From edizquie at indiana.edu Tue Dec 1 12:09:18 2015 From: edizquie at indiana.edu (Izquierdo, Eduardo J.) Date: Tue, 1 Dec 2015 17:09:18 +0000 Subject: Connectionists: Postdoctoral Position in Computational Neuroscience at Indiana University Message-ID: <7171DDFD-196D-4E25-A3B1-AE7F65958680@indiana.edu> Dear all, We are happy to announce that we are in the process of hiring a postdoctoral scientist interested in developing and analyzing integrated neuromechanical models of behavior at Indiana University. We would greatly appreciate it if you could forward the attached ad to anyone who might be interested. Sincerely, Eduardo J. Izquierdo Randall D. Beer Postdoctoral Position in Computational Neuroscience, Indiana University, Bloomington Applications are invited for a post-doctoral in Computational Neuroscience. The position will be available in Spring 2016, but the starting date is flexible. The initial appointment will be for one year, with the possibility of renewal for a second year. The successful candidate will be working with Professors Eduardo Izquierdo and Randall Beer to construct and analyze integrated neuromechanical models of behavior in the nematode worm C. elegans. The ideal candidate will have completed their doctoral studies, and should have expertise in modeling and computational neuroscience. Experience in parameter optimization algorithms, dynamical systems theory, and information theory would be preferred but not necessary. Strongest consideration will be given to applications received before December 31, 2015; however, applications will be considered until the position is filled. Interested candidates should review the application requirements and submit their applications at https://indiana.peopleadmin.com/postings/1962. Questions regarding the position can be directed to Professors Eduardo Izquierdo or Randall Beer at Cognitive Science Program, Indiana University, 1900 East 10th St., 819 Eigenmann, Bloomington, Indiana 47406-7512 or, by email, edizquie at indiana.edu or rdbeer at indiana.edu. Indiana University is an equal employment and affirmative action employer and a provider of ADA services. All qualified applicants will receive consideration for employment without regard to age, ethnicity, color, race, religion, sex, sexual orientation or identity, national origin, disability status or protected veteran status. Applications from women and minority group members are especially encouraged. -------------- next part -------------- An HTML attachment was scrubbed... URL: From irina.illina at loria.fr Wed Dec 2 11:28:56 2015 From: irina.illina at loria.fr (Irina Illina) Date: Wed, 2 Dec 2015 17:28:56 +0100 (CET) Subject: Connectionists: Master2 (research) position at Multispeech Team, LORIA (Nancy, France) In-Reply-To: <571553580.11780916.1445982942371.JavaMail.zimbra@loria.fr> References: <571553580.11780916.1445982942371.JavaMail.zimbra@loria.fr> Message-ID: <223712604.27429625.1449073736855.JavaMail.zimbra@loria.fr> Master2 position at Multispeech Team, LORIA (Nancy, France) Automatic speech recognition: contextualisation of the language model based on neural networks by dynamic adjustment Framework of ANR project ContNomina The technologies involved in information retrieval in large audio/video databases are often based on the analysis of large, but closed, corpora, and on machine learning techniques and statistical modeling of the written and spoken language. The effectiveness of these approaches is now widely acknowledged, but they nevertheless have major flaws, particularly for what concern proper names, that are crucial for the interpretation of the content. In the context of diachronic data (data which change over time) new proper names appear constantly requiring dynamic updates of the lexicons and language models used by the speech recognition system. As a result, the ANR project ContNomina (2013-2017) focuses on the problem of proper names in automatic audio processing systems by exploiting in the most efficient way the context of the processed documents. To do this, the student will address the contextualization of the recognition module through the dynamic adjustment of the language model in order to make it more accurate. Subject Current systems for automatic speech recognition are based on statistical approaches. They require three components: an acoustic model, a lexicon and a language model. This stage will focus on the language model. The language model of our recognition system is based on a neural network learned from a large corpus of text. The problem is to re-estimate the language model parameters for a new proper name depending on its context and a small amount of adaptation data. Several tracks can be explored: adapting the language model, using a class model or studying the notion of analogy. Our team has developed a fully automatic system for speech recognition to transcribe a radio broadcast from the corresponding audio file. The student will develop a new module whose function is to integrate new proper names in the language model. Required skills Background in statistics and object-oriented programming. Localization and contacts Loria laboratory, Multi speech team , Nancy, France Irina.illina at loria.fr dominique.fohr at loria.fr Candidates should email a detailed CV and diploma References [1] J. Gao, X. He, L. Deng Deep Learning for Web Search and Natural Language Processing , Microsoft slides, 2015 [2] X. Liu, Y. Wang, X. Chen, M. J. F. Gales, and P. C. Woodland. Efficient lattice rescoring using recurrent neural network langage models , in Proc. ICASSP, 2014, pp. 4941?4945. [3] M. Sundermeyer, H. Ney, and R. Schl?ter. From Feedforward to Recurrent LSTM Neural Networks for Language Modeling . IEEE/ACM Transactions on Audio, Speech, and Language Processing, volume 23, number 3, pages 517-529, March 2015. -- Associate Professor Lorraine University LORIA-INRIA office C147 Building C 615 rue du Jardin Botanique 54600 Villers-les-Nancy Cedex Tel:+ 33 3 54 95 84 90 -------------- next part -------------- An HTML attachment was scrubbed... URL: From mnick at mit.edu Tue Dec 1 21:27:10 2015 From: mnick at mit.edu (Maximilian Nickel) Date: Tue, 1 Dec 2015 21:27:10 -0500 Subject: Connectionists: Call for participation: Symposium "Brains, Minds and Machines" at NIPS 2015 Message-ID: ==== Symposium on Brains, Minds and Machines at NIPS 2015 ==== We cordially invite you to join us at the symposium on Brains, Minds and Machines which will be held at the Neural Information Processing Systems (NIPS) Conference on December 10th, 2015 at the Palais des Congr?s in Montr?al, Canada. The symposium is focused on the scientifc understanding of intelligence and how the science of today enables new approaches to replicate intelligence in engineered systems. http://www.mit.edu/~mnick/brains-minds-and-machines-2015/ == Overview == Understanding intelligence and the brain requires theories at different levels, ranging from the biophysics of single neurons to algorithms, computations, and a theory of learning. In this symposium, we aim to bring together researchers from machine learning, artificial intelligence, neuroscience, and cognitive science to present and discuss research that is focused on understanding intelligence at these different levels. Central questions of the symposium include how intelligence is grounded in computation, how these computations are implemented in neural systems, how intelligence can be described via unifying mathematical theories, and how we can build intelligent machines based on these principles. Our core goal is to develop a science of intelligence, which means understanding human intelligence and its basis in the circuits of the brain and the biophysics of neurons. We also believe that the engineering of tomorrow will need the science of today, in the same way as the basic research of Hubel and Wiesel in the '60s was the foundation for today's deep learning architectures. == Program Highlights == The symposium will consist of talks by invited speakers and a panel discussion. Invited speakers and panelists at the symposium include - Surya Ganguli (Stanford) - Demis Hassabis (Google DeepMind) - Christof Koch (Allen Institute for Brain Science) - Gabriel Kreiman (Harvard) - Gary Marcus (NYU) - Tomaso Poggio (MIT) - Andrew Saxe (Harvard) - Terrence Sejnowski (Salk Institute) - Joshua Tenenbaum (MIT) == Time and Place == Date: Thursday, December 10th Time: 3-9pm Location: Level 5, Room 510 BD, Palais des Congr?s de Montr?al, Canada == Website == For schedule, abstracts, and updates please consult the symposium website at http://www.mit.edu/~mnick/brains-minds-and-machines-2015/ == Organization Committee == - Gabriel Kreiman (Harvard) - Tomaso Poggio (MIT) - Maximilian Nickel (MIT) We are looking forward to seeing you in Montreal! -------------- next part -------------- An HTML attachment was scrubbed... URL: From tat at tchumatchenko.de Wed Dec 2 03:29:23 2015 From: tat at tchumatchenko.de (Tatjana Tchumatchenko) Date: Wed, 2 Dec 2015 09:29:23 +0100 Subject: Connectionists: Ph.D. and Master positions in theoretical neuroscience at the MPI for Brain Research Message-ID: <565EABE3.4080009@tchumatchenko.de> Ph.D. and Master positions in theoretical neuroscience at the Max Planck Institute for Brain Research We are seeking undergraduate students interested in writing a Master thesis and have open positions for Ph.D. Students to join our group "Theory of neural dynamics" at the Max Planck Institute for Brain Research lead by Dr. Tatjana Tchumatchenko. Our group studies how networks of neurons encode and decode sensory stimuli and how these functions are related to computations that underlie cognitive functions and behavior. We develop models to address linear and non-linear properties of neuronal networks and have ongoing collaborations with experimental labs where we analyze in vitro as well as in vivo data and develop appropriate models to explain the observed phenomena. Successful applicants should have a strong background in a quantitative field such as physics, mathematics or computer science and should be interested in an interdisciplinary exchange with other disciplines such as biology or medicine. Life science majors interested in quantitative modeling work are also encouraged to apply, particularly if they would like to combine experiments and theory in their Master or Ph.D. thesis work. We are looking for candidates with strong English skills and prior programming experience. In order to make teamwork in our group enjoyable and fun, the ideal candidate should have a strong work ethic and have demonstrated consistent self-motivation skills. Female students are particularly encouraged to apply. Prospective students should apply by sending an email to theoryneuraldynamics at gmail.com which includes * a letter of motivation, * CV, * and a copy of the current academic transcripts To make your motivation letter easier to write for you and more informative for us, please check the list of questions to be answered in your motivation letter at http://www.tchumatchenko.de/Opportunities.html Let me note, that our institute is hosting the IMPRS graduate school "Neural circuits". It's open call for applications can be found here: http://brain.mpg.de/graduate-studies/call.html Looking forward to your applications! Tatjana Tchumatchenko -- Dr. Tatjana Tchumatchenko Research group leader Theory of Neural Dynamics Max Planck Institute for Brain Research Max-von-Laue-Str 4 60438 Frankfurt am Main, Germany www.tchumatchenko.de -------------- next part -------------- An HTML attachment was scrubbed... URL: From sliman.bensmaia at gmail.com Tue Dec 1 22:27:32 2015 From: sliman.bensmaia at gmail.com (Sliman Bensmaia) Date: Tue, 1 Dec 2015 21:27:32 -0600 Subject: Connectionists: IEEE Transactions on Haptics: Special Issue on Haptics in Neuroscience Message-ID: This special issue calls for papers related to the study of the neural basis of haptic perception and to technologies designed for haptic interaction. In particular, topics will include : ? The psychophysics of touch and its physiological basis in the peripheral and central nervous systems ? Computational models of the skin, the peripheral nerve, and/or central processing of somatosensory information ? Approaches to convey somatosensory feedback through neural interfaces ? Haptic devices that generate well-controlled tactile and kinesthetic stimuli for use in psychophysical, neuroimaging and neurophysiological studies ? Devices and experimental studies that measure the skin response during haptic interactions ? Haptic interfaces, sensors and devices that are inspired by the biology of touch Timeline December 31, 2015 Deadline for paper submissions February 1, 2016 First decisions to authors May 1, 2016 Second decisions to authors August 1, 2016 Final publication materials due from authors November 1, 2016 Special issue publication Submission Process Visit http://www.computer.org/toh to view formatting requirements, and submit your paper at https://mc.manuscriptcentral.com/th-cs. When uploading your paper please select the appropriate special issue under the category ?Manuscript Type.? Guest Editors Dr. Sliman Bensmaia, University of Chicago (sliman at uchicago.edu) Dr. Ingvars Birznieks, University of New South Wales (i.birznieks at unsw.edu.au) Dr. Gregory Gerling, University of Virginia (gg7h at virginia.edu) Dr. Fabrizio Sergi, University of Delaware (fabs at udel.edu) -- ________________________________________________________ Sliman Bensmaia Associate Professor Department of Organismal Biology and Anatomy University of Chicago 773.834.5203 http://bensmaialab.org ________________________________________________________ From vito.trianni at istc.cnr.it Fri Dec 4 06:43:54 2015 From: vito.trianni at istc.cnr.it (Vito Trianni) Date: Fri, 4 Dec 2015 12:43:54 +0100 Subject: Connectionists: [jobs] Postdoctoral position in decentralised cognitive processing Message-ID: ?apologies for multiple postings? Postdoc position in decentralised cognitive processing, with application to distributed systems and swarm robotics systems in particular. (see also http://laral.istc.cnr.it/trianni/index.php/2015/12/04/post-doc-position-in-decentralised-cognitive-processing) A fully-funded postdoctoral fellow position is available in the area of decentralised cognitive processing for autonomous multi-agent systems (e.g., swarm robotics system). The position is open within the DICE project (Distributed Cognition Engineering, http://laral.istc.cnr.it/dice-project), with starting date as early as March 2016 (flexible). The applicant will study cognitive processing in distributed systems resulting from the interaction among the autonomous agents constituting the system. From a theoretical point of view, the research project requires the identification and characterisation of the population-level dynamics that describe the system behaviour. From a practical point of view, the project requires the design of implementation strategies for multi-agent systems (e.g., swarm robotics systems) in order to precisely reproduce the desired macroscopic dynamics. The candidate will focus on problems involving collective decision-making and categorization. Analytical, modelling and programming skills are required, as the research will involve both theoretical investigations and experimental studies with swarms of robots (Kilobots). The deadline for submitting applications is January the 20th, 2016. The notice of selection and the procedure to be followed for submitting applications is available at the following address: http://www.istc.cnr.it/vacancy/assegno-di-ricerca-n?-2262015-modelli-teorici-e-simulazioni-multi-agente-di-processi-cogniti Instructions in English can be found here: http://www.istc.cnr.it/sites/default/files/vacancies/bandi/notice_of_selection_ndeg_istc-adr-226-2015-rm.doc For any informal enquiry about the eligibility conditions, as well as for more details about the position, please contact Vito Trianni . ======================================================================== Vito Trianni, Ph.D. vito.trianni@(no_spam)istc.cnr.it ISTC-CNR http://www.istc.cnr.it/people/vito-trianni Via San Martino della Battaglia 44 Tel: +39 06 44595277 00185 Roma Fax: +39 06 44595243 Italy ======================================================================== From feisha at cs.ucla.edu Sat Dec 5 02:19:56 2015 From: feisha at cs.ucla.edu (Fei Sha) Date: Fri, 4 Dec 2015 23:19:56 -0800 Subject: Connectionists: Tenure Track Faculty Positions at UCLA Computer Science Department Message-ID: Dear colleagues and friends, I would like to draw your attention to the announcement for open positions at UCLA Computer Science Department. For the formal announcement, please see http://www.cs.ucla.edu/faculty-recruitment/ as well as a copy of it at the end of this message. UCLA has been rapidly building and enhancing its strength in many CS areas including artificial intelligence, bioinformatics and computational biology, data science, machine learning , vision and robotics and others. The department has international visibility broadly in those areas with faculty such as Adnan Darwiche, Eleazar Eskin, Jason Ernst, Judea Pearl,Sriram Sankararaman, Fei Sha, Stefano Soatto, Ameet Talwalkar, Guy Van den Broeck, Wei Wang, and Song-chun Zhu. Interdisciplinary research activities between those areas and others have also expanded significantly and cross-cutting many departments and schools on the campus. Please note that "Applications will be accepted through December 15, but will be evaluated starting November 1st. We encourage early application." Thanks Fei -------- Tenure Track Faculty Positions The Computer Science Department of the Henry Samueli School of Engineering and Applied Science at the University of California, Los Angeles, invites applications for tenure-track positions in all areas of Computer Science. Applications are also encouraged from distinguished candidates at senior levels. Candidates must have a Ph.D. to fulfill the basic qualification requirement. Quality is our key criterion for applicant selection. Applicants should have a strong commitment both to research and teaching and an outstanding record of research for their level of seniority. Salary is commensurate with education and experience. The University of California is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability, age or protected veteran status. For the complete University of California nondiscrimination and affirmative action policy see: UC Nondiscrimination & Affirmative Action Policy. The department is committed to building a more diverse faculty, staff and student body as it responds to the changing population and educational needs of California and the nation. To apply, please visit https://recruit.apo.ucla.edu/apply/JPF01512. Applications will be accepted through December 15, but will be evaluated starting November 1st. We encourage early application. -------------- next part -------------- An HTML attachment was scrubbed... URL: From b.torben-nielsen at herts.ac.uk Sat Dec 5 03:51:29 2015 From: b.torben-nielsen at herts.ac.uk (Torben-Nielsen, Benjamin) Date: Sat, 5 Dec 2015 08:51:29 +0000 Subject: Connectionists: PhD Studentships in Computational Neuroscience at the University of Hertfordshire Message-ID: <1449305489878.35057@herts.ac.uk> PhD Studentships in Computational Neuroscience We welcome applications for a funded PhD position in the Biocomputation Research Group at the University of Hertfordshire. The successful applicant will work on a project related to modeling the structure and physiological function of the inferior olive. The inferior olive is an important part of the olivo-cerebellar circuitry as its axons, the climbing fibers, play a central role in all theories of cerebellar learning. Further, the inferior olive has been postulated to act as a clock for the brain. In this project, we aim to use an accurate structural model of the inferior olive to investigate, in silico, recent hypotheses related to the generation and maintenance of timing signals. An integral part of this project involves the further development of the NeuroMac software to generate structural models of the inferior olive. Please refer to the publication list of the Biocomputation Group website (http://biocomputation.herts.ac.uk/) for recent publications. Who are we looking for? - Candidates should have excellent programming skills (preferably also in Python) and familiarity with parallel and high-performance computing and visualization toolkits (such as VTK) is appreciated. - Candidates should possess great curiosity. - Candidates should be able to formulate their own questions about the circuitry and dynamics in the olivo-cerebellar system to direct their research efforts. Knowledge of neuroscience is a plus but the eagerness to learn about the brain and how to use scientific approaches (such as computational neuroscience and neuroinformatics) is considered pivotal. Successful candidates are eligible for a research studentship award from the University (approximately GBP 13,800 per annum bursary plus the payment of the standard UK student fees). Applicants from outside the UK or EU are eligible, but will have to pay half of the overseas fees out of their bursary. Research in Computer Science at the University of Hertfordshire has been recognized as excellent by the latest Research Excellent Framework Assessment, with 50% of the research submitted being rated as world leading or internationally excellent.The Science and Technology Research Institute provides a very stimulating environment, offering a large number of specialized and interdisciplinary seminars as well as general training and researcher development opportunities. The University of Hertfordshire is situated in Hatfield, in the green belt just north of London.? The student will be supervised by Drs. Ben Torben-Nielsen (b.torben-nielsen at herts.ac.uk) and Volker Steuber (v.steuber at herts.ac.uk) to whom informal enquiries can be sent. Application forms can be obtained from Mrs Lorraine Nicholls, Research Student Administrator, STRI, University of Hertfordshire, College Lane, Hatfield, Herts, AL10 9AB, Tel: 01707 286083, l.nicholls @ herts.ac.uk. The short-listing process will begin on 28 December 2015. Dr. Ben Torben-Nielsen Senior Lecturer (Assistant professor) Biocompution Group University of Hertfordshire, UK From ckiw at inf.ed.ac.uk Sun Dec 6 07:44:34 2015 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Sun, 6 Dec 2015 12:44:34 +0000 (GMT) Subject: Connectionists: Machine Learning faculty openings: University of Edinburgh, UK Message-ID: Applications are invited for a Lecturer to join the Machine Learning group in the Institute for Adaptive and Neural Computation, part of the School of Informatics, at The University of Edinburgh. For an exceptional candidate, appointment to the position of Reader will be considered. [A Lectureship is roughly equivalent to a US Assistant Professor, and a Readership to an Associate Professor.] The Machine Learning group carries out research on principled models, algorithms and applications of machine learning. The School of Informatics plays a leading role in the EPSRC Centre for Doctoral Training in Data Science, with opportunities for the appointee to supervise PhD students from the Centre (and from other sources). The University of Edinburgh is also one of the five joint venture partner universities in the UK's Alan Turing Institute for Data Science; this gives rise to opportunities to interact with PhD students, research fellows and senior researchers within the Turing Institute. In addition, there are many opportunities to interact with other parts of the University and beyond in order to further the candidate's research agenda. The latest REF 2014 results confirmed that the School of Informatics has the largest concentration of internationally excellent research in the UK. The successful candidate will have a PhD, experience as an established researcher in Machine Learning, enthusiasm to undertake original research including leading a research group, and the ability to engage with undergraduate and postgraduate teaching and academic supervision. Lecturer grade: UE08 ?38,896 - ?46,414 per annum. Reader grade: UE09 ?49,230 - ?55,389 per annum. Closing date: Friday 15th January 2016 at 5pm (GMT) Interviews will be held in Edinburgh in March 2016. Informal enquiries may be addressed to Prof Chris Williams ckiw at inf.ed.ac.uk . https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=034999 [Note: several Edinburgh machine learning faculty will be attending NIPS and available for informal discussions: Chris Williams, Iain Murray, Amos Storkey, Charles Sutton.] -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From zemel at cs.toronto.edu Thu Dec 3 17:20:27 2015 From: zemel at cs.toronto.edu (Richard Zemel) Date: Thu, 3 Dec 2015 17:20:27 -0500 (EST) Subject: Connectionists: Machine Learning faculty openings: University of Toronto Message-ID: University of Toronto Computer Science is hiring in machine learning broadly this year and for several years to come. The Toronto machine learning group includes faculty members Geoffrey Hinton, Radford Neal, Brendan Frey, Daniel Roy, Sanja Fidler, Raquel Urtasun, and Richard Zemel, and also has strong ties to our vision, NLP, and computational biology research groups. Our department has 2+ openings in machine learning this year: one aimed at machine learning and statistics, a second at applied machine learning. However, we encourage applicants in all areas of machine learning -- we would like to hire new faculty who can complement our existing strengths. There are additional positions that are open to broad areas of CS, which can also include machine learning. http://web.cs.toronto.edu/dcs/contact/employmentopp.htm Review of applications will begin soon, and will continue until the positions are filled. Please forward this message to anyone who might be interested. Best, Richard Zemel & Raquel Urtasun Professors, Computer Science Department University of Toronto From redish at umn.edu Fri Dec 4 17:31:52 2015 From: redish at umn.edu (David Redish) Date: Fri, 4 Dec 2015 16:31:52 -0600 Subject: Connectionists: Computational Neuroscience Graduate Positions available at the University of Minnesota Message-ID: The Neuroengineering IGERT Training Program at the University of Minnesota, funded by the National Science Foundation, is inviting outstanding students to apply through the Graduate Program in Neuroscience or the Biomedical Engineering Program. The IGERT program is aimed at training the next generation of scientific and technical leaders in the interface of engineering and systems neurosciences, as broadly defined. The training themes include: 1) Neural decoding - Computational and theoretical neuroscience and neuroengineering studies on decoding theory, methods, as pursued via animal models or human studies. Neuroimaging is also pursued as means of brain decoding. 2) Neural modulation - Mechanisms of neuromodulation in brains for both deep brain stimulation and transcranial stimulations. 3) Neural interfacing - Mechanisms of motor control and learning as applied to brain-machine interface, as pursued in animal models and humans. Outstanding training opportunities include mentoring by co-advisors from over 40 faculty across engineering and brain sciences, a new neuroengineering minor curriculum, industrial and international internships, and general stipend and tuition coverage. Visit the IGERT program website to find out more: http://www.igert-ne.umn.edu/ -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: IGERT flyer - 2015.pdf Type: application/pdf Size: 470474 bytes Desc: not available URL: From bart at vision.rutgers.edu Thu Dec 3 04:15:19 2015 From: bart at vision.rutgers.edu (Bart Krekelberg) Date: Thu, 3 Dec 2015 10:15:19 +0100 Subject: Connectionists: Ph.D. Program at Rutgers University-Newark (Application deadline: December 15th, 2015) Message-ID: * The Graduate Program in Behavioral and Neural Sciences (BNS) at Rutgers University-Newark is accepting student applications until December 15, 2015.* *The BNS Graduate Program offers training in Cellular, Systems, Behavioral, and Cognitive Neuroscience.* The research interests of BNS faculty span all levels in the neurosciences, from genes and molecules to neuronal networks and complex systems. Their research methods are similarly varied as they combine anatomical, neurochemical, electrophysiological, imaging, behavioral, and neuropsychological methods to analyze how the brain works, develops, interacts with the environment, and is modified by experience and disease. *BNS Students are supported financially by the graduate program for five years; they receive full tuition remission, and benefit from a comprehensive health insurance.