From hans.ekkehard.plesser at nmbu.no Thu Sep 1 02:47:13 2016 From: hans.ekkehard.plesser at nmbu.no (Hans Ekkehard Plesser) Date: Thu, 1 Sep 2016 06:47:13 +0000 Subject: Connectionists: Associate professor position in Data Science (Big Data) Message-ID: The Department of Mathematical Sciences and Technology (IMT) at the Norwegian University of Life Sciences (NMBU) as ?s near Oslo has a permanent, full-time position available for an Associate Professor in Data Sciences (Big Data). The position is part of the University's programme for the recruitment of top researchers, which aims to recruiting an internationally leading, early-career researcher with a high potential for NMBU. The position requires research of high international quality. Big Data is relevant to several of NMBU's academic communities working within the environmental sciences and biosciences, and is especially important in fields of research and teaching in IMT. The goal is for the position to contribute to collaborations in the field across academic communities at IMT and NMBU. The person appointed to the position must therefore have excellent collaboration skills. The position will include: ? one PhD Position (3 years) ? NOK 0.25 million in operating funds For a detailed description of the position, our expectations and conditions, please see https://www.jobbnorge.no/en/available-jobs/job/127472/associate-professor-in-data-sciences-big-data-refno-16-03477 Deadline for applications is Oct 1, 2016. Best regards, Hans Ekkehard Plesser -- Dr. Hans Ekkehard Plesser Associate Professor Dept. of Mathematical Sciences and Technology Norwegian University of Life Sciences PO Box 5003, 1432 Aas, Norway Phone +47 6723 1560 Email hans.ekkehard.plesser at nmbu.no Home http://arken.nmbu.no/~plesser From v.steuber at herts.ac.uk Thu Sep 1 07:14:54 2016 From: v.steuber at herts.ac.uk (Steuber, Volker) Date: Thu, 1 Sep 2016 11:14:54 +0000 Subject: Connectionists: Early Career Research Fellowship in Systems Biology for Food and Disease Message-ID: <1472728500024.71794@herts.ac.uk> Early Career Research Fellowship in Systems Biology for Food and Disease University of Hertfordshire School of Life and Medical Sciences, Department of Biological and Environmental Sciences Closing Date: 27th Oct 2016 Salary ?31,656 - ?37,768 per annum depending on skills and experience. Full time position working 37 hours per week. Fixed term contract for a period of five years. The postdoctoral fellowship will focus on emerging methods in biocomputation to improve food and health or combat plant, animal or human diseases. A first degree in biology, computer science or a relevant subject and a doctoral degree in bioinformatics, machine learning, quantitative biology or related subjects is required. Experience in systems biology, big data science or genomics will be useful. The fellowship is offered for a period of 5 years with the expectation that the fellow will obtain a permanent academic post supported. Qualifications required: You must have a first degree in a science, such as biology, computer science, mathematics or a relevant subject, and a doctoral degree in areas such as bioinformatics, machine learning, quantitative biology or a related subject area. Experience in systems biology, big data science or genomics will be useful. Research focus and environment: The Fellow is expected to develop her/his own line of research. This should include a focus on emerging methods in biocomputation that generate and exploit large data sets of biological information to better understand mechanisms such as those underlying host resistance/immunity and/or resistance breakdown. The Fellow will generate an improved understanding of relevant biological systems to develop specific strategies to improve food and health or combat plant, animal or human diseases. This Fellowship will be supported by existing collaborations between colleagues in Schools of Life & Medical Sciences (Kukol, Stotz, Barling, Fitt) and Computer Science (Steuber). The Fellow is expected to use the University?s high performance computer cluster. Experience and skills required for the post (i) Ability to develop and apply computational methods to biological problems; (ii) Experience with techniques such as machine learning or mathematical modelling of biological datasets, for example in genomics or proteomics; (iii) Evidence of original research and ability to publish in high impact journals. Research expectations : The Fellow is expected to develop a collaborative research program with our academic partners. We envisage that the Research Fellow will become a permanent staff member, supported by funding from successful research grant applications and developing new areas of teaching, especially at the post-graduate level. To ensure this, the two Schools will provide career training for the Fellow. The Fellow will have established collaborations with companies and successfully obtained co-funded industry-government projects. The Fellow will publish high-impact papers and be building a research team. Description of the School(s): This Early Career Research Fellow will work with and receive support from the School of Life and Medical Sciences and the School of Computer Science. The successful candidate can build on the strengths of both Schools and may combine experiment-based empirical research with data-based analysis. Within the School of Life and Medical Sciences (http://www.herts.ac.uk/apply/schools-of-study/life-and-medical-sciences/research), the Centre for Agriculture, Food and Environmental Management (CAFEM) is a research and teaching collaboration with the Royal Veterinary College, Rothamsted Research and Oaklands College. The Fellow will work with researchers in CAFEM who have experience with systems biology applicable to crop protection, combining experimental field and lab research with computational modelling. Within the School of Computer Science, research in the Biocomputation Research Group (http://biocomputation.herts.ac.uk/) involves development of computational models to study biological systems and application of biologically-inspired machine learning algorithms for the analysis of "real-world" data. Members of the Biocomputation Group analyse and simulate computational models at different levels of complexity and collaborate closely with leading experimentalists in the UK and abroad. Informal enquiries are encouraged and should be made to Professor Bruce Fitt, Professor of Plant Pathology, email: b.fitt at herts.ac.uk / Tel + 44 (0)1707 284751 or Dr Volker Steuber, Reader in Biocomputation and Head of the Biocomputation Research Group, email: v.steuber at herts.ac.uk / Tel: +44 (0)1707 284350 Applications should be made through http://www.herts.ac.uk/contact-us/jobs-and-vacancies/research-vacancies -------------- next part -------------- An HTML attachment was scrubbed... URL: From mvanross at inf.ed.ac.uk Thu Sep 1 11:46:41 2016 From: mvanross at inf.ed.ac.uk (Mark van Rossum) Date: Thu, 1 Sep 2016 16:46:41 +0100 Subject: Connectionists: PhD positions in computational neuroscience 2016 Message-ID: 3 YEAR PhD IN COMPUTATIONAL NEUROSCIENCE, UNIVERSITY OF EDINBURGH. We are happy to announce a last minute opening in our PhD programme in COMPUTATIONAL NEUROSCIENCE at the University of Edinburgh. Applicants need to have UK citizenship, or have been in the UK for the last 3 years. The studentships are ideal for students who want to apply their computational and analytical skills to problems in neuroscience and related fields. The following supervisor have openings: Peggy Seri?s: Bayesian approaches to cognition and perception; computational psychiatry. Mark van Rossum: Synaptic plasticity; coding in the visual system; noise in the nervous system. Matthias Hennig: Models of neural networks; homeostasis and development; visual and auditory neuroscience; analysis of large-scale electrophysiological recordings The PhD project can be done in collaboration with one of the many affiliated departments and institutes. Edinburgh has been voted as 'best place to live in Britain', and has many exciting cultural and student activities. Students with a strong background in either computer science, mathematics, physics or engineering are particularly welcome to apply. Motivated students with other backgrounds will also be considered. Application procedure: For more info see http://www.anc.ed.ac.uk/neuroscience and contact one of the supervisors listed above. Next, apply at http://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&id=489 Rapid action from applicants will be required. -- Mark van Rossum, Reader, School of Informatics, U Edinburgh Forum Rm 2.52, 44-131-6511211 -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From lciti at essex.ac.uk Thu Sep 1 17:45:29 2016 From: lciti at essex.ac.uk (Luca Citi) Date: Thu, 1 Sep 2016 17:45:29 -0400 Subject: Connectionists: JOB: postdoc on decoding algorithms for the control of robotic hand prostheses (reminder) Message-ID: <3bf60198-e3e5-72f6-fc13-e4cd1e438fed@essex.ac.uk> We are pleased to announce this postdoctoral position on neural engineering for the control of robotic hand prostheses. The position involves researching and developing robust neuro-muscular control algorithms for decoding users' intentions and enabling efficient control of hand prostheses from high-density surface EMG recordings. The project is led by Dr Luca Citi at the University of Essex (UK) and involves a collaboration with Dr Christian Cipriani from Prensilia SRL, Dr Demba Ba from Harvard SEAS, Professor Silvestro Micera from EPFL, and Professor Dario Farina from University of G?ttingen. The successful applicant will have received a PhD in Biomedical Engineering, Electronic Engineering, Statistics, Computer Science or a closely related discipline. The ideal candidate will have significant experience in neural engineering and applicants are also expected to have a strong publication record as first author, ideally including publications in 1st quartile journals in relevant areas. The successful applicant will be part of the Essex BCI Lab, the UK's largest research group in brain-computer interfaces. This post is fixed-term for 17 months. Interested applicants can find further information about the post and the application process at http://csee.essex.ac.uk/staff/lciti/postdoc_epsrc . Closing date: 06/09/2016 Please feel free to email lciti at essex.ac.uk to discuss this opportunity. From psadowsk at uci.edu Thu Sep 1 17:53:52 2016 From: psadowsk at uci.edu (Peter Sadowski) Date: Thu, 01 Sep 2016 21:53:52 +0000 Subject: Connectionists: [publication] A Theory of Local Learning, the Learning Channel, and the Optimality of Backpropagation Message-ID: Members of this list may be interested in our recent work investigating local learning rules for deep neural networks. This publication can be downloaded for free at the following link for 50 days: http://authors.elsevier.com/a/1TddD3BBjKOKjG Cheers, Peter Sadowski Department of Computer Science University of California, Irvine -------------- next part -------------- An HTML attachment was scrubbed... URL: From p.gleeson at ucl.ac.uk Fri Sep 2 08:07:29 2016 From: p.gleeson at ucl.ac.uk (Padraig Gleeson) Date: Fri, 2 Sep 2016 13:07:29 +0100 Subject: Connectionists: Opportunity in Open Source Brain project for experienced software developer Message-ID: (Apologies for cross postings) The Open Source Brain initiative (http://www.opensourcebrain.org) is looking to hire an experienced software developer to work on the web infrastructure for collaborative development of models in computational neuroscience as part of our multidisciplinary group at University College London: https://goo.gl/kROHnZ This would be a great opportunity for someone who has plenty of experience with Java/JavaScript development (and a good helping of Python and/or Ruby) to get a job at the leading edge of efforts to build a truly open infrastructure for modelling and understanding the brain. Previous experience in computational neuroscience is an advantage, though excellent software development skills in a web environment and a desire to make a difference in this field are essential. The successful applicant will have the opportunity to fully participate in the academic activities related to this initiative including contributing to publications and attending scientific conferences. Deadline for applications is 12th Sept 2016. For informal enquiries, please contact p.gleeson at ucl.ac.uk ----------------------------------------------------- Padraig Gleeson Room 321, Anatomy Building Department of Neuroscience, Physiology& Pharmacology University College London Gower Street London WC1E 6BT United Kingdom +44 207 679 3214 p.gleeson at ucl.ac.uk ----------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From rcs at inf.ed.ac.uk Fri Sep 2 09:07:11 2016 From: rcs at inf.ed.ac.uk (Richard Shillcock) Date: Fri, 2 Sep 2016 14:07:11 +0100 Subject: Connectionists: PhD positions in computational neuroscience 2016 In-Reply-To: References: Message-ID: <09C45FC9-69C8-4389-9DE0-3C8C101630E4@inf.ed.ac.uk> 3 YEAR PhD IN COMPUTATIONAL NEUROSCIENCE, UNIVERSITY OF EDINBURGH. We are happy to announce a last minute opening in our PhD programme in COMPUTATIONAL NEUROSCIENCE at the University of Edinburgh. Applicants need to have UK citizenship, or have been in the UK for the last 3 years. The studentship is ideal for a student who wants to apply their computational and analytical skills to problems in neuropsychology and related fields. The following PhD is available (supervised by Richard Shillcock, in Informatics and Psychology, and Bonnie Auyeung, in Psychology) ?Computational and neuropsychological study of hemisphericity in the distribution of cognitive ability across a population, with particular reference to autistic savantism.? The PhD project will be in collaboration with Psychology in the University Edinburgh. Edinburgh has been voted as 'best place to live in Britain', and has many exciting cultural and student activities. Applicants should have a competent computational background, particularly in neural networks, and a background/interest in neuropsychology. Motivated students with other backgrounds may also be considered. Application procedure: For general information, see http://www.anc.ed.ac.uk and for specific information contact Richard Shillcock at rcs at inf.ed.ac.uk Apply formally at http://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&id=489 Rapid action from applicants will be required. **************************************** Dr. Richard Shillcock School of Informatics Room 4.24, University of Edinburgh Informatics Forum, 10 Crichton Street Edinburgh EH8 9AB MAIL : R.Shillcock at ed.ac.uk VOICE : +44 (131) 650 4425 https://sites.google.com/site/rcspplsinf/home and School of Philosophy, Psychology and Language Sciences 7 George Square, Edinburgh EH8 9JZ UK OFFICE HOURS: 9.00?10.00am Monday to Friday, in 4.24IF no appointment necessary **************************************** -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: not available URL: From hans.ekkehard.plesser at nmbu.no Fri Sep 2 10:08:46 2016 From: hans.ekkehard.plesser at nmbu.no (Hans Ekkehard Plesser) Date: Fri, 2 Sep 2016 14:08:46 +0000 Subject: Connectionists: NEST User Workshop 3-4 November 2016 in Karlsruhe, Germany Message-ID: <0D093C00-689A-4610-9690-35FEC32B4CC9@nmbu.no> Dear all! The NEST Initiative is excited to invite all NEST users and developers to the second annual NEST User Workshop on 3-4 November 2016 in Karlsruhe, Germany. The Workshop provides an opportunity for the NEST Community to meet, exchange success stories, swap advice, learn about current developments in and around NEST and spiking network simulation and application. This year, the workshop will focus on the use of spiking networks in Neurorobotics and will kindly be hosted by Forschungszentrum Informatik (FZI) in Karlsruhe, Germany, in collaboration with the Human Brain Project and Forschungszentrum J?lich. The workshop is supported by the Human Brain Project Education Office. Registration for the Workshop is now open at http://indico-jsc.fz-juelich.de/e/nest2016 where you also will find more information about the workshop program and ways to contribute. Deadline for contributions is 18 September, for registration 7 October. Participation is free of charge, but you will have to cover your travel costs. Space is limited, so please register soon! I am looking forward to seeing you in Karlsruhe! Hans Ekkehard Plesser President, The NEST Initiative -- Dr. Hans Ekkehard Plesser Associate Professor Dept. of Mathematical Sciences and Technology Norwegian University of Life Sciences PO Box 5003, 1432 Aas, Norway Phone +47 6723 1560 Email hans.ekkehard.plesser at nmbu.no Home http://arken.nmbu.no/~plesser From bhammer at techfak.uni-bielefeld.de Fri Sep 2 11:37:31 2016 From: bhammer at techfak.uni-bielefeld.de (Barbara Hammer) Date: Fri, 2 Sep 2016 17:37:31 +0200 Subject: Connectionists: workshop NC^2 Message-ID: <278a9021-f438-1a80-a7be-df1985244d5a@techfak.uni-bielefeld.de> The program for this year's workshop *New Challenges in Neural Computation* just went online: https://www.techfak.uni-bielefeld.de/~bhammer/GINN/NC2/ It covers a large number of interesting contributions ranging from deep learning, robotics, learning with non-vectorial data, transfer learnign up to challenging applications. Looking forward to meet you on September 12th in Hanover, Germany. Barbara Hammer -- Prof. Dr. Barbara Hammer CITEC centre of excellence Bielefeld University D-33594 Bielefeld Phone: +49 521 / 106 12115 Fax: +49 521 / 106 12181 From tarek.besold at googlemail.com Sat Sep 3 09:16:00 2016 From: tarek.besold at googlemail.com (Tarek R. Besold) Date: Sat, 