research will be conducted in the context of a new project funded by the European Commission (five partners in four countries). The positions offer the opportunity to collaborate with prominent European research teams in robotics, vision, and multimodal interaction. The overall goal of the project is to endow humanoid robots with audio-visual sensing and interaction cabilities for navigation in complex environments, person localization, and social interaction. Specific research areas involve the design of perceptual algorithms to recognize human nonverbal behavior from audio-visual sensors; new approaches to identify people interactions and relationships; and principled methods to exploit physical and social context for effective human-robot interaction. The ideal Ph.D student, who will be enrolled in EPFL's doctoral program, will have a master's degree in computer science or electrical engineering with a strong mathematical background. Experience in statistical learning theory, image processing, computer vision, or audio processing is a plus. Strong programming skills are expected. The position is for four years. The postdoctoral researcher should have a strong background in machine learning, computer vision, audio processing, or robotics. Experience in one or several of the following areas is required: human tracking, event recognition and discovery, and human-robot or human-computer multimodal interfaces. The applicant should also have strong programming skills. The position is for one year with possibilities of renewal based on performance. Salaries are competitive. Idiap is located in Martigny in Valais, a scenic region in the south of Switzerland surrounded by the highest mountains of Europe, which offers multiple recreational activities, including hiking, climbing, and skiing, as well as varied cultural activities, all within close proximity to Lausanne and Geneva. Idiap is an equal opportunity employer and offers a young, multicultural environment where English is the main working language. For further details and application please contact: Jean-Marc Odobez (odobez at idiap.ch, tel : +41 (0)27 721 77 26) Daniel Gatica-Perez (gatica at idiap.ch, tel : +41 (0)27 721 77 33) From juergen at idsia.ch Fri Sep 25 13:24:05 2009 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Fri, 25 Sep 2009 19:24:05 +0200 Subject: Connectionists: 3 postdocs / several PhD students at the Swiss AI Lab IDSIA Message-ID: Recently three of my postdocs accepted professorships abroad. Now I am looking for three FRESH postdocs to replace them! We also encourage applications for PhD fellowships. INSTRUCTIONS AND DETAILS UNDER http://www.idsia.ch/~juergen/sn2010.html Summary. We expect expertise / interest in areas related to: Recurrent Neural Networks & Program Learning: http://www.idsia.ch/~juergen/rnn.html Reinforcement Learning & Evolution: http://www.idsia.ch/~juergen/rl.html http://www.idsia.ch/~juergen/evolution.html Robot Learning (e.g., vision-based robots) http://www.idsia.ch/~juergen/learningrobots.html In particular, self-modeling robots: http://www.idsia.ch/~juergen/resilientmachines.html Theory of Universal Problem Solvers & Universal AI: http://www.idsia.ch/~juergen/unilearn.html http://www.idsia.ch/~juergen/goedelmachine.html http://www.idsia.ch/~juergen/oops.html Optimal Program Search: http://www.idsia.ch/~juergen/oops.html Unsupervised Learning and Deep Nets: http://www.idsia.ch/~juergen/ica.html Artificial Curiosity & Creativity / Theory of Novelty & Surprise: http://www.idsia.ch/~juergen/interest.html SALARY: Postdocs: SFR 72,000/year (~ US$ 70,000/year as of 25 Sept 2009). PhD students: SFR 38,000/year (~ US$ 37,000/year as of 25 Sept 2009). INTERVIEWS at IDSIA or at the Singularity Summit in NYC (3-4 Oct) http://www.singularitysummit.com/program or at the EUCogII meeting in Hamburg (10-11 Oct) http://www.eucognition.org/index.php?page=first-members-conference-program IDSIA is affiliated with the University of Lugano and SUPSI. It is one of the world's top AI labs, according to Business Week, located in Switzerland, the most competitive country, according to the World Economic Forum, and also the top science nation, according to per capita rankings based on citations, patents, Nobel Prizes, etc. Related jobs (not all of them filled yet): http://www.idsia.ch/~juergen/eu2009.html http://www.idsia.ch/~juergen/sinergia2008.html Juergen Schmidhuber Director of the Swiss AI Lab IDSIA, Lugano Professor of Artificial Intelligence, Univ. Lugano Professor SUPSI, Manno-Lugano, Switzerland Head of CogBotLab at TU Muenchen, Germany http://www.idsia.ch/~juergen/ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20090925/15b740a1/attachment.html From m.lengyel at eng.cam.ac.uk Mon Sep 28 09:57:24 2009 From: m.lengyel at eng.cam.ac.uk (=?ISO-8859-1?Q?M=E1t=E9_Lengyel?