* The campus of the BNS program is located in Newark, New Jersey, 13 miles from Manhattan, New York City, with extensive public transportation links between the two. *More information about the program, including how to apply and faculty profiles:* http://bns.rutgers.edu --- Bart Krekelberg, PhD Professor, Rutgers University - Newark Associate Director, Center for Molecular and Behavioral and Neuroscience Associate Director, Rutgers Brain Imaging Center -------------- next part -------------- An HTML attachment was scrubbed... URL: From ilpincy+ants at gmail.com Thu Dec 3 09:04:54 2015 From: ilpincy+ants at gmail.com (Carlo Pinciroli) Date: Thu, 3 Dec 2015 09:04:54 -0500 Subject: Connectionists: [2nd CFP] ANTS 2016: Tenth International Conference on Swarm Intelligence Message-ID: *** Apologies if you have received this CFP more than once *** ANTS 2016 Tenth International Conference on Swarm Intelligence September 7-9, 2016. Brussels, Belgium Call for papers prepared on October 5, 2015 More details and up-to-date information at http://iridia.ulb.ac.be/ants2016 Scope of the Conference ======================= Swarm intelligence is the discipline that deals with the study of self-organizing processes both in nature and in artificial systems. Researchers in ethology and animal behavior have proposed a number of models to explain interesting aspects of social insect behavior such as self-organization and shape-formation. Recently, algorithms and methods inspired by these models have been proposed to solve difficult problems in many domains. An example of a particularly successful research direction in swarm intelligence is ant colony optimization, the main focus of which is on discrete optimization problems. Ant colony optimization has been applied successfully to a large number of difficult discrete optimization problems including the traveling salesman problem, the quadratic assignment problem, scheduling, vehicle routing, etc., as well as to routing in telecommunication networks. Another interesting approach is that of particle swarm optimization, that mainly focuses on continuous optimization problems. Here too, a number of successful applications can be found in the recent literature. Swarm robotics is another relevant field. Here, the focus is on applying swarm intelligence techniques to the control of large groups of cooperating autonomous robots. ANTS 2016 will give researchers in swarm intelligence the opportunity to meet, to present their latest research, and to discuss current developments and applications. The three-day conference will be held in Brussels, Belgium, on September 7-9, 2016. Relevant Research Areas ======================= ANTS 2016 solicits contributions dealing with any aspect of swarm intelligence. Typical, but not exclusive, topics of interest are: Behavioral models of social insects or other animal societies that can stimulate new algorithmic approaches. Empirical and theoretical research in swarm intelligence. Application of swarm intelligence methods, such as ant colony optimization or particle swarm optimization, to real-world problems. Theoretical and experimental research in swarm robotics systems. Publication Details =================== Conference proceedings will be published by Springer in the LNCS. series. The journal Swarm Intelligence will publish a special issue dedicated to ANTS 2016 that will contain extended versions of the best research works presented at the conference. Further details will soon be published on the web site. Conference Location =================== Auditorium R42.4.502, Solvay Brussels School of Economics and Management, Campus du Solbosch, Universit? Libre de Bruxelles, Av. F.D. Roosevelt 42, 1050 Brussels, Belgium. Best Paper Award ================ A best paper award will be presented at the conference. Further Information =================== Up-to-date information will be published on the web site http://iridia.ulb.ac.be/ants2016/. For information about local arrangements, registration forms, etc., please refer to the above-mentioned web site or contact the local organizers at the address below. Conference Address ================== ANTS 2016 IRIDIA CP 194/6 Tel +32-2-6502729 Universit? Libre de Bruxelles Fax +32-2-6502715 Av. F. D. Roosevelt 50 http://iridia.ulb.ac.be/ants2016 1050 Bruxelles, Belgium email: ants at iridia.ulb.ac.be Important Dates =============== Submission deadline March 2, 2016 Notification of acceptance May 4, 2016 Camera ready copy May 18, 2016 Conference September 7-9, 2016 ANTS 2016 Organizing Committee ============================== General chair Marco Dorigo, Universit? libre de Bruxelles, Belgium Vice-chairs Mauro Birattari, Universit? libre de Bruxelles, Belgium Thomas St?tzle, Universit? libre de Bruxelles, Belgium Technical program chairs Manuel L?pez-Ib??ez, University of Manchester, UK Xiaodong Li, RMIT University, Australia Kazuhiro Ohkura, Hiroshima University, Japan Publication chair Carlo Pinciroli, ?cole Polytechnique de Montr?al, Canada From huajin.tang at gmail.com Sat Dec 5 04:08:23 2015 From: huajin.tang at gmail.com (Huajin Tang) Date: Sat, 5 Dec 2015 17:08:23 +0800 Subject: Connectionists: CFP: IEEE WCCI 2016 Workshop on Neuromorphic Computing and Cyborg Intelligence Message-ID: 2016 IEEE World Congress on Computational IntelligenceJuly 25-29, 2016 - Vancouver, CanadaInternational Workshop onNeuromorphic Computing and Cyborg Intelligence Overview Emulating brain-like learning performance has been a key challenge for research in neural networks and learning systems, including recognition, memory and perception. In the last few decades, a wealth of machine learning approaches have been proposed including sparse representations, hierarchical and deep learning neural networks. While achieving impressive performance these methods still compare poorly to biological systems and the problem of reducing the amount of human supervision and computations needed for learning remains a challenge. On the other hand, the development of novel data representation and learning approaches from recent advances in neuromorphic systems have shown appealing computational advantages. For example, using neural coding theory to represent the external sensory data, and developing spiking timing based learning algorithm have achieved real-time learning performance, either in neuromorphic computational models or hardware systems. Attributed to the new visual or auditory sensors, neuromorphic hardware has provided a fundamentally different technique for data representation, i.e., asynchronous events rather than frames of images as in main stream recognition algorithms. However, the current neuromorphic information processing algorithms are not comparable to achieve sophisticated features and power learning performance as what machine learning approaches can offer. One promising method is to develop integrated learning models that apply brain-like data presentation and learning mechanisms, e.g., implementing deep learning in neuromorphic systems. Neuromorphic systems also overlap with another framework called cyborg intelligence, combining brain functions with computational machines to achieve the best of both via brain-machine interface. The workshop will target the challenging problems in these areas by reporting new solutions, theoretical and technical advances in neuromorphic computing and cyborg intelligence from the worldwide researchers and engineers. Technical Program Committee Tetsuya Asai, Hokkaido University, Japan Ryad Benosman, University of Pierre and Marie Curie, France Badong Chen, Xi?an Jiao Tong University, China Feng Chen, Tsinghua University, China J?rg Conradt, Technische Universit?t M?nchen, Germany Shoushun Chen, Nanyang Technolological University, Singapore Yiran Chen, University of Pittsburgh, USA Tomoki Fukai, RIKEN Brain Science Institute, Japan Jun Hu, Institute for Infocomm Research, Singapore Giacomo Indiveri, Institute of Neuroinformatics, Switzerland Sio-Hoi Ieng, University of Pierre and Marie Curie, France Shih-Chii Liu, Institute of Neuroinformatics, Switzerland Garrick Orchard, National University of Singapore, Singapore Tarek M. Taha, University of Dayton, USA Jun Tani, KAIST, Korea Yiwen Wang, Zhejiang University, China Si Wu, Beijing Normal University, China Qiang Yu, Max-Planck-Institute for Experimental Medicine, Germany Bo Zhao, Institute for Infocomm Research, Singapore Relevant Topics Cognitive computing and cyborg intelligence Neuromorphic information/signal processing Brain-inspired data representation models Neuromorphic learning and cognitive systems Spike-based sensing and learning Neuromorphic sensors and hardware systems Intelligence for embedded systems Cognition mechanisms for big data Embodied cognition and neuro-robotics Important Dates Submission deadline: 15 January 2016 Notification of acceptance: 15 March 2016 Camera-ready deadline: 15 April 2016 Workshop date: 25 July 2016 Submission Guidelines Prospective authors are invited to submit papers according to the IEEE format. All submissions should follow the specifications of WCCI 2016. Manuscripts will be submitted through the IEEE WCCI 2016 paper submission website and will be subject to the same peer-review procedure as the WCCI2016 regular papers. Accepted contributions will be part of the IJCNN conference proceedings, which will be available in IEEE Xplore. For more information about the workshops, please visit: http://wcci 2016.org/programs.php?id=workshop?sd=w_ijcnn Organizers - Huajin Tang, Sichuan University, Chengdu, China (htang at scu.edu.cn ) - Gang Pan, Zhejiang University, China (gpan at zju.edu.cn) - Arindam Basu, Nanyang Technological University, Singapore ( arindam.basu at ntu.edu.sg) - Luping Shi, Tsinghua University, China (lpshi at mail.tsinghua.edu.cn) -------------- next part -------------- An HTML attachment was scrubbed... URL: From aranoya at gmail.com Thu Dec 3 05:03:10 2015 From: aranoya at gmail.com (Oya Aran) Date: Thu, 3 Dec 2015 11:03:10 +0100 Subject: Connectionists: Call for Grand Challenges - International Conference on Multimodal Interaction - ICMI 2016 Message-ID: ICMI 2016 Call for Grand Challenges The International Conference on Multimodal Interaction (ICMI) is the premier international forum for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, and system development. Developing systems that can robustly understand human-human communication or respond to human input requires identifying the best algorithms and their failure modes. In fields such as computer vision, speech recognition, and computational linguistics for example, the availability of datasets and common tasks have led to great progress. We invite the ICMI community to collectively define and tackle the scientific Grand Challenges in our domain for the next 5 years. ICMI Multimodal Grand Challenges aim to inspire new ideas in the ICMI community and create momentum for future collaborative work. Analysis, synthesis, and interactive tasks are all possible. Challenge papers will be indexed by ACM. The grand challenge sessions will likely be held on November 12th 2016 before the ICMI main technical program. We invite organizers from various fields related to multimodal interaction to propose and run Grand Challenge events. We are looking for exciting and stimulating challenges including but not limited to the following categories Dataset-driven challenge. This challenge will provide a dataset that is exemplary of the complexities of current and future multimodal problems, and one or more multimodal tasks whose performance can be objectively measured. Participants in the Challenge will evaluate their methods against the challenge data in order to identify areas of strengths and weakness. Use-case challenge. This challenge will provide an interactive problem system (e.g. dialog-based) and the associated resources, which can allow people to participate through the integration of specific modules or alternative full systems. Proposers should also establish systematic evaluation procedures. We are also soliciting proposals that align with the theme of the conference which is machine learning for multimodal interactions. Prospective organizers should submit a five-page maximum proposal containing the following information 1. Title 2. Abstract appropriate for possible Web promotion of the Challenge 3. Detailed description of the challenge and its relevance to multimodal interaction 4. Plan for soliciting participation 5. Description of how submissions will be evaluated, and a list of proposed reviewers 6. Proposed schedule for releasing datasets (if applicable) and receiving submissions 7. Short biography of the organizers 8. Funding source (if any) that supports or could support the challenge organization. Proposals will be evaluated based on originality, ambition, feasibility, and implementation plan. The ICMI organizers will offer support with basic logistics. Important Dates and Contact Details Proposals should be emailed to both ICMI 2016 Multimodal Grand Challenge Chairs, Dr. Hatice Gunes (h.gunes at qmul.ac.uk ) and Dr. Mohammad Soleymani (mohammad.soleymani at unige.ch ). Prospective organizers are also encouraged to contact the co-chairs if they have any questions. Continuation of or variants on the 2015 challenges are welcome, though we ask for submissions of this form to highlight the number of participants that attended during the previous year and describe what changes will be made from the previous year. Proposals are due by January 15th, 2016. Notifications will be sent on February 1st, 2016 -------------- next part -------------- An HTML attachment was scrubbed... URL: From redish at umn.edu Mon Dec 7 09:37:19 2015 From: redish at umn.edu (David Redish) Date: Mon, 7 Dec 2015 08:37:19 -0600 Subject: Connectionists: Computational Neuroscience Graduate Positions available at the University of Minnesota Message-ID: *The Neuroengineering IGERT Training Program at the University of Minnesota, funded by the National Science Foundation, is inviting outstanding students to apply through the Graduate Program in Neuroscience or the Biomedical Engineering Program. The IGERT program is aimed at training the next generation of scientific and technical leaders in the interface of engineering and systems neurosciences, as broadly defined. The training themes include: * 1) Neural decoding - Computational and theoretical neuroscience and neuroengineering studies on decoding theory, methods, as pursued via animal models or human studies. Neuroimaging is also pursued as means of brain decoding. 2) Neural modulation - Mechanisms of neuromodulation in brains for both deep brain stimulation and transcranial stimulations. 3) Neural interfacing - Mechanisms of motor control and learning as applied to brain-machine interface, as pursued in animal models and humans. Outstanding training opportunities include mentoring by co-advisors from over 40 faculty across engineering and brain sciences, a new neuroengineering minor curriculum, industrial and international internships, and general stipend and tuition coverage. Visit the IGERT program website to find out more: http://www.igert-ne.umn.edu/ *==========================================================More information:Become the future of systems neuroengineering.* The University of Minnesota is home to an Integrative Graduate Education and Research Traineeship *(IGERT) program in Systems Neuroengineering*, sponsored by the National Science Foundation (NSF). Bright, high-achieving students who are admitted to a University of Minnesota?s Ph.D. program in Biomedical Engineering, Electrical Engineering, Mechanical Engineering, or Neuroscience are eligible for this prestigious training program. The program provides a generous stipend and tuition coverage as well as access to cutting-edge research in neuroengineering. Minnesota is also home to the largest collection of medical device manufacturers in the world and our program provides opportunities for IGERT trainees to gain practical experience working with these companies. Through our education and research-training model, students in our program learn to develop the skills to revolutionize neurotechnologies and advance our understanding of neuroscience processes underlying these technologies. *Program Faculty* The Systems Neuroengineering IGERT Program has over 40 outstanding faculty members who have made significant contributions to neural decoding, neuromodulation, neural interfacing, and neuroimaging research, and who are committed to graduate training. Many of them are world class leaders who have shaped where the field is in cutting-edge research, including noninvasive brain-computer interface controlling quadcopter, deep-brain stimulation, high field MRI imaging, and dynamic brain mapping. *Key Program Features* - Choice of research advisors from over 40 participating training faculty across engineering and brain sciences - Joint faculty mentoring and team advising of research - Tailored neuroengineering graduate curriculum - Lab rotations in engineering and basic/clinical brain sciences - Industrial internship rotations - Generous stipend ($30,000/year for up to two years on IGERT program) and tuition coverage *Eligibility Requirements* Trainees must be U.S. citizens or permanent residents who have been admitted to one of the four participating University of Minnesota doctoral programs: *Biomedical Engineering, Electrical Engineering, Mechanical Engineering,* and *Neuroscience.* For more information on this highly selective training program and how to apply, please visit our website at http://www.igert-ne.umn.edu/, or contact us at igert-ne at umn.edu. -------------- next part -------------- An HTML attachment was scrubbed... URL: From feisha at cs.ucla.edu Sun Dec 6 20:08:41 2015 From: feisha at cs.ucla.edu (Fei Sha) Date: Sun, 6 Dec 2015 17:08:41 -0800 Subject: Connectionists: Postdoctoral Position in Machine Learning at UCLA Computer Science Department Message-ID: Dear colleagues and friends, The machine learning group at UCLA, led by Fei Sha ( http://web.cs.ucla.edu/~feisha/) and Ameet Talwalkar ( http://web.cs.ucla.edu/~ameet/) , has an open postdoctoral position. We seek applicants from all areas of machine learning. Candidates must hold a PhD in computer science, statistics or a closely related discipline, and have a strong publication record in top conferences and journals (NIPS, ICML, JMLR, etc.). The expected start date is late Spring and can be flexible. The postdoctoral researcher is to interact and collaborate closely with both faculty and graduate students in the research group. While the research group has a rich set of ongoing research projects, the postdoctoral researcher is also encouraged to be independent and develop his/her own research agenda that complements existing research endeavors. Quality of research is the ultimate criterion. The UCLA CS department is rapidly growing with core strengths in machine learning, artificial intelligence, bioinformatics, data science, computer vision and robotics. UCLA provides a thriving research environment with interdisciplinary activities between these areas and others, and with cross-cutting collaborations among various departments and schools on campus. The campus is located on the west side of Los Angeles, with convenient access to beaches / mountains / national parks and a fantastic assortment of cultural diversity and activities throughout the metropolitan LA area. UCLA is also in close proximity to many other renowned academic institutions such as Caltech, USC, and other UC campuses. Interested candidates should email Fei Sha (feisha at cs.ucla.edu) and Ameet Talwalkar (ameet at cs.ucla.edu) with their CVs, research statements and a list of reference letter writers. Best -------------- next part -------------- An HTML attachment was scrubbed... URL: From bart at parc.com Mon Dec 7 21:04:43 2015 From: bart at parc.com (bart at parc.com) Date: Tue, 8 Dec 2015 02:04:43 +0000 Subject: Connectionists: internship in deep learning, reinforcement learning, and vision at Xerox PARC Message-ID: Xerox PARC is looking for interns in the area of reinforcement learning. PhD candidates willing to do part of their graduate work at PARC will also be considered. We are particularly interested in deep learning, reinforcement learning, and Bayesian optimization. Additional details about the project and the application process can be found here: http://careers.jobscore.com/jobs2/paloaltoresearchcenter/learning-autonomous-control-for-real-world-manipulation-tasks/aZr3aKMf0r5ArNeMg-44q7?ref=rss&sid=68 You can also email me with questions if necessary. Sincerely, Eugene Bart -------------- next part -------------- An HTML attachment was scrubbed... URL: From d.goodman at imperial.ac.uk Tue Dec 8 11:25:25 2015 From: d.goodman at imperial.ac.uk (Dan Goodman) Date: Tue, 8 Dec 2015 16:25:25 +0000 Subject: Connectionists: PhD position in computational neuroscience available for project "Learning to hear with plasticity across multiple timescales" at Imperial College London Message-ID: <56670475.10309@imperial.ac.uk> A PhD position is available as part of the Neurotechnology centre for doctoral training at Imperial College London, jointly supervised by Dan Goodman, Paul Chadderton, Claudia Clopath and in collaboration with Agnes Leger: - http://neural-reckoning.org/ - http://www.bg.ic.ac.uk/research/p.chadderton/ChaddertonLab/Home.html - http://www.bg.ic.ac.uk/research/c.clopath/ - http://www.psych-sci.manchester.ac.uk/staff/Agnes.Leger The title of the project is "Learning to hear with plasticity across multiple timescales", and it aims at understanding how the brain adapts and learns to cope with difficult listening situations (e.g. a crowded pub or restaurant), and applying this to developing new technology (e.g. for speech recognition). It will involve (1) developing mathematical and computational models of hearing and neural adaptation and plasticity, (2) experimental testing (including animal electrophysiology and human psychoacoustics), and (3) technology development for speech recognition, hearing aids and cochlear implants. The candidate should be willing to learn experimental techniques (animal electrophysiology and/or human psychophysics), but is not required to have any previous experience. The PhD programme is fully funded for four years, of which the first year is a taught MRes course. In addition to working within the centre, studying at Imperial College provides excellent opportunities for interacting with other theoretical and experimental researchers, both at Imperial (recently ranked 8th in the world in the QS world university rankings) and in the many neuroscience groups in London. Note that unfortunately funding for non-UK/EU residents is quite limited and there will therefore be stronger competition for these places. For more details on this project, the centre, and how to apply: http://www.imperial.ac.uk/neurotechnology/cdt/projects/hear_with_plasticity/ Dan Goodman From dmochowski at gmail.com Tue Dec 8 15:03:58 2015 From: dmochowski at gmail.com (Jacek Dmochowski) Date: Tue, 8 Dec 2015 15:03:58 -0500 Subject: Connectionists: PhD position in non-invasive brain stimulation at CCNY Message-ID: Applications are invited for one Ph.D. position in the Department of Biomedical Engineering at the City College of New York (start date of Fall 2016). The research will be conducted in the lab of Jacek Dmochowski, and will combine electroencephalography (EEG) and transcranial electrical stimulation (TES) to develop rational techniques for modulating brain activity. The work will span theoretical, computational, and experimental approaches, and will thus allow the candidate to develop a breadth of expertise in the promising area of non-invasive brain stimulation. The ideal candidate holds a Master?s Degree in Biomedical Engineering, Physics, Neurobiology, or a closely related field, and possesses an interest in human neuroscience. Strong computer programming skills are an asset. Interested applicants should send a cv, a brief statement of interests, along with contact information for two references to jdmochowski at ccny.cuny.edu. Location: the main campus of The City College of New York is comprised of 36 tree-lined acres running from 133rd Street to 140th Street in Harlem, bounded by St. Nicholas Terrace and St. Nicholas Park on the east and Amsterdam Avenue on the west. -------------- next part -------------- An HTML attachment was scrubbed... URL: From stefano.panzeri at gmail.com Tue Dec 8 22:58:24 2015 From: stefano.panzeri at gmail.com (Stefano Panzeri) Date: Wed, 9 Dec 2015 04:58:24 +0100 Subject: Connectionists: Postdoctoral position in Computational Neuroscience at the Italian Institute of Technology to study origin and function of slow cortical oscillations Message-ID: *Postdoctoral position in Computational Neuroscience at the Italian Institute of Technology to study origin and function of slow cortical oscillations* We are soliciting applications a new postdoctoral position in computational neuroscience in the newly established and highly interdisciplinary Neural Coding Laboratory at the IIT. This laboratory, jointly supervised by Stefano Panzeri and Tommaso Fellin, aims at combining experiments and mathematics to crack the neural code. The successful candidate will develop and use tools for the analysis of joint recordings of field potentials and single-neuron activity from genetically identified cell types in the cortex to understand the causal contribution of specific cellular subpopulations to the generation of slow oscillations. The project will also require the development of computational models that may explain the contribution of specific cell types to slow oscillations. The laboratory offers a range of strongly interdisciplinary and highly complementary expertise including computational neuroscience, electrophysiology and optogenetics. The successful candidate will have the opportunity to analyze experimental data and to suggest causal manipulations based on the predictions that arise from the theoretical work. The applicants should have a strong background in numerate sciences, be highly independent and have a strong propensity for interdisciplinary research. Experience in or understanding of experimental neuroscience is desirable, but not necessary. Candidates must hold a PhD in computational neuroscience, (bio)-physics, (bio)-engineering or a related discipline and be highly motivated and creative individuals who want to work in a dynamic, multi-disciplinary research environment and who are willing to interact with both experimental and theoretical neuroscientists. For reference to recent work of the PIs please see Zuo et al. Cur. Biol. 2015; Panzeri et al. Trends Cogn. Neurosci. 2015; Bovetti and Fellin, J. Neurosci. Methods 2015; Einevoll et al. Nat. Rev. Neurosci. 2013; Beltramo et al., Nat. Neurosci. 2013. Applications (full CV, two recommendation letters and statement of research interest) should be sent by email to Dr. Stefano Panzeri ( stefano.panzeri at iit.it ) and Dr. Tommaso Fellin (tommaso.fellin at iit.it ). -------------- next part -------------- An HTML attachment was scrubbed... URL: From Pavis at iit.it Wed Dec 9 09:07:39 2015 From: Pavis at iit.it (Pavis) Date: Wed, 9 Dec 2015 14:07:39 +0000 Subject: Connectionists: IIT - Italy - Postdoctoral position in Pattern Recognition, Machine Learning and Computer Vision for the analysis of retinal electrophysiology in response to visual stimulation, with specific expertise in deep learning and sparse learning BC: 713... In-Reply-To: <0E09F354EB71FC40A4D51EE54D8A9C883B59BA4E@IITMXWGE015.iit.local> References: <0E09F354EB71FC40A4D51EE54D8A9C883B59BA4E@IITMXWGE015.iit.local> Message-ID: <0E09F354EB71FC40A4D51EE54D8A9C883B59BA72@IITMXWGE015.iit.local> Postdoctoral position in Pattern Recognition, Machine Learning and Computer Vision for the analysis of retinal electrophysiology in response to visual stimulation, with specific expertise in deep learning and sparse learning BC: 71326 - 71327 Fondazione Istituto Italiano di Tecnologia ? IIT ? was established by the Italian government to promote technological development and training in the scientific and technological field. Toward this end, IIT is implementing a detailed scientific program, which comprises integration across fundamental research and application. IIT?s research endeavour focuses on high-tech and innovation, representing the forefront of technology with possible application from medicine to industry, computer science, robotics, life sciences and nano-biotechnologies. One postdoctoral position in Computer Vision, Pattern Recognition and Machine Learning is available in the department of Pattern Analysis and Computer Vision (PAVIS) at the Istituto Italiano di Tecnologia (IIT) ,Genova, Italy. PAVIS department has consolidated expertise in image processing, computer vision, pattern recognition and machine learning and aims at studying and designing intelligent systems for the analysis and understanding of real-world problems. PAVIS focuses in particular on activities related, but not limited, to surveillance and security, biomedical imaging, and bioinformatics. Project Description The research position is funded by the European project ?RENVISION - Retina-inspired ENcoding for advanced VISION tasks? (http://www.renvision-fp7.eu/). The overall aim of the project is to achieve a comprehensive understanding of how the retina encodes complex visual scenes, and to use such insights to develop new computational models of retina and toapply them to high-level computer vision tasks, such as scene categorization and action recognition. The project is highly interdisciplinary, including neuro-engineering, electrophysiology, high-resolution microscopy imaging, computational modelling, data analysis, machine learning and computer vision. RENVISION is funded by the European Commission FP7 Future Emerging Technologies programme, under contract n. 600847. Description of the research The candidate will design novel methodologies and algorithms based on pattern recognition and machine learning techniques, aiming at analysing electrophysiological recordings in response to visual stimulation of retina. The main objective of the research is the discovery/determination of representative and/or discriminative features in retina coding allowing for high-level vision tasks, such as scene categorization and action recognition. To this purpose, deep learning, sparse and dictionary learning approaches are to be considered. Experience and Qualifications We are seeking a self-motivated individual with the ability to take day-to-day responsibility for the progress of the proposed work. The ideal candidate will have a PhD in Computer Science, Mathematics, Electronic Engineering or a closely-related discipline, with competences on machine learning/pattern recognition/computer vision, coupled with a keen interest in neuroscience and biological data processing and analysis. Expertise in deep learning, compressive sensing, and/or dictionary learning is in general preferred. Experience in spiking networks or retinal function will be appreciated while not being a discriminating factor. A strong programming skill is required. Annual salary will depend on research experience and qualification. Closing Date The initial deadline for applications is January 31st, 2016, however please note that the search will continue until appropriate candidates have been identified. How to apply Completed application forms along with a curriculum listing all publications (possibly including pdfs of the most representative ones), names of 2 referees and a research statement (describing previous research experience and outlining its relevance to the above topics) should be sent by email to Prof. Vittorio Murino vittorio.murino at iit.it or Diego Sona diego.sona at iit.it, quoting PAVIS-PD 71327 ? 71326 as reference number. For informal enquiries please write to Prof. Vittorio Murino vittorio.murino at iit.it or Diego Sona diego.sona at iit.it. In order to comply with Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), the candidate is kindly asked to give his/her consent to allow Istituto Italiano di Tecnologia to process his/her personal data. We inform you that the information you provide will be solely used for the purpose of evaluating and selecting candidates in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, with its headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper-based means, observing the rules on the protection of personal data, including those relating to the security of data, and they will not be communicated to thirds. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Holder. Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in its workforce From Pavis at iit.it Wed Dec 9 09:05:24 2015 From: Pavis at iit.it (Pavis) Date: Wed, 9 Dec 2015 14:05:24 +0000 Subject: Connectionists: IIT - Italy - Postdoctoral position in Computer Vision, Machine Learning and Pattern Recognition - BC 71372 In-Reply-To: <0E09F354EB71FC40A4D51EE54D8A9C883B59BA38@IITMXWGE015.iit.local> References: <0E09F354EB71FC40A4D51EE54D8A9C883B59BA38@IITMXWGE015.iit.local> Message-ID: <0E09F354EB71FC40A4D51EE54D8A9C883B59BA61@IITMXWGE015.iit.local> Postdoctoral position in Computer Vision, Machine Learning and Pattern Recognition BC:71372 Fondazione Istituto Italiano di Tecnologia - IIT - was founded with the objective of promocting Italy?s technological development and further education in science and technology. In this sense, IIT?s scientific program is based in the combination of basic scientific research and development of technical applications, a major inspirational principle. Researchareas cover scientific topics of high innovative content, representing the most advanced frontiers of modern technology, with wide application possibilities in various fields ranging from medicine to industry, from computer science to robotics, life sciencesand nanobiotechnology. PAVIS department at Istituto Italiano di Tecnologia (IIT) (http://www.iit.it/pavis) is looking for a highly qualified researcher with a strong background in Computer Vision, Pattern Recognition and Machine Learning, with particular emphasis on recognition, video analysis, behavior understanding and prediction. As the activities may be carried out in collaboration with other research units inside IIT, previous multidisciplinary experience is an added value which will be duly considered. The main mission of PAVIS (Pattern Analysis and Computer Vision) is to design and develop innovative video surveillance systems, characterized by the use of highly-functional smart sensors and advanced video analytics features. PAVIS also plays an active role in supporting the other research units inside IIT providing providing scientists in Neuroscience, Nanophysics and other IIT departments/centers with ad hoc solutions. To this end, the group is involved in activities concerning computer vision and pattern recognition, machine learning, multimodal data analysis and sensor fusion, and embedded computer vision systems. The lab will pursue this goal by working collaboratively and in cooperation with external private and public partners. In particular, this call aims at consolidating PAVIS expertise in one or more of the following research areas: Analysis of static and dynamic scenes. Recognition (objects, scenes, actions, events, etc.). Behavior Analysis & Activity Recognition (individuals, groups, crowd). Prediction of intentions. And, from the methodological point of view, in one or more of the following subjects: Graphical Models, Topic Models, Deep Learning, Representation/Feature Learning, Transfer Learning, Domain Adaptation, Sparse Learning, and Statistical and Probabilistic Models in general. Candidates to this position have a Ph.D. in computer vision, machine learning or related areas. Research experience and qualification in computer vision and pattern recognition/machine learning are clearly a must and evidence of top quality research on the above specified areas in the form of published papers in top conferences/journals and/or patents is mandatory. Experience in the preparation and management of research proposals (EU, US, national) and a few years of postdoc experience, either in academia or industrial lab, will also be duly considered. The scientist is expected to publish his/her research results in leading international journals and conferences. She/he is also expected to contribute to the set-up of new project proposals, participate in funding activities,supervising PhD candidates and collaborate with other scientists, also with different (neuroscience) expertise. Salary will be commensurate to qualification and experience and in line with international standard. Working location: Genova, Italy. Further details and informal enquires can be made by email to pavis at iit.it quoting PAVIS-PD 71372 as reference number. Completed application forms along with a curriculum listing all publications (possibly including pdf of your most representative publications), and a research statement describing your previous research experience and outlining its relevance to the above topics should be sent by email to pavis at iit.it, quoting PAVIS-PD 71372 as reference number. Please also indicate 2 independent references inside the CV or the email. This call will remain open and applications will be reviewed until the position is filled but for full consideration please apply by January 31st, 2015. In order to comply with Italian law (art. 23 of Privacy Law of the Italian Legislative Decree n. 196/03), the candidate is kindly asked to give his/her consent to allow Istituto Italiano di Tecnologia to process his/her personal data. We inform you that the information you provide will be solely used for the purpose of evaluating and selecting candidates in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, with its headquarters in Genoa, Via Morego 30, acting as the Data Holder, using computer and paper-based means, observing the rules on the protection of personal data, including those relating to the security of data, and they will not be communicated to thirds. Please also note that, pursuant to art.7 of Legislative Decree 196/2003, you may exercise your rights at any time as a party concerned by contacting the Data Holder. Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in the workforce. -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.hennig at ed.ac.uk Thu Dec 10 10:00:53 2015 From: m.hennig at ed.ac.uk (Matthias Hennig) Date: Thu, 10 Dec 2015 15:00:53 +0000 Subject: Connectionists: PhD at Edinburgh on data analysis Message-ID: <566993A5.2040500@ed.ac.uk> A funded PhD position is available at the University of Edinburgh to develop and implement efficient paralellised methods for analysis of large scale, high density multielectrode array recordings. The project will focus on analysis of primary raw data from a 4,096 channel array, and aims at improving spike detection and sorting, and statistical analysis of multi-neuron activity. Data will come from the labs of Evelyne Sernagor (Newcastle, retina) and Luca Berdondini (IIT Genova, cultured networks). Applicants should have a strong quantitative background and interest in interdisciplinary research. Background in neuroscience and/or parallel programming is desirable, but not essential. This position is available to UK/EU applicants, and eligible for funding by the EPSRC CDT in Pervasive Parallelism. Interested individuals should send a c.v., statement of interest and the names of three references to Matthias Hennig (h.hennig at ed.ac.uk). Apply by 1 February 2016. PPar http://pervasiveparallelism.inf.ed.ac.uk/ J.-O. Muthmann, H. Amin, E. Sernagor, A. Maccione, D. Panas, L. Berdondini, U.S. Bhalla, M.H. Hennig (2015). Spike detection for large neural populations using high density multielectrode arrays. Front Neuroinform, 9:28. http://journal.frontiersin.org/article/10.3389/fninf.2015.00028/abstract D. Panas, H. Amin, A. Maccione, O. Muthmann, M. van Rossum, L. Berdondini, M.H. Hennig (2015). Sloppiness in spontaneously active neuronal networks. J Neurosci, 35(22): 8480-8492. http://www.jneurosci.org/content/35/22/8480.full -- Matthias H Hennig http://homepages.inf.ed.ac.uk/mhennig/ -- Matthias H Hennig http://homepages.inf.ed.ac.uk/mhennig/ The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From H.Abbass at adfa.edu.au Tue Dec 8 23:51:05 2015 From: H.Abbass at adfa.edu.au (Hussein Abbass) Date: Wed, 9 Dec 2015 04:51:05 +0000 Subject: Connectionists: Post-Doctoral Fellow - UNSW-Canberra - User-Task Co-adaptation Message-ID: School of Engineering and Information Technology Post-Doctoral Fellow: Fixed term - 1 Year Extendable to 3 Years Salary: Level A: $69,341 - $92,453 (+super) Applications must be submitted online at: https://www.unsw.adfa.edu.au/online-application-form?id=15856 Advertisement on UNSW-Canberra Website: https://www.unsw.adfa.edu.au/career/academic-job-opportunities Advertisement on Seek: http://www.seek.com.au/job/30024507?pos=1&type=standout&engineConfig=control&tier=no_tier&whereid=3000 Advertisement on UniJobs: http://www.unijobs.com.au/unsw-canberra-jobs/HY06/post-doctoral-fellow The School of Engineering and Information Technology is currently seeking a suitably qualified and motivated Post-Doctoral Fellow to contribute to an Australian Research Council Discovery Project grant entitled "User-task co-adaptation for effective interactive simulation environments". The project is collaboration between the Trusted Autonomy Group at UNSW-Canberra and teams from the National University of Singapore and the Singapore Institute of Neurotechnology (SINAPSE). This is a fixed term position available initially for 12 months with an extension of 2 years, subject to performance indicators being met, to be negotiated and agreed on before the start of position. The successful applicant will be able to demonstrate their ability to design and implement innovative machine learning and augmented cognition models that can learn user and task features dynamically from behaviours in a human-robot task. User data may include keyboard strokes, eye gaze, speech, gesture, and EEG signals. Task data normally takes the form of time-series task performance indicators and/or task complexity metrics. Applicants should have a PhD in computer science, electrical engineering, cognitive science, or a relevant discipline; are expected to be self-motivated and independent researchers capable of working as part of a team; have a proven record of high quality conference and/or journal papers; and possess excellent communication skills. Skills in deep networks and/or multi-agent systems are desirable. For application and position description information, please visit our website: https://www.unsw.adfa.edu.au/post-doctoral-fellow-1 For additional information about this position, please contact Prof. Hussein Abbass on (02) 6268 8158 or email h.abbass at adfa.edu.au An applicant may be required to undergo pre-employment checks prior to appointment to this role. ________________________________ UNSW AUSTRALIA UNSW CANBERRA AT THE AUSTRALIAN DEFENCE FORCE ACADEMY PO Box 7916, CANBERRA BC 2610, Australia Web: http://unsw.adfa.edu.au CRICOS Provider no. 00098G This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender and are not necessarily the views of UNSW. -------------- next part -------------- An HTML attachment was scrubbed... URL: From gluck at pavlov.rutgers.edu Thu Dec 10 09:02:05 2015 From: gluck at pavlov.rutgers.edu (Mark Gluck) Date: Thu, 10 Dec 2015 09:02:05 -0500 Subject: Connectionists: Coming February, 3rd edition of our textbook, Learning and Memory: From Brain to Behavior. REQUEST A FREE EXAMINATION COPY FOR INSTRUCTORS Message-ID: The 3rd edition of our textbook, Learning and Memory: From Brain to Behavior (Gluck, Mercado, & Myers, 2016), will be published by Macmillan/Worth this coming February. There are also Spanish, German, and Korean translations available. For more information, and to submit an online Request for a Free Examination Copy for Instructors, see: http://www.macmillanhighered.com/Catalog/product/learningandmemory-thirdedition-gluck "With its modular organization, consistent chapter structure, and contemporary perspective, this groundbreaking survey is ideal for courses on learning and memory, and is easily adaptable to courses that focus on either learning or memory. Instructors can assign the chapters they want from four distinctive modules (introduction, learning, memory, and integrative topics), with each chapter addressing behavioral processes, then the underlying neuroscience, then relevant clinical perspectives. The book is further distinguished by its full-color presentation and coverage that includes comparisons between studies of human and nonhuman brains. *** The new edition offers enhanced pedagogy and more coverage of animal learning *** REVIEWS: Students rated the reading very highly and felt the information was very clearly written and engaging. - Nanthia Suthana, UCLA I love the way this textbook organizes the chapters to the three different parts. It helps me with teaching the material because it keeps me organized and it allows for a nice transition during the lectures. This structure seems to benefit the students as well. They have said that it makes studying the material in the book easier when it is broken down into chunks. - Monica Bolton, University of Nevada, Las Vegas Between the writing style and wonderful graphics I am absolutely in love with this text. - Arlo Clark-Foos, University of Michigan, Dearborn I love the organization, that?s the primary reason I selected the book in the first place. Covering all three parts [behavioral processes, brain substrates, and clinical perspectives] ensures that most (if not all) students can find something of interest. For instance, I have a number of clinical psych students take the course who typically enjoy learning how the behavior and brain material is translated into clinical outcomes. - Derek Lindquist, The Ohio State University TABLE OF CONTENTS: Introductory Module 1. The Psychology of Learning and Memory 2. The Neuroscience of Learning and Memory Learning Module 3. Habituation, Sensitization, and Familiarization: Learning about Repeated Events 4. Classical Conditioning: Learning to Predict Important Events 5. Operant Conditioning: Learning the Outcome of Behaviors 6. Generalization and Discrimination Learning Memory Module 7. Episodic and Semantic Memory: Memory for Facts and Events 8. Skill Memory: Learning by Doing 9. Working Memory and Cognitive Control Integrative Topics Module 10. Emotional Influences on Learning and Memory 11. Social Learning and Memory: Observing, Interacting, and Reenacting 12. Development and Aging: Learning and Memory across the Lifespan COVER: ___________________________________ Dr. Mark A. Gluck, Professor Center for Molecular & Behavioral Neuroscience Rutgers University ? Newark 197 University Ave. Newark, New Jersey 07102 Web: http://www.gluck.edu Email: gluck at pavlov.rutgers.edu Ph: ( 973) 353-3298 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: gluckcomp 11_30_15_B.pdf Type: application/pdf Size: 60418 bytes Desc: not available URL: -------------- next part -------------- An HTML attachment was scrubbed... URL: From g.goodhill at uq.edu.au Thu Dec 10 05:24:28 2015 From: g.goodhill at uq.edu.au (Geoff Goodhill) Date: Thu, 10 Dec 2015 20:24:28 +1000 Subject: Connectionists: ACAN 2016 - Call for Applications Message-ID: <9958333E-2C06-412C-BE93-45569F3FDB46@uq.edu.au> Graduate students and postdoctoral fellows interested in using electrophysiological and optical techniques in their research are encouraged to apply for the Australian Course in Advanced Neuroscience (ACAN) 2016, which will be held from 10th to 30th of April 2016 at the Moreton Bay Research Station, North Stradbroke Island, Queensland, Australia. ACAN is an intensive three-week course that guides participants through the theory and practice of electrophysiological recording and optical imaging techniques using a unique balance of small group lectures and hands-on laboratory work. Lectures from leading faculty will outline in an informal atmosphere the theoretical basis of cellular and systems neuroscience, and the principles of electrophysiological and optical recording techniques. During the course each participant will become proficient in patch-clamp recording, both in vitro and in vivo, calcium imaging, optogenetics, and many other techniques through unbridled access to state-of-the-art equipment, guided by the faculty. The course is also a lot of fun, with many ACAN students developing close friendships and collaborations during and after the course. In 2016 ACAN faculty will include: Cliff Abraham Ehsan Arabzadeh George Augustine Brad Baker John Bekkers Yossi Buskila Vincent Daria Alan Finkel Andreas Frick Yukiko Goda Geoff Goodhill Brett Graham Maarten Kole Matthew Larkum Joe Lynch Peregrine Osborne Lucy Palmer Steve Petrou Chris Reid Mala Shah Stephen Williams Twelve students will be selected to attend ACAN 2016. The application deadline is Monday 11th Jan 2016. For full details about the course, including the program, please visit: http://acan.qbi.uq.edu.au In order to apply for ACAN 2016, you must: be a currently-enrolled PhD student, a postdoctoral fellow, or junior faculty (preferably with no more than 5 years after completing your PhD). Preference will be given, but is not exclusive, to those who are full-time residents of Australia or NZ (but you do not need to be a citizen or permanent resident of those countries). In your application you should include: - a completed application form (obtained from http://acan.qbi.uq.edu.au) - your CV. - a covering letter that clearly states how you will apply the skills taught at ACAN to your research. - a reference from your supervisor, including a confirmation that funds are available to allow you to attend the course. - The fee for ACAN 2016 is A$4500, which covers all meals, accommodation, laboratory supplies and teaching materials. Scholarships from the Neurological Foundation of New Zealand are available for NZ citizens/permanent residents. Please send applications to: Prof Stephen Williams Queensland Brain Institute Email: srw at uq.edu.au http://www.qbi.uq.edu.au/group-leader-williams From xwe at cis.upenn.edu Mon Dec 14 18:16:20 2015 From: xwe at cis.upenn.edu (Wei Xu) Date: Mon, 14 Dec 2015 18:16:20 -0500 Subject: Connectionists: NAACL HLT 2016 - 2nd Call for Papers Message-ID: The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT 2016) June 12 to June 17, 2016 San Diego, California, United States http://naacl.org/naacl-hlt-2016/ NAACL HLT 2016 will feature long papers, short papers, demonstrations, and a student research workshop, as well as associated tutorials and workshops. In addition, some of the presentations at the conference will be of papers accepted for the new Transactions of the ACL journal ( http://www.transacl.org). The conference invites the submission of long and short papers on substantial, original, and unpublished research in all aspects of automated language processing and creation of language resources. The short paper format may also be appropriate for a small, focused contribution, a work in progress, a negative result, an opinion piece or an interesting application nugget. Topics of interest include, but are not limited to the study of the following language areas, tasks, genres and approaches to language analysis: * Linguistic Areas of Study * - Discourse: anaphora resolution, discourse relation tagging, theories and systems for text organization evaluation, methods for analysis of dialog structure (spoken or written) and discourse semantics - Morphology - Phonology and phonetics - Pragmatics - Prosody - Semantics: event, lexical, distributional, formal, extra-propositional, grounding and ontologies - Tagging, chunking, syntax and parsing * Application Tasks * - Dialogue and interactive systems, automatic speech recognition other spoken language processing - Image/video description generation - Language understanding, language generation, summarization, information extraction, question answering, information retrieval, machine translation, recognizing textual entailment and semantic equivalence, relation extraction, text simplification - Mathematical models of language - Predicting speaker/writer characteristics - Sentiment analysis, text categorization (of words, sentences and longer texts), text quality prediction, style analysis and lexicon induction - Spelling and grammar correction and computer-aided learning - Tokenization/word segmentation for Chinese and similar languages and word segmentation in spoken utterances * Research Goals * - Cognitive modeling and psycholinguistic research - Corpus creation and evaluation - End-user application building - Integrate language and other modalities - Linguistic theories for NLP - Machine learning for NLP - Sociolinguistic research * Approaches to Language Processing Tasks * - Machine learning: topic modeling, structured prediction, deep learning, bayesian models, kernel methods, generative models, discriminative models, semi-supervised learning, representation learning - Optimization - Exploiting multilingual resources - Modeling linguistic knowledge (e.g., grammars) - Algorithm development for NLP - Corpus/data analysis * Genres * - Biological and medical text (BioNLP) - Chat and Email (private unedited written dialog) - Literature - News - Social media: twitter, blogs, discussion forums and other social media - Spoken dialog and other spoken genres - Search log analysis * Languages * - Low-Resource Languages - Morphologically rich languages - Other specific living language(s) = Important Dates = * Deadline for BOTH Long and Short paper submission: Jan 6, 2016 * Author response period: Feb 10?15, 2016 * Notification to authors: Mar 2, 2016 All deadlines are 11:59PM Pacific Time. Please DO NOT submit the same paper in long and short paper form. = Submissions = * Long Papers * NAACL HLT 2016 long paper submissions must describe substantial, original, completed and previously unpublished work. The long paper deadline is January 6, 2016 by 11:59PM Pacific Standard Time (GMT-8). Each submission will be reviewed by at least three program committee members. Long papers may consist of up to eight (8) pages of content, plus unlimited pages for references. Upon acceptance, final versions of long papers will be given one additional page (up to 9 pages with unlimited pages for references) so that reviewers? comments can be taken into account. Papers will be presented orally or as a poster presentation as determined by the program committee. There will be no distinction in the proceedings between long papers presented orally and those presented as poster presentations. * Short Papers * NAACL HLT 2016 also solicits short papers. Short paper submissions must describe original, completed and previously unpublished work. The short paper deadline this year is also January 6, 2016 by 11:59PM Pacific Standard Time (GMT-8). Types of short papers include: - A small, focused contribution - A negative result - An opinion piece - An interesting application nugget Short papers may consist of up to four (4) pages of content, plus unlimited pages for references. Upon acceptance, short papers will be given five (5) pages in the proceedings and unlimited pages for references. Authors are encouraged to use this additional page to address reviewers comments in their final versions. Short papers will be presented in one or more oral or poster sessions. While short papers will be distinguished from long papers in the proceedings, there will be no distinction in the proceedings between short papers presented orally and those presented as poster presentations. Each short paper submission will be reviewed by at least three program committee members. * Electronic Submission * Papers should be submitted electronically using the Softconf START conference management system at the following URL: https://www.softconf.com/naacl2016/papers The site will be open for accepting submissions one month before the conference deadline. * Multiple Submission Policy * Papers that have been or will be submitted to other meetings or publications must indicate this at submission time. Authors of papers accepted for presentation at NAACL HLT 2016 must notify the program chairs by the camera-ready deadline as to whether the paper will be presented. All accepted papers must be presented at the conference to appear in the proceedings. We will not accept for publication or presentation papers that overlap significantly in content or results with papers that will be (or have been) published elsewhere. Authors submitting more than one paper to NAACL HLT must ensure that submissions do not overlap significantly (>25%) with each other in content or results. Authors should not submit short and long versions of papers with substantial overlap in their original contributions. What is Considered ?Unpublished Work?? All prior peer-reviewed publications, either at a conference or workshop, are considered published prior work. Preprints such as those on arXiv.org and technical reports that are not peer reviewed are not considered prior published work for purposes of submission. Authors must state in the online submission form the name of the workshop or preprint server and title of the non-archival version. The version submitted to NAACL HLT should be suitably anonymized and not contain references to the prior non-archival version. Reviewers will be told: ?The author(s) have notified us that there exists a non-archival previous version of this paper with significantly overlapping text. We have approved submission under these circumstances, but to preserve the spirit of blind review, the current submission does not reference the non-archival version.? Reviewers are free to do what they like with this information. = Contact = * Program Co-Chairs * Ani Nenkova, University of Pennsylvania Owen Rambow, Columbia University Email: naacl2016-program at googlegroups.com * General Chair * Kevin Knight, USC Information Sciences Institute * Area chairs * Mohit Bansal, TTI-Chicago Regina Barzilay, MIT Eduardo Blanco, University of North Texas Asli Celikyilmaz, Microsoft Cristian Danescu-Niculescu-Mizil, Cornell University Markus Dreyer, Amazon Chris Dyer, Carnegie Mellon University Jacob Eisenstein, Georgia Institute of Technology Micha Elsner, The Ohio State University Eric Fosler-Lussier, The Ohio State University Alexander Fraser, University of Munich Michel Galley, Microsoft Research Kevin Gimpel, Toyota Technological Institute at Chicago Dilek Hakkani-T?r, Microsoft Research Helen Hastie, Heriot-Watt University Yulan He, Aston University Dirk Hovy, University of Copenhagen Heng Ji, Rensselaer Polytechnic Institute Jing Jiang, Singapore Management University Annie Louis, University of Essex Chin-Yew Lin, Microsoft Research Daniel Marcu, Information Sciences Institute, University of Southern California Margaret Mitchell, Microsoft Research Alessandro Moschitti, Qatar Computing Research Institute, HBKU Hwee Tou Ng, National University of Singapore Viet-An Nguyen, Facebook Mari Ostendorf, University of Washington Marius Pasca, Google Slav Petrov, Google Dan Roth, University of Illinois Alexander Rush, Harvard University Kenji Sagae, KITT.AI Giorgio Satta, University of Padua Hinrich Schuetze, LMU Munich William Schuler, the Ohio State University Mihai Surdeanu, University of Arizona Kristina Toutanova, Microsoft Research Byron Wallace, University of Texas at Austin Xiaojun Wan, Peking University Furu Wei, Microsoft Research Dekai Wu, Hong Kong University of Science and Technology Fei Xia, University of Washington -------------- next part -------------- An HTML attachment was scrubbed... URL: From ralph.etiennecummings at gmail.com Mon Dec 14 09:46:26 2015 From: ralph.etiennecummings at gmail.com (Ralph Etienne-Cummings) Date: Mon, 14 Dec 2015 09:46:26 -0500 Subject: Connectionists: Telluride Neuromorphic Cognition Engineering Workshop 2016: Call for Topics Message-ID: Call for Topic Area Proposals 2016 Neuromorphic Cognition Engineering Workshop *Telluride, Colorado, June 26 ?July 16, 2016* *DEADLINE: January 8th, 2016* We are now accepting proposals for Topic Areas in the 2016 Telluride Neuromorphic Cognition Engineering Workshop. We support topics and projects in neuromorphic cognition, particularly those that involve solving challenging ?everyday? tasks that incorporate domain-specific knowledge, exploration, prediction, and problem solving. In particular, we are interested in projects that hold promise for addressing Grand Challenge types of problems that do not have strong solutions of any form, neuromorphic or not. These Challenge problems should feature long-duration sensorimotor problems that involve autonomous cognitive decision making. Examples might include tasks such as learning a new language, navigating through an unknown environment to locate an object or reach a desired location, visual and auditory understanding of human actions, adaptively manipulating unknown or complex objects in the service of a task, playing a game requiring inference of hidden information or long-term planning and learning, etc. Proposals related to hardware technologies that aim to bring these capabilities to reality are also encouraged. Topic proposals that aim to solve a particular problem using the multidisciplinary experience of participants will be favored over topics that simply gather a large number of people working within a discipline, or using a single technology, or approach. Topic areas for this summer's Telluride Neuromorphic Cognition Engineering Workshop will be chosen from proposals submitted to the organizers. *Topic areas can span a large field; we are looking for leadership in planning activities and inviting good people in a field.* Although past topic areas have tended to be very broad and discipline-oriented (e.g., cognition, audition, vision, robotics, neural interfacing, neuromorphic VLSI, etc.), application-oriented topic areas (e.g., sensor fusion, game-playing robot, object recognition, sound localization, human robot interaction, etc.) are especially desirable. *Topic area leaders will receive housing for themselves and their invitees, and limited travel funds.* Topic area leaders will help to define the field of neuromorphic cognition engineering through the projects they pursue and the people they invite. They shape their topic by inviting speakers and project leaders (the *invitees*) and by initiating topic area project discussions prior to the workshop. Teams of two organizers are required. One of the organizers should be an attendee of a previous Telluride Workshop (in any capacity) and has stayed at the Workshop for at least one week. *Pre-workshop topic area choices and study assignments.* Before the workshop begins, each topic area will be required to prepare and distribute study materials that constitute: 1) an introductory presentation (e.g., pptx, video, review paper) of the fundamental knowledge associated with the topic area that *everyone at the workshop* should be exposed to, and 2) a few critical papers that the participants in the topic area should read before the workshop. The topic area should 3) begin a serious group discussion of the projects (e.g., via Facebook, Skype, email, etc). *The maximum 2-page proposals should include:* 1. Title of topic area. 2. Names of the two topic leaders, their affiliations, and contact information (email addresses). 3. A paragraph explaining the focus and goals of the topic area. 4. A list of possible specific topic area projects. 5. A list of example invitees (up to six names and institutions). No commitments necessary. 6. Any other material that fits within the two-page limit that will help us make a smart choice. *Send your topic area proposal* in pdf or text format to organizers13 at neuromorphs.net with subject line containing "topic area proposal". *Proposals must be received by January 8, 2016*; proposals received after the deadline may still be considered if space is available. *We expect to accept 4-5 topic areas*, each with 5 invitees*.