3 Sep 2016 15:16:00 +0200 Subject: Connectionists: 1st CfP: NIPS-Workshop "Cognitive Computation: Integrating Neural and Symbolic Approaches" (CoCo @ NIPS 2016) Message-ID: **************************************************** Cognitive Computation: Integrating Neural and Symbolic Approaches (CoCo @ NIPS 2016) **************************************************** Workshop at NIPS 2016, Barcelona, Spain December 09, 2016 == WORKSHOP WEBPAGE == http://www.neural-symbolic.org/CoCo2016/ == MISSION STATEMENT == While early work on knowledge representation and inference was primarily symbolic, the corresponding approaches subsequently fell out of favor, and were largely supplanted by connectionist methods. In this workshop, we will work to close the gap between the two paradigms, and aim to formulate a new unified approach that is inspired by our current understanding of human cognitive processing. This is important to help improve our understanding of Neural Information Processing and build better Machine Learning systems, including the integration of learning and reasoning in dynamic knowledge-bases, and reuse of knowledge learned in one application domain in analogous domains. The workshop brings together established leaders and promising young scientists in the fields of neural computation, logic and artificial intelligence, knowledge representation, natural language understanding, machine learning, cognitive science and computational neuroscience. Invited lectures by senior researchers will be complemented with presentations based on contributed papers reporting recent work (following an open call for papers) and a poster session, giving ample opportunity for participants to interact and discuss the complementary perspectives and emerging approaches. The workshop targets a single broad theme of general interest to the vast majority of the NIPS community, namely translations between connectionist models and symbolic knowledge representation and reasoning for the purpose of achieving an effective integration of neural learning and cognitive reasoning, called neural-symbolic computing. The study of neural-symbolic computing is now an established topic of wider interest to NIPS with topics that are relevant to almost everyone studying neural information processing. == KEYWORDS == The following list gives some (but by far not all) relevant keywords for the CoCo @ NIPS 2016 workshop: - neural-symbolic computing; - language processing and reasoning; - cognitive agents; - multimodal learning; - deep networks; - knowledge extraction; - symbol manipulation; - variable binding; - memory-based networks; - dynamic knowledge-bases; - integration of learning and reasoning; - explainable AI. == CALL FOR PAPERS == We invite submission of papers dealing with topics related to the research questions discussed in the workshop. The reported work can range from theoretical/foundational research to reports on applications and/or implemented systems. We explicitly also encourage the submission of more controversial papers which can serve as basis for open discussions during the event. Possible topics of interest include but are (by far!) not limited to: - The representation of symbolic knowledge by connectionist systems; - Neural Learning theory; - Integration of logic and probabilities, e.g., in neural networks, but also more generally; - Structured learning and relational learning in neural networks; - Logical reasoning carried out by neural networks; - Integrated neural-symbolic approaches; - Extraction of symbolic knowledge from trained neural networks; - Integrated neural-symbolic reasoning; - Neural-symbolic cognitive models; - Biologically-inspired neural-symbolic integration; - Applications in robotics, simulation, fraud prevention, natural language processing, semantic web, software engineering, fault diagnosis, bioinformatics, visual intelligence, etc. - Approaches/techniques making AI and/or Machine Learning systems/algorithms better explainable or increasing human comprehensibility. = Submission instructions = - Submissions have to be made via EasyChair ( https://easychair.org/conferences/?conf=coconips2016) before the paper submission deadline indicated below. - Submissions are limited to at most eight pages, an additional ninth page containing only cited references is allowed. Still, also shorter papers are expressly welcomed. - Submissions have to use the NIPS 2016 submission format (see http://nips.cc/Conferences/2016/PaperInformation/StyleFiles). - Reviewing will be single-blind, i.e., you are free to indicate your name etc. on the paper. (Still, this is not an obligation.) Please note that at least one author of each accepted paper must register for the event and be available to present the paper at the workshop. =Publication= Accepted papers will be published in official workshop proceedings submitted to CEUR-WS.org. Authors of selected papers will be invited to submit a revised and extended version of their papers to a journal special issue after the workshop. == IMPORTANT DATES == - Deadline for paper submission: October 10, 2016 - Notification of paper acceptance: October 30, 2016 - Camera-ready paper due: November 14, 2016 - Workshop date: December 09, 2016 - NIPS 2015 main conference: December 5-8, 2016 == ADMISSION == The workshop is open to anybody, please register via NIPS 2016 ( http://nips.cc). == WORKSHOP ORGANIZERS == - Tarek R. Besold (University of Bremen, Germany) - Antoine Bordes (Facebook AI Research, USA) - Artur d'Avila Garcez (City University London, UK) - Greg Wayne (Google DeepMind, UK) == ADDITIONAL INFORMATION == - General questions concerning the workshop should be addressed to Tarek R. Besold at Tarek(dot)Besold(at)uni(hyphen)bremen(dot)de. - This workshop is conceptually related to the series of International Workshops on Neural-Symbolic Learning and Reasoning (NeSy). If interested, have a look at http://www.neural-symbolic.org - Please also feel free to join the neural-symbolic integration mailing list for announcements and discussions - it's a low traffic mailing list. If interested, register at http://maillists.city.ac.uk/mailman/listinfo/nesy . -------------- next part -------------- An HTML attachment was scrubbed... URL: From zoltan.szabo.list at gmail.com Sun Sep 4 15:54:22 2016 From: zoltan.szabo.list at gmail.com (Zoltan Szabo) Date: Sun, 4 Sep 2016 21:54:22 +0200 Subject: Connectionists: CFP: NIPS-2016: Adaptive and Scalable Nonparametric Methods in ML workshop Message-ID: <20160904215422.1f008453@gmail.com> Apologies for cross-posting. ========================================================================= CALL FOR PAPERS Adaptive and Scalable Nonparametric Methods in ML workshop @ NIPS-2016 December 10th, 2016 Barcelona, Spain https://sites.google.com/site/nips2016adaptive/ Important dates: Submission deadline: Sept. 23, 2016. Acceptance notification: Oct. 10, 2016. ========================================================================= Description: Large amounts of high-dimensional data are routinely acquired in scientific fields ranging from biology, genomics and health sciences to astronomy and economics due to improvements in engineering and data acquisition techniques. Nonparametric methods allow for better modelling of complex systems underlying data generating processes compared to traditionally used linear and parametric models. From statistical point of view, scientists have enough data to reliably fit nonparametric models. However, from computational point of view, nonparametric methods often do not scale well to big data problems. The aim of this workshop is to bring together practitioners, who are interested in developing and applying nonparametric methods in their domains, and theoreticians, who are interested in providing sound methodology. We hope to effectively communicate advances in development of computational tools for fitting nonparametric models and discuss challenging future directions that prevent applications of nonparametric methods to big data problems. We encourage submissions on a variety of topics, including but not limited to: - Randomized procedures for fitting nonparametric models. For example, sketching, random projections, core set selection, etc. - Nonparametric probabilistic graphical models - Scalable nonparametric methods - Multiple kernel learning - Random feature expansion - Novel applications of nonparametric methods - Bayesian nonparametric methods - Nonparametric network models This workshop is a fourth in a series of NIPS workshops on modern nonparametric methods in machine learning. Previous workshops focused on time/accuracy tradeoffs, high dimensionality and dimension reduction strategies, and automating the learning pipeline. Submission: Papers submitted to the workshop should be up to four pages long (including references), extended abstracts in camera-ready format using the NIPS style. They should be uploaded (.pdf, up to 5MB) to CMT (https://cmt.research.microsoft.com/ADAPTIVE2016). Accepted submissions will be presented as talks or posters. Format: The workshop will be a one day workshop. As with last year's workshop, the workshop will consist of 6-8 invited and contributed talks, with a poster session. Confirmed speakers: - Arthur Gretton (University College London) - David Dunson (Duke University) - Francis Bach (INRIA, ENS) - Ming Yuan (University of Wisconsin-Madison) - Olga Klopp (CNRS) - Richard Samworth (University of Cambridge) Organizers: - Aaditya Ramdas (UC Berkeley) - Bharath K. Sriperumbudur (Pennsylvania State University) - Han Liu (Princeton University) - John Lafferty (University of Chicago) - Mladen Kolar (University of Chicago Booth School of Business) - Samory Kpotufe (Princeton University) - Zoltan Szabo (University College London) From M.Gillies at gold.ac.uk Mon Sep 5 05:27:03 2016 From: M.Gillies at gold.ac.uk (Marco Gillies) Date: Mon, 5 Sep 2016 09:27:03 +0000 Subject: Connectionists: Research Associate - Machine Learning and Virtual Reality for Social Neuroscience References: Message-ID: <4E9DCB50-5DD9-4E97-A632-E7F4BE847BBC@campus.goldsmiths.ac.uk> Applications are invited for the position of post-doctoral research associate to model and generate human social behaviour using machine learning and virtual reality. The post-holder will be responsible for using machine learning to analyse human movement data and train computational models for controlling virtual characters, in a collaboration between computer science and psychology. The post holder will be based in Marco Gillies lab at Goldsmiths College and in Antonia Hamilton's lab at the UCL Institute of Cognitive Neuroscience, and will spend time in both locations. This post is funded by a Leverhulme grant and is available for 3 years from January 2017 in the first instance. More details can be found here: https://atsv7.wcn.co.uk/search_engine/jobs.cgi?amNvZGU9MTU3NzU3NiZ2dF90ZW1wbGF0ZT05NjUmb3duZXI9NTA0MTE3OCZvd25lcnR5cGU9ZmFpciZicmFuZF9pZD0wJnZhY194dHJhNTA0MTE3OC41MF81MDQxMTc4PTkyNzg2JnZhY3R5cGU9MTI3NiZwb3N0aW5nX2NvZGU9MjI0JnJlcXNpZz0xNDcyMjE0NDI1LTZhYWI0NTcwZDhlY2UyZGNlODc1ZmM1OWU3YjA1ODlmMjBmZDJmZGU=&jcode=1577576&vt_template=965&owner=5041178&ownertype=fair&brand_id=0&vac_xtra5041178.50_5041178=92786&vactype=1276&posting_code=224&reqsig=1472214425-6aab4570d8ece2dce875fc59e7b0589f20fd2fde -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Mon Sep 5 14:08:59 2016 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 05 Sep 2016 11:08:59 -0700 Subject: Connectionists: NEURAL COMPUTATION - September 1, 2016 In-Reply-To: Message-ID: Neural Computation - Volume 28, Number 9 - September 1, 2016 Available online for download now: http://www.mitpressjournals.org/toc/neco/28/9 ----- Articles Learning Minimal Latent Directed Information Polytrees Jalal Etesami, Negar Kiyavash, and Todd Coleman Dynamic Multi-scale Modes of Resting State Brain Activity Detected by Entropy Field Decomposition Lawrence R. Frank, Vitaly L Galinsky Letters Active Inference and Learning in the Cerebellum Karl Friston, Ivan Herreros A Mathematical Framework for Statistical Decision Confidence Balazs Hangya, Joshua I. Sanders, and Adam Kepecs Linking Neuromodulated Spike-Timing Dependent Plasticity With the Free-Energy Principle Takuya Isomura, Koji Sakai, Kiyoshi Kotani, and Yasuhiko Jimbo The Geometry of Plasticity-induced Sensitization in Isoinhibitory Rate Motifs Gautam Kumar, ShiNung Ching The Enhanced Rise and Delayed Fall of Memory in a Model of Synaptic Integration: Extension to Discrete State Synapses Terry Elliott Dynamic Signal Tracking in a Simple V1 Spiking Model Guillaume Lajoie, Lai-Sang Young ------------ 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 tomas.hromadka at gmail.com Mon Sep 5 18:26:43 2016 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Tue, 6 Sep 2016 00:26:43 +0200 Subject: Connectionists: COSYNE 2017: Meeting Announcement and Call for Abstracts Message-ID: <343aec31-6201-f3d0-77a0-f8e8de58d887@gmail.com> ==================================================== Computational and Systems Neuroscience 2017 (Cosyne) MAIN MEETING 23 - 26 February 2017 Salt Lake City, Utah WORKSHOPS 27 - 28 February 2017 Snowbird, Utah www.cosyne.org ==================================================== MEETING ANNOUNCEMENT 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. For details on workshop proposals please visit Cosyne.org -> Workshops. Cosyne topics include but are not limited to: neural coding, natural scene statistics, dendritic computation, neural basis of persistent activity, nonlinear receptive field mapping, representations of time and sequence, reward systems, decision-making, synaptic plasticity, map formation and plasticity, population coding, attention, and computation with spiking networks. This year we would like to foster increased participation from experimental groups as well as computational ones. Please circulate widely and encourage your students and postdocs to apply. IMPORTANT DATES Abstract submission opens: 01 October 2016 Abstract submission deadline: 10 November 2016 Workshop pre-proposal deadline: 01 October 2016 Workshop proposal deadline: 31 October 2016 CONFIRMED SPEAKERS Yoshua Bengio (Montreal) Brent Doiron (Pittsburgh) Catherine Du Lac (Harvard) Greg Gage (Backyard Brains) Surya Ganguli (Stanford) Maria Geffen (Penn) Ann Graybiel (MIT) Gero Miesenbock (Oxford) Liz Phelps (NYU) Jonathan Pillow (Princeton) Vanessa Ruta (Rockefeller) Daphna Shahomy (Columbia) Kay Tye (MIT) Nao Uchida (Harvard) When preparing an abstract, authors should be aware that not all abstracts can be accepted for the meeting, due to space constraints. Abstracts will be selected based on the clarity with which they convey the substance, significance, and originality of the work to be presented. ORGANIZING COMMITTEE: General Chairs: Megan Carey (Champalimaud) and Emilio Salinas (Wake Forest) Program Chairs: Ilana Witten (Princeton) and Eric Shea-Brown (U Washington) Workshop Chairs: Laura Busse (LMU, Munich) and Alfonso Renart (Champalimaud) Publicity Chair: Il Memming Park (Stony Brook) EXECUTIVE COMMITTEE: Anne Churchland (CSHL) Zachary Mainen (Champalimaud) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) CONTACT cosyne.meeting [at] gmail.com COSYNE MAILING LISTS Please consider adding yourself to Cosyne mailing lists (groups) to receive email updates with various Cosyne-related information and join in helpful discussions. See Cosyne.org -> Mailing lists for details. From levink at unimelb.edu.au Mon Sep 5 21:42:10 2016 From: levink at unimelb.edu.au (Levin Kuhlmann) Date: Tue, 6 Sep 2016 01:42:10 +0000 Subject: Connectionists: Melbourne-University AES-MathWorks-NIH Seizure Prediction Challenge Message-ID: After much anticipation the Melbourne-University AES-MathWorks-NIH Seizure Prediction Challenge has launched on Kaggle.com! Enter for your chance to win part of the US$20,000 prize pool and test your data science skills against the one-of-a-kind long-term human intracranial EEG database from the world-first human clinical trial of the NeuroVista Seizure Advisory System that was co-ordinated by the University of Melbourne. This device was implanted in the heads of epilepsy patients to record brain activity over a period of 6 months to 3 years. Typical recordings of intracranial EEG in humans only last up to two weeks and do not provide enough data to allow accurate evaluation of seizure prediction algorithms because often only a handful of seizures can be collected over two weeks. The durations of data in the NeuroVista dataset overcome this problem. Analysis of the human NeuroVista dataset has indicated that seizure prediction in humans is in fact possible, however, improvements can still be achieved depending on the patient. This contest seeks to find improved methods by contributing data from 3 patients whose seizures are difficult to predict. In 2014, our contest partners from the Mayo Clinic and University of Pennsylvania ran a seizure prediction contest on Kaggle.com involving long-term data from dogs, that were also implanted with the NeuroVista device, and short-term human data. The contest revealed several novel and existing approaches that performed well and now we want to know how well they can perform on long-term data from humans. Can you help us find out, or can you come up with even better algorithms? Neural net/deep learning approaches are strongly encouraged, although any approach is welcome. Everything you need to get started is on the contest web page: https://www.kaggle.com/c/melbourne-university-seizure-prediction Be sure to get started soon as the contest ends on November 21 and the winners will be announced at the American Epilepsy Society Annual Meeting on December 5. Good luck! On behalf of the organising team University of Melbourne: Levin Kuhlmann, Mark Cook, David Grayden, Dean Freestone, Philippa Karoly University of Pennsylvania: Brian Litt Mayo Clinic: Greg Worrell, Ben Brinkmann Alliance for Epilepsy Research: Susan Arthurs And our co-sponsors American Epilepsy Society MathWorks National Institutes of Health And Kaggle.