=) Date: Mon, 28 Sep 2009 14:57:24 +0100 Subject: Connectionists: postdoc in computational neuroscience Message-ID: <1AB3E890-40E5-4631-B8B3-F142932D6903@eng.cam.ac.uk> UNIVERSITY OF CAMBRIDGE The University is committed to equality of opportunity DEPARTMENT OF ENGINEERING Senior Research Associate in Computational Neuroscience A position exists for a Senior Research Associate (equivalent of a senior postdoctoral fellow) to work on theories of spike timing-based memory in the hippocampus. The project is funded by the Wellcome Trust and will involve work in the group of Mate Lengyel at the recently established Computational and Biological Learning Lab (learning.eng.cam.ac.uk) in close collaboration with Peter Dayan (Gatsby Computational Neuroscience Unit, UCL, www.gatsby.ucl.ac.uk). The project also involves collaboration with the groups of Ole Paulsen (Department of Physiology, Anatomy and Genetics, Oxford University, noggin.physiol.ox.ac.uk) and Francesco Battaglia (SILS Center for Neuroscience, University of Amsterdam, http://www.sils-cns.nl/PGBattaglia.html) providing direct access to relevant in vitro and in vivo electrophysiological data. The aim of the project is to develop normative theories of spike- timing based interactions (neural dynamics and synaptic plasticity rules) between hippocampal neurons for efficient memory processing that make testable prediction at the electrophysiological level (starting from Lengyel et al, Nat Neurosci 2005; Lengyel & Dayan, Advances in NIPS 2007). The successful candidate will have a strong analytical background and demonstrable interest in theoretical neuroscience. They should have a PhD or equivalent in computational neuroscience, physics, mathematics, computer science, machine learning or a related field. Preference will be given to candidates with sufficient programming skills to run numerical simulations (eg. in C or MatLab) and expertise with neural network models, analysis of dynamical systems, and Bayesian techniques. Familiarity with the neurobiology of the hippocampus is an advantage. The appointment will be for 1 year initially (extendable subject to funding) starting 1 January 2010 or as soon as possible thereafter. Salary is highly competitive and is in the range ?36,532 to ?46,278 p.a. The cover sheet for applications, PD18 is available from www.admin.cam.ac.uk/offices/personnel/forms/pd18/ . Parts I, II and III should be sent, preferably by e-mail, with a letter of application, a statement of research interests, and a CV (in pdf or plain text formats if possible) with the names and full contact details (including e-mail addresses) of three referees to Ms Diane Unwin, Department of Engineering, Trumpington Street, Cambridge, CB2 1PZ, (Tel +44 (0)1223 3 32600, Fax +44 (0)1223 3 32662, email dsu21 at cam.ac.uk ) so as to reach her not later than 9 October 2009. Shortlisted applicants will be interviewed on 23 October, 2009. -- Mate Lengyel, PhD Computational and Biological Learning Lab Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ, UK tel: +44 (0)1223 748 532, fax: +44 (0)1223 332 662 email: m.lengyel at eng.cam.ac.uk web: www.eng.cam.ac.uk/~m.lengyel From esann at dice.ucl.ac.be Mon Sep 28 15:30:25 2009 From: esann at dice.ucl.ac.be (esann@dice.ucl.ac.be) Date: Mon, 28 Sep 2009 21:30:25 +0200 Subject: Connectionists: CFP: ESANN'2010 special sessions Message-ID: <000101ca4072$213a51c0$63aef540$@ucl.ac.be> ESANN'2010 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges (Belgium) - April 28-29-30, 2010 Special sessions ====================================================== The following message contains a summary of all special sessions that will be organized during the ESANN'2010 conference. Authors are invited to submit their contributions to one of these sessions or to a regular session, according to the guidelines found on the web pages of the conference http://www.dice.ucl.ac.be/esann/. Deadline for submissions: November 25, 2009. According to our policy to limit the number of unsolicited e-mails, we gathered all special session descriptions in a single message, and try to avoid sending it to overlapping distribution lists. We apologize if you receive multiple copies of this e-mail despite our precautions. Special sessions that will be organized during the ESANN'2010 conference ========================================================= 1. Sparse representation of data Thomas Villmann (Univ. Apllied Sciences Mittweida, Germany), Frank-Michael Schleif (Univ. Leipzig, Germany), Barbara Hammer (Clausthal Univ. Of Tech., Germany) 2. Computational Intelligence in Biomedicine Paulo J.G. Lisboa (Liverpool John Moores Univ., U.K.), Alfredo Vellido (Tech. Univ. Catalonia, Spain), Jos? D. Mart?n (Univ. Valencia, Spain) 3. Machine learning techniques based on random projections Benjamin Schrauwen (Ghent Univ., Belgium), Amaury Lendasse (Helsinki Univ. of Tech., Finland), Yoan Miche (I.N.P. Grenoble, France) 4. Information Visualization, Nonlinear Dimensionality Reduction, Manifold and Topological Learning Axel Wism?ller (Univ. Rochester, New York, USA), Michel Verleysen (Univ. cat. Louvain, Belgium), Michael Aupetit (CEA, France), John Aldo Lee (Univ. cat. Louvain, Belgium) 5. Computational Intelligence Business Applications Thiago Turchetti Maia (Vetta Group, Brazil), Antonio Braga (Univ. Fed. Minas Gerais, Brazil) 6. Neuro-Symbolic Reasoning: Theory and Applications Massimo De Gregorio (Ist. Cibernetica-CNR, Italy), Priscila M. V. Lima (Univ. Fed. Rio de Janeiro, Brazil), Gadi Pinkas (Center for Academic Studies, Israel) Short descriptions ================== 1. Sparse representation of data ----------------------------------------------------------------------- Organized by: Thomas Villmann (Univ. Apllied Sciences Mittweida, Germany), Frank-Michael Schleif (Univ. Leipzig, Germany), Barbara Hammer (Clausthal Univ. Of Tech., Germany) The amount of data available for