* If your proposal for the topic area is not accepted, we will work with you to see if there is a natural way to include your ideas (and you) into the accepted topic areas. We hope to have significant turn-over each year in the topic areas and leaders to ensure fresh new ideas and participants. See the Institute of Neuromorphic Engineering (www.ine-web.org) for background information on the workshop and neuromorphs.net for past workshop wikis. We look forward to your topic proposals! *Deadline: January 8, 2016* *The Workshop Directors:* Cornelia Ferm?ller (University of Maryland), Ralph Etienne-Cummings (Johns Hopkins Univ.) Shih-Chii Liu (University of Zurich and ETH Zurich), Timmer Horiuchi (University of Maryland), Katalin Gotthard (University of Arizona), Michael Pfeiffer (University of Zurich and ETH Zurich), Francisco Barranco (University of Granada) *Former 2007-2013 Workshop Director: * Tobi Delbruck (University of Zurich and ETH Zurich) -- Ralph Etienne-Cummings, PhD, FIEEE Professor and Chairman Department of Electrical and Computer Engineering Computational Sensor Motor Systems Lab Laboratory for Computational Sensing and Robotics The Johns Hopkins University Baltimore, MD [image: cid:image001.png at 01CFC064.B58B46A0] -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 20171 bytes Desc: not available URL: From rloosemore at susaro.com Mon Dec 14 11:20:57 2015 From: rloosemore at susaro.com (Richard Loosemore) Date: Mon, 14 Dec 2015 11:20:57 -0500 Subject: Connectionists: Comparing speech recognition Word Error Rates is deceiptful, please stop In-Reply-To: <9958333E-2C06-412C-BE93-45569F3FDB46@uq.edu.au> References: <9958333E-2C06-412C-BE93-45569F3FDB46@uq.edu.au> Message-ID: <566EEC69.1020501@susaro.com> I just read "Deep Speech 2: End-to-End Speech Recognition in English and Mandarin" by Amodei et al. ( http://arxiv.org/abs/1512.02595v1, and I have finally reached the end of my tether over the reporting of Word Error Rates (WER). These rates are being used to make a comparison with human performance on TRANSCRIPTION of speech. But transcription involves recognition plus a complex pile of work like memory storage, time pressure, and semantic paraphrasing. And I would be willing to bet that almost all the errors are in the non-recognition parts. But by using transcription error, the reported error rate for humans is supposedly about 5%, and on that basis Amodei et al declare that their system is now better than human. That is ludicrous. If I give an hour-long lecture I can cram in about 20,000 words, and I would be willing to bet that not one of those words would be misrecognized by any of the students in my audience who were actually awake. That would be an error rate that is three orders of magnitude smaller than the one for transcription. Amodei et al (and all the other deep learning speech recognition folks who overinflate claiims on a regular basis): your system is NOT outperforming humans, because your system should be compared with the primal recognition rate in humans, and since humans are probably about 1000 times better, you have a long way to go. Richard Loosemore From emmanuel.vincent at inria.fr Sun Dec 13 18:52:20 2015 From: emmanuel.vincent at inria.fr (Emmanuel Vincent) Date: Mon, 14 Dec 2015 00:52:20 +0100 Subject: Connectionists: 1-year research position on deep learning for distant-mic speech recognition Message-ID: <566E04B4.4020003@inria.fr> Dear list, We are offering a 1-year postdoc/R&D engineer position on distant-mic speech recognition in the context of a large-scale R&D project on voice control of home appliances involving 5 companies and 3 academic labs. The successful candidate will conduct research on state-of-the-art acoustic model adaptation and contribute to transfer his/her ideas into a commercial ASR product. More specifically, we are interested in adapting DNN acoustic models to reveberation and noise conditions by exloring deep learning-based uncertainty propagation techniques in the line of [1,2]. Ideal start: March 2016 (possible until June) Salary: 2600 to 3300 ?/month gross depending on experience, plus free health insurance and additional benefits Ideal profile: - MSc or PhD in speech processing, machine learning, audio signal processing, or applied statistics - proficient programming in C++, shell, Matlab/Python - experience with Kaldi and deep learning software To apply: send a CV, a motivation letter, a list of publications, and one or more recommendation letters to emmanuel.vincent at inria.fr and irina.illina at loria.fr. Applications will be assessed on a continuous basis until Jan 15. Please apply as soon as possible before that date. PS: if you happen to be at ASRU this week and you're interested by this position, please come and say hello. References: [1] A.H. Abdelaziz, S. Watanabe, J.R. Hershey, E. Vincent, D. Kolossa, "Uncertainty propagation through deep neural networks", Interspeech 2015. [2] Y. Tachioka, S. Watanabe, "Uncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features", Interspeech 2015. -- Emmanuel Vincent PAROLE Project-Team Inria Nancy - Grand Est 615 rue du Jardin Botanique, 54600 Villers-l?s-Nancy, France Phone: +33 3 8359 3083 - Fax: +33 3 8327 8319 Web: http://www.loria.fr/~evincent/ From poole at cs.ubc.ca Thu Dec 10 14:58:36 2015 From: poole at cs.ubc.ca (David Poole) Date: Thu, 10 Dec 2015 11:58:36 -0800 Subject: Connectionists: Faculty Positions in Computer Science at UBC, Vancouver, Canada Message-ID: <48BF5B30-6C47-47BE-9233-A15A24F994FB@cs.ubc.ca> Hi All, We have multiple tenure-track assistant professor positions in the Department of Computer Science at University of British Columbia in Vancouver. We are looking for candidates in machine learning and/or computer vision (as well as HCI and algorithms & complexity). See: https://www.cs.ubc.ca/our-department/employment/faculty-positions/tenure-track-research-positions Please forward this message to anyone who may be interested. David David Poole, Department of Computer Science, University of British Columbia, http://cs.ubc.ca/~poole poole at cs.ubc.ca From martaruizcostajussa at gmail.com Mon Dec 14 10:07:59 2015 From: martaruizcostajussa at gmail.com (Marta Ruiz) Date: Mon, 14 Dec 2015 16:07:59 +0100 Subject: Connectionists: 1st CALL FOR PAPERS: Computer Speech and Language Special Issue on Deep Learning for Machine Translation Message-ID: *Computer Speech andLanguage Special Issue on Deep Learning for Machine Translation * Deep Learning has been successfully applied to many areas including Natural Language Processing, Speech Recognition and Image Processing. Deep learning techniques have surprised the entire community both academy and industry by powerfully learning from data. Recently, deep learning has been introduced to Machine Translation (MT). It first started as a kind of feature which was integrated in standard phrase or syntax-based statistical approaches. Deep learning has been shown useful in translation and language modeling as well as in reordering, tuning and rescoring. Additionally, deep learning has been applied to MT evaluation and quality estimation. But the biggest impact on MT appeared with the new paradigm proposal: Neural MT, which has just recently (in the Workshop of Machine Translation 2015) outperformed state-of-the-art systems. This new approach uses an autoencoder architecture to build a neural system that is capable of translating. With the new approach, the new big MT challenges lie on how to deal with large vocabularies, document translation and computational power among others*.* This hot topic is raising interest from the scientific community and as a response there have been several related events (i.e. tutorial[1] <#151a106fdef5395b__ftn1> and winter school[2] <#151a106fdef5395b__ftn2>). Moreover, the number of publications on this topic in top conferences such as ACL, NAACL, EMNLP has dramatically increased in the last three years. This would be the first special issue related to the topic. With this special issue, we pretend to offer a compilation of works that give the reader a global vision of how the deep learning techniques are applied to MT and what new challenges offers. This Special Issue expects high quality submissions on the following topics (but not limited): ? Including deep learning knowledge in standard MT approaches (statistical, rule-based, example-based...) ? Neural MT approaches ? MT hybrid techniques using deep learning ? Deep learning challenges in MT: vocabulary limitation, document translation, computational power ? MT evaluation with deep learning techniques ? MT quality estimation with deep learning techniques ? Using deep learning in spoken language translation *IMPORTANT DATES* Submission deadline: 30th March 2016 Notification of rejection/re-submission: 30th July 2016 Notification of final acceptance: 30th October 2016 Expected publication date: 30th January 2017 *GUEST EDITORS* Marta R. Costa-juss?, Universitat Polit?cnica de Catalunya, Spain. marta.ruiz at upc.edu Alexandre Allauzen, Centre National de la Recherche Scientifique, France. allauzen at limsi.fr Lo?c Barrault, Universit? du Maine, France. loic.barrault at lium.univ-lemans.fr Kyunghyun Cho, New York University, USA. kyunghyun.cho at nyu.edu Holger Schwenk, Facebook, USA. schwenk at fb.com ------------------------------ [1] <#151a106fdef5395b__ftnref1> http://naacl.org/naacl-hlt-2015/tutorial-deep-learning.html [2] <#151a106fdef5395b__ftnref2> http://dl4mt.computing.dcu.ie/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From mccallum at cs.umass.edu Thu Dec 10 19:24:46 2015 From: mccallum at cs.umass.edu (Andrew McCallum) Date: Thu, 10 Dec 2015 19:24:46 -0500 Subject: Connectionists: Faculty positions at UMass Amherst: junior & senior openings in data science In-Reply-To: References: Message-ID: <726CCFB3-AEE7-49A9-A2A0-4460A21D5F4E@cs.umass.edu> I will be at NIPS throughout the workshops, and would be happy to meet in person with anyone interested in learning more about our multiple faculty openings---this year and in the years to come. I can tell you about our department's growth plans, our collegial and super-collaborative culture, the exciting research going on, and answer any questions you may have. Send me email, and we can set up a time and place. If you aren't at NIPS, contact me by email any way, and we can set up a phone call for the following week. Best, Andrew > On Nov 2, 2015, at 9:57 AM, Andrew McCallum wrote: > > > UMass Amherst Computer Science is hiring in data science broadly this year and for multiple years to come---at both the junior and senior levels. > > 3+ openings in data science this year; 12+ openings over the coming several year; (there are additional openings in other areas this year, as well). > > I am chairing faculty recruiting. I would be happy to receive email from anyone interested and to answer further questions. > > https://www.cics.umass.edu/job/assistant-associate-professor-positions > > Review of applications will begin on November 30, 2015, and will continue until the positions are filled. > > Please forward this message to anyone who might be interested. > > Best, > Andrew > Professor; Director, Center for Data Science > College of Information and Computer Sciences > UMass Amherst > > =============================================================== > > data science, broadly: > machine learning & decision-making, broadly > systems & scalable data management, broadly > theory & algorithms for big data, broadly > ...non-exclusive list of examples: > > theory & algorithms for big data > artificial intelligence with big data > databases > decision processes and reinforcement learning > deep learning > distributed systems > game theory, mechanism design > learning theory > optimization > parallel-distributed machine learning > probabilistic programming > scalable probabilistic inference > statistical machine learning > visualization and data exploration > > crowd sourcing and human computation > images & video > information integration > natural language processing > sensor networks and wearable sensors > social networks and computational social science > > climate, ecology and sustainability > computational economics > computational biology & bio-medicine > education > eGovernment > energy > eScience > finance > health analytics > internet of things > manufacturing > cities & regions > > > =============================================================== > > Our Department has become a College and we are dramatically growing our current set of ~40 faculty. UMass CS is highly ranked in AI, exceptionally collaborative, and has long-standing broad interests touching many areas of data science. Selected current faculty include: > * Akshay Krishnamurthy (statistical machine learning) > * Arya Mazumdar (information theory) > * Joydeep Biswas (robotics) > * Subhransu Maji (computer vision & ML) > * Brendan O'Connor (NLP and computational social science) > * Barna Saha (algorithms & data management) > * Alexandra Meliou (databases, analytics & causality) > * Yuriy Brun (software engineering & analytics) > * Dan Sheldon (computational ecology & ML) > * Evangelos Kalogerakis (graphics & ML) > * Ben Marlin (graphical models, ML, health analytics) > * Hanna Wallach (computational social science & ML) > * Deepak Ganesan (sensor and mobile networks, wearable health) > * Yanlei Diao (databases) > * Gerome Miklau (databases & privacy) > * Andrew McGregor (algorithms) > * Rui Wang (graphics) > * Erik Learned-Miller (computer vision & ML) > * David Jensen (data mining & causality) > * Andrew McCallum (information extraction & ML) > * Brian Levine (security) > * Sridhar Mahadevan (ML, RL & manifolds) > * Prashant Shenoy (distributed systems, cloud computing) > * Ramesh Sitaraman (theory & parallel/distributed systems) > * Shlomo Zilberstein (AI) > * James Allan (information retrieval) > * Beverly Woolf (intelligent tutoring systems) > * Rod Grupen (robotics) > * Jim Kurose (networking, on leave as head of NSF CISE) > * Neil Immerman (complexity theory) > * Bruce Croft (information retrieval) > * Don Towsley (networking) > > =============================================================== > > > The College of Information and Computer Sciences at the University of Massachusetts Amherst invites applications for multiple tenure-track faculty positions in computer science for the 2016-2017 academic year. Applicants must have a Ph.D. in Computer Science or a related area, and should show evidence of exceptional research promise. > > Subareas of interest include 1) Security and Privacy and 2) Data Science. We are seeking talented applicants at both the assistant and associate professor levels. Under exceptional circumstances, highly qualified candidates at other ranks may receive consideration. In a separately advertised search, we are also hiring in the area of wearable and mobile health sensing. > > Computer Science at the University of Massachusetts Amherst is in the midst of a major expansion of its highly ranked program. Recent initiatives include its elevation to a College, creation of the Center for Data Science, and formation of the Cybersecurity Institute. Our college is highly supportive of junior faculty, providing both formal and informal mentoring. Many of our faculty are involved in interdisciplinary research, working closely with other departments including statistics/mathematics, linguistics, electrical and industrial engineering, biology, physics, behavioral sciences, economics, political science, and nursing, as well as new "green" initiatives. Amherst, a historic New England town, is the center of a vibrant and culturally rich area that includes four other colleges. For more information, visit https://cics.umass.edu. > > Applicants should submit a cover letter, a curriculum vita, research statement, statement of teaching interests, and the names and contact information for three references, using the submission link specific to the position. > https://umass.interviewexchange.com/jobofferdetails.jsp?JOBID=64843 (Security and Privacy) > https://umass.interviewexchange.com/jobofferdetails.jsp?JOBID=64842 (Data Science) > > Review of applications will begin on November 30, 2015 and may continue until a suitable candidate pool has been identified. Rank and salary will be commensurate with qualifications and experience. Inquiries and requests for more information can be sent to: facrec at cs.umass.edu. > > The university is committed to active recruitment of a diverse faculty and student body. The University of Massachusetts Amherst is an Affirmative Action/Equal Opportunity Employer of women, minorities, protected veterans, and individuals with disabilities and encourages applications from these and other protected group members. Because broad diversity is essential to an inclusive climate and critical to the University's goals of achieving excellence in all areas, we will holistically assess the many qualifications of each applicant and favorably consider an individual's record working with students and colleagues with broadly diverse perspectives, experiences, and backgrounds in educational, research or other work activities. We will also favorably consider experience overcoming or helping others overcome barriers to an academic degree and career. > From d.polani at herts.ac.uk Fri Dec 11 18:03:46 2015 From: d.polani at herts.ac.uk (Daniel Polani) Date: Fri, 11 Dec 2015 23:03:46 +0000 Subject: Connectionists: PhD Studentships on Information in Artificial Life and Cognition/AI Message-ID: <22123.22098.370506.357021@gargle.gargle.HOWL> ///////////////////////////////////////////////////////////////////// PhD Studentships Available on INFORMATION IN SELF-ORGANIZATION, ARTIFICIAL LIFE AND COGNITION/AI Adaptive Systems Research Group School of Computer Science University of Hertfordshire, UK ///////////////////////////////////////////////////////////////////// PhD studentships are available in the Adaptive Systems Research Group at the University of Hertfordshire in the topics of Self-Organization, Artificial Life including Origins of Life and principled models for modeling cognition. We are especially interested in the study of principles behind information processing in adaptive, complex and self-organizing systems. Here, understanding and characterizing emergence and growth of complexity as a basis for understanding life and the rise of intelligence is a research area which has witnessed a dramatic increase of interest in the last years. An arsenal of mathematical tools, with special emphasis on Shannon's information theory are used to characterize and predict organismic behaviour, and we also use them to construct AI/robotic models employing these principles. Topics of interest include, but are not limited to: - information-theoretic treatment of information processing and the Perception-Action Loop in agents and understanding the informational balance of intelligent agents - theoretically grounded and systematic pathways towards self-organization in complex systems and generation of increasingly capable cognitive and operational dynamics; Origin of Life and its links to physics - biologically plausible AI/control methods for embodied robotics based on information theory derived from first principles - powerful and generic intrinsic motivation models and artificial creativity for AI/agents/robots - fundamental principles underlying biological (e.g. neural) computation (with opportunities to collaborate with the Biocomputation Research Group) The prospective candidates should have a very strong first degree, a keen interest in contributing to a new, highly dynamic and quickly expanding research area and an outstanding background in Computer Science, Physics, Mathematics, Statistics or another relevant computational/quantitative discipline. In particular, they should demonstrate excellent programming skills in at least one major computer language. A mathematical/numerical background would be highly desirable. Knowledge in at least one of the following fields would be a plus: probability theory, information theory, differential geometry, control, data modelling/neural network techniques. The envisaged research will take place in the vibrant, enthusiastic and enterprising research environment of the Adaptive Systems Research Group in the School of Computer Science at the University of Hertfordshire; in case of interest, there will also be the opportunity to collaborate with the socSMCs (Socializing Sensorimotor Contingencies, FET Open) and WiMUST (Widely Scalable Mobile Underwater Sonar Technology) EU Horizon 2020 projects, as well as the School's successful humanoid robot RoboCup team, the Bold Hearts. The school offers a large number of specialized and interdisciplinary seminars as well as general training opportunities. Research in Computer Science at the University of Hertfordshire has been recognized as excellent by the latest Research Assessment Exercise, with 50% of the research submitted being rated as world leading or internationally excellent. The University of Hertfordshire is located in Hatfield, Hertfordshire UK which is considered the "northern green belt" of London. Hatfield is close to London (less than 25 minutes by train to Kings Cross), has convenient access to Stansted, Luton and Heathrow airports, and, via the historic town of St. Albans, also to Gatwick airport. Successful candidates are eligible for a research studentship award from the University (which includes approximately GBP 14,057 per annum bursary and the payment of the standard UK/EU student fees). Applicants from outside the UK or EU are eligible, but will have to pay half of the overseas fees out of their bursary. Information about the current tuition fees can be found at http://www.herts.ac.uk/apply/fees-and-funding Closing date for application is the 28. December 2015, though excellent application may be considered after that date. As start of the studentships we aim for 1. February 2016. For informal inquiries on the research topic please contact: Dr. Daniel Polani (E-mail: d.polani at herts.ac.uk) Application forms are available from http://homepages.stca.herts.ac.uk/~comqvs/ApplicationFormUHStudentship.doc and should be returned to: Mrs Lorraine Nicholls Research Student Administrator, STRI University of Hertfordshire College Lane Hatfield, AL10 9AB Herts Hertfordshire UK Tel: +44 1707 286083 Email: l.nicholls at herts.ac.uk Applications should also include two references and transcripts of previous academic degrees. The shortlisting process for the applications will begin on 28. December 2015. From irina.illina at loria.fr Mon Dec 14 07:43:32 2015 From: irina.illina at loria.fr (Irina Illina) Date: Mon, 14 Dec 2015 13:43:32 +0100 (CET) Subject: Connectionists: Master2 (research) position at Multispeech Team, LORIA and INRS (Nancy, France) In-Reply-To: <1039501969.27431498.1449073917001.JavaMail.zimbra@loria.fr> References: <1498747398.11780922.1445982958323.JavaMail.zimbra@loria.fr> <489945052.18103442.1447361250552.JavaMail.zimbra@loria.fr> <1039501969.27431498.1449073917001.JavaMail.zimbra@loria.fr> Message-ID: <1552932251.4713988.1450097012020.JavaMail.zimbra@loria.fr> Master2 (research) position at Multispeech Team, LORIA and INRS (Nancy, France) Speech intelligibility: how to determine the degree of nuisance Irina Illina, Patrick Chevret General information Supervisors Irina Illina , LORIA, Campus Scientifique - BP 239, 54506 Vandoeuvre-l?s-Nancy, illina at loria.fr Patrick Chevret, INRS, 1 rue du Morvan, 54519 Vandoeuvre-l?s-Nancy, patrick.chevret at inrs.fr Motivations The intelligibility of speech means the ability of a conversation to be understood by a listener located nearby. The level of speech intelligibility depends on several criteria: the level of ambient noise, the possible absorption of part of the sound spectrum, acoustic distortion, echoes, etc. The intelligibility of speech is used to assess the performance of telecommunication systems or absorption in rooms. The speech intelligibility can be evaluated: - subjectively: listeners hear several words or sentences and answer different questions (the transcription of sounds, the percentage of perceived consonants, etc.). The scores are the value of intelligibility ; - objectively, without involving listeners, using acoustic measures: the index of speech intelligibility (speech transmission index, STI) and the interference level with speech. Subjective measures are dependent of listeners and require a large number of listeners. This is difficult to achieve, especially when there are different types of environments. Moreover, it is necessary to evaluate this measure for each listener. Objective measures have the advantage of being automatically quantifiable and to be precise. However, which objective measures can measure the nuisance of the environment on the intelligibility of speech and people's health remains an open problem. For example, the STI index consists of measuring the energy modulation. But the energy modulation can be produced by the machines, yet it does not match the speech. Subject In this internship, we focus on the study of various objective measures of speech intelligibility. The goal is to find reliable measures to evaluate the level of nuisance of environment to speech understanding, to long-term mental health of people and to productivity. Some possible solutions consist to correlate the word confidence measure, noise measurement confidence and subjective measures of speech intelligibility. To develop these measures, the automatic speech recognition system will be used. This internship will be performed through collaboration between our Multispeech team of LORIA and INRS ( National Institute of Research and Safety ). INRS works on professional risk identification, analysis of their impact on health and prevention. INRS has a rich corpus of recordings and subjective measures of speech intelligibility. This corpus will be used in the context of this internship. Our Multispeech team has great expertise in signal processing and has developed several methodologies for noise estimation. The Multispeech team developed the complete system of automatic speech recognition. Required skills Background in statistics and object-oriented programming. -- Associate Professor Lorraine University LORIA-INRIA office C147 Building C 615 rue du Jardin Botanique 54600 Villers-les-Nancy Cedex Tel:+ 33 3 54 95 84 90 -- Associate Professor Lorraine University LORIA-INRIA office C147 Building C 615 rue du Jardin Botanique 54600 Villers-les-Nancy Cedex Tel:+ 33 3 54 95 84 90 -------------- next part -------------- An HTML attachment was scrubbed... URL: From mpavone at dmi.unict.it Mon Dec 14 18:44:15 2015 From: mpavone at dmi.unict.it (Mario Pavone) Date: Tue, 15 Dec 2015 00:44:15 +0100 Subject: Connectionists: HM 2016 - Hybrid Metaheuristics - Save the date Message-ID: <20151215004415.Horde.TUwoDuph4B9Wb1RPjUzD9cA@mbox.dmi.unict.it> CALL FOR PAPERS ** Apologies for cross-posting ** ** Please forward to anybody who might be interested. ** HM 2016 - 10th International Workshop on Hybrid Metaheuristics June 8-10, 2016 - Plymouth, United Kingdom http://www.dmi.unict.it/hm2016/ https://easychair.org/conferences/?conf=hm2016 hm2016 at dmi.unict.it HM Workshops are intended to be an international forum for researchers in the area of design, analysis, and experimental evaluation of hybrid metaheuristics. http://www.dmi.unict.it/hm2016/ **** You are invited to submit papers to this exciting event! *** **** HM 2016 is organized as a NON-PROFIT event. **** SUBMISSION DEADLINE: 18th January 2016 http://www.dmi.unict.it/hm2016/dates.html **** PROCEEDINGS in LNCS, Springer http://www.dmi.unict.it/hm2016/submission.html **** SPECIAL ISSUE in SOFT COMPUTING, Springer http://www.dmi.unict.it/hm2016/call.html **** PLENARY SPEAKERS ** ** Carlos A. Coello Coello, CINVESTAV, Mexico ?Evolutionary Multi-Objective Optimization using Hybrid Approaches? ** Jin-Kao Hao, University of Angers, France ?Hybrid Methods for some Knapsack Problems: lessons learnt? More speakers will be announced! **** SUBMISSIONS HM 2016 includes two different types of submission: 1) *regular paper*: 15 pages maximum length in Springer LNCS format, including figures, table & references, and should report on new and unpublished work; 2) *abstract for oral/poster presentation* (no page restriction; any format): it should discuss work in progress; new research ideas; works previously published elsewhere (it is essential that a reference to the previous article is clearly cited); and all that may be relevant and fruitful for soliciting discussions at the workshop. **** SPECIAL SESSIONS ** ** ?Hybrid Metaheuristics for Bioinformatics? organizers: Laetitia Jourdan and Julia Handl ** ?Hybrid Metaheuristics for Dynamic Environments? organizers: Amir Nakib and Mario Pavone ** ?Engineering Applications of Hybrid Metaheuristics? organizer: Alessandro Di Nuovo more special sessions will be announced! http://www.dmi.unict.it/hm2016/special-sessions.html **** PC Members http://www.dmi.unict.it/hm2016/committee.html **** Organizing Team - General Chairs: Angelo Cangelosi & Vincenzo Cutello - Program Chairs: Christian Blum, Mario Pavone & El-Ghazali Talbi - Publication Chair: Maria J. Blesa - Local Chair: Alessandro Di Nuovo ----- http://www.dmi.unict.it/hm2016/ hm2016 at dmi.unict.it Looking forward to welcoming you to Plymouth in June 2016. The HM 2016 organizing team! -- Dr. Mario Pavone (PhD) Assistant Professor Department of Mathematics and Computer Science University of Catania V.le A. Doria 6 - 95125 Catania, Italy tel: 0039 095 7383038 fax: 0039 095 330094 Email: mpavone at dmi.unict.it http://www.dmi.unict.it/mpavone/ =========================================================================== HM 2016 - 10th International Workshop on Hybrid Metaheuristics June 8-10, 2016 - Plymouth, UK http://www.dmi.unict.it/hm2016/ =========================================================================== SSBSS - International Synthetic & Systems Biology Summer School * Biology meets Engineering and Computer Science * =========================================================================== ICSI^3 - International Congress on Systems Immunology & ImmunoInformatics * Immunology without Borders * =========================================================================== 12th European Conference on Artificial Life - ECAL 2013 http://mitpress.mit.edu/books/advances-artificial-life-ecal-2013 =========================================================================== From bruno.cessac at inria.fr Tue Dec 15 01:52:30 2015 From: bruno.cessac at inria.fr (Bruno Cessac) Date: Tue, 15 Dec 2015 07:52:30 +0100 Subject: Connectionists: Master position in computational neuroscience at INRIA Message-ID: <566FB8AE.1090503@inria.fr> Master position in computational neuroscience at INRIA We are seeking an undergraduate student interested in doing a Master thesis, possibly followed by a funded Ph.D. in our group Biovision at INRIA Sophia Antipolis lead by Dr. Bruno Cessac. The detailed proposition can be found here ftp://ftp-sop.inria.fr/neuromathcomp/team/bruno.cessac/internships/2016/Trajectory.pdf In collaboration with experimentalists our group studies how the visual system encodes information about external word. We propose biophysical models, we develop methods coming from theoretical physics and mathematics to analyse them, and we design software inspired from the visual system to mimic its behaviour and to analyse experimental data. Successful applicants should have a strong background in computer science. Physics, mathematics or life science majors with strong skills in computer science (especially C/C++), interested in quantitative modeling work are also encouraged to apply, particularly if they would like to combine experiments and theory in their Master or Ph.D. thesis work. In order to make teamwork in our group enjoyable and fun, the ideal candidate should have a strong work ethic and have demonstrated consistent self-motivation skills. Prospective students should apply by sending an email to which includes * a letter of motivation, * CV, * and a copy of the current academic transcripts to be sent to bruno.cessac at inria.fr Looking forward to your applications! Bruno Cessac -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: bruno_cessac.vcf Type: text/x-vcard Size: 363 bytes Desc: not available URL: From zoubin at eng.cam.ac.uk Tue Dec 15 11:31:11 2015 From: zoubin at eng.cam.ac.uk (Zoubin Ghahramani) Date: Tue, 15 Dec 2015 16:31:11 +0000 Subject: Connectionists: Faculty Position in Machine Learning at the University of Cambridge (deadline: 11 Jan 2016) Message-ID: Faculty Position in Machine Learning I?m delighted to advertise that the University of Cambridge is inviting applications for a faculty position in Machine Learning (as a University Lecturer, roughly equivalent to US Assistant Professor). The successful candidate will join the Machine Learning Group (mlg.eng.cam.ac.uk ), which currently includes Zoubin Ghahramani, Carl E. Rasmussen, Richard Turner, David MacKay and about 25 PhD students and postdocs. The position also offers the opportunity to participate in inter-disciplinary collaborations with the newly established national Alan Turing Institute for Data Science (turing.ac.uk ). To apply online and for further information, please follow the instructions at http://www.jobs.cam.ac.uk/job/8737/ . The closing date for applications is 11 January 2016. Informal enquiries may be made to Zoubin Ghahramani (zoubin at eng.cam.ac.uk ), Carl Rasmussen (cer54 at cam.ac.uk ) or Richard Turner (ret26 at cam.ac.uk ). -Zoubin --------------- Zoubin Ghahramani FRS Professor of Information Engineering University of Cambridge http://learning.eng.cam.ac.uk/zoubin Cambridge Liaison Director Alan Turing Institute http://turing.ac.uk -------------- next part -------------- An HTML attachment was scrubbed... URL: From sen.cheng at rub.de Tue Dec 15 11:46:26 2015 From: sen.cheng at rub.de (Sen Cheng) Date: Tue, 15 Dec 2015 17:46:26 +0100 Subject: Connectionists: Postdoc in Computational Neuroscience/ Robotics Message-ID: A postdoctoral position in computational neuroscience/ robotics is available immediately in the research unit of Prof. Sen Cheng in the Institute for Neural Computing at the Ruhr University Bochum in Germany. For further information see www.rub.de/cns. The postdoc will study spatial navigation and learning in robots using biologically realistic algorithms. The focus will be on understanding the neural mechanisms underlying spatial navigation and learning in mammals, in particular, the role of the hippocampus in these processes. The salary will be on the standard German pay scale of TV-L E13. The full-time position is available immediately for two years with the possibility of extension. Limited teaching in computational neuroscience and/ or robotics is required. Candidates should have a doctoral degree in neuroscience, robotics, computer science, physics, or a related field. Competence in mathematical modeling, and excellent programming skills are mandatory. Familiarity with robotics and computational neuroscience would be a further asset. To apply please send a statement of your motivation and research interests, academic transcripts, and a complete CV to sen.cheng at rub.de in a single PDF file. Please, also request from at least two academic referees that they send letters of reference directly to the same email address. The Ruhr University Bochum is committed to equal opportunity. We strongly encourage applications from qualified women and persons with disabilities. --- Prof. Dr. Sen Cheng Ruhr-University Bochum Mercator Research Group "Structure of Memory" Universitaetsstr. 