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From erik at oist.jp Mon Sep 5 20:33:26 2016 From: erik at oist.jp (Erik De Schutter) Date: Tue, 6 Sep 2016 00:33:26 +0000 Subject: Connectionists: Faculty positions open in theoretical biology, computational sciences and big data Message-ID: Dear all, Faculty recruitment is ongoing in the Okinawa Institute of Science and Technology Graduate University Japan in fields that are of interest members of this mailing list, including: theoretical biology (including theoretical neuroscience), computational sciences and big data analysis. Please go to https://groups.oist.jp/facultypositions for more information. Application deadline is October 24, 2016. Erik De Schutter Full advertisement: Open Faculty Positions The Okinawa Institute of Science and Technology Graduate University (www.oist.jp) invites applications for at least 5 new faculty positions as part of its planned expansion. Targeted areas for the current search include*: Chemistry: Chemical Biology; Materials Chemistry (including Polymer Chemistry, Metal-Organic Frameworks) Life Sciences: Cell Biology; Theoretical Biology; Behavioral Learning Theory Mathematics: Discrete Mathematics; Computational Sciences; Big Data Analysis Physics: Quantum Information; Ultracold Physics; Condensed Matter; Cosmology/Gravitational Waves We are seeking applicants with excellent scholarship and creativity. Successful candidates are expected to establish an active program of research, supervise student research and teach in the graduate program. Generous research resources are provided which may be supplemented with external grants. Appointments will be Tenure-Track or Tenured. Starting date is flexible. Applications should include: a letter of intent, CV, summary of previous research, research proposal, and a teaching statement. Information and instructions for submitting applications can be accessed at https://groups.oist.jp/facultypositions *Applications from strong candidates in other fields may be considered. Application Deadline: Noon on Monday, October 24, 2016 (any time zone) The OIST Graduate University offers a world-class research environment with an international research community and opportunities for interdisciplinary research. Research and teaching is conducted in English. The campus is located in a beautiful subtropical setting in Okinawa, Japan. The OIST Graduate University is an equal opportunity educator and employer committed to increasing the diversity of its faculty, students and staff through proactive policies. We provide a family-friendly working environment, including a bilingual child development center on campus. Applications from women and other underrepresented groups are strongly encouraged. See https://groups.oist.jp/ged Inquiries should be directed to Professor Gordon Arbuthnott, Dean of Faculty Affairs, faculty-recruiting at oist.jp -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 3682 bytes Desc: not available URL: From dengdehao at gmail.com Mon Sep 5 21:10:37 2016 From: dengdehao at gmail.com (Teng Teck Hou) Date: Tue, 6 Sep 2016 09:10:37 +0800 Subject: Connectionists: [IJCNN 2017] Approaching deadline on Thursday, 15th September 2016 Message-ID: <007501d207db$7b56e410$7204ac30$@gmail.com> [Apologies for cross-postings] ################################################## COMBINED CALLS [DUE ON THURSDAY, 15 SEPTEMBER] CALL FOR COMPETITIONS http://www.ijcnn.org/call-for-competition CALL FOR SPECIAL SESSIONS http://www.ijcnn.org/call-for-special-sessions CALL FOR PANELS http://www.ijcnn.org/call-for-panels CALL FOR WORKSHOPS http://www.ijcnn.org/call-for-workshops CALL FOR TUTORIALS http://www.ijcnn.org/call-for-tutorials CALL FOR PAPERS http://www.ijcnn.org/call-for-papers CALL FOR SPONSORS http://www.ijcnn.org/call-for-sponsors International Joint Conference on Neural Networks May 14-19, 2017, Anchorage, Alaska, USA http://www.ijcnn.org/ ################################################## IJCNN is the premier international conference in the area of neural network theory, analysis, and applications. Co-sponsored by the International Neural Network Society (INNS) and the IEEE Computational Intelligence Society (IEEE-CIS), over the last three decades this conference and its predecessors has hosted [past, present, and future] leaders of neural network research. IJCNN 2017 will feature invited plenary talks by world-renowned speakers in the areas of neural network theory and applications, computational neuroscience, robotics, and distributed intelligence. In addition to regular technical sessions with oral and poster presentations, the conference program will include special sessions, competitions, tutorials and workshops on topics of current interest. The 2017 International Joint Conference on Neural Networks (IJCNN 2017) will be held at the William A. Egan Civic and Convention Center in Anchorage, Alaska, USA, May 14-19, 2017. "... Only in Anchorage can you meet a moose, walk on a glacier and explore a vast, natural park all in a single day. Between mountains and an inlet, surrounded by national parks and filled with Alaska wildlife, Anchorage combines the best of Alaska in a city that has the comforts of home and the hospitality of the Last Frontier. ..." For the latest updates, follow us on Facebook (https://fb.me/ijcnn2017/) and Twitter (@ijcnn2017). ##############################Important Dates############################## * Special Session, Panel Sesion & Competition Proposals September 15, 2016 * Tutorial and Workshop Proposals October 15, 2016 * Paper Submission November 15, 2016 * Paper Decision Notification January 20, 2017 * Camera-Ready Submission February 20, 2017 ########################################################################### ##########################Plenary Speakers########################## * Stephen Grossberg, Boston University, USA * Christof Koch, Allen Institute for Brain Science, USA * Hava Siegelmann, DARPA, and University of Massachusetts, Amherst, USA * Jose Principle, University of Florida, USA #################################################################### ##########################Call for Competitions########################## Competition organizers are kindly invited to submit their proposals to IJCNN2017 Competition Chair (TBA) by September 15, 2016. The notifications of acceptance of the competition proposals will be provided by TBA and will be shortly publish in the IJCNN 2017 website. Please note that each accepted competition will be published in a separate web link. The competition proposal should contain the following information (please fill out the form at the bottom of this page, or send the required information in the form as a single pdf file to the competition chair [email below]) The aims and objectives of the competition, The rules of the competition, including which data sets will be used, How the competition will serve the neural networks community/society, How to enter the competitions and how to evaluate them, and Which competition platform (or result submission and validation method) you will use (e.g. similar to Kaggle). Summary of performance results directly reported by the competition participants and not verified by the competition organizers are not acceptable. Please note that you need to select a category for your competition from the following list: * Category A: You are planning to organise an associated special session, in which the proposal must be submitted separately to the special session chairs. In addition, you require that each team must submit at least one paper to the special session. * Category B: You are planning to organise an associated special session, whose proposal must be also submitted separately to the special session chairs. However, submission of papers to the special session by competition participants is not mandatory. * Category C: You have no plan to organize an associated special session. Note: For categories B and C, please also indicate whether or not conference participation is required for each entry. Sponsorship A winning certificate and free registration will be provided to the winner of each competition who attends IJCNN 2017. For further details, please refer to http://www.ijcnn.org/call-for-competition. If you need any other information, please do not hesitate to contact the IJCNN2017 Competition Chair: Juyang (John) Weng, Michigan State University. E-mail: weng at cse.msu.edu ######################################################################### ##########################Call for Special Sessions########################## The IJCNN 2017 Program Committee solicits proposals for special sessions within the technical scopes of the conference. Special sessions, to be organized by international recognized experts, aim to bring together researchers focused in special, novel, and challenging topics. Fast-developing themes such as Deep Learning, Big Data, or applications to fields like chemistry, biology, computer games, robotics, etc. are examples. Papers submitted for special sessions are to be peer-reviewed with the same criteria used for the regular sessions. Researchers interested in organizing special sessions are invited to submit a formal proposal using the on-line form of the Special Sessions webpage. Due to large expected number of submissions, please do not directly email the information to the special session co-chairs Derong Liu, University of Chicago & Chinese Academy of Sciences. Beijing, and Tatiana Tambouratzis, University of Piraeus, Greece. For further details, please refer to http://www.ijcnn.org/call-for-special-sessions Any questions regarding this proposal can be asked to the Special Session Chairs: Derong Liu, University of Chicago, USA. E-mail: derong at uic.edu Tatiana Tambouriatzis, University of Piraeus, Greece. E-mail: tatianatambouratzis at gmail.com ############################################################################ # ##########################Call for Panels########################## The IJCNN 2017 Program Committee solicits proposals for panel sessions to provide forums for lively, interactive discussions among world-leading experts in specific areas. Panel Session proposals are solicited in a broad range of areas related to NNs, including but not limited to the following: hot topics and challenges in NNS, such as Deep learning, Big Data, Brain-Computer Interfaces, new generation of AI; history of NNs, with special emphasis on the upcoming 30th birthday of INNS; government funding opportunities; outreach to industry and to sister societies, and many more. Panel proposals should include the information listed below. Please email the following information in a single file to the Panel Chair (contact information below). * Topic of the panel * Name of proposer(s) * Email of main contact person * Brief bio of proposers * Brief description of the panel and why the panel format is appropriate for the topic. * List of potential panelists Researchers interested in organizing panels are invited to submit a formal proposal. Any questions regarding this proposal can be asked to the Panel Chair: Robert Kozma, University of Memphis, USA. Email: rkozma at memphis.edu ##################################################################### ##########################Call for Workshops########################## Post-conference workshops offer a unique opportunity for in-depth discussions of specific topics in neural networks and computational intelligence. The workshops should be moderated by scientists or professionals who has significant expertise and /or whose recent work has had a significant impact within their field. IJCNN 2017 will emphasize emerging and growing areas of computational intelligence. Each workshop has a duration of 3 or 6 hours. The format of each workshop will be up to the moderator, and can include interactive presentations as well as panel discussions among participants. These interactions should highlight exciting new developments and current research trends to facilitate a discussion of ideas that will drive the field forward in the coming years. Workshop organizers can prepare various materials including handouts or electronic resources that can be made available for distribution before or after the meeting. Researchers interested in organizing workshops are invited to submit a formal proposal including the following information as a single file (pdf, doc, etc.) to the workshop chair: * Title * Organizers and their short bio * Brief description of the scope and impact of the workshop * Timeliness of the topic * Confirmed and/or potential speakers * Half day (3 hours) or full day (6 hours) * Link to organizer's web page and/or workshop web site (optional) For further details, please refer http://www.ijcnn.org/call-for-workshops. Any questions regarding this proposal can be asked to the Workshop Chair: Lazaros Iliadis, Democritus University of Thrace, Greece. E-mail: liliadis at fmenr.duth.gr ###################################################################### ##########################Call for Tutorials########################## IJCNN 2017 will feature pre-conference tutorials addressing fundamental and advanced topics in computational intelligence. Tutorial proposals should be emailed to the Tutorial Chair (see below). A tutorial proposal should include the * Title * Presenter/organizer name(s) and affiliations * Expected enrollment * Abstract (less than 300 words) * Additional outline if needed * Presenter/organizer biography * Links to the presenter/organizer web page or the tutorial page (optional) * The proposal should not exceed two pages in 1.5 space, Times 12 point font. The tutorial format (preliminary) is 1 hour and 45 minutes with a 10-minute break. Researchers interested in organizing workshops are invited to submit a formal proposal. For further details, please refer to http://www.ijcnn.org/call-for-tutorials. Any questions regarding this proposal can be asked to the Tutorials Chair: Asim Roy, Arizona State University, USA. E-mail: ASIM.ROY at asu.edu ###################################################################### ##########################Call for Sponsors########################## You are invited to support the 2017 International Joint Conference on Neural Networks (IJCNN 2017), organized by the International Neural Network Society (INNS) and the IEEE Computational Intelligence Society (IEEE-CIS). This is an ideal way to demonstrate your organization's commitment to the field of artificial intelligence ? including neural networks, biomorphic systems, computational neuroscience, neuroengineering, and many other areas at the frontier of technological innovation ? and to publicize this support to many leaders and students in the field. Corporate support is typically used to permit a greater number of students to attend IJCNN at reduced fees without increasing the general registration, and to allow student volunteers to receive complimentary registration. Exhibits by sponsors also help inform researchers ? especially students and postdocs ? about relevant applications and opportunities. Corporate support can be targeted to a particular event or activity at the Conference. IJCNN 2017 has four sponsorship levels: Platinum, Gold, Silver, and Bronze. Your support is very important to the conference, and the conference committee ensures that these contributions are well recognized. We list the benefits and costs below. * PLATINUM (US$10,000 or greater contribution) You will get 4 free registrations to the main conference and tutorials and workshops, 4 banquet tickets, 3 exhibition tables. You will also get second choice at naming events at the conference. For example, there are generally two receptions, several lunches and coffee breaks, plus a student reception. Naming of events will be decided based on the amount of the contribution and the order received. Your company or institution (with logo and URL) will be listed in all conference announcements, on the advance program, and on the conference web pages, at www.ijcnn.org We will specially acknowledge your company's contribution and offer thanks at the opening and closing sessions of the conference You will have the opportunity to include material and giveaways with the conference material for each attendee You will get early notification direct from the Corporate Support Chair of conference news * GOLD SPONSORSHIP (US$5,000 or greater contribution) You will get 3 free registrations to the main conference or tutorials and workshops, 3 banquet tickets, 2 exhibition tables. You will also get third choice at naming events at the conference (after the Platinum). For example, there are generally two receptions, several lunches and coffee breaks, plus a student reception. Naming of events will be decided based on the amount of the contribution and the order received. Your company or institution (with logo and URL) will be listed in all conference announcements, on the advance program, and on the conference web pages, at www.ijcnn.org We will acknowledge your company's contribution and offer thanks at the opening and closing sessions of the conference You will have the opportunity to include material and giveaways with the conference material for each attendee You will get early notification direct from the Corporate Support Chair of conference news * SILVER SPONSORSHIP (US$3,000 or greater contribution) You will get 2 free registrations to the main conference or tutorials