investigation and analysis is rapidly growing in various areas of research like in biology/bioinformatics/life sciences, astronomy/astro physics, physics & chemistry or medicine. Many of these data sets are very complex such that advanced methods are needed to extract their inherent but hidden information. Thus, an important task for data processing is to model these data in an adequate manner while keeping the models as simple as possible, i.e. a sparse representation of the data or sparse modelling of the respective underlying problem is demanded. Thereby, sparseness can be seen in different directions such as dimensionality/complexity, information optimum modelling, etc. Examples for spare concepts are the sparse coding of images introduced by Olshausen&Field, dimensionality reduction in supervised and unsupervised learning, relevance learning and feature selection in classification, sparse prototype representations or sparse wavelet representation and signal reconstruction, to mention just few. Sparseness can be achieved by several methodologies which also may include additional knowledge about data to be processed, for example the utilization of functional norms for similarity determination for functional data. The session invites to submit paper about topics in adaptive data processing and machine learning, which explicitly focus on sparseness of data representation or/and sparse models. Example topics could be but are not restricted to - the representation of very large data sets, - dimensionality reduction, - data specific approaches for sparse modelling of special data types like time series or sequences, spectra, images, - information optimum data processing - sparse prototype models for vector quantization 2. Computational Intelligence in Biomedicine ----------------------------------------------------------------------- Organized by: Paulo J.G. Lisboa (Liverpool John Moores Univ., U.K.), Alfredo Vellido (Tech. Univ. Catalonia, Spain), Jos? D. Mart?n (Univ. Valencia, Spain) Computational Intelligence techniques (including, broadly, neural networks, connectionist systems, genetic algorithms, evolutionary programming, fuzzy systems, and hybrid intelligent systems, according to the scope provided by the IEEE-CIS) have made significant inroads over the last two decades in the area of biomedical applications. This is both as beacons of evidence-based medicine and as robust building blocks of medical decision support systems. Systems based on Computational Intelligence techniques should have an important role in defining the methodologies for the next generation of healthcare delivery technologies. This is expected to follow the 4P (personalized, predictive, preventive and participatory) agenda, which demands greater personalization to the needs of the individual patient, a focus on preventive medicine with the support of predictive approaches, as well as greater emphasis on pro-active involvement by the patient at the point of healthcare delivery. This special session aims to be of interest to CI practioners (with a strong focus on Machine Learning) working in the area of biomedicine, but also to those biomedicine researchers that have made CI techniques their tools of choice. The sinergy between both worlds should guarantee that leading-edge techniques become known to medical practitioners and that CI research in biomedicine complies with the real-world requirements of the field. The main topics of interest, any of them based on Computational Intelligence, Machine Learning and otherwise AI-related techniques, include (but are indeed not necessarily limited to): - Methodologies with a focus on model interpretation (including, for instance, visualization, feature selection and extraction, graphs, and rules). - Structured methodologies for multi-modal data (data fusion combining different modalities, e.g.: molecular biomarkers, histology, imaging, electrophysiological measurements and clinical signs). - Methodologies for the analysis of functional and spectral signal and imaging data. - Survival analysis. - Methodologies for computer-based medical decision support and treatment planning. - Current and planned clinical applications. - Methodologies of mining and knowledge discovery applied to medical data. - Pharmaceutical research. All contributions are meant to strike a reasonable balance between theoretical novelty and the originality and appropriateness of the biomedical application. 3. Machine learning techniques based on random projections ----------------------------------------------------------------------- Organized by: Benjamin Schrauwen (Ghent Univ., Belgium), Amaury Lendasse (Helsinki Univ. of Tech., Finland), Yoan Miche (I.N.P. Grenoble, France) Machine learning techniques based on random projections have recently been widely used to perform regression, classification and Time Series prediction tasks. Among the most successful proposed methods lie Reservoir Computing [1], Extreme Learning Machine [2], Associative Neural Networks [3], Optimally-Pruned Extreme Learning Machine [4]?.. One of the reasons for the success of random projections based methods is the extremely good performance in terms of ratio between accuracy and computational time. Indeed, even though random projection based methods are often not the most accurate ones, their usual training (learning) time is orders of