150 44801 Bochum Germany office: GA 04/48 | +49-234- 32 27136 | FAX: +49-234- 32 07136 sen.cheng at rub.de | http://www.rub.de/cns -------------- next part -------------- An HTML attachment was scrubbed... URL: From cchrist at cs.ucy.ac.cy Tue Dec 15 15:14:00 2015 From: cchrist at cs.ucy.ac.cy (Chris Christodoulou) Date: Tue, 15 Dec 2015 22:14:00 +0200 Subject: Connectionists: BioSystems - Special Issue on Neural Coding Message-ID: <56707488.8060703@cs.ucy.ac.cy> Dear Colleagues, We would like to announce a /BioSystems/ Special Issue on Neural Coding: /BioSystems/ -- Volume 136 - October 2015 Available online for download now from: http://www.sciencedirect.com/science/journal/03032647/136/supp/C The Table of Contents of this special issue can be seen at the end of this email. Kind regards, Philippe Lucas, Jean-Pierre Rospars and Chris Christodoulou Guest Editors ------------------------------------------------------------------------------------------------------------ /BioSystems/ - Contents -- Volume 136 - October 2015 Selected papers presented at the Eleventh International Workshop on Neural Coding, Versailles, France, 2014 Available online for download now from: http://www.sciencedirect.com/science/journal/03032647/136/supp/C *Editorial**/ /* Editorial/ /Philippe Lucas, Jean-Pierre Rospars, Chris Christodoulou *Single neurons** */Information theory and statistics// / Optimal decoding and information transmission in Hodgkin?Huxley neurons under metabolic cost constraints Lubomir Kostal, Ryota Kobayashi On the Cram?r?Rao bound applicability and the role of Fisher information in computational neuroscience Stevan Pilarski, Ondrej Pokora A review of the methods for neuronal response latency estimation Marie Levakova, Massimiliano Tamborrino, Susanne Ditlevsen, Petr Lansky *Experimental** * Olfactory signal coding in an odor background Michel Renou, Virginie Party, Ang?la Rouyar, Sylvia Anton Firing and intrinsic properties of antennal lobe neurons in the Noctuid moth /Agrotis ipsilon/ C?line Lavialle-Defaix, Vincent Jacob, Christelle Monsemp?s, Sylvia Anton, Jean-Pierre Rospars, Dominique Martinez, Philippe Lucas *Synaptic integration** * A model of dopamine modulated glutamatergic synapse Vito Di Maio, Francesco Ventriglia, Silvia Santillo Information transfer through a signaling module with feedback: A perturbative approach Gerardo Aquino, Martin Zapotocky Phase-locking of bursting neuronal firing to dominant LFP frequency components Maria Constantinou, Daniel H. Elijah, Daniel Squirrell, John Gigg, Marcelo A. Montemurro On learning time delays between the spikes from different input neurons in a biophysical model of a pyramidal neuron Achilleas Koutsou, Guido Bugmann, Chris Christodoulou Analytical description of coincidence detection synaptic mechanisms in the auditory pathway Peter G. Toth, Petr Marsalek *Neural systems** */Abstract models// / Spin torque oscillator neuroanalog of von Neumann's microwave computer Frank Hoppensteadt Structure of a randomly grown 2-d network Fioralba Ajazi, George M. Napolitano, Tatyana Turova, Izbassar Zaurbek *Biologically-based models** * Altered intensity coding in the salicylate-overdose animal model of tinnitus Ilynn Wan, Ondrej Pokora, Tzaiwen Chiu, Petr Lansky, Paul Waifung Poon Navigation-specific neural coding in the visual system of Drosophila Alex D.M. Dewar, Antoine Wystrach, Paul Graham, Andrew Philippides A cortical network model of cognitive and emotional influences in human decision making Azadeh Hassannejad Nazir, Hans Liljenstr?m -------------- next part -------------- An HTML attachment was scrubbed... URL: From rloosemore at susaro.com Tue Dec 15 17:49:01 2015 From: rloosemore at susaro.com (Richard Loosemore) Date: Tue, 15 Dec 2015 17:49:01 -0500 Subject: Connectionists: Comparing speech recognition Word Error Rates is deceiptful, please stop In-Reply-To: <566EEC69.1020501@susaro.com> References: <9958333E-2C06-412C-BE93-45569F3FDB46@uq.edu.au> <566EEC69.1020501@susaro.com> Message-ID: <567098DD.2090607@susaro.com> So, can I take it that no-one disagrees with this? :-) I have received private emails from people who say they agree with this analysis, but no one speaks out publicly (and that, on a mailing list with some ferociously opinionated correspondents, too! If so, is this not a little .... shocking? That no one bats an eye when leading researchers give the strong impression that their systems are "near or exceeding human performance" when in fact the truth is that they are ONE THOUSAND times worse than human performance? Richard Loosemore On 12/14/15, 11:20 AM, Richard Loosemore wrote: > > I just read "Deep Speech 2: End-to-End Speech Recognition in English > and Mandarin" by Amodei et al. ( http://arxiv.org/abs/1512.02595v1, > and I have finally reached the end of my tether over the reporting of > Word Error Rates (WER). > > These rates are being used to make a comparison with human performance > on TRANSCRIPTION of speech. But transcription involves recognition > plus a complex pile of work like memory storage, time pressure, and > semantic paraphrasing. And I would be willing to bet that almost all > the errors are in the non-recognition parts. > > But by using transcription error, the reported error rate for humans > is supposedly about 5%, and on that basis Amodei et al declare that > their system is now better than human. > > That is ludicrous. If I give an hour-long lecture I can cram in about > 20,000 words, and I would be willing to bet that not one of those > words would be misrecognized by any of the students in my audience who > were actually awake. That would be an error rate that is three orders > of magnitude smaller than the one for transcription. > > Amodei et al (and all the other deep learning speech recognition folks > who overinflate claiims on a regular basis): your system is NOT > outperforming humans, because your system should be compared with the > primal recognition rate in humans, and since humans are probably about > 1000 times better, you have a long way to go. > > > Richard Loosemore > > > From friedhelm.schwenker at uni-ulm.de Tue Dec 15 15:27:56 2015 From: friedhelm.schwenker at uni-ulm.de (Dr. Schwenker) Date: Tue, 15 Dec 2015 21:27:56 +0100 Subject: Connectionists: IJCNN Special Session on Transfer Learning Message-ID: <567077CC.8030807@uni-ulm.de> Call for Papers ************************************************************************************************** IJCNN-43 Neural Network Transfer Learning for the Recognition of Human Behavior and Affect Special Session at IEEE World Congress on Computational Intelligence (IEEE WCCI 2016) 25-29 July 2016, Vancouver, Canada Organizers: Friedhelm Schwenker and Stefan Scherer Submission deadline : Januray 15, 2015 ************************************************************************************************** The special session focuses on neural network-based transfer learning and knowledge adaptation for pattern recognition problems in human-computer interaction scenarios. Of particular interest for the special session is the classification of human behavior patterns and affect. Scope and Topics The special session?s topics include but are not limited to: Learning from multiple sources Deep learning architectures Multi instance learning Multi label learning Learning from unlabeled data Learning from partially labeled data Affective Computing Human Behavior Analysis I ntelligent interaction, Assistive systems, Companion systems -- Dr. Friedhelm Schwenker University of Ulm Institute of Neural Information Processing D-89069 Ulm, Germany phone: +49-731-50-24159 fax: +49-731-50-24156 email: friedhelm.schwenker at uni-ulm.de www: http://www.uni-ulm.de/in/neuroinformatik/mitarbeiter/f-schwenker.html From ndjaitly at gmail.com Wed Dec 16 00:14:50 2015 From: ndjaitly at gmail.com (Navdeep Jaitly) Date: Tue, 15 Dec 2015 21:14:50 -0800 Subject: Connectionists: Comparing speech recognition Word Error Rates is deceiptful, please stop In-Reply-To: <567098DD.2090607@susaro.com> References: <9958333E-2C06-412C-BE93-45569F3FDB46@uq.edu.au> <566EEC69.1020501@susaro.com> <567098DD.2090607@susaro.com> Message-ID: After skimming the paper, I want to point out that most of these results are reported on short utterances, not on long conversations such as lectures. In the domain of voice search queries, language models play a very strong role in helping improve WER and it's not a fair stretch to say that current systems are performing close to the accuracy of human transcription (although I would stop short of saying that it is actually better). On longer conversations such as lectures, human beings are obviously much better than speech recognition systems for a variety of mechanisms that our speech recognition systems do not have. So its not clear that we can infer from our failings in this domain, to say that we are proportionally just as bad in the domain of short queries. One of these mechanisms, I think, has to do with the human ability to adapt language models on the fly (for example if we are in a lecture on abstract algebra, we are able to adapt our language model to expect to hear Homeomorphisms over and over again, and having heard it once, we can use it to inform ourselves later). Our techniques for doing this just haven't evolved to the point that we can do so well in this domain. On Tue, Dec 15, 2015 at 2:49 PM, Richard Loosemore wrote: > > So, can I take it that no-one disagrees with this? :-) > > I have received private emails from people who say they agree with this > analysis, but no one speaks out publicly (and that, on a mailing list with > some ferociously opinionated correspondents, too! > > If so, is this not a little .... shocking? That no one bats an eye when > leading researchers give the strong impression that their systems are "near > or exceeding human performance" when in fact the truth is that they are ONE > THOUSAND times worse than human performance? > > > Richard Loosemore > > > > > > On 12/14/15, 11:20 AM, Richard Loosemore wrote: > >> >> I just read "Deep Speech 2: End-to-End Speech Recognition in English and >> Mandarin" by Amodei et al. ( http://arxiv.org/abs/1512.02595v1, and I >> have finally reached the end of my tether over the reporting of Word Error >> Rates (WER). >> >> These rates are being used to make a comparison with human performance on >> TRANSCRIPTION of speech. But transcription involves recognition plus a >> complex pile of work like memory storage, time pressure, and semantic >> paraphrasing. And I would be willing to bet that almost all the errors are >> in the non-recognition parts. >> >> But by using transcription error, the reported error rate for humans is >> supposedly about 5%, and on that basis Amodei et al declare that their >> system is now better than human. >> >> That is ludicrous. If I give an hour-long lecture I can cram in about >> 20,000 words, and I would be willing to bet that not one of those words >> would be misrecognized by any of the students in my audience who were >> actually awake. That would be an error rate that is three orders of >> magnitude smaller than the one for transcription. >> >> Amodei et al (and all the other deep learning speech recognition folks >> who overinflate claiims on a regular basis): your system is NOT >> outperforming humans, because your system should be compared with the >> primal recognition rate in humans, and since humans are probably about 1000 >> times better, you have a long way to go. >> >> >> Richard Loosemore >> >> >> >> > -------------- next part -------------- An HTML attachment was scrubbed... URL: From rloosemore at susaro.com Wed Dec 16 11:27:50 2015 From: rloosemore at susaro.com (Richard Loosemore) Date: Wed, 16 Dec 2015 11:27:50 -0500 Subject: Connectionists: Comparing speech recognition Word Error Rates is deceiptful, please stop In-Reply-To: <1450252292.567118045efe2@webmail.unige.it> References: <9958333E-2C06-412C-BE93-45569F3FDB46@uq.edu.au> <566EEC69.1020501@susaro.com> <567098DD.2090607@susaro.com> <1450252292.567118045efe2@webmail.unige.it> Message-ID: <56719106.3020102@susaro.com> The comments in reply to my original post (... including some of the ones I have received offlist) are getting surreal. My main point was: in the paper, humans were reported to have an error rate for speech recognition of one word in twenty. If what we are talking about is ordinary, in-the-wild recognition of speech, that rate is transparently ridiculous. Do you make a mistake recognizing every 20th word you hear? Clearly not. The rate reported is for a human who is recognizing AND transcribing. Yes, I am appealing to common sense to make that point: but am I really supposed to do a factor analysis to demonstrate that it is "transparently ridiculous" to suggest that humans have a 1-in-20 error rate? I suggested (that is all: suggested) that the real number for a pure recognition task was probably closer to 1 in 20,000 or less. Do we really have to have a debate about how accurate that suggestion was, or how irresponsible I am to make the suggestion? It is clearly not 1 in 20, so I made a first stab at a better number. Secondly: in BOTH the case of people naturally listening to speech (the lecture that I mentioned) and a transcriber trying to write down speech in an online task, there will be all kinds of high-level processing that makes a top-down contribution to the recognition task, so it makes no sense (Stefano Rovetta) to discount what I said about possible error rates of less than 1 in 20,000 when listening to a lecture. Yes, you can help the recognition process by understanding the content of a lecture ... but so can the person doing transcription. Finally, my comments were not a specific accusation of fraud directed against Amodei et al., because I extended my target to "all the other deep learning speech recognition folks who overinflate claims on a regular basis". Here is the last paragraph of the conclusion to the Amodei et al paper: "Overall, we believe our results confirm and exemplify the value of end-to-end Deep Learning methods for speech recognition in several settings. In those cases where our system is not already comparable to humans, the difference has fallen rapidly, largely because of application-agnostic Deep Learning techniques. We believe these techniques will continue to scale, and thus conclude that the vision of a single speech system that outperforms humans in most scenarios is imminently achievable." Everything about this paragraph shouts "speech system that outperforms humans". What it does not say is "speech system that outperforms humans .... but only if we are talking about humans who are being overloaded by the need to simultaneously perform the task of transcribing the results of recognition". The computer speech recognition system finds the transcription part utterly trivial; the human finds it crippling. It doesn't take a rocket surgeon to figure that out. Richard Loosemore -------------- next part -------------- An HTML attachment was scrubbed... URL: From mail at mkaiser.de Wed Dec 16 08:15:18 2015 From: mail at mkaiser.de (Marcus Kaiser) Date: Wed, 16 Dec 2015 13:15:18 +0000 Subject: Connectionists: Three PhD projects in modelling brain diseases and brain development at Newcastle University Message-ID: Dear all, we are currently advertising the following three 4-year PhD positions for our lab with application deadlines early next year. The funding covers living expenses and UK/EU fees over four years and, using overseas research studentships, potentially also the higher fees for non-EU applicants. Students are chosen in competition with students who choose projects in other fields, which means that we would particularly encourage strong applicants with very good academic marks and previous research experience to apply. Please follow the links below for more information. *Newcastle-DTA PhD studentships* (1) Building brains: Which developmental pathways lead to better performance in information processing? (School: Computing Science Ref: DTA122) Within this project, a student will help to develop detailed simulations of brain network development. In addition, the student will test the performance of the grown networks on visual tasks. Through this, we will investigate (a) how developmental mechanisms are linked to the resulting topology and (b) how the resulting network is linked to processing performance. As a result, we will get a better understanding how changes during development are linked to brain architecture and how they can lead to cognitive deficits. Supervisors: Prof. Marcus Kaiser, Dr Gavin Clowry, and Dr Roman Bauer (2) Predicting patient outcomes following traumatic brain injury (School: Computing Science Ref: DTA123) In this study we will investigate the impact of simulated brain lesions using human brain connectivity data and computer simulations. We shall aim to produce biomarkers for patient outcomes. These techniques may hive wider applications in stroke, multiple sclerosis and ageing. Supervisors: Prof. Marcus Kaiser and Dr Peter Taylor Please *apply by 22 January* at http://www.ncl.ac.uk/sage/study/postgrad/dta/ *Newcastle-Singapore PhD studentships* (3) Improving surgery in focal epilepsy using computational modelling (School: Computing Science Ref: NSS12) In this project we shall attempt to predict which patients will be seizure free after surgery using human brain connectivity information of patients. For those patients predicted to be not seizure free we shall suggest alternative strategies for surgery. See also our recent article in PLOS CB: http://www.ploscompbiol.org/article/metrics/info%3Adoi%2F10.1371%2Fjournal.pcbi.1004642 Supervisors: Dr. Peter Taylor, Prof. Marcus Kaiser, and Asst. Prof. Justin Dauwels (NTU, Singapore). The student will be based at Newcastle but also visit Singapore Please *apply by 26 February* at http://www.ncl.ac.uk/sage/study/postgrad/singapore/ *Research Environment* There are currently 12 faculty members with a link to neuroinformatics and computational neuroscience. Using computational models for clinical applications is a strong interest of our group (see http://neuroinformatics.ncl.ac.uk/ for an overview). Students will be based in the School of Computing Science, which was ranked #9 for research and #1 for impact in the recent UK Research Excellence Framework evaluation, as part of the ICOS Group (http://ico2s.org/ ). They will also be affiliated with the Institute of Neuroscience which integrates more than 100 principal investigators across medicine, psychology, computer science, and engineering and which was ranked #9 overall and #5 for impact in the UK ( http://www.ncl.ac.uk/ion/). Newcastle University, with 20,000 students, lies in the city of Newcastle-upon-Tyne -- an area in the North-East of England with around one million inhabitants. The university is at the centre of Newcastle which itself is on the main train-line between London and Edinburgh, 20 minutes away from both the airport and the sand beach by public transport ( http://www.ncl.ac.uk/about/visit/city/ ). We also offer a one-year master programme in Computational Neuroscience and Neuroinformatics (http://www.ncl.ac.uk/computing/study/postgrad/taught/5199/ ) which is now accepting applications. Best, Marcus -- Marcus Kaiser, Ph.D. @ConnectomeLab Professor in Neuroinformatics Interdisciplinary Computing and Complex Biosystems (ICOS) Research Group School of Computing Science Newcastle University Claremont Tower Newcastle upon Tyne NE1 7RU, UK Lab website: http://www.dynamic-connectome.org/ Neuroinformatics at Newcastle: http://neuroinformatics.ncl.ac.uk / -------------- next part -------------- An HTML attachment was scrubbed... URL: From eb-ballester at bournemouth.ac.uk Thu Dec 17 11:43:45 2015 From: eb-ballester at bournemouth.ac.uk (Emili Balaguer-Ballester) Date: Thu, 17 Dec 2015 16:43:45 +0000 Subject: Connectionists: PhD position in computational neuroscience: 'Identification of Metastable Cortical Dynamics Underlying Cognitive Decisions'. Bournemouth & Barcelona Universities Message-ID: <8b62ee4f0253454182e30b146a90b253@Tremail.bournemouth.ac.uk> PhD position in computational neuroscience. "Identification of Metastable Cortical Dynamics Underlying Cognitive Decisions? Bournemouth University-IDIBAPS. A PhD position is available in 3-years fully-funded project 'Identification of Metastable Cortical Dynamics Underlying Cognitive Decisions'; based at Bournemouth University (UK) https://research.bournemouth.ac.uk/centre/interdisciplinary-neuroscience-research/ and at the Biomedical Research Institute August Pi I Sunyer (IDIBAPS, http://www.idibaps.org/en_index.htm, University of Barcelona, Spain). Do we have analysis tools for a reliable identification of the dynamical processes underlying decision-making? This is a fundamental question, touching the very basics of our understanding of neural computation and hence one of the most exciting topics in neuroscience. However, to reconstruct in detail neural dynamics generating cognitive decisions is a major challenge for current methodologies. This would be a highly significant advance; for instance the identification of stable dynamical patterns of activity in hippocampus deserved to win the last Nobel Prize. The aim of the project is to develop innovative approaches designed for the identification of metastable dynamics underlying cognitive decisions. We aim for the fusion of statistical learning approaches to pattern discovery with methods for identifying neural attractor dynamics and neurocomputational modelling. The novel approach will reconstruct neural dynamics during tasks specifically designed at Sanchez-Vives Lab in rodents and in human subjects at the Bournemouth EEG lab. The training possibilities that this interdisciplinary project offers are multiple and relevant in building-up a high-profile as a neuroscientist. The student will benefit from the vibrant scientific environment of neural computation and neurosciences at BU https://research.bournemouth.ac.uk/centre/interdisciplinary-neuroscience-research/ and at the cortical networks lab; embedded in the renowned systems neuroscience network in Barcelona http://www.sanchez-vives.org/. Applicants holding a degree in Physics, Mathematics, Engineering, Computer Science or similar disciplines are welcome. Interest or previous training in neuroscience or laboratory experience and a strong mathematical or machine learning background would be very welcome. The researcher will be based at the Faculty of Science, Bournemouth University, and work with Dr Balaguer-Ballester at the Computational Neuroscience laboratory in the context of the interdisciplinary group for neurosciences; and will spend prolonged periods of time in the Cortical Networks Lab (IDIBAPS , Barcelona) led by Prof Maria Victoria Sanchez-Vives; providing an outstanding opportunity to gain a diverse experience of both neuro-computational and experimental approaches. For formally applying and more information please visit https://research.bournemouth.ac.uk/pgr/funded-phd-studentships-in-the-faculty-of-science-and-technology-2015/ Please Cc your application to eb-ballester at bournemouth.ac.uk For further details please do not hesitate to contact me any time: eb-ballester at bournemouth.ac.uk: Twitter: @emilibalball; http://dec.bournemouth.ac.uk/staff/ebb/ Kind regards, Emili BU is a Disability Two Ticks Employer and has signed up to the Mindful Employer charter. Information about the accessibility of University buildings can be found on the BU DisabledGo webpages This email is intended only for the person to whom it is addressed and may contain confidential information. If you have received this email in error, please notify the sender and delete this email, which must not be copied, distributed or disclosed to any other person. Any views or opinions presented are solely those of the author and do not necessarily represent those of Bournemouth University or its subsidiary companies. Nor can any contract be formed on behalf of the University or its subsidiary companies via email. -------------- next part -------------- An HTML attachment was scrubbed... URL: From dwang at cse.ohio-state.edu Wed Dec 16 20:21:39 2015 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Wed, 16 Dec 2015 20:21:39 -0500 Subject: Connectionists: NEURAL NETWORKS, Dec. 2015 Message-ID: <56720E23.6000907@cse.ohio-state.edu> Neural Networks - Volume 72, Dec. 2015 http://www.journals.elsevier.com/neural-networks SPECIAL ISSUE: Neurobiologically Inspired Robotics: Enhanced Autonomy through Neuromorphic Cognition Guest Editorial: Jeffrey L. Krichmar, Jorg Conradt, Minoru Asada Choice reaching with a LEGO arm robot (CoRLEGO): The motor system guides visual attention to movement-relevant information Soeren Strauss, Philip J.W. Woodgate, Saber A. Sami, Dietmar Heinke Modeling human target reaching with an adaptive observer implemented with dynamic neural fields Farzaneh S. Fard, Paul Hollensen, Dietmar Heinke, Thomas P. Trappenberg Generalisation, decision making, and embodiment effects in mental rotation: A neurorobotic architecture tested with a humanoid robot Kristsana Seepanomwan, Daniele Caligiore, Angelo Cangelosi, Gianluca Baldassarre Bio-inspired homogeneous multi-scale place recognition Zetao Chen, Stephanie Lowry, Adam Jacobson, Michael E. Hasselmo, Michael Milford Goal-oriented robot navigation learning using a multi-scale space representation M. Llofriu, G. Tejera, M. Contreras, T. Pelc, J.M. Fellous, A. Weitzenfeld A GPU-accelerated cortical neural network model for visually guided robot navigation Michael Beyeler, Nicolas Oros, Nikil Dutt, Jeffrey L. Krichmar An embodied biologically constrained model of foraging: from classical and operant conditioning to adaptive real-world behavior in DAC-X Giovanni Maffei, Diogo Santos-Pata, Encarni Marcos, Marti Sanchez-Fibla, Paul F.M.J. Verschure Development of compositional and contextual communicable congruence in robots by using dynamic neural network models Gibeom Park, Jun Tani Off-line simulation inspires insight: A neurodynamics approach to efficient robot task learning Emanuel Sousa, Wolfram Erlhagen, Flora Ferreira, Estela Bicho Multimodal emotional state recognition using sequence-dependent deep hierarchical features Pablo Barros, Doreen Jirak, Cornelius Weber, Stefan Wermter Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks Florian Walter, Florian Rohrbein, Alois Knoll From zivbj at cs.cmu.edu Thu Dec 17 09:37:35 2015 From: zivbj at cs.cmu.edu (Ziv Bar-Joseph) Date: Thu, 17 Dec 2015 09:37:35 -0500 Subject: Connectionists: Faculty Openings in the Machine Learning Department at CMU Message-ID: <5672C8AF.7060303@cs.cmu.edu> The Machine Learning Department of the School of Computer Science at Carnegie Mellon University invites applications for a tenure-track position at the rank of Assistant Professor. All areas of machine learning will be considered. Applicants are expected to have an active research program and a commitment to teaching excellence. The Machine Learning Department has close relationships through shared faculty and active collaboration across the university, especially the Statistics Department and other academic units in the School of Computer Science (Computer Science Department, Language Technologies Institute, Computational Biology Department, and the Robotics Institute). We seek applicants who will thrive in this interdisciplinary setting. Members of underrepresented groups are strongly encouraged to apply. Additional details including application instructions, can be found here: http://www.ml.cmu.edu/Faculty_Hiring.html Ziv Bar-Joseph Professor Machine Learning Department School of Computer Science Carnegie Mellon University From rothkopf at fias.uni-frankfurt.de Thu Dec 17 12:19:52 2015 From: rothkopf at fias.uni-frankfurt.de (Constantin Rothkopf) Date: Thu, 17 Dec 2015 18:19:52 +0100 Subject: Connectionists: 4 faculty positions: Centre for Cognitive Science at Technische Universitaet Darmstadt Message-ID: <5672EEB8.6020009@fias.uni-frankfurt.de> Technische Universit?t Darmstadt is establishing a Centre for Cognitive Science and invites applications for 4 tenured professorships. The Centre?s research programme will be based on computational and engineering approaches to Cognitive Science, with strong interactions with the engineering departments. Research methodologies will include, but are not limited to, theoretical studies, human experimental work, cognitive engineering applications, the use of big data, and ubiquitous sensing. The professorships are to be filled in the Department of Human Sciences (Institutes of Psychology and of Sports Science) and in the Department of Computer Science, and will complement and interact with the existing research activities in Cognitive science at Technische Universit?t Darmstadt. The four positions are to be filled in the following areas: 1) One professorship (W2/W3) in the Institute of Sports Sciences in the area Sensorimotor Control & Learning 2) two professorships (W2/W3) in the Institute of Psychology in the areas Perception, Decision Making & Preference or Models of Higher Cognition (e.g. reasoning, natural language, learning and memory), 3) and one professorship (W3) in the Department of Computer Science in the areas Machine Learning or Biosignal Processing (e.g. prosthetics, brain-computer interface). Successful appointees are expected to contribute to teaching in the study programme for cognitive science, which is currently being developed, and to the undergraduate and graduate level courses of their respective departments. The positions are tenured with a remuneration package commensurate with experience and qualifications, following the German "W-Besoldung". The regulations for employment are specified under ?? 