and workshops, 2 banquet tickets, 1 exhibition table. We will name an event after your company, if there are events left after those named for Platinum and Gold Your company or institution (with logo and URL) will be listed in the advance program, and on the conference web pages, at www.ijcnn.org We will acknowledge your company's contribution and offer thanks at the opening and closing sessions of the conference You will get early notification direct from the Corporate Support Chair of conference news * BRONZE SPONSORSHIP (US$1,500 or greater contribution) You will get 1 free registration to the main conference or tutorials and workshops and 1 banquet ticket. Your company or institution (with logo and URL) will be listed in the advance program, and on the conference web pages, at www.ijcnn.org We will acknowledge your company's contribution and offer thanks at the opening and closing sessions of the conference You will get early notification direct from the Corporate Support Chair of conference news Sponsorships at lower levels will be considered, with benefits negotiated between the IJCNN 2017 Sponsorship Chair and the Sponsor. For further details, please refer to http://www.ijcnn.org/call-for-sponsors Any questions regarding this proposal can be asked to the Sponsor Chair: Lipo Wang, Nanyang Technological University, Singapore. E-mail: elpwang at ntu.edu.sg ###################################################################### ############Paper Submission and Publication############ * Regular paper can have up to 8 pages in double-column IEEE Conference format * All papers are to be prepared using IEEE-compliant Latex or Word templates on paper of U.S. letter size. * All submitted papers will be checked for plagiarism through the IEEE CrossCheck system. * Papers with significant overlap with the authors own papers or other papers will be rejected without review. ######################################################## ##################Topics and Areas of Interest################## This conference solicits papers addressing original works in topics and areas of interest including, but are not limited to: NEURAL NETWORK MODELS * Feedforward neural networks * Recurrent neural networks * Self-organizing maps * Radial basis function networks * Attractor neural networks and associative memory * Modular networks * Fuzzy neural networks * Spiking neural networks * Reservoir networks (echo-state networks, liquid-state machines, etc.) * Large-scale neural networks * Other topics in artificial neural networks MACHINE LEARNING * Supervised learning * Unsupervised learning and clustering, (including PCA, and ICA) * Reinforcement learning * Probabilistic and information-theoretic methods * Support vector machines and kernel methods * EM algorithms * Mixture models, ensemble learning, and other meta-learning or committee algorithms * Bayesian, belief, causal, and semantic networks * Statistical and pattern recognition algorithms * Visualization of data * Feature selection, extraction, and aggregation * Evolutionary learning * Hybrid learning methods * Computational power of neural networks * Deep learning * Other topics in machine learning NEURODYNAMICS * Dynamical models of spiking neurons * Synchronization and temporal correlation in neural networks * Dynamics of neural systems * Chaotic neural networks * Dynamics of analog networks * Neural oscillators and oscillator networks * Dynamics of attractor networks * Other topics in neurodynamics COMPUTATIONAL NEUROSCIENCE * Connectomics * Models of large-scale networks in the nervous system * Models of neurons and local circuits * Models of synaptic learning and synaptic dynamics * Models of neuromodulation * Brain imaging * Analysis of neurophysiological and neuroanatomical data * Cognitive neuroscience * Models of neural development * Models of neurochemical processes * Neuroinformatics * Other topics in computational neuroscience NEURAL MODELS OF PERCEPTION, COGNITION AND ACTION * Neurocognitive networks * Cognitive architectures * Models of conditioning, reward and behavior * Cognitive models of decision-making * Embodied cognition * Cognitive agents * Multi-agent models of group cognition * Developmental and evolutionary models of cognition * Visual system * Auditory system * Olfactory system * Other sensory systems * Attention * Learning and memory * Spatial cognition, representation and navigation * Semantic cognition and language * Neural models of symbolic processing * Reasoning and problem-solving * Working memory and cognitive control * Emotion and motivation * Motor control and action * Dynamical models of coordination and behavior * Consciousness and awareness * Models of sleep and diurnal rhythms * Mental disorders * Other topics in neural models of perception, cognition and action NEUROENGINEERING * Brain-machine interfaces * Neural prostheses * Neuromorphic hardware * Embedded neural systems * Other topics in neuroengineering BIO-INSPIRED AND BIOMORPHIC SYSTEMS * Brain-inspired cognitive architectures * Embodied robotics * Evolutionary robotics * Developmental robotics * Computational models of development * Collective intelligence * Swarms * Autonomous complex systems * Self-configuring systems * Self-healing systems * Self-aware systems * Emotional computation * Artificial life * Other topics in bio-inspired and biomorphic systems APPLICATIONS * Bioinformatics * Biomedical engineering * Data analysis and pattern recognition * Speech recognition and speech production * Robotics * Neurocontrol * Approximate dynamic programming, adaptive critics, and Markov decision processes * Neural network approaches to optimization * Signal processing, image processing, and multi-media * Temporal data analysis, prediction, and forecasting; time series analysis * Communications and computer networks * Data mining and knowledge discovery * Power system applications * Financial engineering applications * Applications in multi-agent systems and social computing * Manufacturing and industrial applications * Expert systems * Clinical applications * Big data applications * Smart grid applications * Other applications CROSS-DISCIPLINARY TOPICS * Hybrid intelligent systems * Swarm intelligence * Sensor networks * Quantum computation * Computational biology * Molecular and DNA computation * Computation in tissues and cells * Artificial immune systems * Other cross-disciplinary topics ################################################################ ##########################Organizing Committee########################## General Chair * Yoonsuck Choe, Texas A and M University, USA Program Chair * Christina Jayne, Robert Gordon University, UK Technical Co-Chairs * Irwin King, The Chinese University of Hong Kong, China * Barbara Hammer, University of Bielefeld, Germany Plenary Chair * Cesare Alippi, Politecnico di Milano, Italy Special Session Co-Chairs * Derong Liu, University of Chicago, USA * Tatiana Tambouriatzis, University of Piraeus, Greece Tutorial Chair * Asim Roy, Arizona State University, USA Workshop Chair * Lazaros Iliadis, Democritus University of Thrace, Greece Poster Session Chair * Richard Duro, Universidad Coruna, Spain Competition Chair * Juyang (John) Weng, Michigan State University, USA Panels Chair * Robert Kozma, University of Memphis, USA Awards Chair * Nikola Kasabov, Auckland University of Technology, Australia Web Reviews Chair * Tomasz Cholewo, Lexmark International Inc., USA Sponsors & Exhibits Chair * Lipo Wang, Nanyang Technological University, Singapore Publication Chair * Bill Howell, Natural Resources Canada (retired), Canada International Liaison * Teresa Ludermir, Universidade Federal de Pernambuco, Brazil European Liaison * Danilo P. Mandic, Imperial College, UK Asia-Pacific Liaison * Minho Lee, Kyungpook National University, Korea Neuroscience Liaison * P?ter ?rdi, Kalamazoo College, USA Robotics Liaison * Pierre-Yves Oudeyer, INRIA, France Industry Liaison * Sven F. Crone, Lancaster University, UK Publicity Co-Chairs * Giacomo Boracchi, Politecnico di Milano, Italy * Simone Scardapane, Sapienza University, Italy * Teck-Hou Teng, Singapore Management University, Singapore Local Arrangements Co-Chairs * Frank W. Moore, University of Alaska, USA * Kenrick Mock, University of Alaska, USA Registration Chair * Jaerock Kwon, Kettering University, USA Webmaster * Jaewook Yoo, Texas A & M University, USA ####################################################################### ##################Sponsoring Organizations################## * INNS - International Neural Network Society * IEEE - Computational Intelligence Society ############################################################ -------------- next part -------------- An HTML attachment was scrubbed... URL: From Miel.VanderSande at UGent.be Tue Sep 6 03:40:09 2016 From: Miel.VanderSande at UGent.be (Miel Vander Sande) Date: Tue, 6 Sep 2016 07:40:09 +0000 Subject: Connectionists: [CfP] ISWC2016: Call for Lightning Talks Message-ID: <8F391731-13B6-46D6-B716-D1B739EC789E@ugent.be> *** Call for Lightning Talks *** 15th International Semantic Web Conference (ISWC 2016) Kobe, Japan, October 17 -21, 2016 Website: http://iswc2016.semanticweb.org Facebook: https://www.facebook.com/groups/113652365383847 Twitter: https://twitter.com/ISWC2016 ============================= This session provides an open forum for participants to present a topic of their choosing (late breaking research, a position statement, an announcement of some new software or dataset or maybe a reaction to a presentation). Each presenter is limited to one slide and two minutes time. Limited presentation slots will be awarded on a first-come-first-served basis, so early submission is advised! Presenters must submit their slide in pdf format to the following address: iswc2016lightningtalks at gmail.com Please also indicate the title of your talk as well as the name and affiliation of the authors. Submissions due: *October 20th 23:59*. Check the call here: http://iswc2016.semanticweb.org/pages/calls/lightning-talks.html Lightning Talks Chair * Miriam Fernandez - The Open University, United Kingdom ( miriam.fernandez at open.ac.uk ) -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 842 bytes Desc: Message signed with OpenPGP using GPGMail URL: From rothkopf at fias.uni-frankfurt.de Tue Sep 6 05:12:13 2016 From: rothkopf at fias.uni-frankfurt.de (Constantin Rothkopf) Date: Tue, 6 Sep 2016 11:12:13 +0200 Subject: Connectionists: PhD position in computational and experimental approaches to visuomotor behavior Message-ID: <00c46313-e10c-c594-cf99-07289dbddaba@fias.uni-frankfurt.de> Applications are invited for a PhD student position in the lab of Constantin Rothkopf at the Technical University Darmstadt. The lab focuses on experimental and computational approaches to further the understanding of naturalistic, sequential visuomotor behavior in humans. Current topics include: - statistics of visuomotor behavior in naturalistic tasks, - image statistics during visuomotor behavior in-the-wild, - optimal control models of visuomotor behavior, - inverse-optimal-control applied to human visuomotor behavior, - eye-movements in naturalistic tasks. For further information please visit the websites: http://www.pip.tu-darmstadt.de/ http://www.fias.uni-frankfurt.de/~rothkopf/ Applicants need to have a Master's degree in cognitive science, computer science, psychology or related fields. In addition to a general interest in cognitive science, experimental psychology, computational science, and interdisciplinary research, the ideal candidate has a background in eye-tracking or virtual reality technology. Experience with programming (e.g. Matlab, Python, C++) is inevitable. Analytical aptitude as well as awareness of experimental literature is expected. We offer a supportive and multidisciplinary environment driven by scientific curiosity, lab facilities for measuring extended visuomotor behavior in-the-wild and in VR, international collaborations. Informal inquiries may be made to Constantin Rothkopf at rothkopf at psychologie.tu-darmstadt.de. In your application please include a brief (max. 2 pages) cover letter explaining your research interests, what you are looking for in a PhD, why you would like to study in the lab, your longer term career goals, and contact information for 2-3 references. Applications may be submitted to the Dean of the Department of Human Sciences of the Technical University Darmstadt, Alexanderstra?e 10, 64283 Darmstadt, in electronic form as a single pdf document via e-mail at: dekanat at humanw.tu-darmstadt.de More details (ref.-no. 338) are available at: https://www.intern.tu-darmstadt.de/dez_vii/stellen/stellen_details_202688.de.jsp -- Prof. Constantin A. Rothkopf, PhD phone: +49 6151 16-23367 http://www.pip.tu-darmstadt.de/ mailto:rothkopf at psychologie.tu-darmstadt.de From sen.cheng at rub.de Tue Sep 6 10:25:28 2016 From: sen.cheng at rub.de (Sen Cheng) Date: Tue, 6 Sep 2016 16:25:28 +0200 Subject: Connectionists: CFP: What is episodic memory? Message-ID: CALL FOR PAPERS What is episodic memory? Perspectives from Philosophy, Psychology and Neuroscience Mercator Research Group ? Structure of Memory Closing Symposium ------------------------------------------------------------------------ Bochum, November 29-30, 2016 Organization: Sen Cheng, Magdalena Sauvage, Markus Werning http://www.rub.de/mrg/memory/events/symposium.html ----------------------------------------------------------------------- Episodic memory is a critical part of the human mind and has frequently been claimed to be a cornerstone of personal identity. Yet, there is no universal consensus on what constitutes episodic memory. In many textbooks, the notion of episodic memory is introduced in a hierarchical taxonomical manner: First, a distinction between declarative and non-declarative memory (Squire & Zola-Morgan, 1988) is made. In a second step, two subordinate categories are introduced within the superordinate category of declarative memory, namely, semantic memory and episodic memory. Tulving (1972) introduced the what-where-when criterion to define the content of episodic memory. However, this criterion was found to be insufficient to distinguish semantic from episodic memories. As a result, Tulving (1985) later revised his definition of episodic memory and based it on autonoetic consciousness, the conscious reliving of a past experience. Suddendorf and Corballis (1997) went even further and suggested that episodic memory is linked to mental time travel into the past and facilitates mental time travel into the future. More recently, Cheng and Werning (2016) have focused on whether episodic memory is a natural kind and what implications this has for what episodic memory is best taken to be. The symposium tries to formulate new answers on the nature of episodic memory and addresses an interdisciplinary audience of philosophers, psychologists, and empirical as well as theoretical neuroscientists. Abstracts for talks and posters are welcome. INVITED SPEAKERS: - Sven Bernecker (U Cologne) - Ekrem Dere (MPI G?ttingen) - Katharina Henke (U Bern) - Christoph Hoerl (U Warwick) - Martijn Meeter (U Amsterdam) - Kirk Michaelian (U Otago) - Edmund Rolls (U Oxford) SUBMISSION: We invite authors to submit an anonymous one-page abstract by September 30, 2016 for a talk of 17 minutes (plus 3 minutes discussion). Submissions should be made via Easychair (details at http://www.rub.de/mrg/memory/events/symposium.html). TIME & PLACE: - deadline for one-page abstracts: September 30, 2016 - notification of acceptance: October 15, 2016 - conference dates: November 29 ? 