magnitude smaller than this of classical methods. Furthermore, these methods are easily parallelized and can thus benefit from the recent improvements in the multi-core architecture of modern computers and video cards. Recent developments in random projection led to groundbreaking advances and different approaches in machine learning. For example, exhaustive and brute force strategies that were not computationally possible became feasible within a reasonable time. This special session is interested in theoretical advances, new random projection methods, new learning or meta-learning strategies and industrial applications for which the ratio accuracy/computational time is crucial. REFERENCES: [1] David Verstraeten, Benjamin Schrauwen, Michiel D`Haene and Dirk Stroobandt: An experimental unification of reservoir computing methods Neural Networks, Vol. 20(3) pp. 391-403 (2007) [2] G.-B. Huang, Q.-Y. Zhu and C.-K. Siew: Extreme Learning Machine: Theory and Applications, Neurocomputing, vol. 70, pp. 489-501, 2006. [3] Miller W. T., Glanz F. H., and Kraft L. G. Cmac: An associative neural network alternative to backpropagation. In Proceedings of the IEEE, volume 70, pages 1561???1567. October 1990. [4] Yoan Miche, Patrick Bas, Christian Jutten, Olli Simula and Amaury Lendasse: A methodology for Building Regression Models using Extreme Learning Machine: OP-ELM, ESANN 2007, European Symposium on Artificial Neural Networks, Bruges (Belgium), pages 457-462. April, 2008. 4. Information Visualization, Nonlinear Dimensionality Reduction, Manifold and Topological Learning ----------------------------------------------------------------------- Organized by: Axel Wism?ller (Univ. Rochester, New York, USA), Michel Verleysen (Univ. cat. Louvain, Belgium), Michael Aupetit (CEA, France), John Aldo Lee (Univ. cat. Louvain, Belgium) To extract useful knowledge from exceedingly growing amounts of high-dimensional data is a ubiquitous challenge throughout science and engineering. Here, information visualization by topological learning is an emerging field which is expected to bring new insights in all areas of the data mining and knowledge discovery process. Nonlinear dimensionality reduction methods and manifold learning techniques are closely related to learning data topology. The differences reside more in the paradigms (preservation of distances, similarities, or topology) than in the fundamental goals: visualizing data in 2D or 3D spaces, or embedding high-dimensional data into lower-dimensional spaces, for information visualization, data compression, reduction, fighting the curse of dimensionality, and more. Recently there has been significant activity in the field, with the publication of many methods based for instance on: - Inner product preservation by spectral techniques (Isomap, locally linear embedding, maximum variance unfolding, Laplacian eigenmaps, etc.); - Weighted distance or similarity preservation by nonlinear optimization techniques (Sammon mapping, curvilinear component analysis, stochastic neighbor embedding, etc.); - Self-organization in various types of topology learning networks (Kohonen feature maps, exploration machines, etc.) Some of these methods can be applied to non-metric data as well. There is no consensus however which method has to be applied in specific circumstances, or which method performs best in general. More critically, most of the published works illustrate the methods on toy examples, or on very few, carefully selected real databases. In addition to these performance issues, there is no consensus either on which paradigm has to be followed: distance preservation, topology preservation, self-organization, other? To stimulate the field of nonlinear dimensionality reduction, manifold and topological learning and its application to information visualization, we invite paper submissions related, but not limited, to the following non-exhaustive list of topics: - Algorithms, theory and applications of nonlinear dimensionality reduction, manifold and topological learning - Information visualization using manifold and topological learning - Spectral clustering and embedding - Linear and non-linear dimensionality reduction - Links between the above-mentioned paradigms - Performance measures for manifold and topological learning - Real-world applications of manifold and topological learning throughout science and engineering, such as in medicine, life and social sciences, astronomy, economics, and the humanities 5. Computational Intelligence Business Applications ----------------------------------------------------------------------- Organized by: Thiago Turchetti Maia (Vetta Group, Brazil), Antonio Braga (Univ. Fed. Minas Gerais, Brazil) There is often a significant research effort from the community to develop new computational intelligence techniques, but much less effort about how to effectively deploy these techniques in real-world business applications. Whenever one goes about applying such techniques to solve existing problems, one must overcome several practical gaps between theory and effective applications. In this special session, we welcome contributions with solutions to these problems. Topics of interest include (and are not limited to): - Improving the execution time of methods to enhance their applicability in real problems; - Improving the robustness and reliability