61 and 62 HHG (Hessisches Hochschulgesetz). The Technische Universit?t Darmstadt intends to increase the number of female faculty members and encourages female candidates to apply. In case of equal qualifications applicants with a degree of disability of at least 50 or equal will be given preference. The Technische Universit?t Darmstadt is certified as a familiy-friendly university and offers a dual career program. Applications should include a curriculum vitae, list of publications, copies of relevant diplomas, as well as a research and teaching statement, preferably all in a single PDF file. Applications for the positions in the Institute of Sport Science and the Institute of Psychology should be directed to the Dean of the Department of Human Sciences, Professor Frank H?nsel (dekanat at humanw.tu-darmstadt.de); applications for the position in Computer Science should be directed to the Dean of the Department of Computer Science, Professor Reiner H?hnle (dekanat at informatik.tu-darmstadt.de). It is possible to apply for several of the positions. Please include the code number of the position(s) you apply for. Informal enquiries may be addressed to Professor Constantin Rothkopf (Tel +49 6151 16-76084; rothkopf at psychologie.tu-darmstadt.de) or Professor Jan Peters (Tel +49-6151-16-7351; peters at ias.tu-darmstadt.de). For further information please also visit www.cogsci.tu-darmstadt.de. Code No. 489 (Sensorimotor Control) Code No. 490 (Perception, Decision Making & Preference, Models of Higher Cognition) Code No. 491 (Machine Learning, Biosignal Processing) Application deadline: January 31, 2016 From m.plumbley at surrey.ac.uk Fri Dec 18 10:11:42 2015 From: m.plumbley at surrey.ac.uk (m.plumbley at surrey.ac.uk) Date: Fri, 18 Dec 2015 15:11:42 +0000 Subject: Connectionists: Research Software Developer: Making Sense of Sounds Message-ID: Dear Connectionists, Please forward the following job information to anyone who may be interested. Apologies for cross-posting. Research Software Developer: Making Sense of Sounds http://jobs.surrey.ac.uk/087015 Deadline: 17 January 2016 Additional information below. Many thanks, Mark Plumbley ---- Research Software Developer on Making Sense of Sounds University of Surrey, Department of Electrical & Electronic Engineering Centre for Vision Speech and Signal Processing (CVSSP) Salary: GBP 30,738 to GBP 35,609 Closing Date: 17 January 2016 (midnight GMT) Reference: 087015 Applications are invited for a Research Software Developer to work full-time on an EPSRC-funded project "Making Sense of Sounds" for 33 months starting February 2016. This project will investigate how to make sense from sound data, focussing on how to convert sound recordings into understandable and actionable information, and specifically how to allow people to search, browse and interact with sounds. The candidate will be responsible for the development of research software in connection with research into new signal processing methods to analyse sound and audiovisual files and new interaction methods to search and browse through sets of sound files. The successful applicant is expected to have a Masters degree in Electronic Engineering, Computer Science or equivalent professional experience in a relevant discipline, at least 1 year's experience in software development relevant to audio or audio-visual signal processing, and experience in software development in topics such as: digital signal processing, machine learning, blind source separation, spatial audio, audio coding, speech processing, audio-visual signal processing, data visualisation, human computer interaction, and/or large scale data processing. Direct research experience in audio or audio-visual signal processing, or experience of software development with signal processing researchers is desirable, as is significant software development experience in Python, Matlab, and/or C/C++. The project will be led by Prof Mark Plumbley in the Machine Audition Lab of the Centre for Vision Speech and Signal Processing (CVSSP) at the University of Surrey, in collaboration with the Digital World Research Centre (DWRC) at Surrey and the University of Salford. The postholder will be based in CVSSP and work under the direction of Prof Plumbley and Co-Investigators Dr Wenwu Wang and Dr Philip Jackson. CVSSP is one of the largest groups of its type in the UK, with over 120 active researchers working in the areas of vision, image processing, medical imaging, and audio, and a grant portfolio of over ?12M. The Centre has state-of-the-art acoustic capture and analysis facilities enabling research into audio source separation, music transcription and spatial audio, and a Visual Media Lab with video and audio capture facilities supporting research in real-time video and audio processing and visualisation. Informal enquires are welcome, to: Prof Mark Plumbley (m.plumbley at surrey.ac.uk), Dr Wenwu Wang (w.wang at surrey.ac.uk), or Dr Philip Jackson (p.jackson at surrey.ac.uk). Expected start date: As soon as possible Further Details: http://jobs.surrey.ac.uk/087015 -- Prof Mark D Plumbley Professor of Signal Processing Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey Guildford, Surrey, GU2 7XH, UK Email: m.plumbley at surrey.ac.uk From muftimahmud at gmail.com Thu Dec 17 13:31:27 2015 From: muftimahmud at gmail.com (Mufti Mahmud) Date: Thu, 17 Dec 2015 19:31:27 +0100 Subject: Connectionists: CFP on "Computationally Intelligent Methods in Neural Information Processing" at the IEEE WCCI2016. Message-ID: Sorry for cross-posting. Please consider circulating and contributing to the session. Thanks and regards, Mufti *Call for Paper for Special Session on * *Computationally Intelligent Methods in Neural Information Processing* *at the IEEE World Congress on Computational Intelligence (IEEE WCCI) 2016* Organized by: Mufti Mahmud 1-4, ?, Amir Hussain 4, 5, ? 1*NeuroChip Lab, University of Padova, 35131 ? Padova, Italy, *2*Institute of Information Technology, Jahangirnagar University, 1342 ? Dhaka, Bangladesh, *3*Theoretical Neurobiology & Neuroengineering Lab, University of Antwerp, 2610 ? Wilrijk, Belgium, *4*COSIPRA Lab, University of Stirling, FK9 4LA ? Stirling, UK, *5*Anhui University, Hefei, Anhui, 230601 - China* ?*Email: muftimahmud at gmail.com , *?*Email: ahu at cs.stir.ac.uk * *Introduction:* The brain, being the most complex organ in human body, is specialized to process information simultaneously coming from many different sources. The neurons work as basic information processing units in the brain and interconnect to each other to form hierarchical and/or parallel pathways. These pathways are mainly involved in transforming information originated from one or more sources into either action (as in motor movements) or specialized information understood by the brain itself (as in cognitive functions). To have a detailed and better understanding of these biological phenomena two approaches have been practiced by the research community ? experimental and theoretical studies. Also, some theoretical studies are inspired by the nature itself which reframes earlier computational techniques to suggest research on biophysical basis of brain research and its information processing capabilities. Needless to say that most of these studies are results of interdisciplinary research involving medical sciences, life sciences, physical sciences, engineering, and cognitive sciences. *Scope:* The focus of this special session is to address the recent advances in computationally intelligent techniques in processing neural information. Developing intelligent methods capable of deciphering brain?s information processing capability is one the biggest challenges in brain research. The objective of this special session is to provide updated information and a forum for the scientists and researchers who are looking for more relevant information in decoding brain functions using expert and computationally intelligent systems. This special session is expected to attract papers on recent research progress in the area of intelligent methods in processing neural signals. The targeted research topics are, but not limited to, the following: ? Computationally intelligent tools for analysis of Spikes, LFP, EEG, MEG, MRI/fMRI, PET, and fNIRS; ? Computationally intelligent methods for modeling and estimating neural signals; ? Computational intelligence in developing smart BMI and neural prosthesis; ? Biologically inspired methods for pattern analysis in neuronal signals; ? Machine learning methods applied to brain research; *Submission of papers:* Submit IEEE US Letter complaint pdf papers to IEEE CEC 2016, following the steps below: ? Visit http://ieee-cis.org/conferences/cec2016/upload.php ? Provide paper details (i.e., Paper Title, Author(s), PDF file to upload, Abstract, Preferred form of presentation, Main paper focus) ? At '*Main research topic*' or '*Additional research topics'*, select '*8bc. Computationally Intelligent Methods in Neural Information Processing*' from the dropdown list. *Important dates:* ? Paper submission deadline: *15 January 2016* ? Decision notification: *15 March 2016* ? Final paper submission and early registration deadline: *15 April 2016* ? Conference dates: *25-29 July 2016*. -- Mufti Mahmud, PhD ?Postdoctoral Research Fellow NeuroChip Lab - Dept. of Biomedical Sciences University of Padova Via f. Marzolo 3 35131 - Padova, Italy Lab: +39 049 827 5308 Fax: +39 049 827 5301 https://sites.google.com/site/muftimahmud/ & Assistant Professor (on leave) Institute of Information Technology Jahangirnagar University Savar, 1342 - Dhaka, Bangladesh? -------------- next part -------------- An HTML attachment was scrubbed... URL: From graduateprograms at bccn-berlin.de Fri Dec 18 09:59:03 2015 From: graduateprograms at bccn-berlin.de (Robert Martin) Date: Fri, 18 Dec 2015 15:59:03 +0100 Subject: Connectionists: [Call for applications] *Graduate Programs in Computational Neuroscience* in Berlin; MSc and PhD; 6 PhD scholarships; deadline March 15, 2016 Message-ID: <56741F37.4090708@bccn-berlin.de> [Apologies for cross-posting] *Doctoral* and *Master Program* "Computational Neuroscience" at the Bernstein Center for Computational Neuroscience Berlin in Berlin, Germany Application deadline: *March 15, 2016* Begin of courses: October 2016 Internet: www.computational-neuroscience-berlin.de _Doctoral Program_ The Bernstein Center for Computational Neuroscience Berlin and the TU Berlin invite applications for *6 fellowships* of the Research Training Group "Sensory Computation in Neural Systems" (GRK 1589/2, https://www.eecs.tu-berlin.de/grk_15891/). The *scientific program* of the research training group combines techniques and concepts from machine learning, computational neuroscience, and systems neurobiology in order to specifically address sensory computation. Doctoral candidates will work on interdisciplinary projects investigating the mechanisms of neural computation, address the processes underlying perception on different scales and different levels of abstraction, and develop new theories of computation hand in hand with well-controlled experiments in order to put functional hypotheses to the test. The training group offers structured supervision complemented by a teaching and training program. Each student will be supervised by two investigators with complementary expertise and will be associated with the Bernstein Center for Computational Neuroscience Berlin (https://www.bccn-berlin.de/) a leading research center dedicated to the theoretical study of neural processing. Candidates are expected to hold a Masters degree (or equivalent) in a relevant subject (e.g., neuroscience, cognitive science, computer science, physics, mathematics, etc.) and have the required advanced mathematical background. Candidates selected in the first application step will be invited for lab visits and an interview, expected to take place in June 2015. The *fellowships of 1468 ?/month* - with additional children allowances if applicable---will be granted for up to three years. _Master's Program_ The tuition-free Master program in Computational Neuroscience offers *15 places* per year, has a duration of 2 years and is fully taught in English. The *curriculum* is subdivided into ten modules, whose content includes theoretical neuroscience, programming, machine learning, cognitive neuroscience, acquisition, modelling, and computational analysis of neural data, with a strong focus on a complementary theoretical and experimental training. Three lab rotations and a Master's thesis are accomplished in the second year. The aim of the program is to provide the students with an interdisciplinary education and an early contact to the neurocomputational research environment. *Requirements* BSc or equivalent degree in a relevant subject (typically in the natural sciences, in an engineering discipline, in cognitive science, or in mathematics), certificate of English proficiency, proof of sufficient mathematical knowledge (at least 24 ECTS credit points). ~~~ _For more information_ ... ... come and visit us on our *information day* on January 27, 2016, at 3 PM (sharp) at the BCCN Berlin: https://www.bccn-berlin.de/Calendar/Events/event/?contentId=3822 ... or browse: www.computational-neuroscience-berlin.de ... or e-mail: graduateprograms at bccn-berlin.de . Best regards, Robert Martin -- Robert Martin, PhD Teaching Coordinator Bernstein Center for Computational Neuroscience Humboldt-Universitaet zu Berlin Philippstr. 13 House 6; 10115 Berlin; Germany Phone/Fax +49 (0)30 2093 6773/6771 http://www.computational-neuroscience-berlin.de GRK 1589/1, Sensory Computation in Neural Systems Technische Universitaet Berlin Sekretariat MAR 5-6; Marchstr. 23; 10587 Berlin Phone/Fax +49 (0)30 314 72006/73121 http://www.eecs.tu-berlin.de/grk_15891/ From ASIM.ROY at asu.edu Fri Dec 18 05:22:13 2015 From: ASIM.ROY at asu.edu (Asim Roy) Date: Fri, 18 Dec 2015 10:22:13 +0000 Subject: Connectionists: Call for Papers: WCCI 2016, Vancouver - Special Session on BIG DATA Message-ID: <4AD8F84F0AA4E1448BD8131BA7E55EB42B461BE8@exmbt02.asurite.ad.asu.edu> World Congress on Computational Intelligence (WCCI 2016) Cross-Disciplinary and CI Applications (CDCI) 2016 July 25-29, 2016, Vancouver, Canada Special Session on ?Computational Intelligence, Nature-Inspired Learning and Big Data? The aim of this special session is to promote new advances and research directions in efficient and innovative algorithmic approaches to analyzing big data (e.g. deep learning, nature-inspired and computational intelligence approaches), implementations on different computing platforms (e.g. neuromorphic, GPUs, clouds, clusters) and applications of big data to solve real-world problems (e.g. weather prediction, transportation, energy management). A paper accepted for presentation at this cross-disciplinary and CI applications special session will be published in one of the three conference proceedings (IJCNN, FUZZ-IEEE, or IEEE CEC) that is most appropriate for the paper. Topics and Areas include, but not limited to: ? Autonomous, online, incremental learning ? theory, algorithms and applications in big data ? High dimensional data, feature selection, feature transformation ? theory, algorithms and applications for big data ? Scalable algorithms for big data ? Learning algorithms for high-velocity streaming data ? Deep learning algorithms ? Machine vision and big data ? Brain-machine interfaces and big data ? Cognitive modeling and big data ? Embodied robotics and big data ? Fuzzy systems and big data ? Evolutionary systems and big data ? Evolving systems and big data ? Neuromorphic hardware for scalable machine learning ? Parallel and distributed computing for big data (cloud, HPC, GPUs, clusters, etc.) ? Big data and healthcare/medical applications ? Big data and energy systems/smart grids ? Big data and transportation systems ? Big data in large sensor networks ? Big data and machine learning in computational biology, bioinformatics ? Big data and cloud computing, large scale stream processing on the cloud Paper submission: Potential authors may submit their manuscripts for presentation consideration through the WCCI2016 submission system. All the submissions will go through peer review. Details on manuscript submission can be found from http://www.wcci2016.org/submission.php Important dates: Paper submission deadline: January 15, 2016 Notification of acceptance: March 15, 2016 Final paper submission and early registration deadline: April 15, 2016 Organizers: Asim Roy, Arizona State University, Asim.Roy at asu.edu Plamen Angelov, Lancaster University, p.angelov at lancaster.ac.uk Marley Vellasco, Pontifical Catholic University of Rio de Janeiro, marley at ele.puc-rio.br Adel Alimi, University of Sfax, adel.alimi at ieee.org G. Kumar Venayagamoorthy, Clemson University, gvenaya at clemson.edu Juyang Weng, Michigan State University, weng at cse.msu.edu Leonid Perlovsky, Harvard University, lperl at rcn.com De-Shuang Huang, Tongji University, dshuang at tongji.edu.cn From ASIM.ROY at asu.edu Sat Dec 19 00:22:44 2015 From: ASIM.ROY at asu.edu (Asim Roy) Date: Sat, 19 Dec 2015 05:22:44 +0000 Subject: Connectionists: Call for Contributions - Frontiers Research Topic - "Representation in the brain" Message-ID: <4AD8F84F0AA4E1448BD8131BA7E55EB42B46AD0B@exmbt02.asurite.ad.asu.edu> Mental representation in the brain remains an unresolved issue. However, there has been significant research in a variety of fields in the last four decades - from neuroscience to theoretical computer science - which can provide new insights on the issue of representation. Frontiers in Psychology, Cognition section, will publish a comprehensive set of articles as an open access e-book, under the title ?Representation in the brain,? that aims to provide new insights on this decades long question. A more elaborate outline of the Research Topic is available at: http://frontiersin.org/Cognition/researchtopics/Representation_in_the_brain/4398 More than 20 authors from a variety of fields have already committed to submit articles to this Research Topic. All articles will go through the standard Frontiers review process and we expect this e-book to serve as standard reference on this topic in the future. The following are the deadlines: 1. An abstract for the paper is due by January 15, 2016 2. Papers are due by June 30, 2016 With best regards, Guest Editors, Frontiers in Psychology Asim Roy, Arizona State University, USA Leonid Perlovsky, Harvard University and Air Force Research Lab, USA Juyang Weng, Michigan State University, USA Tarek Besold, Free University of Bozen-Bolzano, Italy Jonathan Edwards, University College London, UK From dengdehao at gmail.com Sat Dec 19 22:49:57 2015 From: dengdehao at gmail.com (Teng Teck Hou) Date: Sun, 20 Dec 2015 11:49:57 +0800 Subject: Connectionists: [INNS-BigData 2016] Updated Call for Papers Message-ID: <010401d13ad9$7fe603f0$7fb20bd0$@gmail.com> [Apologies for cross-postings] ########################################################### CALL FOR PAPERS The 2nd INNS Conference on Big Data 2016 October 23-25, 2016, Thessaloniki, Greece http://conferences.cwa.gr/inns-big-data2016/ ########################################################### Big data is not just about storage of and access to data. Analytics play a big role in making sense of that data and exploiting its value. But learning from big data has become a significant challenge and requires development of new types of algorithms. Most machine learning algorithms can't easily scale up to big data. Plus there are challenges of high-dimensionality, velocity and variety. The neural network field has historically focused on algorithms that learn in an online, incremental mode without requiring in-memory access to huge amounts of data. This type of learning is not only ideal for streaming data (as in the Industrial Internet or the Internet of Things), but could also be used on stored big data. Neural network technologies thus can become significant components of big data analytics platforms and this inaugural INNS Conference on Big Data will begin that collaborative adventure with big data and other learning technologies. Thus the aim of this conference is to promote new advances and research directions in efficient and innovative algorithmic approaches to analyzing big data (e.g. deep networks, nature-inspired and brain-inspired algorithms), implementations on different computing platforms (e.g. neuromorphic, GPUs, clouds, clusters) and applications of Big Data Analytics to solve real-world problems (e.g. weather prediction, transportation, energy management). #################### Important dates ##################### - Tutorial and workshops proposals: February 15th, 2016 - Notification of tutorial and workshops proposals: February 20th, 2016 - Paper submission: April 30th, 2016 - Notification of paper acceptance: May 30th, 2016 - Camera-ready submission (AISC): June 11th, 2016 - Early registration: June 20th, 2016 Registration deadline: papers without confirmed registration by June 24th 2016 risk their inclusion in the proceedings ########################################################## #################### Invited speakers #################### - Francesco Bonchi, ISI Foundation, Torino, Italy - Stephen Furber, University of Manchester, UK - Rudolf Kruse, OVG University of Magdeburg, Germany - Piotr Mirowski, Google Deep Mind, London, UK ########################################################## #################### Organizing committees ############### General Chairs - Plamen Angelov, Lancaster University, UK - Yannis Manolopoulos, Aristotle University of Thessaloniki, Greece Program Chairs - Lazaros Iliadis, Democritus University of Thrace, Greece - Asim Roy, Arizona State University, Tempe USA - Marley Vellasco, PUC-Rio, Rio de Janeiro, Brazil Advisory Board - Nikola Kasabov, Auckland University of Technology, New Zealand - Ali Minai, University of Cincinnati, USA - Danil Prokhorov, Toyota Tech Center, Michigan, USA - Theodore Trafalis University of Oklahoma, USA - G. Kumar Venayagamoorthy, Clemson University, USA Tutorials/Workshop Chairs - Apostolos Papadopoulos, Aristotle University of Thessaloniki, Greece - Bernardete Ribeiro, Portugal Poster Session Chairs - Yi Lu Murphey, University of Michigan-Dearborn, USA Special Sessions Chairs - Irwin King, Chinese University of Hong Kong, China - Luca Oneto, University of Genoa, Italy Panel Chairs - Leonid Perlovsky, Harvard University, Boston, USA Awards Chair - Araceli Sanchis de Miguel, Carlos III University, Spain Competitions Chairs - Adel Alimi, University of Sfax, Tunisia Publication Chairs - Mariette Awad, American University of Beirut, Lebanon - Danilo Mandic, Imperial College, London, UK Publicity Chairs - Jose Antonio Iglesias Martinez, Carlos III University of Madrid, Spain - Simone Scardapane, The Sapienza University of Rome, Italy - Teck Hou Teng, Singapore Management University, Singapore International Liaison Chairs - Petia Georgieva, University of Aveiro, Portugal - De-Shuang Huang, Tongji University, Shanghai, China Local Organizing Committee: - Anastasios Gounaris, Aristotle University of Thessaloniki, Greece WebMaster - Yannis Karydis, Ionian University, Greece ########################################################## ############# Paper Submission and Publication ########### * Original works submitted as a regular paper limited to a maximum of 14 pages in Springer format will be published in the proceedings to be available electronically as a Springer book in ADVANCES IN INTELLIGENT SYSTEMS AND COMPUTING Series, to download for delegates. * It will be peer-reviewed by at least three PC members on the basis of technical quality, relevance, originality, significance and clarity. * At least one author of an accepted submission to the conference should register with a regular fee to present their work at the conference. ########################################################## #################### Awards ############################## * Best papers will be selected and awarded as follows: - Best regular paper - Best student paper * This will be based on a combination of reviewers' comments, presentations and importance and quality judged by a panel. * Best paper awards (500 Euros) are donated by the sponsor Springer Verlag, Germany and will be commemorated by a certificate. ########################################################## ###### Topics and Areas include, but not limited to ###### * Autonomous, online, incremental learning - theory, algorithms and applications in big data * High dimensional data, feature selection, feature transformation - theory, algorithms and applications for big data * Scalable algorithms for big data * Learning algorithms for high-velocity streaming data * Big data streams analytics * Deep neural network learning * Machine vision and big data * Brain-machine interfaces and big data * Cognitive modeling and big data * Embodied robotics and big data * Fuzzy systems and big data * Evolutionary systems and big data * Evolving systems for big data analytics * Neuromorphic hardware for scalable machine learning * Parallel and distributed computing for big data analytics (cloud, map-reduce, etc.) * Big data and collective intelligence/collaborative learning * Big data and hybrid systems * Big data and self-aware systems * Big Data and infrastructure * Big data analytics and healthcare/medical applications * Big data analytics and energy systems/smart grids * Big data analytics and transportation systems * Big data analytics in large sensor networks * Big data and machine learning in computational biology, bioinformatics * Recommendation systems/collaborative filtering for big data * Big data visualization * Online multimedia/ stream/ text analytics * Link and graph mining * Big data and cloud computing, large scale stream processing on the cloud ########################################################## #################### Co-Sponsors ######################### * International Neural Network Society (INNS) * Springer ########################################################## -------------- next part -------------- An HTML attachment was scrubbed... URL: From dengdehao at gmail.com Sun Dec 20 01:45:50 2015 From: dengdehao at gmail.com (Teng Teck Hou) Date: Sun, 20 Dec 2015 14:45:50 +0800 Subject: Connectionists: [UKCI 2016] Updated Call for Papers Message-ID: <01cd01d13af2$12487490$36d95db0$@gmail.com> [Apologies for cross-postings] ########################################################### CALL FOR PAPERS The 16th Annual UK Workshop on Computational Intelligence, UKCI-2016 September 7-9, 2016, Lancaster, United Kingdom http://wp.lancs.ac.uk/ukci2016/ ########################################################### The 16th Annual UK Workshop on Computational Intelligence, UKCI-2016 this year is being hosted by Lancaster University. UKCI is the premier UK event for presenting leading research on all aspects of Computational Intelligence. The aim of this Workshop is to provide a forum for the academic community and industry to share ideas about developing and using Computational Intelligence (CI) techniques, the new trends and to exchange views and ideas. CI is a rapidly expanding research field, attracting a large number of scientists, engineers and practitioners working in areas such as fuzzy systems, neural networks, evolutionary computation, evolving systems and machine learning. A growing number of companies are employing CI techniques to improve previous solutions and to deal with new problems. These include evolving systems that allow high performance in spite of changes which are either external or internal to the system, thereby increasing the re-usability of developed systems. This also include smart, intelligent and autonomous systems, self-learning, self-adapting, self-calibrating and self-tuning. UKCI-2016 will take place in Lancaster House Hotel, located conveniently within the campus of Lancaster University, few miles from the city centre including Lancaster Castle. The city offers excellent transport links, with easy access to the M6, railway station and ferry links. Beyond the array of activities within the city, Lancaster is close to the Britain?s premier touristic area ? Lake District, home to theatres, museums, Ashton Memorial and Williamson park. #################### Important dates ##################### - Special Session proposals: January 4th, 2016 - Paper submission: April 1st, 2016 - Notification of paper acceptance: June 15th, 2016 - Camera-ready submission: July 15th, 2016 ########################################################## #################### Plenary speakers #################### - Jose Principe, Distinguished Professor, University Of Florida, USA - Trevor Martin, Bristol University and Senior Researcher, British Telecom ########################################################## #################### Organizing committees ############### * Honorary Chair - Prof. Janusz Kacprzyk, Fellow Polish Academy of Sciences * General Chair - Prof. Plamen Angelov, Lancaster University * Programme Chairs - Prof. Qiang Shen, Aberystwyth University - Prof. Chrisina Jane, Robert Gordon University * Publication Chair - Dr. Alexander Gegov, Portsmouth University * International Liaison - Ms Azliza Mohd Ali, Lancaster University * Finance Chair - Ms Carol Airey, Lancaster University * Local Organisation Chairs - Dr. John Mariani, Lancaster University - Mr Richard Gnosill, Lancaster University * Publicity Chair - Dr. Teng Teck Hou, Singapore Management University * Awards Chair - Prof. Araceli Sanchis de Miguel, Carlos III University, Spain * Special Session Chair - Dr. Xiao Jun Zeng, Manchester University ########################################################## ############# Paper Submission and Publication ########### * Papers for UKCI 2016 should be submitted electronically through the Conference website at http://www.lancaster.ac.uk/fas/scc/sites/ukci2016/, and will be refereed by experts in the fields and ranked based on the criteria of originality, significance, quality and