30, 2016 - venue: Ruhr University Bochum, Germany -------------- next part -------------- An HTML attachment was scrubbed... URL: From ksmith at kth.se Tue Sep 6 11:16:33 2016 From: ksmith at kth.se (Kevin Smith) Date: Tue, 6 Sep 2016 17:16:33 +0200 Subject: Connectionists: [Job] Postdoc in deep learning for histopathological image analysis at KTH and SciLifeLab in Stockholm Message-ID: Job description: This position is part of a collaboration with pathologists from the Karolinska University Hospital. The main task will be to develop novel computational methods to analyze histopathological images of breast cancer tissue from the Karolinska tissue biobank. The successful applicant will develop methods to recognize and categorize morphological growth patterns of cancer cells within histopathological images. The goal is to find correlations between these growth patterns and patient outcome. If successful, these patterns may serve as powerful predictors for patient treatment. One of the main responsibilities of the position will be to develop convolutional neural networks (CNN) and statistical methods capable of recognizing and categorizing morphological patterns from tissue image data. Qualifications Candidates must have a PhD in computer science, computational science, or a related field and proven experiences in implementing, analyzing, and optimizing scientific applications for image analysis. Good knowledge of standard computer vision techniques and a deep learning framework (Theano, Tensorflow, Caffe, Torch) is required. Programming knowledge of a related scientific computing language (R, Matlab, Python, Lua, C++) is also required. Experience with parallel programming environments and cloud computing is a plus. Previous experience working with medical or biological images is also desirable. Application: Log into KTH's recruitment system in order to apply to this position ( https://www.kth.se/en/om/work-at-kth/lediga-jobb/what:job/ jobID:112608/where:4/). You are responsible to ensure that your application is complete according to the ad. Applications shall include the following documents: Cover letter Curriculum vitae Transcripts from university References Representative publications (optional) Please observe that all material needs to be in English. Your complete application must be received at KTH no later than 01.Oct.2016 11:59 PM CET About KTH and Science for Life Laboratory: KTH Royal Institute of Technology in Stockholm (www.kth.se) is one of Europe?s leading technical and engineering universities, as well as a key centre of intellectual talent and innovation. We are Sweden?s largest technical research and learning institution and home to students, researchers and faculty from around the world. Our research and education covers a wide area including natural sciences and all branches of engineering, as well as in architecture, industrial management, urban planning, history and philosophy. The position will be formally placed with the department for Computational Science and Technology (CST) at KTH ( https://www.kth.se/en/csc/forskning/cst), but work will be carried out at the Science for Life Laboratory (www.scilifelab.se). The Science for Life Laboratory (SciLifeLab) is a collaboration between four universities in Stockholm and Uppsala: Karolinska Institutet, KTH, Stockholm University and Uppsala University. It combines advanced technology with broad knowledge in translational medicine and molecular life sciences. Since 2013, SciLifeLab has a mission from the Swedish government to run infrastructure to support researchers nationally and to be an internationally leading center for large-scale analyses in molecular life sciences targeting research in health and environment. Other details: Type of employment: Temporary position longer than 6 months Contract type: Full time First day of employment: According to agreement Salary: Monthly salary Number of positions: 1 Working hours: 100% City: Stockholm County: Stockholms l?n Country: Sweden Reference number: D-2016-0596 Contact: Maria Widlund, HR Manager, mwidlund at csc.kth.se, +46 8 790 97 54 Kevin Smith, Assistant Professor, ksmith at kth.se, +46 8 524 812 46 -------------- next part -------------- An HTML attachment was scrubbed... URL: From thomas.wennekers at plymouth.ac.uk Tue Sep 6 14:53:33 2016 From: thomas.wennekers at plymouth.ac.uk (Thomas Wennekers) Date: Tue, 6 Sep 2016 19:53:33 +0100 Subject: Connectionists: MSBDy -- Workshop on Brain dynamics on multiple scales, Dresden 19-23 June 2017 Message-ID: <201609061953.33459.thomas.wennekers@plymouth.ac.uk> CALL FOR PARTICIPATION Workshop on Brain dynamics on multiple scales ? paradigms, their relations, and integrated approaches MSBDy 2017, 19-23 June, Dresden, Germany WORKSHOP WEBSITE: http://www.pks.mpg.de/msbdy17/ APPLICATION DEADLINE: 28 Feb 2017 Summary Previous research paradigms in the brain sciences have often focused on one spatial or temporal scale only, for instance defined by the experimental technique of choice or a specific set of cognitive phenomena. This workshop aims at exploring paradigms and concepts such as complexity, information, or dynamical systems that provide bridges, links, relations, or connections between two, three or more "elements of brain science" and link them to recent developments in mathematics, physics, and neurobiological experimental techniques. Workshop sessions 1. The Brain as a complex system ? complex networks, dynamics and criticality, ?understanding the interplay between structure, dynamics, and function. 2. Information Processing and Coding ?: what is the current state in using information?-theoretic principles like infomax, complexity measures, evidence, or surprise ?as tools to understand the brain? 3. Brain Oscillations, Waves and Synchronisation ?: what are their functional roles? 4. Multiple scales and levels: ? what are proper "building blocks" of the brain or a brain theory? 5. Large? scale cognitive brain systems: ? what are the best approaches to an understanding of high? level cognitive and brain functions including consciousness? DETAILS The workshop takes place on the premises of the Max Planck Institute for the Physics of Complex systems in Dresden. Thanks to a generous grant by the MPIPKS participation in the event is free, with the exception of a modest fee of Euro 120 for social dinners, excursions and coffee breaks. The grant otherwise covers food and subsistence in the guest house of the MPIPKS for accepted participants. Posters can be hung for the duration of the meeting. To apply, please follow: http://www.pks.mpg.de/msbdy17/ IMPORTANT DATES: - Application Deadline: 28 Feb 2017 - Notification of acceptance: 31 Mar 2017 - Workshop Date: 19 Jun - 23 Jun 2017 SPEAKERS Nicolas Brunel (Univ Chicago, USA) Bruno Cessac (INRIA, Sophia Antipolis, France) Gustavo Deco (UPF Barcelona, Spain) Stanislas Dehaene (INSERM-CEA, College de France) Alain Destexhe (UNIC, CNRS, France) Markus Diesmann (J?lich Research Centre, Germany) Ole Jensen (Donders Institute, Nijmegen, NL) Mark A Kramer (Boston University, USA) Anders Lansner (Stockholm University and KTH, Sweden) Christoph Michel (Universit? de Gen?ve, Switzerland) Juergen Jost (MPI for Mathematics in the Sciences, Leipzig, Germany) Guenther Palm (University of Ulm, Germany) Simon Schulz (Imperial College London, UK) Murray Shanahan (Imperial College London, UK) Elad Schneidman (Weizmann Institute of Science, Rehovot, Israel) Marc Timme (MPI f?r Dynamik und Selbstorganisation, G?ttingen, Germany) Giulio Tononi (University of Wisconsin-Madison, USA, to be confirmed) Vlad Vyazovskiy (University of Oxford, UK) ORGANIZERS Peter Achermann (University of Zurich, Switzerland) Eckehard Olbrich (MPI for Mathematics in the Sciences, Leipzig, Germany) Thomas Wennekers (University of Plymouth, UK) ACKNOWLEDGMENT: This workshop is supported by the Max Planck Institute for the Physics of Complex Systems. ________________________________ [http://www.plymouth.ac.uk/images/email_footer.gif] This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form. -------------- next part -------------- An HTML attachment was scrubbed... URL: From julian.mcauley at gmail.com Tue Sep 6 13:37:35 2016 From: julian.mcauley at gmail.com (Julian McAuley) Date: Tue, 6 Sep 2016 10:37:35 -0700 Subject: Connectionists: CFP: SoCal Machine Learning Symposium: Friday Nov 18 @ Caltech Message-ID: We are pleased to invite you to the Southern California Machine Learning Symposium, on Friday November 18 at Caltech! http://dolcit.cms.caltech.edu/scmls/ The SoCal ML Symposium brings together students and faculty to promote machine learning in the Southern California region. The workshop serves as a forum for researchers from a variety of fields working on machine learning to share and discuss their latest findings. Topics to be covered at the symposium include, but are not limited to: + Machine learning with graphs, social networks, and structured data. + Active learning, reinforcement learning, crowdsourcing. + Learning with images and natural language. + Learning with high-dimensional data. + Neural networks, deep learning, and graphical models. + Learning dynamic and streaming data. + Applications to interesting new domains. + Addressing each of these issues at scale. The majority of the workshop will be focused on student contributions, in the form of contributed talks and posters. We invite submissions in the form of 1-2 page extended absracts, to be presented as posters and oral presentations at the symposium. Submissions may be made on our easychair page: https://easychair.org/conferences/?conf=scmls16 A $500 first-prize and a $250 runner-up prize, sponsored by Google Research, will be awarded for the best student presentations. Timeline: Oct 4: Abstract submission Oct 14: Notification Nov 11: Registration deadline Nov 18: Symposium For more details, including submission and registration instructions, visit our symposium webpage: http://dolcit.cms.caltech.edu/scmls/ and please help distribute our flyer: http://dolcit.cms.caltech.edu/scmls/scmls.pdf Hope to see you there! Yisong Yue, Julian McAuley -------------- next part -------------- An HTML attachment was scrubbed... URL: From mvzaanen at uvt.nl Tue Sep 6 15:07:02 2016 From: mvzaanen at uvt.nl (Menno van Zaanen) Date: Tue, 6 Sep 2016 21:07:02 +0200 Subject: Connectionists: Call for Participation ICGI 2016 Message-ID: <20160906190702.GJ18809@pinball.uvt.nl> Apologies for cross-posting ================================ CALL FOR PARTICIPATION ICGI 2016 5-7 October 2016 ================================ icgi2016.tudelft.nl SCOPE AND LOCATION ICGI 2016 is the 13th edition of the International Conference on Grammatical Inference series, held every two years. The conference will be held at Delft University of Technology; in Delft, the Netherlands, from October 5-7, 2016. Delft is one of the most beautiful and historic cities in the world, situated in the central (western) part of the Netherlands. The city is directly accessible by train from Schiphol airport (a large international airport near Amsterdam). The conference will be hosted in the "Mekelzaal", a beautiful historic venue in a small science museum at the university campus. AREAS OF INTEREST The conference is on grammatical inference. Key interests are machine-learning methods applied to discrete combinatorial structures such as strings, trees, or graphs, and algorithms for learning symbolic models such as grammars, automata, Markov models, or pattern languages. The conference seeks to provide a forum for presentation and discussion of original research papers on all aspects of grammatical inference. A full program can be found on the website: icgi2016.tudelft.nl INVITED SPEAKERS - Hendrik Blockeel - Valentin Spitkovsky - TBA CONFERENCE FORMAT The conference will include plenary, work in progress presentations, and invited talks. REGISTRATION http://icgi2016.tudelft.nl/#register We are looking forward to seeing you in Delft in October. Organizing committee: Rick Smetsers Sicco Verwer Menno van Zaanen From dbalduzzi at gmail.com Tue Sep 6 16:53:20 2016 From: dbalduzzi at gmail.com (David Balduzzi) Date: Wed, 7 Sep 2016 08:53:20 +1200 Subject: Connectionists: Postdoc position: Deep Learning applied to Compressing Audio Signals Message-ID: *Postdoc position: Deep Learning applied to Compressing Audio Signals* Applications are invited for a position as a postdoctoral researcher working with Prof Bastiaan Kleijn and Dr David Balduzzi at Victoria University Wellington. The project, funded by Google, is to develop new multi-channel audio encoding methods using deep learning (specifically, recurrent neural networks) in collaboration with researchers at UC Santa Barbara. The position is for one year, potentially renewable. Victoria University is located in Wellington, a compact, cosmopolitan city of 400,000 people. The campus is a short walk from downtown and the waterfront. QUALIFICATIONS: Applicants should have a Ph.D. in Computer Science, Electrical Engineering or related fields. Experience in machine learning and/or signal processing along with a strong research track record is essential. For further information please contact Bastiaan Kleijn at bastiaan.kleijn at ecs.vuw.ac.nz ( http://ecs.victoria.ac.nz/Main/BastiaanKleijn) or David Balduzzi at david.balduzzi at vuw.ac.nz ( https://sites.google.com/site/dbalduzzi/). TO APPLY: Applications should include - a curriculum vitae with list of publications - names and email addresses of two references - a short (1-2 page) summary of past research and relevant qualifications - a personal Web page, if available The position is to start as early as December 2016 or at an agreed later date. Applications will be reviewed when they are received. -------------- next part -------------- An HTML attachment was scrubbed... URL: From simone.scardapane at uniroma1.it Wed Sep 7 04:35:53 2016 From: simone.scardapane at uniroma1.it (Simone Scardapane) Date: Wed, 7 Sep 2016 10:35:53 +0200 Subject: Connectionists: 2nd CfP: Advances in Biologically Inspired Reservoir Computing (Cognitive Computation, IF 1.933) Message-ID: [Apologies if you receive multiple copies of this CFP] -------------------------------------------------------------------------- Call for papers: Cognitive Computation Special Issue ADVANCES IN BIOLOGICALLY INSPIRED RESERVOIR COMPUTING Submission deadline: 31th September, 2016 [extensions are possible] http://ispac.diet.uniroma1.it/cognitive-computation-special-issue/ -------------------------------------------------------------------------- Scope and motivations -------------------------------------------------------------------------- Reservoir computing is a family of techniques for training and analyzing recurrent neural networks, wherein the recurrent portion of the network is assigned before the training process, typically via stochastic assignment of its weights. The non-linear reservoir acts as a high-dimensional kernel space, which generates complex dynamics characterized by sharp transitions between ordered and chaotic regimes. The behavior of this model emulates the functioning of many biological (complex) systems, among which the brain. Driven by the conceptual simplicity of the reservoir and by links with neuroscience, computer science and systems? theory, researchers have achieved remarkable breakthroughs, both in theory and in practice. These include dynamical models for explaining the working behavior of reservoirs, unsupervised strategies for the adaptation of the network, and the design of unconventional computing architectures for its execution. The recent upsurge of interest in fully adaptable recurrent networks, far from shifting the attention from the field, has brought renewed interest in reservoir computing models. In our era of extreme computational power and sophisticated problems, it is essential to understand the limits and the potentialities of simple (both deterministic and random) collections of processing units. For this reason, many fundamental questions remain open, including the design of optimal task-dependent reservoirs in a stable fashion, novel investigations on the memory and power capabilities of reservoir devices, and their applicability in an ever-increasing range of domains. In light of this, the aim of this special issue is to provide a unified platform for bringing forth and advancing the state-of-the-art in reservoir computing approaches. Researchers are invited to submit innovative works on the theory and implementation of this family of techniques, in order to provide an up-to-date overview on the field. Topics -------------------------------------------------------------------------- The topics of interest to be covered by this Special Issue include, but are not limited to: * Theoretical analyses on the computational power of reservoir computing. * Deep reservoir models. * Techniques for the automatic adaptation of the reservoir and the readout. * Supervised, unsupervised and semi-supervised training criteria. * Non-conventional substrates for the implementations of reservoirs. * Parallel and distributed algorithms for reservoir computing. * Comparisons between reservoir computing and standard (deep) neural networks. * Reservoir computing for reinforcement learning problems. * Fundamental links between reservoir computing and neuroscientific findings. * Investigation of reservoir dynamic in a phase space of reduced dimensionality. Applicative papers in all areas (including robotics, industrial control, etc.) are welcome, as well as outstanding surveys on specific aspects of the field. Paper submission -------------------------------------------------------------------------- All papers should follow the manuscript preparation requirements for the Springer Cognitive Computation submissions, see http://www.springer.com/biomed/neuroscience/journal/12559. The authors are requested to submit their manuscripts via the online submission manuscript system, available at http://www.editorialmanager.com/cogn/. During submission, authors should explicitly choose the title of the special issue in the Subject line. Should there be any further enquiries, please feel free to address them to the lead guest editor: Simone Scardapane (simone.scardapane at uniroma1.it) Important dates -------------------------------------------------------------------------- * Paper submission deadline: September 31, 2016 * First notification of acceptance: November 30, 2016 * Submission of revised papers: January 15, 2017 * Final notification to the authors: January 31, 2017 * Submission of final/camera-ready papers: February 15, 2017 * Publication of special issue: TBD Organizers -------------------------------------------------------------------------- * Simone Scardapane (Sapienza University of Rome) - simone.scardapane at uniroma1.it * John B. Butcher (Keele University) - j.b.butcher at keele.ac.uk * Filippo M. Bianchi (UiT, Troms?) - filippo.m.bianchi at uit.no * Zeeshan K. Malik (University of Stirling) - zkm at cs.stir.ac.uk From Nicolas.Rougier at inria.fr Wed Sep 7 07:04:41 2016 From: Nicolas.Rougier at inria.fr (Nicolas P. Rougier) Date: Wed, 7 Sep 2016 12:04:41 +0100 Subject: Connectionists: New replication in ReScience Message-ID: <6F6D0089-2068-4F4A-8FBE-BD5871EF8BC8@inria.fr> Dear all, It's my great pleasure to announce that the following article: * Multiple dynamical modes of thalamic relay neurons: rhythmic bursting and intermittent phase-locking Wang XJ, Neuroscience, 1994 59(1):21-31. has been successfully replicated in ReScience (using Python): * [Re] Multiple dynamical modes of thalamic relay neurons: rhythmic bursting and intermittent phase-locking Georgios Detorakis, ReScience, volume 2, issue 1, 2016. You can read more at http://rescience.github.io/read. Article and code are available from https://github.com/ReScience-Archives/Detorakis-2016 Nicolas Rougier From florian at