of methods to handle boundary conditions in data; - Development of new human-machine interfaces meant for non-experts, allowing the average user to visualize, interact with, and utilize sophisticated methods; - Automatic and semi-automatic model selection; - Automatic and semi-automatic parameter tuning; - Methodologies and best-practices to collect and prepare data, criteria for model selection, techniques for parameter tuning, and assessment of model fitness; - Methodologies and best-practices to identify solvable business problems, evaluate results, and assess returns on investment; - New insights in the application of computational intelligence techniques to real-life business applications; - Novel applications of computational intelligence techniques to real-world problems. Authors are encouraged to submit works directly addressing any of the above (or correlated) items, as well as works on specific business applications that created innovative solutions to the same problems. Authors are also encouraged to submit works on novel applications of computational intelligence to unexplored business problems. 6. Neuro-Symbolic Reasoning: Theory and Applications ----------------------------------------------------------------------- Organized by: Massimo De Gregorio (Ist. Cibernetica-CNR, Italy), Priscila M. V. Lima (Univ. Fed. Rio de Janeiro, Brazil), Gadi Pinkas (Center for Academic Studies, Israel) The crucial role of logic in knowledge representation and processing is unquestionable. However, mechanical reasoning is often a computationally expensive task, regardless of whether deductive or uncertain reasoning is effected. Furthermore, most reasoning systems do not exhibit inherent noise tolerance and learning capabilities. Over the years, sustained efforts have been made to tackle some of these difficulties by means of Artificial Neural Networks (ANNs). Still, there is room for improvement in several fronts ranging from theoretical and methodological issues to real applications, not to mention efficient solutions to the integration of paradigms. ======================================================== ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews, registrations: Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at uclouvain.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at uclouvain.be ======================================================== From jkrichma at uci.edu Mon Sep 28 18:10:21 2009 From: jkrichma at uci.edu (Jeff Krichmar) Date: Mon, 28 Sep 2009 15:10:21 -0700 Subject: Connectionists: Postdoctoral Scholar Position in Computational Neuroscience and Neurorobotics Research at the University of California, Irvine Message-ID: Postdoctoral Scholar Position in Computational Neuroscience and Neurorobotics Research at the University of California, Irvine A NSF-funded postdoctoral position is immediately available in the field of Computational Neuroscience and Neurorobotics within the Department of Cognitive Sciences at the University of California, Irvine. Research ? The research involves developing computational models of neuromodulatory systems to understand their affect on attention. Different neuromodulatory systems are thought to play important and distinct roles in attention. A collaborative approach, which compares rodent experiments with robots having simulated nervous systems, will examine these attentional systems. These experiments will lead to a better understanding of how animals cope with uncertainty in the environment, and will lead to the design of a robot capable of flexible and complex behavior. The applicant will work closely with both roboticists and rodent neurophysiologists and will be involved in various aspects of research involving neural modeling, robot experiments, data analysis, and manuscript preparation. Requirements ? The applicant must have a Ph.D. degree in Cognitive Sciences, Neuroscience, Computer Science, or Engineering and have expertise in computational modeling of neural processes. The applicant must also have excellent computer skills in the C programming language and in Matlab programming. Experience with real-time programming, robotics, or data analysis of neuronal responses is preferable. Salary is commensurate with experience. Application procedure ? Please send a letter of application, curriculum vitae, and the names of three references to: Jeffrey L. Krichmar, Ph.D. Department of Cognitive Sciences University of California, Irvine 3151 Social Science Plaza Irvine, CA 92697-5100. jkrichma at uci.edu The University of California, Irvine is an equal opportunity employer committed to excellence through diversity. Jeff Krichmar Department of Cognitive Sciences 2175 Social Science Plaza A University of California, Irvine Irvine, CA 92697-5100 jkrichma at uci.edu or jeff.krichmar at uci.edu http://www.socsci.uci.edu/~jkrichma From krausea at caltech.edu Mon Sep 28 13:06:51 2009 From: krausea at caltech.edu (Andreas Krause) Date: Mon, 28 Sep 2009 10:06:51 -0700 Subject: Connectionists: CFP: NIPS 2009 Workshop on Discrete Optimization in Machine Learning -- Submodularity, Sparsity & Polyhedra (DISCML) Message-ID: =============================================== Call for Papers Discrete Optimization in Machine Learning Submodularity, Sparsity & Polyhedra Workshop at the 23rd Annual Conference on Neural Information Processing Systems (NIPS 