clarity. * Selected papers will be considered for publication, following substantial extension, in a Special Issue of the Soft Computing Journal (Springer). ########################################################## #################### Awards ############################## * A best regular paper and a best student paper will be selected for this award * This best paper award consists of a plaque and a ?200 honorarium * The best paper awards are sponsored by Springer ########################################################## ###### Topics and Areas include, but not limited to ###### Topics of interest include (but are not limited to) * Computational intelligence methodology * Computational intelligence for big data * Making Sense from Data (streams) * Knowledge representation * Fuzzy logic, fuzzy systems, approximate reasoning; * New Machine Learning Methodologies * Artificial Neural Networks * Evolutionary computation, swarm intelligence, artificial immune systems, memetic computing, Nature-inspired computing * New and emerging computational intelligence approaches from hybrid learning and systems, molecular and quantum computing * Software agents and multi-agent systems, intelligent control * Intelligent Video Analytics * Applications of computational intelligence techniques in engineering, healthcare, finances, (cyber)security, signal, image and video processing ########################################################## #################### Call for Special Session Proposals ######################### * UKCI-2016 will retain its traditional format of a single track with special sessions on selected ?hot? topics. * Please email proposals for special sessions to ukci2016 at lancaster.ac.uk by 4th January 2016 ########################################################## #################### Co-Sponsors ######################### * Springer * Department of Engineering and the School of Computing and Communications, Lancaster University ########################################################## -------------- next part -------------- An HTML attachment was scrubbed... URL: From hava at cs.umass.edu Sat Dec 19 20:14:51 2015 From: hava at cs.umass.edu (Hava Siegelmann) Date: Sat, 19 Dec 2015 20:14:51 -0500 Subject: Connectionists: How abstraction is created in brain Message-ID: <5676010B.1020503@cs.umass.edu> http://www.sciencedaily.com/releases/2015/12/151216151738.htm -- Hava T. Siegelmann, Ph.D. Professor Director, BINDS Lab (Biologically Inspired Neural Dynamical Systems) Dept. of Computer Science Program of Neuroscience and Behavior University of Massachusetts Amherst Amherst, MA, 01003 Phone: 413-545-2744 Fax: 413-545-1249 LAB WEBSITE: http://binds.cs.umass.edu/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From aurel at ee.columbia.edu Sun Dec 20 11:57:27 2015 From: aurel at ee.columbia.edu (Aurel A. Lazar) Date: Sun, 20 Dec 2015 11:57:27 -0500 Subject: Connectionists: Columbia Workshop on Brain Circuits, Memory and Computation Message-ID: <4E4D8E61-B14C-4005-9344-2A944AE697BC@ee.columbia.edu> Columbia Workshop on Brain Circuits, Memory and Computation BCMC 2016 Friday and Saturday, March 18-19, 2016 Center for Neural Engineering and Computation Columbia University, New York, NY 10027 Overview The goal of the workshop is to bring together researchers interested in developing executable models of neural computation/processing of the brain of model organisms. Of interest are models of computation that consist of elementary units of processing using brain circuits and memory elements. Elementary units of computation/processing include population encoding/decoding circuits with biophysically-grounded neuron models, non-linear dendritic processors for motion detection/direction selectivity, spike processing and pattern recognition neural circuits, movement control and decision-making circuits, etc. Memory units include models of spatio-temporal memory circuits, circuit models for memory access and storage, etc. A major aim of the workshop is to explore the integration of various sensory and control circuits in higher brain centers. A Fruit Fly Brain Hackathon is being conducted in conjunction with the workshop. Confirmed Invited Speakers J. Douglas Armstrong , School of Informatics, University of Edinburgh. Alexander Borst , Max Planck Institute of Neurobiology, Martinsried. Thomas R. Clandinin , Department of Neurobiology, Stanford University. Michael Hawrylycz , Allen Institute of Brain Science Stanley Heinze , Department of Biology, Lund University. Chung-Chuan Lo , National Tsing Hua University, Hsinchu, Taiwan. Matthieu Louis , Centre for Genomic Regulation, Barcelona. Gaby Maimon , Rockefeller University. Mala Murthy , Princeton University. Michael B. Reiser , Janelia Research Campus, Ashburn, VA. Vanessa Ruta , Rockefeller University. Glenn C. Turner , Janelia Research Campus, Ashburn, VA. Marta Zlatic , Janelia Research Campus, Ashburn, VA. Aurel http://www.bionet.ee.columbia.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Wed Dec 23 11:08:16 2015 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 23 Dec 2015 08:08:16 -0800 Subject: Connectionists: NEURAL COMPUTATION - January 1, 2016 In-Reply-To: Message-ID: Neural Computation - Volume 28, Number 1 - January 1, 2016 Available online for download now: http://www.mitpressjournals.org/toc/neco/28/1 ----- Articles Neural Network Spectral Robustness Under Perturbations of the Underlying Graph Anca Radulescu Sequential Tests for Large Scale Learning Anoop Korattikara, Yutian Chen, and Max Welling Note A Note on Support Vector Machines With Polynomial Kernels Hongzhi Tong Letters Analytical Calculation of Errors in Time and Value Perception Due to a Subjective Time Accumulator: A Mechanistic Model and the Generation of Weber's Law Vijay Mohan K Namboodiri, Stefan Mihalas, and Marshall G Hussain Shuler Efficient Associative Computation With Discrete Synapses Andreas Knoblauch Reduction of Trial-to-trial Perceptual Variability by Intracortical Tonic Inhibition Osamu Hoshino, Meihong Zheng, and Kazuo Watanabe An Empirical Overview of the No Free Lunch Theorem and Its Effect on Real-World Machine Learning Classification David Gomez, Alfonso Rojas Global Exponential Stability of Cohen-Grossberg Neural Networks With Piecewise Constant Argument of Generalized Type and Impulses Qiang Xi ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp SUBSCRIPTIONS - 2016 - VOLUME 28 - 12 ISSUES Student/Retired $78 Individual $138 Institution $1,108 MIT Press Journals, One Rogers Street, Cambridge, MA 02142-1209 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-cs at mit.edu ------------ From se37 at cornell.edu Sun Dec 20 13:17:05 2015 From: se37 at cornell.edu (Shimon Edelman) Date: Sun, 20 Dec 2015 18:17:05 +0000 Subject: Connectionists: on Deep Networks and real brains and behavior Message-ID: Seeing that Deep Network skepticism is becoming a thing ? at least among those of us who care about real brains and real behavior ? I thought I?d offer my two cents? worth of comments. (If you cannot get past the paywall, I?ll be happy to send along a PDF.) 1. Shimon Edelman, The minority report: some common assumptions to reconsider in the modeling of the brain and behavior, Journal of Experimental and Theoretical AI (JETAI), DOI 10.1080/0952813X.2015.1042534 (2015). http://www.tandfonline.com/doi/full/10.1080/0952813X.2015.1042534 Reverse-engineering the brain involves adopting and testing a hierarchy of working hypotheses regarding the computational problems that it solves, the representations and algorithms that it employs and the manner in which these are implemented. Because problem-level assumptions set the course for the entire research programme, it is particularly important to be open to the possibility that we have them wrong, but tacit algorithm- and implementation-level hypotheses can also benefit from occasional scrutiny. This paper focuses on the extent to which our computational understanding of how the brain works is shaped by three such rarely discussed assumptions, which span the levels of Marr's hierarchy: (i) that animal behaviour amounts to a series of stimulus/response bouts, (ii) that learning can be adequately modelled as being driven by the optimisation of a fixed objective function and (iii) that massively parallel, uniformly connected layered or recurrent network architectures suffice to support learning and behaviour. In comparison, a more realistic approach acknowledges that animal behaviour in the wild is characterised by dynamically branching serial order and is often agentic rather than reactive. Arguably, such behaviour calls for open-ended learning of world structure and may require a neural architecture that includes precisely wired circuits reflecting the serial and branching structure of behavioural tasks. 2. Oren Kolodny and Shimon Edelman, The problem of multimodal concurrent serial order in behavior, Neuroscience and Biobehavioral Reviews 56:252-265 (2015). http://www.sciencedirect.com/science/article/pii/S0149763415001943 The ?problem of serial order in behavior,? as formulated and discussed by Lashley (1951), is arguably more pervasive and more profound both than originally stated and than currently appreciated. We spell out two complementary aspects of what we term the generalized problem of behavior: (i) multimodality, stemming from the disparate nature of the sensorimotor variables and processes that underlie behavior, and (ii) concurrency, which reflects the parallel unfolding in time of these processes and of their asynchronous interactions. We illustrate these on a number of examples, with a special focus on language, briefly survey the computational approaches to multimodal concurrency, offer some hypotheses regarding the manner in which brains address it, and discuss some of the broader implications of these as yet unresolved issues for cognitive science. Shimon Edelman Professor, Department of Psychology, 232 Uris Hall Cornell University, Ithaca, NY 14853-7601 Home page: http://kybele.psych.cornell.edu/~edelman Latest book: http://kybele.psych.cornell.edu/~edelman/Beginnings -------------- next part -------------- An HTML attachment was scrubbed... URL: From schwarzwaelder at bcos.uni-freiburg.de Mon Dec 21 06:41:22 2015 From: schwarzwaelder at bcos.uni-freiburg.de (Kerstin Schwarzwaelder) Date: Mon, 21 Dec 2015 12:41:22 +0100 Subject: Connectionists: Open Position: Coordinator of the Smart Start Training Program Message-ID: <5677E562.8030705@bcos.uni-freiburg.de> Dear colleagues, The Forschungszentrum J?lich GmbH and theCoordination Site of the Bernstein Network Computational Neuroscience are looking for a Coordinator of the Smart Start Training Program . Please find the announcement and online application system here . Application deadline: January 14, 2016 For inquiries regarding the position please contact Andrea Huber Broesamle (e-mail: andrea.huber at bcos.uni-freiburg.de) or Kristin Urbach (phone: +49 2461 61-9700) Best regards, Kerstin Schwarzw?lder -------------- next part -------------- An HTML attachment was scrubbed... URL: From renato at krohling.com.br Tue Dec 22 05:29:55 2015 From: renato at krohling.com.br (renato at krohling.com.br) Date: Tue, 22 Dec 2015 08:29:55 -0200 Subject: Connectionists: comparing algorithms performance Message-ID: <7ed7c6546c906de196d40192bf3db5dc@krohling.com.br> Dear All, We would like to announce an article _Ranking and comparing evolutionary algorithms with Hellinger-TOPSIS [1]_ _which might be of interest of the community, since it is of general purpose in computational intelligence._ Available online for download from: http://www.sciencedirect.com/science/article/pii/S1568494615005104 Best regards, Renato Krohling ps: abstract When multiple algorithms are applied to multiple benchmarks as it is common in evolutionary computation, a typical issue rises, how can we rank the algorithms? It is a common practice in evolutionary computation to execute the algorithms several times and then the mean value and the standard deviation are calculated. In order to compare the algorithms performance it is very common to use statistical hypothesis tests. In this paper, we propose a novel alternative method based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to support the performance comparisons. In this case, the _alternatives_ are the algorithms and the _criteria_ are the benchmarks. Since the standard TOPSIS is not able to handle the stochastic nature of evolutionary algorithms, we apply the Hellinger-TOPSIS, which uses the Hellinger distance, for algorithm comparisons. Case studies are used to illustrate the method for evolutionary algorithms but the approach is general. The simulation results show the feasibility of the Hellinger-TOPSIS to find out the ranking of algorithms under evaluation. Links: ------ [1] http://www.sciencedirect.com/science/article/pii/S1568494615005104 -------------- next part -------------- An HTML attachment was scrubbed... URL: From mpavone at dmi.unict.it Wed Dec 23 12:29:17 2015 From: mpavone at dmi.unict.it (Mario Pavone) Date: Wed, 23 Dec 2015 18:29:17 +0100 Subject: Connectionists: "Immunology without Borders", special issue in BMC Immunology journal Message-ID: <20151223182917.Horde.J4MsNOph4B9WetntYPHBOmA@mbox.dmi.unict.it> Call for Papers special issue on ? Immunology without Borders? BMC IMMUNOLOGY Submission Deadline: *** 10 January 2016 *** Authors are invited to submit original and unpublished papers on any topics related to immunology and complex systems, and all that is within the scope of the special issue and journal. *** You may send your manuscript now or up until the deadline **** For more information see http://www.dmi.unict.it/mpavone/download/cfp-icsi%5e32015-bmcImmunology.pdf Any Manuscript must be prepared in according to the journal guidelines and should conform to the standard format of BMC Immunology journal, making particular attention on manuscripts type and related sections. Figures and tables should be put in the text. Separated files for figures are not requested at the submission time: they will be requested, if the paper will be accepted for publication, for its Camera Ready version. All submissions will undergo a blind peer-review process subject to the standards of the journal. All instructions needed for authors may be found at the link: http://www.biomedcentral.com/bmcimmunol/authors/instructions We kindly ask you to give a first response regarding your interest in publishing sending your agreement, and a tentative title with the list of authors to icsi3.bmc2015 at gmail.com. Manuscripts *MUST* be submitted sending the manuscript to icsi3.bmc2015 at gmail.com *** Important dates - Manuscript submission deadline: January 10, 2016 - Notification of acceptance/rejection: February 28, 2016 - Final manuscript submission: March 20, 2016 Papers appearing in BMC Immunology has an associated publishing cost of ?1,095 per paper. By submitting a manuscript, authors will therefore agree to pay these costs, in case of publication. Please, note that if you need to be invoiced individually then a surcharge of ? 22 will be required. Further deadlines and methods for the payment of publication costs will be communicated at a later time. We hope that you will take this opportunity and we are greatly looking forward to keeping working with you! **** Guest Editors # Carlos A. Coello Coello, CIVENSTAV-IPN, Mexico - ccoello at cs.cinvestav.mx # Vincenzo Cutello, University of Catania, Italy ? cutello at dmi.unict.it # Doheon Lee, KAIST, Republic of Korea - dhlee at kaist.ac.kr # Mario Pavone, University of Catania, Italy ? mpavone at dmi.unict.it # Luca Zammataro, Italian Institute of Technology, Italy - Luca.Zammataro at iit.it -- Dr. Mario Pavone (PhD) Assistant Professor Department of Mathematics and Computer Science University of Catania V.le A. Doria 6 - 95125 Catania, Italy tel: 0039 095 7383038 fax: 0039 095 330094 Email: mpavone at dmi.unict.it http://www.dmi.unict.it/mpavone/ =========================================================================== HM 2016 - 10th International Workshop on Hybrid Metaheuristics June 8-10, 2016 - Plymouth, UK http://www.dmi.unict.it/hm2016/ =========================================================================== SSBSS - International Synthetic & Systems Biology Summer School * Biology meets Engineering and Computer Science * =========================================================================== ICSI^3 - International Congress on Systems Immunology & ImmunoInformatics * Immunology without Borders * =========================================================================== 12th European Conference on Artificial Life - ECAL 2013 http://mitpress.mit.edu/books/advances-artificial-life-ecal-2013 =========================================================================== From alberto at cs.rhul.ac.uk Mon Dec 21 19:46:52 2015 From: alberto at cs.rhul.ac.uk (Alberto Paccanaro) Date: Tue, 22 Dec 2015 00:46:52 +0000 Subject: Connectionists: Fully funded postdoctoral position in Machine Learning and Computational Biology at Royal Holloway University of London Message-ID: <56789D7C.9070804@cs.rhul.ac.uk> [Apologies for cross-posting] Applications are invited for a postdoctoral position at the Department of Computer Science of Royal Holloway, University of London. The successful candidates will work with Prof Alberto Paccanaro on different projects in the area of Systems Biology and Network Medicine -- please see http://www.paccanarolab.org/ for a description of the research carried out in the lab. Candidates should have a PhD degree in a relevant quantitative field (e.g. Computer Science, Statistics, Engineering), a strong background in machine learning and a keen interest in computational biology. Previous experience in the area of graphical models would be an asset for this position. The successful candidates will have the opportunity to collaborate with members of the interdisciplinary Centre for Systems and Synthetic Biology (Computer Science and Biological Sciences) at Royal Holloway and collaborators at Imperial College, University of Tennessee and Yale University. The post is therefore ideal for someone with a computer science or maths background who is looking to move into computational biology. The Department of Computer Science is located on Royal Holloway's pleasant campus (see http://www.royalholloway.ac.uk/), in Egham, just outside London. The position is for 30 months, full-time, beginning in the Spring 2016. The starting salary will be up to 37,743 GBP p.a. (about 57,000 USD), with annual increments. The position is funded by a joint BBSRC/NSF grant. Applicants should send a CV including a list of publications, a statement of research interests, and contact information of 3 referees electronically to alberto at cs.rhul.ac.uk If you wish to discuss details of the position, please contact Alberto Paccanaro at the same address. Alberto -- ===================================== Prof Alberto Paccanaro Department of Computer Science Royal Holloway, University of London Homepage: www.cs.rhul.ac.uk/~alberto Labpage: www.paccanarolab.org From k.wong-lin at ulster.ac.uk Mon Dec 21 12:21:39 2015 From: k.wong-lin at ulster.ac.uk (Wong-Lin, Kongfatt) Date: Mon, 21 Dec 2015 17:21:39 +0000 Subject: Connectionists: Opportunities for Ph.D. Studentships Message-ID: The Intelligent Systems Research Centre (ISRC) at Ulster University, UK, invites applications for 3-year Ph.D. studentships. A list of studentships offered for the year 2016 and the projects' details can be found at: http://www.compeng.ulster.ac.uk/rgs/showPhDProposals.php?ri=3. The computational neuroscience and neural systems research community at the ISRC focuses on both fundamental brain and behavioural sciences, and their applications, including clinical neuroscience and neural engineering. In particular, I have the available computational neuroscience projects available for 2016: 1. Dynamics of decision making in heterogeneous systems. http://www.compeng.ulster.ac.uk/rgs/displayPhDProposal.php?id=894&ri=3 2. Big data analytics and computational modelling in mental health. http://www.compeng.ulster.ac.uk/rgs/displayPhDProposal.php?id=893&ri=3 3. Computational neuromodulation. http://www.compeng.ulster.ac.uk/rgs/displayPhDProposal.php?id=892&ri=3 The application process for the Ph.D. studentship is opened with a closing date for applications on the 26th February 2016. All studentships, which are highly competitive, are expected to start in September 2016, and include tuition fees and an annual maintenance allowance for EU and non-EU students. All applicants should hold a first or upper second class honours degree (or equivalent) in an appropriate subject, such as computer science, engineering, physics, mathematics or neuroscience. Applicants must be highly motivated and willing to pursue research and develop skills across disciplines. If you wish to apply for a studentship, please follow the instructions at: http://www.compeng.ulster.ac.uk/rgs/guideForApplicants.php. Unless indicated, successful students will be based primarily at the ISRC with opportunities to interact with other related ISRC research teams, including from the Biomedical Sciences Research Institute, Centre for Stratified Medicine, and external collaborators. The ISRC has recently established state-of-the-art functional brain mapping facility, and high performance computing facility for big data analytics. The ISRC is situated in the city of Derry~Londonderry, which received the City of Culture 2013 award. Please note that some studentship (DEL Awards) have restrictions on residence eligibility - see guidance notes for details. For further information, please contact me (k.wong-lin at ulster.ac.uk). ------------------- Dr. KongFatt Wong-Lin Intelligent Systems Research Centre School of Computing and Intelligent Systems Faculty of Computing and Engineering Ulster University http://isrc.ulster.ac.uk/kwonglin/contact.html ________________________________ This email and any attachments are confidential and intended solely for the use of the addressee and may contain information which is covered by legal, professional or other privilege. If you have received this email in error please notify the system manager at postmaster at ulster.ac.uk and delete this email immediately. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Ulster University. The University's computer systems may be monitored and communications carried out on them may be recorded to secure the effective operation of the system and for other lawful purposes. Ulster University does not guarantee that this email or any attachments are free from viruses or 100% secure. Unless expressly stated in the body of a separate attachment, the text of email is not intended to form a binding contract. Correspondence to and from the University may be subject to requests for disclosure by 3rd parties under relevant legislation. The University of Ulster was founded by Royal Charter in 1984 and is registered with company number RC000726 and VAT registered number GB672390524.The primary contact address for Ulster University in Northern Ireland is Cromore Road, Coleraine, Co. Londonderry BT52 1SA -------------- next part -------------- An HTML attachment was scrubbed... URL: From gary.marcus at nyu.edu Sun Dec 20 13:30:40 2015 From: gary.marcus at nyu.edu (Gary Marcus) Date: Sun, 20 Dec 2015 13:30:40 -0500 Subject: Connectionists: Machine learning jobs at Geometric Intelligence (as recently featured in Technology Review) Message-ID: <5226065D-5F16-4AE5-B3ED-97A933157804@nyu.edu> Geometric Intelligence , the machine learning research startup recently featured here , and mentioned by Zoubin Ghahramani in his December 2015 invited address at NIPS, is looking for machine learning researchers with strong coding skills and a desire to learn new things. We are based in New York City, with offices in Soho. If interested, send a cover letter and c.v, to jobs at geometric dot ai. Best wishes for a fruitful new year, Gary Marcus CEO, Geometric Intelligence Professor, New York University -------------- next part -------------- An HTML attachment was scrubbed... URL: From erik at oist.jp Mon Dec 21 22:20:50 2015 From: erik at oist.jp (Erik De Schutter) Date: Tue, 22 Dec 2015 12:20:50 +0900 Subject: Connectionists: Announcing Okinawa/OIST Computational Neuroscience Course 2016 Message-ID: <782653C6-B720-4F6C-83CA-9D88479A3B46@oist.jp> OKINAWA/OIST COMPUTATIONAL NEUROSCIENCE COURSE 2016 Methods, Neurons, Networks and Behaviors June 13 - June 30, 2016 Okinawa Institute of Science and Technology Graduate University, Japan https://groups.oist.jp/ocnc The aim of the Okinawa/OIST Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn the latest advances in neuroscience, and for those with experimental backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, held from June 13th through June 30th, 2015 at an oceanfront seminar house of the Okinawa Institute of Science and Technology Graduate University. Applications are through the course web page (https://groups.oist.jp/ocnc) only; January 4 - February 5, 2016. Applicants will receive confirmation of acceptance in March. Like in preceding years, OCNC will be a comprehensive three-week course covering single neurons, networks, and behaviors with ample time for student projects. The first week will focus exclusively on methods with hands-on tutorials during the afternoons, while the second and third weeks will have lectures by international experts. The course has a strong hands-on component based on student proposed modeling or data analysis projects, which are further refined with the help of a dedicated tutor. Applicants are required to propose their project at the time of application. There is no tuition fee. The sponsor will provide lodging and meals during the course and may support travel for those without funding. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet each other and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. Invited faculty: ? Erik De Schutter (OIST) ? Sophie Deneve (?cole Normale Sup?rieure, France) ? Kenji Doya (OIST) ? Chris Eliasmith (University of Waterloo, Canada) ? Tomoki Fukai (RIKEN BSI, Japan) ? Michael H?usser (University College London, UK) ? Yukiyasu Kamitani (ATR & Kyoto University, Japan) ? Etienne Koechlin (?cole Normale Sup?rieure, France) ? Bernd Kuhn (OIST) ? Partha Mitra (Cold Spring Harbor, USA) ? Astrid Prinz (Emory University, USA) ? John Rinzel (New York University, USA) ? Yoko Yazaki-Sugiyama (OIST) ? more tba From p.chadderton at imperial.ac.uk Thu Dec 24 05:25:17 2015 From: p.chadderton at imperial.ac.uk (Chadderton, Paul T) Date: Thu, 24 Dec 2015 10:25:17 +0000 Subject: Connectionists: PhD position in Neurotechnology @ Imperial College Message-ID: <65641A30-6CE6-42FC-B29C-D4ACAE2E8281@imperial.ac.uk> Open PhD position in Neurotechnology at Imperial College London in the Chadderton and Clopath labs. The candidate will be doing in vivo electrophysiology in mouse cerebellum and computational modelling of learning-related changes in this circuit. Candidate must be EU national. Project: Biologically inspired computation for real-time motor control Supervisors: Paul Chadderton (http://neuralcircuitsinbehaviour.squarespace.com/) Claudia Clopath (http://www.bg.ic.ac.uk/research/c.clopath/) An important area of robotics research is focused on developing machines that can learn and adapt to changing environments as efficiently as animals. Biological principles underlying the acquisition of motor skills are likely to inspire these new technologies. The aim of our project is to characterise computational principles of motor learning in real time using novel neurophysiological data from a uniquely tractable and well-controlled system, the whisker circuitry of the cerebellar cortex. Neural recordings will reveal how the brain adapts during learning, and will then be used to develop and apply a biologically constrained computational model in an actively sensing robot. For full application instructions, see: http://www.imperial.ac.uk/neurotechnology/cdt/projects/computation_for_motor_control/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From smart at neuralcorrelate.com Thu Dec 24 07:13:18 2015 From: smart at neuralcorrelate.com (Susana Martinez-Conde) Date: Thu, 24 Dec 2015 07:13:18 -0500 Subject: Connectionists: call for illusion submissions: the 12th Best Illusion of the Year Contest In-Reply-To: <006a01d13e44$402b68e0$c0823aa0$@neuralcorrelate.com> References: <005b01d13e44$23321cc0$69965640$@neuralcorrelate.com> <006a01d13e44$402b68e0$c0823aa0$@neuralcorrelate.com> Message-ID: <008801d13e44$7a7b8a70$6f729f50$@neuralcorrelate.com> ****CALL FOR ILLUSION SUBMISSIONS: THE WORLD'S 12TH ANNUAL BEST ILLUSION OF THE YEARSM CONTEST**** http://illusionoftheyear.com We are happy to announce the 12th edition of world's Best Illusion of the YearSM Contest!! Submissions are now welcome! In 2015, the Best Illusion of the YearSM Contest became an annual online event, with the goal of bringing the creativity of the illusion creator community all around the world. Anybody with an internet connection can now participate! No matter where you live, you can be a contestant, and/or vote for the Top 3 winners! Contestants are invited to submit 1-minute YouTube videos featuring novel illusions (unpublished, or published no earlier than 2015) of all sensory modalities (visual, auditory, etc.) and/or cognitive nature. The content of the 1-minute video presenting your illusion is solely up to you, and the only requirement is that it wows all viewers! Some examples include, but are not limited to: * -A slide presentation, or succession of images, with a voice over (and/or written text, if you prefer) * -A video of yourself describing your illusion * -A video animation/enactment of your illusion An international panel of impartial judges will rate all the videos and narrow them down to the Top 10. Then, online voters around the world will choose their favorite illusions from the Top 10 finalists. All Top 10 finalists will receive a commemorative plaque. In addition, the Top 3 winners will receive cash prizes: $3,000 USD for first place; $2,000 USD for second place, and $1,000 USD for third place. The Judge Panel will rate illusions according to: * -Significance to our understanding of the human mind and brain * -Simplicity of the description * -Sheer beauty * -Counterintuitive quality * -Spectacularity Submissions will be held in strict confidence by the Judge Panel. Only the Top 10 illusions will be posted online, to allow worldwide voting. Participation in the Best Illusion of the YearSM Contest does not preclude you from also submitting your work for publication elsewhere. By participating in the Best Illusion of the YearSM Contest you agree to have your illusion posted on the Contest website, if selected among the Top 10, and included in press releases and other promotional materials/fundraising initiatives for the Contest. You (and your co-authors, if appropriate) will retain the full copyright of your illusion, and receive full credit as illusion creator(s). Illusions submitted to previous editions of the contest can be re-submitted to the 2016 Contest, as long as they meet the above requirements and were not among the Top 3 winners in previous years. You can send your 1-minute video to Susana Martinez-Conde via email ( smart at neuralcorrelate.com) until April 15, 2016. On behalf of the Executive Board of the Neural Correlate Society: Jose-Manuel Alonso, Stephen Macknik, Susana Martinez-Conde, Luis Martinez, Xoana Troncoso, Peter Tse ----------------------------------- Susana Martinez-Conde, PhD Professor of Ophthalmology, Neurology, and Physiology & Pharmacology Empire Innovator Scholar Director, Laboratory of Integrative Neuroscience State University of New York (SUNY) Downstate Medical Center 450 Clarkson Ave, Brooklyn NY 11203, USA Email: smart at neuralcorrelate.com Phone: +1 718-270-4520 http://smc.neuralcorrelate.