coneural.org Wed Sep 7 07:33:21 2016 From: florian at coneural.org (R. Valentin Florian) Date: Wed, 7 Sep 2016 14:33:21 +0300 Subject: Connectionists: Open position: Postdoctoral research associate in machine learning (representation learning, curiosity-based learning, Bayesian theories of deep learning, reinforcement learning) Message-ID: We are looking for a postdoctoral research associate who will work on machine learning models that allow an artificial agent to develop structured, hierarchical representations of its environment, by interacting with this environment. These models will integrate and develop upon curiosity-based learning, Bayesian theories of deep learning, and reinforcement learning, and will be tested in simulations of physical environments (e.g., a robotic simulator) as well as in purely computational environments. The position is available within an EU-funded project that aims to develop artificial intelligent systems able to automatically generate software. After 3-4 years, the project is expected to spin off a startup, and the candidate will have the opportunity to be part of this startup. The position is offered for an initial period of 3 years, at the Romanian Institute of Science and Technology (RIST) in Cluj, Romania. The position will be part of the Deep Computational Intelligence group, one of two newly-formed groups in machine learning where about 20 new postdoctoral research associates and research software developers will be hired in the next year. We are looking for self-motivated, independent, creative scientists, with strong analytical and computational modeling skills. Candidates should have a PhD, preferably in machine learning, statistical learning, representation learning, robotics or related fields. Candidates must have a strong publication record. To apply, send to dci at rist.ro your CV (indicating your 3 most representative publications), a letter of intent in which you motivate your interest in this position and explain why your skills, knowledge and experience makes you a suitable candidate for the position, as well as the names and contact details of at least two references. The contract will start as soon as the position is filled, after September / October 2016. Net salary is from 1,700 to 2,000 euros per month, while the cost of living in Cluj is significantly lower than in Western Europe or the USA. The working language is English. The project, called ?Automated software development through abstraction in deep, distributed computational models? (AutoWare), is funded by European structural funds and is led by Dr. Bipin Indurkhya (project director) and Dr. R?zvan Valentin Florian (associate project director). Cluj hosts Romania?s largest university and boasts a strong, rapidly developing IT industry. Cluj is the main city of Transylvania, which has been named by Lonely Planet as the top region to visit in its 2016 Best in Travel ranking. More information: http://rist.ro/en/details/news/postdoctoral-research-associate-in-machine-learning.html From bremeseiro at udc.es Wed Sep 7 07:23:28 2016 From: bremeseiro at udc.es (Beatriz Remeseiro =?utf-8?Q?L=C3=B3pez?=) Date: Wed, 7 Sep 2016 13:23:28 +0200 (CEST) Subject: Connectionists: 2nd CFP for the special issue of Computational and Mathematical Methods in Medicine Message-ID: <1689365807.24768539.1473247408200.JavaMail.zimbra@udc.es> ================================================== Apologies if you receive this more than once ================================================== CALL FOR PAPERS Machine learning in Bioinformatics and Biomedical Engineering Special issue in Computational and Mathematical Methods in Medicine (open access, JCR-indexed) http://www.hindawi.com/journals/cmmm/si/618503/cfp/ Machine learning is an Artificial Intelligence branch that has been well applied and recognized as an effective tool to handle a wide range of real situations. In the last few years, we have witnessed to the explosion of Big Data, which has enabled researchers to store data for analysis in an unprecedented way. This explosion in data available for analysis is as evident in healthcare as anywhere else. In particular, this special issue is focused on the areas of bioinformatics and biomedical engineering. These are two of the fastest developing research fields in the last few decades, since the biological data used to provide information is rapidly generated, and is mandatory to be able to extract information and knowledge from them, as technological innovation in these fields are to be probably one of the most important developments in the next coming years. Many research problems in the field, such as DNA microarray classification or the identification of candidate genes and nucleotides (SNPs) are computationally hard. Machine learning techniques have become an indispensable tool to discover new biomedical and bioinformatics insights, enabling unprecedented advances and yet embracing new emerging challenges with the advent of Big Data. Visualization will be undoubtedly a challenge during this post-genomic era, as researchers are trying to confront the difficulty of exploring and analyzing a huge amount of biological data as well as making it possible the analysis and data mining by aiding recognition of patterns and trends. In this special issue, we invite investigators to contribute with their recent advances addressing machine learning methods related to, or with application in, Bioinformatics and Biomedical Engineering, as well as review articles that will stimulate the continuing efforts to understand the problems usually encountered in this field. ========================= LIST OF TOPICS ========================= Topics of interest include, but are not limited to: Clinical interpretation, diagnosis and prediction Feature selection and extraction Pattern recognition and classification Dealing with unbalanced, non-static and/or cost-sensitive data Image analysis and visualization Microarray and SNPs analysis Ontologies, taxonomies and semantic web Intelligent sensorization Data mining for knowledge discovery Security, privacy and data integrity ========================= IMPORTANT DATES ========================= Manuscript due: September 23, 2016 First round of reviews: December 16, 2016 Publication date: February 10, 2017 ========================= SUBMISSION ========================= Authors can submit their manuscripts via the Manuscript Tracking System at http://mts.hindawi.com/submit/journals/cmmm/raml/ ========================= ORGANIZATION ========================= Guest Editors Ver?nica Bol?n-Canedo, Universidade da Coru?a, Spain. Beatriz Remeseiro, INESC TEC ? INESC Technology and Science, Portugal. Diego ?lvarez-Est?vez, Medisch Centrum Haaglanden and Bronovo-Nebo, The Netherlands. Amparo Alonso-Betanzos, Universidade da Coru?a, Spain. From urut at caltech.edu Wed Sep 7 14:56:17 2016 From: urut at caltech.edu (Ueli Rutishauser) Date: Wed, 7 Sep 2016 11:56:17 -0700 Subject: Connectionists: Postdoctoral position in primate neurophysiology (University of Tucson) Message-ID: Please see below job ad, which I am posting on behalf of a colleague. *=====* *Postdoctoral position in primate neurophysiology.* *University of Arizona, College and Medicine,* *Department of Physiology, Tucson. * We are inviting application of postdoctoral trainees interested in working on the neural basis of natural social behaviors in non-human primates. The applicant will have access to state-of-the art equipment, facilities, and will work in a team with established expertise in behavioral neurophysiology of the amygdala. Candidates should have a PhD in neuroscience, psychology, biomedical engineering, or related field. Strong computational skill and communication skills are required. Experience in neurophysiology is preferred. The position is available immediately, with a competitive/negotiable salary commensurate with prior experience. The University of Arizona is an equal opportunity employer and women and minorities are encouraged to apply. Please send a CV, statement of research accomplishments and interests, copies of 2-3 representative publications and contact information for 2-3 reference letters to Katalin Gothard at kgothard at email.arizona.edu . Informal inquiries are welcome. Katalin M. Gothard, M.D., Ph.D. Professor of Physiology and Neuroscience The University of Arizona College of Medicine Department of Physiology webpage: http://www.gothardlab.com/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From kau.subbu at gmail.com Wed Sep 7 16:35:52 2016 From: kau.subbu at gmail.com (Kaushik Subramanian) Date: Wed, 7 Sep 2016 13:35:52 -0700 Subject: Connectionists: CfP: Future of Interactive Learning Machines Workshop @ NIPS 2016 Message-ID: Hi Everyone, We are organizing a workshop on the Future of Interactive Learning Machines at NIPS 2016 in Barcelona, Spain in December this year. In recent years there has been increasing interest in the idea of machines interacting with humans to learn from and/or about them. Several researchers, with years of experience in the field, have come together to organize this workshop. Please find the call for papers below. We look forward to your submissions. ====================================================================== NIPS 2016 Workshop: Future of Interactive Learning Machines Barcelona, Spain http://www.filmnips.com/ ====================================================================== Important Dates ------------------------------------------------------------ --------------------------- Paper submission deadline: *Oct 14th 2016* Notification of acceptance: Oct 29th 2016 Camera-ready submission deadline: Nov 11th 2016 FILM workshop at NIPS 2016 in Barcelona, Spain: Dec 9th or 10th 2016 Overview ------------------------------------------------------------ --------------------------- Interactive machine learning (IML) explores how intelligent agents solve a task together, often focusing on adaptable collaboration over the course of sequential decision making tasks. Past research in the field of IML has investigated how autonomous agents can learn to solve problems more effectively by making use of interactions with humans. Designing and engineering fully autonomous agents is a difficult and sometimes intractable challenge. As such, there is a compelling need for IML algorithms that enable artificial and human agents to collaborate and solve independent or shared goals. The range of real-world examples of IML spans from web applications such as search engines, recommendation systems and social media personalization, to dialog systems and embodied systems such as industrial robots and household robotic assistants, and to medical robotics (e.g. bionic limbs, assistive devices, and exoskeletons). As intelligent systems become more common in industry and in everyday life, the need for these systems to interact with and learn from the people around them will also increase. This workshop seeks to brings together experts in the fields of IML, reinforcement learning (RL), human-computer interaction (HCI), robotics, cognitive psychology and the social sciences to share recent advances and explore the future of IML. Some questions of particular interest for this workshop include: How can recent advancements in machine learning allow interactive learning to be deployed in current real world applications? How do we address the challenging problem of seamless communication between autonomous agents and humans? How can we improve the ability to collaborate safely and successfully across a diverse user set? We hope that this workshop will produce several outcomes: - A review of current algorithms and techniques for IML, and a focused perspective on what is lacking - A formalization of the main challenges for deploying modern interactive learning algorithms in the real world - A forum for interdisciplinary researchers to discuss open problems and challenges, present new ideas on IML and plan for future collaborations Relevant Topics ------------------------------------------------------------ --------------------------- - Human-robot interaction - Collaborative and/or shared control - Semi-supervised learning with human intervention - Learning from demonstration, interaction and/or observation - Reinforcement learning with human-in-the-loop - Active learning, Preference learning - Transfer learning (human-to-machine, machine-to-machine) - Natural language processing for dialog systems - Computer vision for human interaction with autonomous systems - Transparency and feedback in machine learning - Computational models of human teaching - Intelligent personal assistants and dialog systems - Adaptive user interfaces - Brain-computer interfaces (e.g. human-semi-autonomous system interfaces) - Intelligent medical robots (e.g. smart wheelchairs, prosthetics, exoskeletons) We seek broad participation from researchers in the fields of artificial intelligence, machine learning, human-computer interaction, cognitive science, robotics, intelligent interface design, adaptive systems and related fields. Submission Details ------------------------------------------------------------ --------------------------- We encourage submissions covering new ideas in interactive learning, reports on research in progress as well as discussions of open problems and challenges facing interactive machine learning. We are particularly interested in research regarding the practical application of interactive learning systems (for robotics, virtual agents, online education, dialog systems, health care, security, transportation, etc.), and the ability of these systems to handle the complexity of real world problems. We also encourage submissions bringing perspectives from the fields of psychology and social science, and from human computer interaction. Authors are invited to submit long papers (8 pages for main text and 1 page for references) or short papers (2 to 4 pages for main text and 1 page for references) on research relevant to the theme of the workshop. The papers should be formatted according to NIPS formatting guidelines and submitted as a PDF document. All submissions are handled electronically through EasyChair (https://easychair.org/conferences/?conf=filmnips2016). Papers will be subject to a single-blind peer review, i.e. authors can keep their names and affiliations on their submitted papers. Papers will be evaluated based on originality, technical soundness, clarity and potential impact on the field of interactive machine learning. Accepted papers will be made publicly available on the workshop website. Accepted papers will be presented as talks and/or posters at the workshop. ------------------------------------------------------------ --------------------------- Contact: If you have any questions, comments or concerns, please contact the organizers at film.nips2016 at gmail.com. Looking forward to seeing you in Barcelona! - FILM Organizers -------------- next part -------------- An HTML attachment was scrubbed... URL: From dhallabhinav at gmail.com Wed Sep 7 23:45:50 2016 From: dhallabhinav at gmail.com (abhinav dhall) Date: Wed, 7 Sep 2016 20:45:50 -0700 Subject: Connectionists: CFP: IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2017) Message-ID: [Apologies for cross-postings] Call for papers ----------------------------------------------- IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2017) Location: New Delhi, India Dates: February 22-24 2017 http://ieee-biometrics.org/isba2017/ ----------------------------------------------- ISBA is a unique conference series initiated by the IEEE Biometrics Council and its third edition will be held in New Delhi, India. This conference is intended to meet the emerging need for a winter meeting, especially for the Asian participants where the introduction of large scale biometrics programs have attracted significant increase in research and development efforts. It will be a forum that brings together experts in biometrics, security, and human behavior to consider research issues and solutions that are robust, comprehensive, and broader than currently considered in each of these individual research areas. This conference serves to provide a new form for such broad areas defining human side of security and user behavior as well as social influence in the biometrics security. Topics of interest include, but are not limited to: ? Anti-Spoofing, Behavioral Biometrics, Biometric System Evaluation, Biometrics in Law Enforcement, Cybercrime ? De-identification, Detection and Tracking, Device Identification, Digital Forensics ? Human Behavior Analysis, Human Activity Understanding, Identity Management, Information Security, Person Re-identification ? Performance Evaluation, Privacy-preserving Computing, Predictive Analytics, Single and Multi-modal Biometrics ? Social Biometrics, Social and Criminal Network Inference, Surveillance Identification, Template Protection and Data Privacy ? Usability and Performance, User-centric Biometric Security Submitted papers may not be accepted or under review elsewhere. Submissions may be up to eight pages in conference format (double blind reviewing). Papers accepted and presented at ISBA 2017 will be published in conference proceedings and made available in IEEE Xplore library. Important dates Submission deadline: October 10, 2016 Decision to authors: December 10, 2016 Camera ready submission: December 20, 2016 Conference: February 22-24, 2017 General Chair Rama Chellappa (University of Maryland, USA) General Co-chairs Ajay Kumar (PolyU, Hongkong) Richa Singh (IIIT-Delhi, India) Program Co-chairs M. Ehsan Hoque (University of Rochester, USA) Nitesh Saxena (University of Alabama at Birmingham, USA) Vishal M. Patel (Rutgers University, USA) Mayank Vatsa (IIIT-Delhi, India) Publication Chair Soma Biswas (Indian Institute of Science, India) Finance Chair Angshul Majumdar (IIIT-D, India) Publicity Chair Abhinav Dhall (University of Waterloo, Canada) Industry Liaison Sameer Shah (HCL, India) http://ieee-biometrics.org/isba2017/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen at idsia.ch Thu Sep 8 09:59:57 2016 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Thu, 8 Sep 2016 15:59:57 +0200 Subject: Connectionists: NIPS 2016 Symposium: Recurrent Neural Networks and Other Machines that Learn Algorithms - Call for Posters In-Reply-To: References: Message-ID: <949C1B1C-0F71-411C-AD6D-C1D25286C407@idsia.ch> NIPS 2016 Symposium: Recurrent Neural Networks and Other Machines that Learn Algorithms Thursday, December 8, 2016, Barcelona Soon after the birth of modern computer science in the 1930s, two fundamental questions arose: 1. How can computers learn useful programs from experience, as opposed to being programmed by human programmers? 