2009) http://www.discml.cc Submission Deadline: November 6, 2009 =============================================== - We apologize for multiple postings - Solving optimization problems with ultimately discretely solutions is becoming increasingly important in machine learning: At the core of statistical machine learning is to infer conclusions from data, and when the variables underlying the data are discrete, both the tasks of inferring the model from data, as well as performing predictions using the estimated model are discrete optimization problems. This workshop aims at exploring discrete structures relevant to machine learning and techniques relevant to solving discrete learning problems. We would like to encourage high quality submissions of short papers relevant to the workshop topics. Accepted papers will be presented as spotlight talks and posters. Of particular interest are new algorithms with theoretical guarantees, as well as applications of discrete optimization to machine learning problems in areas such as the following: Combinatorial algorithms - Submodular & supermodular optimization - Discrete convex analysis - Pseudo-boolean optimization - Randomized / approximation algorithms Continuous relaxations - Sparse approximation & compressive sensing - Regularization techniques - Structured sparsity models Applications - Graphical model inference & structure learning - Clustering - Feature Selection & experimental design - Structured prediction - Novel discrete optimization problems in ML Submission deadline: November 6 Length & Format: max. 6 pages NIPS 2009 format Time & Location: December 11 2009, Whistler, Canada Submission instructions: Email to submit at discml.cc Organizers: Andreas Krause (California Institute of Technology), Pradeep Ravikumar (University of Texas, Austin), Jeff A. Bilmes (University of Washington) From gertito at gmail.com Thu Sep 24 20:35:36 2009 From: gertito at gmail.com (Gert Lanckriet) Date: Thu, 24 Sep 2009 17:35:36 -0700 Subject: Connectionists: Call for contributions: NIPS 2009 Workshop on Understanding Multiple Kernel Learning Methods Message-ID: <5769A145-6FF8-4432-BF70-5BCF9C46E543@gmail.com> ******************************************************* Call for contributions - Understanding Multiple Kernel Learning Methods http://mkl.ucsd.edu/workshop Workshop at the Twenty-Third Annual Conference on Neural Information Processing Systems (NIPS 2009), Whistler, BC, Canada, December 11 or 12, 2009. ******************************************************* DESCRIPTION Multiple kernel learning has been the subject of nearly a decade of research. Designing and integrating kernels has proven to be an appealing approach to address several, challenging real world applications, involving multiple, heterogeneous data sources in computer vision, bioinformatics, audio processing problems, etc. The goal of this workshop is to step back and evaluate the achievements of multiple kernel learning in the past decade, covering a variety of applications. In short, this workshop seeks to understand where and how kernel learning is relevant (with respect to accuracy, interpretability, feature selection, etc.), rather than exploring the latest optimization techniques and extension formulations. More specifically, the workshop envisions to discuss the following two questions: -- 1 -- Kernel learning vs. kernel design: Does kernel learning offer a practical advantage over the manual design of kernels? -- 2 -- Given a set of kernels, what is the optimal way, if any, to combine them (sums, products, learned or non learned, with or without cross-validation)? We are seeking participants interested in presenting their work and relating their experience in the workshop, providing insight on the above two questions. This includes evidence of MKL improving accuracy beyond any existing method based on single kernels (provided with insights as to why there is such improvement), as well as evidence of the opposite (with insights as to why). We welcome presentation of recent results, as well as presentations based on previously published work that shed light on the above questions. If you are interested in participating and contributing a presentation, please send an email to bmcfee at cs.ucsd.edu with an abstract or a summary. If the presentation is based on previously published work, please include details of such publications. REPOSITORY In conjunction with the workshop, we are establishing an open repository of data sets for use with MKL algorithms. Authors are encouraged to contribute data to the MKL Repository (mkl.ucsd.edu), and use the repository to benchmark new algorithms. ORGANIZERS * Gert Lanckriet (University of California, San Diego), gert at ece.ucsd.edu * Francis Bach (Ecole Normale Superieure/INRIA), francis.bach at ens.fr * Nathan Srebro (Toyota Technological Institute, Chicago), nati at uchicago.edu * Brian McFee (University of California, San Diego), bmcfee at cs.ucsd.edu From arthur.gretton at googlemail.com Fri Sep 25 20:05:02 2009 From: arthur.gretton at googlemail.com (arthur gretton) Date: Sat, 26 Sep 2009 02:05:02 +0200 Subject: Connectionists: Call for contributions: NIPS 2009 Workshop on Large-Scale Machine Learning, Parallelism and Massive Datasets Message-ID: <6ab54c960909251705u1afc08acu8574b98f728acb39@mail.gmail.com> "NIPS 2009 Workshop: Large-Scale Machine