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From tomas.hromadka at gmail.com Fri Dec 25 06:30:40 2015 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Fri, 25 Dec 2015 12:30:40 +0100 Subject: Connectionists: [COSYNE2016] Travel grants, registration, and hotels Message-ID: <567D28E0.9040204@gmail.com> ==================================================== Computational and Systems Neuroscience 2016 (Cosyne) MAIN MEETING Feb 25 - Feb 28, 2016 Salt Lake City, Utah WORKSHOPS Feb 29 - Mar 01, 2016 Snowbird Ski Resort, Utah www.cosyne.org ==================================================== REGISTRATION AND HOTELS: Travel grants submission is currently open. Online registration is currently open. Hotel booking is currently open. Travel grant application deadlines Dec 31, 2015, 11.59PM PST (Undergraduate Travel Grant) Jan 14, 2016, 11.59PM PST (Other travel grants) Early registration deadline Jan 31, 2016, 11.45PM EST Hotel booking deadlines Jan 19, 2016, Last day for reduced hotel rates at workshops Feb 03, 2016, Last day for reduced hotel rates at main meeting For more detailed information on Cosyne, please visit www.cosyne.org. TRAVEL GRANTS Applications are now open for travel grants to attend the conference. Each awardee will receive at least $500 to help offset the costs of travel, registration, and accommodations. Larger grants may be available to those traveling from outside North America. Special consideration is given to scientists who have not previously attended the meeting, under-represented minorities, students who are attending the meeting together with a mentor, undergraduate students, and authors of submitted Cosyne abstracts. We currently offer four travel grant programs for New Attendees, Presenters, Mentors, and Undergraduates. For details on applying, see cosyne.org, section Travel grants. THE MEETING The annual Cosyne meeting provides an inclusive forum for the exchange of empirical and theoretical approaches to problems in systems neuroscience, in order to understand how neural systems function. The MAIN MEETING is single-track. A set of invited talks are selected by the Executive Committee, and additional talks and posters are selected by the Program Committee, based on submitted abstracts. The WORKSHOPS feature in-depth discussion of current topics of interest, in a small group setting. Cosyne topics include but are not limited to: neural coding, natural scene statistics, dendritic computation, neural basis of persistent activity, nonlinear receptive field mapping, representations of time and sequence, reward systems, decision-making, synaptic plasticity, map formation and plasticity, population coding, attention, and computation with spiking networks. We would like to foster increased participation from experimental groups as well as computational ones. Please circulate widely and encourage your students and postdocs to apply. CONFIRMED SPEAKERS Blaise Aguera y Arcas (Google) Marisa Carrasco (NYU) Edward Chang (UCSF) Greg DeAngelis (Rochester) Mark Goldman (UC Davis) Sonja Hofer (Basel) Richard Mooney (Duke) Mala Murthy (Princeton) Peggy Series (Edinburgh) Reza Shadmehr (Johns Hopkins) Paul Smolensky (Johns Hopkins) Leslie Vosshall (Rockefeller) Xiao-Jing Wang (NYU) ORGANIZING COMMITTEE General Chairs: Maria Geffen (U Penn) and Konrad K?rding (Northwestern) Program Chairs: Megan Carey (Champalimaud) and Emilio Salinas (Wake Forest) Workshop Chairs: Claudia Clopath (Imperial College) and Alfonso Renart (Champalimaud) Publicity Chair: Xaq Pitkow (Rice) EXECUTIVE COMMITTEE Anne Churchland (CSHL) Zachary Mainen (Champalimaud) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) CONTACT cosyne.meeting [at] gmail.com From Miel.VanderSande at ugent.be Tue Dec 29 08:45:22 2015 From: Miel.VanderSande at ugent.be (Miel Vander Sande) Date: Tue, 29 Dec 2015 14:45:22 +0100 Subject: Connectionists: [CfP]15th International Semantic Web Conference (ISWC2016): Call for papers & proposals Message-ID: <059817FD-6875-4A0D-B22F-D6A68698D98F@ugent.be> For the New Year, the organizers are happy to announce the Call for Papers and Proposals for the 15th International Semantic Web Conference (ISWC 2016). ISWC is the premier venue for presenting innovative systems and research results related to the Semantic Web and Linked Data, attracting yearly a large number of high quality submissions and participants from both, industry and academia. ISWC brings together researchers from different areas, such as artificial intelligence, databases, natural language processing, information systems, human computer interaction, information retrieval, web science, etc., who investigate, develop and use novel methods and technologies for accessing, interpreting and using information on the Web in a more effective way. ISWC 2016 will be held in Kobe, Japan, from October 17 -21, 2016. In this announcement: 1. Call for Papers 2. HTML Submission Guide 3. Call for Workshops and Tutorial proposals 4. Student Grants 5. Important dates For any addition questions, don't hesitate to contact us: Website: http://iswc2016.semanticweb.org Facebook: https://www.facebook.com/groups/113652365383847 Twitter: https://twitter.com/ISWC2016 1. Call for Papers ========================================== For 2016, we present the following tracks, which are now open for submission. Overview: http://iswc2016.semanticweb.org/pages/calls.html -------------------------------------------------------------------------- Call for Research Track Papers -------------------------------------------------------------------------- In this track of ISWC 2016, we are looking for novel and significant research contributions addressing theoretical, analytical, empirical, and practical aspects of this broad field. While we welcome work that relates to the W3C Semantic Web recommendations (e.g., RDF, OWL, SPARQL, etc.), we encourage submissions that investigate other approaches to the intersection of semantics and the Web. All papers will be assessed by a program committee. Each paper will be reviewed by at least four committee members, including one senior member. The review criteria used are outlined on the webpage (see below). We also encourage authors to include pointers to additional material to substantiate the claims and findings discussed in their papers. Additional sources of material include extended technical reports, source code, datasets, as well as links to applications. Authors might consider submitting a separate paper describing these additional resources to the Resources Track. Before submitting, authors are asked to consult the calls of the other tracks featured at ISWC 2016 and to choose the track that best suits their contribution. To produce a coherent conference program the track chairs may suggest transferring a submission to a different track of the conference with authors consent. However, the submission of the same work to multiple tracks is not allowed and may result in a rejection of the work across all tracks without a review. Detailed info: http://iswc2016.semanticweb.org/pages/calls/research-track.html Program Chairs * Paul Groth - Elsevier (pgroth at gmail.com) * Elena Simperl - University of Southampton (e.simperl at soton.ac.uk) -------------------------------------------------------------------------- Call for Applications (Emerging, In-Use, Industry) Track -------------------------------------------------------------------------- Semantic technologies are reaching maturity on the web, especially through the increase in their use to publish, structure and make sense of web data, whether they are in the form of linked data, through schema.org, or even with semantics included in other data formats than RDF (CSV, JSON, etc). The Applications (Emerging, In-Use, Industry) Track at ISWC 2016 provides a forum for the community to explore the benefits and challenges of applying semantic technologies in concrete, practical applications, in contexts ranging from industry to government and science. We are especially interested this year in applications that use the emerging knowledge graphs or semantic technologies on the web together with data mining, reasoning, machine learning, or natural language processing techniques to the benefit of concrete, real-world scenarios. We are also looking for descriptions of applied and validated industry solutions as software tools, systems or architecture that benefit from the adoption of semantic technologies. Detailed info: http://iswc2016.semanticweb.org/pages/calls/applications.html Program Chairs * Markus Kr?tzsch - TU Dresden Germany (markus.kroetzsch at tu-dresden.de) * Freddy Lecue - IBM Research, Ireland (freddy.lecue at ie.ibm.com) -------------------------------------------------------------------------- Call for Doctoral Consortium Papers -------------------------------------------------------------------------- The ISWC 2016 Doctoral Consortium will take place as part of the 15th International Semantic Web Conference in Kobe, Japan. This forum will provide PhD students an opportunity to share and develop their research ideas in a critical but supportive environment, to get feedback from mentors who are senior members of the Semantic Web research community, to explore issues related to academic and research careers, and to build relationships with other Semantic Web PhD students from around the world. The Consortium aims to broaden the perspectives and to improve the research and communication skills of these students. The Doctoral Consortium is intended for students who have a specific research proposal and some preliminary results, but who have sufficient time prior to completing their dissertation to benefit from the consortium experience. Generally, students in their second or third year of PhD will benefit the most from the Doctoral Consortium. In the Consortium, the students will present their proposals and get specific feedback and advice on how to improve their research plan. All proposals submitted to the Doctoral Consortium will undergo a thorough reviewing process with a view to providing detailed and constructive feedback. The international program committee will select the best submissions for presentation at the Doctoral Consortium. We anticipate that students with accepted submissions at the Doctoral Consortium will receive travel fellowships to offset some of the travel costs. Detailed info: http://iswc2016.semanticweb.org/pages/calls/doctoral-consortium.html Program Chairs * Philippe Cudr?-Mauroux - University of Freiburg, Switzerland * Natasha Noy - Google Inc. * Riichiro Mizoguchi - JAIST, Japan -------------------------------------------------------------------------- Call for Posters and Demos -------------------------------------------------------------------------- The ISWC 2016 Posters and Demonstrations complement the paper tracks of the conference and offer an opportunity for presenting late-breaking research results, on-going research projects, and speculative or innovative work in progress. The informal setting of the Posters and Demonstrations encourages presenters and participants to engage in discussions about the work. Such discussions can be invaluable inputs for the future work of the presenters, while offering participants an effective way to broaden their knowledge of the emerging research trends and to network with other researchers. We invite submissions relevant to the area of the Semantic Web and which address, but are not limited to, the topics of the Research Track; the Application Track; and the Resource Track. Technical posters, reports on Semantic Web software systems (free or commercial), descriptions of completed work, and work in progress are all welcome. Demonstrations are intended to showcase innovative Semantic Web related implementations and technologies, both in academia and in industry. We explicitly welcome entries from the industry. However, submissions for posters and demos should go beyond pure advertisements of commercial software packages and convey a minimal scientific contribution. Authors of full papers accepted for the Research Track; the Application Track; and the Resource Track are explicitly invited to submit a demonstration. The submission should be formatted as the other posters and demonstrations but must cite the accepted full paper and needs to include an explanation of its added value with respect to the conference paper. The added value could include: a) extended results and experiments not presented in the conference paper for reasons of space, or b) a demonstration of a supporting prototype implementation. Detailed info: http://iswc2016.semanticweb.org/pages/calls/posters-demos.html Posters and Demos Track Chairs * Takahiro Kawamura - Japan Science and Technology Agency, Japan (takahiro.kawamura at jst.go.jp) * Heiko Paulheim - University of Mannheim, Germany (heiko at informatik.uni-mannheim.de) -------------------------------------------------------------------------- Call for Resources Track Papers -------------------------------------------------------------------------- Resources such as datasets, ontologies, workflows, software tools or evaluation benchmarks are important outputs of any scientific work. Sharing these resources with the research community does not only ensure the reproducibility of one?s results, but also has the benefit of supporting other researchers in their own work. Although high quality shared resources have a key role and an essential impact on the advancement of a research community, the academic acknowledgement for sharing such resources is low. Therefore, many researchers primarily focus on publishing scientific papers and lack the motivation to share their resources. An additional challenge is that resources are often shared without following best practices, for example, at non-permanent URLs that become unavailable within a few months. A recent large-scale study identified that 20% of papers providing resources via URLs suffer from URL rot (http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0115253). The ISWC 2016 Resources Track aims to encourage resource sharing following best practice within the Semantic Web community by calling for submissions of resources and their accompanying papers. This track calls for contributions that provide a concise and clear description of a resource and its (expected) usage. Typical resource types are: ontologies, vocabularies, datasets, benchmarks and replication studies, services and software. Besides these established types of resources, we also welcome the submission of new types of resources such as ontology design patterns, crowdsourcing task designs, workflows, methodologies, protocols and measures, and so forth. Detailed info: http://iswc2016.semanticweb.org/pages/calls/resource-track.html Program Chairs * Alasdair Gray - Heriot-Watt University, United Kingdom (a.j.g.gray at hw.ac.uk) * Marta Sabou - Vienna University of Technology, Austria (martasabou at gmail.com) 2. HTML Submission Guide ========================================== This year we have added an additional option to allow for the submission of articles formatted using HTML. Authors choosing to submit using HTML still need to comply with the page limit and layout requirements of the conference. It?s the author?s responsibility to ensure that reviewers can easily access their submission. On http://iswc2016.semanticweb.org/pages/calls/html-submission.html, you can find helpful tools that can make HTML submissions easier. Your HTML submission with any extensions if accepted will be available on the ISWC web page in preprint form with all the new elements that you?ve included. 3. Call for Workshops and Tutorial proposals ========================================== In addition to the regular research and workshop program, ISWC 2016 will feature a tutorial program addressing the diverse interests of its audience: Semantic Web practitioners that wish to learn about new technologies, novices to the Semantic Web interested in introductory tutorials to key Semantic Web / Linked Data topics, government and industry representatives focusing on the applicability of Semantic Web / Linked Data technologies in practical settings. We hereby invite you to submit a tutorial proposal on a topic relevant to the ISWC 2016 audience. Detailed info: http://iswc2016.semanticweb.org/pages/calls/tutorials.html Besides tutorials, ISWC will host a number of workshops on topics related to the general theme of the conference. The role of the workshops is to provide a context for a focused and intensive scientific exchange among researchers interested in a particular topic. As such, workshops are the primary venues for the exploration of emerging ideas as well as for the discussion of novel aspects of established research topics. We invite you to submit a proposal for workshops on a topic of interest to ISWC attendees. Detailed info: http://iswc2016.semanticweb.org/pages/calls/workshops.html Workshops & Tutorials Chairs * Chiara Ghidini - Bruno Kessler Foundation, Trento, Italy (ghidini at fbk.eu) * Heiner Stuckenschmidt - Data- and Web Science Group, University of Mannheim, Germany (heiner at dwslab.de) 4. Student Grants ========================================== If you are a student interested in attending ISWC 2016 you may be eligible to apply for a grant to support the costs of travel and lodging. This year, travel grants are funded by the Semantic Web Science Association (SWSA) and the US National Science Foundation (NSF). Detailed info: http://iswc2016.semanticweb.org/pages/calls/student-grants.html 5. Important Dates ========================================== Workshop proposals due March 10, 2016 Tutorial proposals due March 15, 2016 Notifications of workshop proposals out April 15, 2016 Notifications of tutorial proposals out April 20, 2016 Abstracts due (Research, Applications, Resource tracks) April 20, 2016 Submissions due (Research, Applications, Resource tracks) April 30, 2016 DC submissions due May 30, 2016 Author rebuttal period starts (Research, Applications, Resource tracks) June 12, 2016 Author rebuttal period ends (Research, Applications, Resource tracks) June 15, 2016 Notifications for Research, Applications, Resource tracks out June 30, 2016 Notifications for DC applicants out July 01, 2016 Poster/Demo submissions due July 07, 2016 Workshop papers due July 07, 2016 Metadata for Research, Applications, Resource tracks due July 08, 2016 Camera-ready papers for Research, Applications, Resource tracks due July 18, 2016 Workshop paper notifications sent July 30, 2016 Poster/Demo notifications sent August 07, 2016 Camera-ready copies for DC papers August 15, 2016 Camera-ready papers for workshops August 25, 2016 Camera-ready copies for poster and demos August 30, 2016 Student activity applications due August 31, 2016 Early registration deadline September 10, 2016 Turorial materials due September 19, 2016 Last day to reserve a hotel room at confence rates September 30, 2016 Last day to avoid late registration fee October 05, 2016 Workshops and tutorials October 17-18, 2016 Conference October 19-21, 2016 Happy holidays! The ISWC organising committee From a.pons at upc.edu Tue Dec 29 09:45:22 2015 From: a.pons at upc.edu (antonio) Date: Tue, 29 Dec 2015 15:45:22 +0100 Subject: Connectionists: ICANN 2016 Barcelona - Second Call Message-ID: <56829C82.70803@upc.edu> 2nd Call for Papers 2nd Call for special sessions, workshops, demonstrations ============================================================ *www.icann2016.org* *ICANN 2016 * 25th Annual Conference on Artificial Neural Networks BarcelonaTech (UPC), Barcelona, Spain 6 - 9 September 2016* Special event*: ENNS 25th Anniversary ============================================================ /The International Conference on Artificial Neural Networks (ICANN) is the annual flagship conference of the European Neural Network Society (ENNS). In 2016 the Universitat Polit?cnica de Catalunya (BarcelonaTech) will organize the 25th ICANN Conference from //the //6th to //the //9th //of //September 2016 in Barcelona, Spain, in collaboration with the Universit//at//Pompeu Fabra (UPF)./ *INVITED KEYNOTE SPEAKERS* 1. *Wlodek Duch *(Nicolaus Copernicus University, Torun, Poland) 2. *Erkki Oja *(Aalto University, Helsinki, Finland) 3. *Joaquin Fuster *(University of California at Los Angeles, USA) 4. *Murray Shanahan* (Imperial College London, UK) 5. *G?nther Palm*(University of Ulm, Germany) 6. *Stephen Coombes *(University of Nottingham, UK) 7. *Etienne Koechlin*( Pierre and Marie Curie University, France) *IMPORTANT DATES* /Special session / workshop proposals: /15 January 2016 /Proposals for competitions and tutorials:/31 January 2016 /Submission of abstracts and papers: /1 March 2016 /Submission of //d//emonstration proposals: /1 March 2016 /Notification of acceptance:/8 May 2016 /Camera-ready paper and registration: /15 May 2016 /Conference dates:/6-9 September 2016 *CONFERENCE TOPICS* ICANN 2016 will feature the main tracks /Brain Inspired computing/ and /Machine Learning research/, with strong cross-disciplinary interactions and applications. All research fields dealing with Neural Networks will be present at the conference. A non-exhaustive list of topics includes: * Brain Inspired Computing: Cognitive models, Computational Neuroscience, Self-organization, Reinforcement Learning, Neural Control and Planning, Hybrid Neural-Symbolic Architectures, Neural Dynamics, Recurrent Networks, Deep Learning. * Machine Learning: Neural Network Theory, Neural Network Models, Graphical Models, Bayesian Networks, Kernel Methods, Generative Models, Information Theoretic Learning, Reinforcement Learning, Relational Learning, Dynamical Models. * Neural Applications for: Intelligent Robotics, Neurorobotics, Language Processing, Image Processing, Sensor Fusion, Pattern Recognition, Data Mining, Neural Agents, Brain-Computer Interaction, Neural Hardware, Evolutionary Neural Networks. *CONFERENCE REGISTRATION FEES* Early registration fees have been kept particularly low for this kind of event because ENNS and ICANN aim at full implementation of the academic not-for-profit policy. Undergraduate students (Bachelor and Master level): 90 EUR PhD Students: 200 EUR Regular delegates: 250 EUR *ENNS members have a reduction of 40 EUR* Students can apply for ENNS funded travel grants to attend (see the conference website). *CALL FOR CONTRIBUTED SCIENTIFIC COMMUNICATIONS* All scientific communications presented at ICANN 2016 will be reviewed and scientifically evaluated by a panel of experts. The conference will feature three categories of communications: - oral communications (15'+5') - poster communications (on permanent display and 2 hours presentation) - demonstrations Authors willing to present original contributions for any category must submit a manuscript of maximum 8 pages length that will be refereed to international standards by at least three referees. Accepted papers of contributing authors will be published in Springer-Verlag Lecture Notes in Computer Science (LNCS) series. Selected papers will be invited after the conference for a full journal paper submission. Authors willing to present a contribution for oral communications and posters without submitting an full manuscript must submit a 1-page abstract that will also be refereed by at least three referees. The abstracts will be published all together in a proceedings section without an author index. In case of program constraints the priority will be given to original contributions accompanied by a full paper submission. Submission of communications will be online. More details are available on the conference website. *WORKSHOPS, SPECIAL SESSIONS, DEMONSTRATIONS,* *COMPETITION PROPOSALS and TUTORIALS* ICANN 2016 invites proposals for workshops, special sessions, demonstrations, competitions and tutorials to be held during the conference. For more information, please refer to the website. *BEST PAPER AWARDS* ENNS will sponsor a maximum of four best paper awards, two in the Brain Inspired Computing track (one poster and one oral communication) and two in the Machine Learning research track. All awardees will be presented during the final ceremony. *ORGANISATION** General Chair:*/ Antonio J. Pons Rivero/(UPC Barcelona, Spain)* Local**co-Chairs:* /Jordi Garcia-Ojalvo/(UPF Barcelona, Spain), /Paul Verschure/(UPF Barcelona, Spain) *Organising Committee Chairs:*/ Daniel Malagarriga/(UPC Barcelona, Spain), /Lara Escuain/(UPC Barcelona, Spain), /Caroline Kleinheny/(ENNS Lausanne, Switzerland) *Honorary Chair: *Alessandro E. P. Villa * Communication* *Chair:*/ Paolo Masulli/(ENNS Lausanne, Switzerland) *********************************************** Antonio J. Pons Rivero General Chair of ICANN 2016 Terrassa School of Industrial and Aeronautical Engineering (ETSEIAT) Nonlinear dynamics, nonlinear optics and lasers Group BarcelonaTech (UPC) Edifici GAIA Rbla. Sant Nebridi, 22 08222 Terrassa, Spain Caroline Kleinheny Secretary of the European Neural Network Society University of Lausanne Internef 137k, Quartier UNIL Dorigny 1015 Lausanne, Switzerland *********************************************** -------------- next part -------------- An HTML attachment was scrubbed... URL: From yiyin at ee.columbia.edu Tue Dec 29 10:49:10 2015 From: yiyin at ee.columbia.edu (Yiyin Zhou) Date: Tue, 29 Dec 2015 10:49:10 -0500 Subject: Connectionists: Fruit Fly Brain Hackathon Message-ID: Fruit Fly Brain Hackathon 2016 FFBH 2016 March 17, 2016Columbia University, New York, NY 10027 The goal of the hackathon is to bring together researchers interested in developing executable models of the fruit fly brain. Towards that end we will engage systems and computational neuroscientists in modeling, design, implementation and biological validation of an open-source emulation platform of the whole fruit fly brain. All hackathon participants will be provided with an Amazon Machine Image of the recently developed open-source Neurokernel platform for executable fruit fly brain circuits. The hackathon is aimed at three main groups of participants: biologists, modelers and software engineers. For biologists, the hackathon focuses on the intuitive modeling and representation of biological data, such as anatomical and recordings data of the fruit fly brain, in the NeuroArch database. For modelers, the hackathon aims at creating/modifying models of neuropils that are compliant with the Neurokernel API . For software engineers, the hackathon focuses on improving the Neurokernel platform and its API, and developing new, proof-of-concept features that are needed by biologists and modelers alike. All hackathon participants will be strongly encouraged to collaborate towards the realization of executable fruit fly brain models. The Fruit Fly Brain Hackathon is organized in conjunction with the Columbia Workshop on Brain Circuit, Memory and Computation on March 18-19, 2016. Participants of the hackathon are welcome to attend the workshop. Registration is free but all participants have to register ( https://fruit-fly-brain-hackathon16.eventbrite.com/). Organizers: Paul Richmond, Department of Computer Science, University of Sheffield Adam Tomkins, Department of Automatic Control and Systems Engineering, University of Sheffield Nikul Ukani, Department of Electrical Engineering, Columbia University Yiyin Zhou, Department of Electrical Engineering, Columbia University More information can be found on the hackathon website: http://www.bionet.ee.columbia.edu/hackathons/ffbh/2016 ------------------------------------------------------------------------------ Best Regards, Yiyin Zhou, on behalf of the organizers -------------- next part -------------- An HTML attachment was scrubbed... URL: From h.glotin at gmail.com Wed Dec 30 13:38:43 2015 From: h.glotin at gmail.com (Herve Glotin) Date: Wed, 30 Dec 2015 19:38:43 +0100 Subject: Connectionists: 1 Post-doc and 1 Phd positions opens @ DYNI / SABIOD EU Message-ID: Please forward to whom it may concern:The CNRS LSIS Dyni lab (French Riviera, France) opens :1 PHD GRANT (3 YEARS)and1 POSTDOC GRANT (1 YEAR)Topics : 'DEEP LEARNING FOR HUMAN AND NON HUMAN BIOACOUSTICS'OR'ADVANCED DETECTION AND TRACKING OF ACOUSTIC SOURCES' The goal of your research will be to improve soundscape analysis / bioacoustic pattern detection and classification, at low signal to noise ratio. YOUR PROFILE: - Machine learning / Data Science or Applied Mathematics / Computer Science, or Electrical Engineering / Signal Processing, - Creative and highly motivated, good programming skill (Python, Matlab...), - Fluent in English, both written and spoken. DETAILS : http://sabiod.org/jobs.html Please SUBMIT YOUR APPLICATION BEFORE 10TH OF JANUARY TO: phd.application.dyni at gmail.com cc : h.glotin at gmail.com Application materials should include a CV (university grades, awards, brief statement of research interests, contact details of 2 referees), + 1 or 2 work samples, anything that is genuinely the own work of the applicant (e.g. thesis, computer code, demo, manuscript...). For informal inquiries, please contact Pr. Glotin (h.glotin at gmail.com). Screening of applications begins january 10th 2016. Happy new year ! -- H. Glotin, Pr - http://glotin.univ-tln.fr - glotin at univ-tln.fr Institut Univ. de France (IUF), UMR CNRS LSIS, Univ. Toulon (UTLN) Head of Scaled Acoustic Biodiversity (http://sabiod.org) & Dyni projects -------------- next part -------------- An HTML attachment was scrubbed... URL: From j.eppler at fz-juelich.de Thu Dec 31 08:41:22 2015 From: j.eppler at fz-juelich.de (Jochen Martin Eppler) Date: Thu, 31 Dec 2015 14:41:22 +0100 Subject: Connectionists: Release of NEST 2.10.0 Message-ID: <56853082.8080209@fz-juelich.de> Dear NEST users, we're happy to bring you NEST 2.10.0, which contains 303 repository commits by 25 developers since v2.8.0. The most notable changes over v2.8.0 are: * Support for simulations of gap junctions (see Jan Hahne et al., 2015) * Framework for structural plasticity (see Markus Butz et al., 2013 and Markus Butz et al., 2014) * Full support for the K computer (just in case you found one under your Christmas tree ;-)) All users are encouraged to upgrade and adapt their simulation scripts to the changes in the user interface at this point in time to benefit from the improvements in the new version. For a full list of changes and download links, see https://github.com/nest/nest-simulator/releases/tag/v2.10.0 Best regards and a happy new year, Jochen! -- Dr. Jochen Martin Eppler Phone: +49 2461 61-9471 ---------------------------------- Simulation Laboratory Neuroscience J?lich Supercomputing Centre Institute for Advanced Simulation ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Juelich GmbH 52425 Juelich Sitz der Gesellschaft: Juelich Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender), Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt, Prof. Dr. Sebastian M. Schmidt ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------