2. How to program parallel multiprocessor machines, as opposed to traditional serial architectures? Both questions found natural answers in the field of Recurrent Neural Networks (RNNs), which are brain-inspired general purpose computers that can learn parallel-sequential programs or algorithms encoded as weight matrices. The first RNNaissance NIPS workshop dates back to 2003: http://people.idsia.ch/~juergen/rnnaissance.html . Since then, a lot has happened. Some of the most successful applications in machine learning (including deep learning) are now driven by RNNs such as Long Short-Term Memory, e.g., speech recognition, video recognition, natural language processing, image captioning, time series prediction, etc. Through the world's most valuable public companies, billions of people can now access this technology through their smartphones and other devices, e.g., in the form of Google Voice or on Apple's iOS. Reinforcement-learning and evolutionary RNNs are solving complex control tasks from raw video input. Many RNN-based methods learn sequential attention strategies. At this symposium, we will review the latest developments in all of these fields, and focus not only on RNNs, but also on learning machines in which RNNs interact with external memory such as neural Turing machines, memory networks, and related memory architectures such as fast weight networks and neural stack machines. In this context we will also will discuss asymptotically optimal program search methods and their practical relevance. Our target audience has heard a bit about RNNs, the deepest of all neural networks, but will be happy to hear again a summary of the basics and then delve into the latest advanced topics to see and understand what has recently become possible. All invited talks will be followed by open discussions, with further discussions during a poster session. Finally, we will also have a panel discussion on the bright future of RNNs, and their pros and cons. A tentative list of speakers can be found at the symposium website: http://people.idsia.ch/~rupesh/rnnsymposium2016/index.html Call for Posters We invite researchers and practitioners to submit poster abstracts for presentation during the symposium (min. 2 pages, no page limit). All contributions related to the symposium theme are encouraged. The organizing committee will select posters to maximize quality and diversity within the available display space. For submissions, non-anonymous abstracts should be emailed to rnn.nips2016 at gmail.com by the corresponding authors. Selected abstracts will be advertised on the symposium website, and posters will be visible throughout the duration of the symposium. NIPS attendees will interact with poster presenters during the light dinner break (6:30 - 7:30 PM). The submission deadline is October 15th, 23:59 PM CET. J?rgen Schmidhuber & Sepp Hochreiter & Alex Graves & Rupesh Srivastava From haruo.hosoya at gmail.com Thu Sep 8 20:59:15 2016 From: haruo.hosoya at gmail.com (Haruo HOSOYA) Date: Fri, 9 Sep 2016 09:59:15 +0900 Subject: Connectionists: Researcher position at ATR Brain Labs (Kyoto, Japan) Message-ID: <089CFCEC-1DA3-44CF-B5F3-17DCCA5840C5@gmail.com> Dear all, ATR Brain Labs in Kyoto, Japan has an open position for a researcher to work on machine learning for computer vision in collaboration with computational neuroscientists in our institute. I would appreciate if you forward the following message to anyone who might be interested. Best regards, Haruo Hosoya, Senior Researcher Department of Dynamic Brain Imaging ATR Brain Labs, Cognitive Mechanisms Laboratories ------------------------------------------------ ?Researcher position at ATR Brain Labs., Kyoto, Japan Advanced Telecommunications Research Institute International (ATR), Kyoto, Japan, has an open researcher position in brain-inspired computer vision. Our institute has a long tradition in computational neuroscience and has recently been promoting research of computational modeling of primate visual systems based on hierarchical learning theory (project outline: http://www.cns.atr.jp/~hosoya/project_outline.pdf ). We seek for applicants who are interested in working on brain-inspired machine learning algorithms for vision in collaboration with our computational neuroscientists for vision. Applicants must have a Ph.D. or be near completion in a relevant field. The applicants are required to show an expertise in machine learning research for visual processing as well as a strong interest in neuroscience. The successful candidate will be asked to propose and autonomously work on (1) a research topic using an original method that has a realistic applicability (e.g, image/video analysis) and a connection to primate vision, and (2) a research topic that applies, to a realistic problem (e.g., image/video analysis), computational models of primate vision developed in our institute. Haruo Hosoya, Ph.D. Advanced Telecommunications Research Institute International (ATR), Kyoto, Japan 2016, September ?Number of openings One ?Employment conditions Position : Full-time Researcher Tenure : Single year based contract, renewable based on evaluation Treatment: Based on individual performance Work Location: Advanced Telecommunications Research Institute International (ATR) 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan ?Application materials Please submit the following five materials to the contact address below, either in printed or electronic form: ? 1 CV ? 2 List of publications ? 3 Reprints of 1-3 major publications ? 4 Essay (up to two pages in A4 or letter size) describing: ? Summary of your previous research ? Interests for research ? Additional research skills not directly foreseeable from 1 or 2 ? 5 Recommendation letters from more than two researchers * If submitted in printed form, original documents will not be returned. ?Judging system After documentary examination, we ask for presentation and interview if needed. ?Starting date Soon (negotiable) ?Deadline for application Opens until positions are filled. ?Contact Department of Dynamic Brain Imaging ATR Cognitive Mechanisms Laboratories (Application for Researcher Position) 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan Email: dbi-tvn at atr.jp at=@ Web: http://www.cns.atr.jp/dbi/en/open-positons/ ?Use of personal data All personal data received will be properly managed and only be used for the purpose of recruitment. -------------- next part -------------- An HTML attachment was scrubbed... URL: From rw at physics.wustl.edu Thu Sep 8 16:47:01 2016 From: rw at physics.wustl.edu (Ralf Wessel) Date: Thu, 8 Sep 2016 15:47:01 -0500 Subject: Connectionists: Faculty Position in Biophysics including Neurophysics Message-ID: <3a7ed7b72207e21c2b75641ddb683f0e.squirrel@mail.physics.wustl.edu> Biological/Biomedical Physics The Department of Physics in the School of Arts and Sciences announces a tenure-track faculty opening at the Assistant Professor level in the Biophysics sub-discipline. We are searching for an experimentalist, but applications from data-driven theorists will also be favorably considered. We are seeking a candidate who will enhance activities within the Physics Department and develop connections with other Arts and Sciences, Engineering School, and Medical School Departments. The duties of the position will include, but are not limited to, teaching and advising students, conducting original research and publishing the results, and participating in departmental and university service. A PhD in Physics or a closely related field is required, along with the ability to teach a range of traditional undergraduate physics courses in addition to specialized courses. Candidates are sought who have highly visible research achievements and who have a strong aptitude for teaching and mentoring students at the undergraduate and graduate levels. The appointment will begin Fall 2017. Information on our department can be found at http://www.physics.wustl.edu. Applications should consist of the following: cover letter, current resume including publication record, statement of research interests and plans (up to 4 pages), statement of teaching interests and approach (up to 2 pages), and names and complete contact information (including email addresses) of three references. Application materials must be submitted electronically by email as a single file in editable (e.g. not password protected) PDF format to biophysicssearch at physics.wustl.edu. For full consideration applications should be submitted on or before November 1, 2016. http://physics.wustl.edu/faculty_openings -- **************************************************** Ralf Wessel, Professor of Physics Washington University in St. Louis http://www.physics.wustl.edu/people/wessel_ralf http://neuroscience.wustl.edu/ **************************************************** From trentin at dii.unisi.it Fri Sep 9 07:06:31 2016 From: trentin at dii.unisi.it (Edmondo Trentin) Date: Fri, 9 Sep 2016 13:06:31 +0200 Subject: Connectionists: Neural Processing Letters: CFP - Special Issue on "Off the mainstream: advances in neural networks and machine learning for pattern recognition" Message-ID: <0a148eabba52cad140def8ae893a4ba8.squirrel@mailsrv.diism.unisi.it> Call for Papers Special issue on Off the mainstream: advances in neural networks and machine learning for pattern recognition to be published in Neural Processing Letters *** Submission deadline: January 31, 2017 *** Guest editors: Edmondo Trentin, University of Siena, Italy (trentin at dii.unisi.it) Friedhelm Schwenker, University of Ulm, Germany (friedhelm.schwenker at uni-ulm.de) Nemat El Gayar, Cairo University, Egypt (elgayar.neamat at gmail.com) Hazem M. Abbas, Ain Shams University, Egypt (as at eng.asu.edu.eg) Aims and scope of the special issue: "Mainstream science is about publishing what everyone else is publishing with very small changes. You'd better at least start off that way if you want to get tenure," the sociologist Rodney Stark said. But "big ideas don't come to those who avoid risk", as John Bohannon added. The area of artificial neural networks (ANN) and machine learning (ML) makes no exception to these ends: Mainstream topics, originally stemming from exciting breakthroughs (the "big ideas") that gradually become trends and end-up being mostly over-beaten publishing tracks, have characterized the scientific literature throughout the whole history of these research fields. A few, widely known instances of such (more or less recent) mainstream trends are: - Supervised support vector machine training (in both primal and dual) - Supervised multilayer perceptron training via regular backpropagation - Radial basis functions networks - Bayesian networks (either shallow or deep) - Deep feed-forward and convolutional neural networks - Countless applications of the aforementioned machineries - The ?approximation capabilities? of such machineries Based on these premises, this special issue invites paper submissions on real novel research developments in the areas of neural networks and learning machines that (1) are rooted in (or, aimed at) pattern recognition (PR), and that, above all, (2) do not follow in the footsteps of nowadays established trends. Preference (over applications, theoretical analysis, and variants of established techniques) will thus be given to submissions that hand out fresh and innovative ideas/architectures/algorithms, even if they are in their infancy (e.g., possibly lacking of a complete investigation of their theoretical properties). A detailed list of topics of interest would contradict the very perspective of the present special issue. Nonetheless, some general, topical research directions are (to name a few): - New ANN or ML architectures - New ANN, ML, or PR algorithms - New estimation/optimization/assessment techniques for ANNs, ML, or PR - New and sound combination/hybridization of machines - Solutions to new, relevant PR-related problems - New and sound solutions to established PR-related problems If you are not sure on whether your manuscripts matches the aims and scope of this special issue or not, do not hesitate to get in touch with the guest editors at any time. The special issue will comprise (a) papers submitted in response to this call, and (b) extended versions of selected papers from the ANNPR 2016 Workshop (https://neuro.informatik.uni-ulm.de/ANNPR2016/), sponsored by the International Association for Pattern Recognition. Paper submission: Papers must be submitted online via the Neural Processing Letters website (https://www.editorialmanager.com/nepl/default.aspx), selecting the choice that indicates this special issue (identifier: S.I.:Off_mainstream). Prepare your paper following the Journal guidelines for Authors (http://www.springer.com/computer/ai/journal/11063?detailsPage=pltci_1060677). All submitted papers will undergo a regular peer-review process. Important dates: Opening of electronic submission: September 1, 2016 Submission deadline: January 31, 2017 Completion of 1st round of review process: March 31, 2017 Re-submission of revised manuscripts: May 15, 2017 Final decision: June 30, 2017 Tentative publication of the Special Issue: Fall 2017 ----------------------------------------------- Edmondo Trentin, PhD Dip. Ingegneria dell'Informazione e Scienze MM. V. Roma, 56 - I-53100 Siena (Italy) E-mail: trentin at dii.unisi.it Voice: +39-0577-234636 Fax: +39-0577-233602 WWW: http://www.dii.unisi.it/~trentin -------------- next part -------------- A non-text attachment was scrubbed... Name: Open-SI-CfP.docx Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document Size: 8340 bytes Desc: not available URL: From shimon.whiteson at gmail.com Fri Sep 9 11:13:02 2016 From: shimon.whiteson at gmail.com (Shimon Whiteson) Date: Fri, 9 Sep 2016 16:13:02 +0100 Subject: Connectionists: [jobs] Opening for a Postdoctoral Researcher in Reinforcement Learning at the University of Oxford Message-ID: Researcher on Reinforcement Learning Project Department of Computer Science, University of Oxford Grade 7: ?30,738 - ?37,768 p.a. A full-time postdoctoral position is available for a researcher in the area of reinforcement learning. This is a European Research Council-funded project, working with Professor Shimon Whiteson. The goal of the project is to develop a new class of reinforcement learning and sample-based decision-theoretic planning methods that overcome fundamental obstacles to the efficient optimisation of control policies for autonomous agents. Creating agents that are effective in diverse settings is a key goal of artificial intelligence with large potential implications in robotics, e-commerce, information retrieval, traffic control, etc. The postholder will be expected to collaborate in the preparation of research papers, development and analysis of new algorithms, present papers at conferences, act as a source of information and advice to other members of the group on scientific procedures and experimental techniques, which may include stochastic optimisation, Bayesian optimisation, Bayesian quadrature, and deep learning. The postholder will require a doctoral degree (or be very close to completion) in Computer Science or a related area, together with a documented track record of published, peer-reviewed research in machine learning and/or decision-theoretic planning (or a related area) and possess strong mathematical skills in probability and statistics together with strong programming skills. Experience of conducting large-scale experiments with complex datasets and simulators is highly desirable. The closing date for applications is 12.00 noon on 7 October 2016. Interviews are expected to be held in mid-late October 2016. For further details and to apply please visit:?https://www.recruit.ox.ac.uk/pls/hrisliverecruit/erq_jobspec_version_4.jobspec?p_id=125326 ------------------------------------------------------- Shimon Whiteson | Associate Professor Dept. of Computer Science | U. of Oxford Room 407 | Wolfson Building ------------------------------------------------------- Tutorial Fellow | St. Catherine?s College Room 3 | Alan Bullock Building ------------------------------------------------------- +44 (0) 1865 283 515 (dept. office) +44 (0) 1865 281 574 (college office) +44 (0) 7443 287 697 (mobile) ------------------------------------------------------- shimon.whiteson at cs.ox.ac.uk? www.cs.ox.ac.uk/people/shimon.whiteson ------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From mklados at gmail.com Fri Sep 9 14:45:01 2016 From: mklados at gmail.com (Manousos Klados) Date: Fri, 9 Sep 2016 20:45:01 +0200 Subject: Connectionists: Online Webinar in Brain Networks (hands-on) Message-ID: Dear colleagues, please, accept my advanced apologies for any multiple