Learning: Parallelism and Massive Datasets" Submissions are solicited for the workshop to be held on December 11th/ 12th 2009 at this year's NIPS workshop session in Whistler, Canada. This workshop will focus on the role of parallel computation in machine learning with massive data. Physical and economic limitations have forced computer architecture towards parallelism and away from exponential frequency scaling. Meanwhile, increased access to ubiquitous sensing and the web has resulted in an explosion in the size of machine learning tasks. In order to benefit from current and future trends in processor technology we must discover, understand, and exploit the available parallelism in machine learning. This workshop will achieve four key goals: * Bring together people with varying approaches to parallelism in machine learning to identify tools, techniques, and algorithmic ideas which have lead to successful parallel learning. * Invite researchers from related fields, including parallel algorithms, computer architecture, scientific computing, and distributed systems, who will provide new perspectives to the NIPS community on these problems, and may also benefit from future collaborations with the NIPS audience. * Identify the next key challenges and opportunities to parallel learning. * Discuss large-scale applications, e.g., those with real time demands, that might benefit from parallel learning. Contributions can include: * Multicore / Cluster based Learning Techniques * Machine Learning on Alternative Hardware (GPUs, Cell Processors, FPGAs, iPhone, ...) * Distributed Learning * Learning results and techniques on Massive Datasets * Large Scale Kernel Methdos * Fast Online Algorithms * Parallel Computing Tools and Libraries as well as other related topics. Accepted submissions will be presented either as talks or during the workshop poster session, depending on the proposals. The deadline for submission will be October 23th 2009 and notifications will be sent out by November 2nd 2009. The submission should be at most four pages long in NIPS format, and should be sent to "biglearn at gmail.com". From wic-office at wi-consortium.org Sat Sep 26 12:07:09 2009 From: wic-office at wi-consortium.org (WIC Office) Date: Sun, 27 Sep 2009 01:07:09 +0900 Subject: Connectionists: AMT-BI'09 Call for Posters/Participation Message-ID: <4ABE3C2D.8090904@wi-consortium.org> [Apologies if you receive this more than once] #################################################################### Active Media Technology 2009 & Brain Informatics 2009 CALL FOR POSTERS and CALL FOR PARTICIPATION #################################################################### 2009 International Conference on Active Media Technology (AMT 2009) 2009 International Conference on Brain Informatics (BI 2009) October 22-24, 2009, Beijing, China Homepage: http://www.wici-lab.org/amtbi09/ Mirror page: http://www.iwici.org/amtbi09/ Co-organized by Web Intelligence Consortium (WIC) and IEEE Task Force on Brain Informatics (IEEE TF-BI) ------------------------------------------------ On-line registration (and more information) at http://www.wici-lab.org/amtbi09/ Posters Due: *** 30 September 2009 *** Special discount (or free) registration is available for students and poster session presenters ************************************************ You are invited to join Active Media Technology 2009 and Brain Informatics 2009. Active Media Technology is a new area of intelligent information technology and computer science that emphasizes the proactive, seamless roles of interfaces and systems as well as new media in all aspects of digital life. An AMT based system offers services to enable the rapid design, implementation and support of customized solutions. Brain Informatics has recently emerged as an interdisciplinary research field that focuses on studying the mechanisms underlying the human information processing system (HIPS). BI lies in the interplay between the studies of human brain and the research of informatics. The two conferences will have a joint opening, keynote, reception, and banquet. Attendees only need to register for one conference and can attend keynotes, sessions, workshop, posters across the two conferences. ============================ ***** Call for Posters ***** ============================ AMT-BI'09 also welcomes Posters submissions. AMT-BI'09 Posters session will provide researchers and practitioners in active media technology and brain informatics an exciting and highly interactive way to explore new ideas and results. All areas of the AMT/BI conference are of interest to the Posters and Demos. The proposal of a poster must include the following information: - Authors (name, affiliation, email, address, phone and fax) - The corresponding author with her/his email address - Title - Keywords - The category of the submission (AMT or BI) The proposals of posters must be submitted online at the conference websites. The deadline for proposals submission is *** 30 September 2009 ***. Special discount (or free) registration is available for students and poster session presenters AMT-BI 2009 Keynote Speakers ============================ Using Neural Imaging to Inform the Instruction of Mathematics Professor John Anderson Department of Psychology, Carnegie Mellon University http://act-r.psy.cmu.edu/people/ja/ Distributed Human-Machine Systems: Progress and Prospects Dr. Jeffrey M. Bradshaw Florida Institute for Human and Machine Cognition (IHMC) http://www.ihmc.us/users/jbradshaw Large Scale Reasoning on the Semantic Web: what to do when success is becoming a problem Professor Frank van Harmelen AI Department, Vrije Universiteit Amsterdam http://www.cs.vu.nl/~frankh How Midazolam Can Help Us Understand Human Memory: 3 Illustrations and a Proposal for a New Methodology Professor Lynne Reder Department of Psychology, Carnegie Mellon University http://memory.psy.cmu.edu/ Research on Brain-like Computer Professor Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology, Chinese Academy of Sciences http://www.intsci.ac.cn/en/shizz/ A Framework for Machine Learning with Ambiguous Objects Professor Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University, China http://cs.nju.edu.cn/zhouzh/ AMT-BI 2009 Special Sessions ============================ In addition to sessions for presenting accepted papers, we have the following special sessions: Special Session on Information Processing Meets Brain Sciences -------------------------------------------------------------- Data Compression and Data Selection in Human Vision Zhaoping Li (University College London, UK) Do Brain Networks Correlate with Intelligence? Tianzi Jiang (Institute of Automation, Chinese Academy of Sciences, China) How Were Intelligence and Language Created in Human Brain Setsuo Ohsuga (University of Tokyo, Japan) Affective Learning with an EEG Approach Bin Hu (Birmingham City University, UK, and Lanzhou Unviersity, China) Some Web Intelligence Oriented Brain Informatics Studies Yulin Qin (Beijing University of Technology, China, and Carnegie Mellon University, USA) Special Session on Conversational Informatics --------------------------------------------- Implementing a Multi-user Tour Guide system with an Embodied Conversational Agent Aleksandra Cerekovic, Hsuan-Huang Huang, Takuya Furukawa, Yuji Yamaoka, Igor Pandzic, Toyoaki Nishida, and Yukiko Nakano Actively Adaptive Agent for Human-Agent Collaborative Task Yong Xu, Yoshimasa Ohmoto, Kazuhiro Ueda, Takanori Komatsu, Takeshi Okadome, Koji Kamei, Shogo Okada, Yasuyuki Sumi, and Toyoaki Nishida Low-Overhead 3D Items Drawing Engine for Communicating Situated Knowledge Loic Merckel and Toyoaki Nishida A Method to Detect Lies in Free Communication using Diverse Nonverbal Information: Towards an Attentive Agent Yoshimasa Ohmoto, Kazuhiro Ueda, and Takehiko Ohno An Integrative Agent Model for Adaptive Human-Aware Presentation of Information During Demanding Tasks Andy van der Mee, Nataliya Mogles, and Jan Treur Special Session on Human-Web Interaction ---------------------------------------- Consumer Decision Making in Knowledge-Based Recommendation Monika Mandl, Alexander Felfernig, and Monika Schubert Incremental Learning of Triadic PLSA for Collaborative Filtering Hu Wu and Yongji Wang Interactive Storyboard: Animated Story Creation on Touch Interfaces Kun Yu, Hao Wang, Chang Liu, and Jianwei Niu Comparative Evaluation of Reliabilities on Semantic Search Functions: Auto-complete and Entity-centric Unified Search Hanmin Jung, Mi-Kyoung Lee, Beom-Jong You, and Do-Wan Kim Integrated Recommender Systems Based on Ontology and Usage Mining Liang Wei AMT-BI 2009 Workshop ==================== WICI Workshop/Posters on Web Intelligence Meets Brain Informatics Conference Site =============== The conference will take place at the Grand Gongda Jianguo Hotel (Beijing Gongda Jianguo Fandian - 4-stars hotel) is located inside Beijing University of Technology within close proximity of the central business district and only a five-minute walk from the 2008 Beijing Olympic badminton and eurythmics venue. We will give a special discount price for BI-AMT'09 attendees. (400 RMB/1 single room, 450 RMB/1 double room (2 persons use), including Tax, Breakfast, etc.) The hotel reservation information is available at the AMT-BI'09 homepages. ----------------- Co-sponsored by Beijing University of Technology (BJUT) Chinese Society of Radiology National Natural Science Foundation of China (NSFC) State Administration of Foreign Experts Affairs, PRC Shanghai Psytech Electronic Technology Co. Ltd Shenzhen Hanix United, Inc. Beijing Branch Beijing JinShangQi Net System Integration Co. Ltd Springer Lecture Notes in Computer Science (LNCS/LNAI) *** Contact Information *** Email: Jia Hu hujia0601 at gmail.com Jiajin Huang hjj at emails.bjut.edu.cn From swatanab at pi.titech.ac.jp Wed Sep 30 23:30:59 2009 From: swatanab at pi.titech.ac.jp (Sumio Watanabe) Date: Thu, 1 Oct 2009 12:30:59 +0900 Subject: Connectionists: New Book : Algebraic Geometry and Statistical Learning Theory Message-ID: <1254367859352292.9581@mail1.nap.gsic.titech.ac.jp> Dear Connectionists, I'm very happy to announce that the following book has been published. Sumio Watanabe, Algebraic Geometry and Statistical Learning Theory, Cambidge University Press, 2009. ABSTRACT: New mathematical formulas are proved for singular learning machines based on algebraic geometrical methods. Publisher's page: http://www.cambridge.org/catalogue/catalogue.asp?isbn=9780521864671 Author's page: http://watanabe-www.pi.titech.ac.jp/~swatanab/ag-slt.html Questions or Comments are welcome. Sincerely, Sumio Watanabe, Tokyo Institute of Technology. http://watanabe-www.pi.titech.ac.jp/~swatanab/index.html