cross-postings..., As a part of SAN 2016 conference (http://applied-neuroscience.org/san2016) I am organizing a hands-on workshop in Brain Networks on Thursday 6 OCT. This workshop aims to present some novel processing approaches, as well as different ways for visualizing the human connectome and some real studies. After participating in this workshop you will have the ability: - to analyze connectivity using graph theoretical models - to reduce the dimension and consequently the computation complexity of brain networks - to visualize with different ways the human connectome - to apply all these analyses to your data. Considering the huge amount of emails I received asking me for an online version of the workshop, I made an online webinar which is going to run in parallel with the live workshop. You can reserve your seat as well as find more information about the programme in http://app.webinarsonair.com/register/?uuid=7961a35f44ab4cc2a3596492e7fc1ee1 If you need more information please don't hesitate to come in touch with me. Best wishes Manousos Klados [image: photo] *Manousos Klados, MSc, PhD* Postdoctoral Researcher, Max Planck Institute for Human Cognitive & Brain Sciences, +49(0)-341-9940-2507 | +49(0)-176-6988-1781 | http://www.mklados.com | Skype: mklados | Stephanstra?e 1a PC D-04103 Leipzig Germany ------------------------------ *Call for Papers (Frontiers):*Applied Neuroscience: Methodology, Modeling, Theory, Applications and Reviews *Online Webinar in Brain Networks (hands on) - Live: 10-06-16 at 11:00 AM EEST (reserve your seat now )* ------------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Fri Sep 9 11:58:39 2016 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Fri, 9 Sep 2016 11:58:39 -0400 Subject: Connectionists: workshop on high performance computing in neuroscience Message-ID: <1047f4e4-18a1-8c55-61a1-209cbdaf04fa@yale.edu> This year's workshop on the Neuroscience Gateway Portal (NSG) will be held on Saturday, Nov. 12, from 9 AM to noon in downtown San Diego near the convention center, as a satellite to the 2016 meeting of the Society for Neuroscience. This workshop will show you how to use this NSF-supported resource in your computationally-intensive modeling and data analysis projects. It will also feature presentations from several research teams about how they are using high performance computing (HPC) resources in their own research. The NSG has a simple, convenient user interface for running simulations and data analysis tasks on HPC hardware, and provides free CPU time. Currently installed software includes Brian, GENESIS, MOOSE, NEST, NEURON, PyNN, Freesurfer, and the Virtual Personalized Multimodal Connectome Pipeline. The registration deadline for this workshop is Friday Oct. 28, but you should register soon because space is limited. See http://www.neuron.yale.edu/neuron/static/courses/nsg2016/nsg2016.html for more information and a link to the registration form. --Ted From yang at maebashi-it.org Fri Sep 9 12:58:58 2016 From: yang at maebashi-it.org (Yang) Date: Sat, 10 Sep 2016 01:58:58 +0900 Subject: Connectionists: [WI-BIH 2016] Call for Participation Message-ID: <39E489351430425CBC3E5779BAC8FFAE@yangPC> [Apologies if you receive this more than once] =============================================== CALL FOR PARTICIPATION IEEE/WIC/ACM International Conference on Web Intelligence 2016 (WI'16) The 2016 International Conference on Brain Informatics & Health (BIH'16) A Celebration of the 60th Anniversary of AI October 13-16, 2016, Hilton Omaha, USA Homepage: http://wibih.unomaha.edu/ ================================================ *********************************************************** !!! Early-bird Registration by Sept 22, 2016 (extended) !!! *********************************************************** WI'16 Keynote Speakers ++++++++++++++++++++++ Dr. Butler Lampson (Turing Award 1992), Microsoft Corporation and MIT Personal Control of Data Dr. Leslie Valiant (Turing Award 2010), Harvard University A Computational Model and Theory of Cortex BIH'16 Keynote Speakers +++++++++++++++++++++++ Dr. Stephen Smith, Allen Institute for Brain Science Shotgun Connectomic Analysis of Cortical Synaptic Networks Dr. Ivan Soltesz, Stanford School of Medicine Mechanisms of Network Oscillations in Data-driven Full-scale and Rationally Derived Simple Models of the Hippocampus WI'16 Feature Talks +++++++++++++++++++ Dr. Naren Ramakrishnan, Virginia Tech Forecasting Significant Societal Events using Open Source Indicators Dr. Vijay Raghavan, University of Louisiana at Lafayette Triangular Spatial Relationships Based Protein 3-D Comparison Dr. Marek Rusinkiewicz, New Jersey Institute of Technology Towards Smarter Cyber Security Dr. Daniel Siewiorek, Carnegie Mellon University Converting Mobile Sensing into Data and Data into Action Dr. Chris Welty, Google Towards an Embedded Theory of Truth BIH'16 Feature Talks ++++++++++++++++++++ Dr. Steven Schiff, Pennsylvania State University Model-based Observation and Control for the Brain: >From Control of Seizures and Migraines, to Reducing Infant Brain Infections in Africa Dr. Kristen Harris, University of Texas at Austin Analytical Challenges to Understanding Subcellular Resource Allocation for Synaptic Plasticity and Homeostasis Dr. Giulio Tononi, University of Wisconsin at Madison Consciousness: From Theory to Practice Dr. Bob Jacobs, Colorado College Cortical Neuromorphology Beyond Rodents and Primates: A Personal Journey Dr. Partha Mitra, Cold Spring Harbor Laboratory Neuron Trees in the Brain Jungle: Mapping Brainwide Connectivity Dr. Paola Pergami, George Washington University Big Data and Advanced Imaging in Clinical Decision Making: Are We There Yet? WI'16-BIH'16 Joint Panel ~~~~~~~~~~~~~~~~~~~~~~~~ Connecting Network and Brain with Big Data (keynote/feature speakers of the 2 conferences as panelists) ------------- The two conferences will be co-located and have a joint opening, keynotes and invited talks, panel, reception and banquet. Attendees only need to register for one conference and can attend workshops, sessions, keynote/invited talks, panel and tutorials across the two conferences. *********************************************************** !!! Early-bird Registration by Sept 22, 2016 (extended) !!! *********************************************************** On-line registration (and more information) at https://wibih.unomaha.edu/wi/register or https://wibih.unomaha.edu/bih/register Regular registration (non-authors) covers all events of technical program (plenary talks, tutorials, workshops, panel, parallel sessions, industry/demo sessions, etc.), the reception, coffee breaks and lunches. Schedule Outline ++++++++++++++++ October 13: Workshop & Tutorial Day October 14: WI'16-BIH'16 Joint Day October 15-16: Feature Talks, Special-sessions, and Presentations of Accepted Papers in parallel sessions TUTORIALS +++++++++ T1: Context-Awareness in Information Retrieval and Recommender Systems Yong Zheng, Illinois Institute of Technology, USA T2: Ontology Learning and Population from Text Background Rosario Girardi, Federal University of Maranh o, Brasil WORKSHOPS & SPECIAL SESSIONS ++++++++++++++++++++++++++++ BIH'16: ~~~~~~~ B1: International Workshop on Brain and Artificial Intelligence (BAI 2016) B2: International Workshop on Services and Data Modeling in Life Sciences (SDMLS 2016) B3: International Workshop on Brain Big Data Based Wisdom Service B4: Special Session on BigNeuron Project WI'16: ~~~~~~ W1: The International Workshop on Web Personalization and Social Media W2: The Second Workshop on Complex Methods for Data and Web Mining W3: International Workshop on Educational Recommender Systems W4: The First International Workshop on the Internet of Agents (IoA) W5: The 1st International Workshop on Platforms and Applications for Social Problem Solving and Collective Reasoning W6: International Workshop on Advanced Methods in Optimization and Machine Learning SOCIAL PROGRAM ++++++++++++++ October 13, 18:00-20:00 Pre-Conference Reception (with hors d'oeuvres) at the Conference Hotel (Sponsored by Hilton) October 14, 17:00-19:00 -- Tour of the Henry Doorly Zoo 19:00-21:00 -- Welcome Reception (with dinner) sponsored by the Greater Omaha Convention & Visitors Bureau Durham TreeTops Restaurant at the Henry Doorly Zoo October 15, 18:30 to 21:00 -- UNO Jazz Quintet 19:00 to 21:00 -- Banquet and Awards Ceremony in the Conference Hotel You can also enjoy the city of Omaha. More information about the conference hotel, visas and local information can be obtained from the conference homepage: http://wibih.unomaha.edu/ CONTACT INFORMATION +++++++++++++++++++ Deepak Khazanchi Bettina Lechner -------------- next part -------------- An HTML attachment was scrubbed... URL: From veronica.bolon at udc.es Sat Sep 10 07:45:51 2016 From: veronica.bolon at udc.es (Veronica Bolon Canedo) Date: Sat, 10 Sep 2016 13:45:51 +0200 Subject: Connectionists: CFP for ESANN17 Special Session on Algorithmic Challenges in Big Data Analytics Message-ID: [Apologies if you receive multiple copies of this CFP] Call for papers: special session on "Algorithmic Challenges in Big Data Analytics" at ESANN 2017 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2017) 26-28 April 2017, Bruges (Belgium) - http://www.esann.org Algorithmic Challenges in Big Data Analytics Organized by: Veronica Bolon-Canedo, Amparo Alonso-Betanzos (University of A Coru?a, Spain), Beatriz Remeseiro (University of Barcelona, Spain), David Martinez-Rego (University College London, UK), Konstantinos Sechidis (University of Manchester, UK) In the past few years, the advent of Big Data has brought unprecedented challenges to machine learning researchers. Dealing with huge volumes of data, both in terms of instances and features, makes the learning task more complex and computationally demanding than ever. Processing these massive datasets is key to providing a wealth of information, but at the same time is a challenge for machine learning researchers, who see how classic algorithms are now useless. The community expects new methods that not only allow accurate analysis of the available data, but which are also robust and scalable when dataset sizes increase. In other words, the challenge now is to find ?good enough? solutions as ?fast? as possible and as ?efficiently? as possible. This issue becomes critical in situations in which there exist temporal or spatial constraints like real-time applications or unapproachable computational problems requiring learning. We invite papers aiming to examine the recent progress in the field, together with new open challenges derived from the increased data availability. In particular, topics of interest include, but are not limited to: Pre-processing, processing and post-processing of Big Data. Methods, algorithms and theory for Big Data analytics. Recent advances and challenges in machine learning for Big Data. Distributed learning in the context of Big Data. Deep learning with massive-scale datasets. Applications: healthcare, social media, bioinformatics, genomics, finance, surveillance, etc. Submitted papers will be reviewed according to the ESANN reviewing process and will be evaluated on their scientific value: originality, correctness, and writing style. IMPORTANT DATES: Paper submission deadline : 19 November 2016 Notification of acceptance : 31 January 2017 ESANN conference : 26-28 April 2017 -------------- next part -------------- An HTML attachment was scrubbed... URL: From martaruizcostajussa at gmail.com Sun Sep 11 06:49:51 2016 From: martaruizcostajussa at gmail.com (Marta Ruiz) Date: Sun, 11 Sep 2016 12:49:51 +0200 Subject: Connectionists: Second CFP: HyTra-6 Sixth Workshop on Hybrid Approaches to Translation (in conjunction with COLING) Message-ID: *HyTra-6: Sixth Workshop on Hybrid Approaches to Translation* The Sixth Workshop on Hybrid Approaches to Translation (HyTra-6), in conjunction with *COLING 2016*, intends to invite work contributions on integrating any type of data-driven and linguistic-based machine translation approaches. Nowadays, there are more paradigms competing in machine translation including statistical (phrase-based, hierarchical and syntax-based), neural-based and rule-based. Each of them has their own advantages and disadvantages which make it worth the research on hybridization, integration and/or combination of approaches. Given that academic and industry perspectives may differ on the opinion of which are the most suitable paradigms, HyTra gives a strong relevance to the participation of both in the workshop. The fact that machine translation is a highly interdisciplinary field (including engineers, computer scientists, mathematicians, translators, linguists?), specially in the research of hybridization, enriches the workshop in its discussions, proceedings, invited talks and, even, in one contributed volume published by Springer. In this edition, HyTRA will specially focus on motivating the cooperation and interaction between the different human components, as well as to foster innovation and creativity in the Hybrid Machine Translation research community. That is why we encourage the participation of the different integrating fields (engineers, computer scientists, mathematicians, translators, linguists either from academy or industry) to contribute to our special call of shared task proposals. Given the complementarity and mutual attractiveness of data-driven and rule-based MT, the appearance of new data-driven approaches (such as the neural-based one), the question is what the combined architecture should look like. We will solicit contributions including but not limited to the following topics: ? ways and techniques of hybridization ? architectures for the rapid development of hybrid MT systems ? applications of hybrid systems ? hybrid systems dealing with under-resourced languages ? hybrid systems dealing with morphologically rich languages ? using linguistic information (morphology, syntax, semantics) to enhance statistical MT (e.g. with hierarchical or factored models) ? bootstrapping rule-based systems from corpora ? extraction of dictionaries from parallel and comparable corpora ? induction of morphological, grammatical, and translation rules from corpora ? improving MT with statistical and rule-based computational linguistics methods (word sense disambiguation, information extraction, terminology mining, metaphor recognition, etc.) ? machine learning techniques for hybrid MT and complex data structures ? describing and using structural mappings between languages (e.g. tree-structures using synchronous/transduction grammars) ? system combination approaches such as multi-engine MT (parallel) or automatic post-editing (sequential) ? hybrid methods in spoken language translation ? heuristics for limiting the search space in hybrid MT ? translation of user generated contents ? alternative methods for the fair evaluation of the output of different types of MT systems (e.g. relying on linguistic criteria) ? use of word embeddings and continuous vector space representations in hybrid MT ? neural networks, deep learning and neural MT hybridization ? open source tools and free language resources for hybrid MT ? presentations of industrial hybrid MT systems and technologies which involve hybrid MT systems in commercial and professional applications *Call for shared task proposals* We solicit proposals for shared tasks relevant to hybrid translation with the potential to be conducted in future editions of the HyTra workshop series. Proposals should include: 1) A definition of the objectives of the shared task (e.g. user generated content translation) ; 2) A suggestion of a baseline system (if appropriate) ; 3) Data to conduct the shared task; 4) An evaluation measure Proposals should be different from those conducted elsewhere. We particularly welcome proposals which motivate the MT industry to participate. The proposals should be 2 pages long in the format required by the workshop. The best proposals will be published in the proceedings and discussed in a panel. The authors of convincing proposals will be invited to organize a shared task in conjunction with upcoming editions of the HyTra workshop series. Please send your proposals to patrik.lambert at gmail.com *Important Dates* *Paper submission* September 25th, 2016 *Notification to authors* October 16th, 2016 *Camera-ready deadline* October 30th, 2016 *Workshop *December 11th, 2016 *Program Committee * ? Arianna Bisazza, University of Amsterdam, The Netherlands ? Bogdan Babych, University of Leeds, UK ? Rafael E. Banchs, Institute for Infocomm Research, Singapore ? Alexey Baytin, Yandex, Moscow, Russia ? Pierrette Bouillon, ISSCO/TIM/ETI, University of Geneva, Switzerland ? Marta R. Costa-jussa, UPC, Barcelona ? Josep Maria Crego, Systran, Paris, France ? Kurt Eberle, Lingenio GmbH, Heidelberg, Germany ? Cristina Espa?a, UPC, Barcelona ? Christian Federmann, Microsoft Research, Seattle, USA ? Jos? A. R. Fonollosa, UPC, Barcelona ? Maxim Khalilov, Berlin, Germany ? Udo Kruschwitz, University of Essex, UK ? Patrik Lambert, Pompeu Fabra University, Barcelona, Spain ? Maite Melero, Pompeu Fabra University, Barcelona, Spain ? Reinhard Rapp, Universities of Aix-Marseille, France, and Mainz, Germany ? George Tambouratzis, Institute for Language and Speech Processing, Greece ? J?rg Tiedemann, University of Uppsala, Sweden ? Grigori Sidorov, Instituto Polit?cnico Nacional, Mexico *Organizing Committee* Patrik Lambert, Bogdan Babych, Kurt Eberle, Rafael E. Banchs, Reinhard Rapp and Marta R. Costa-juss? *Contact* Patrik Lambert (patrik.lambert at gmail.com) -------------- next part -------------- An HTML attachment was scrubbed... URL: From rrosenb1 at nd.edu Sun Sep 11 22:48:11 2016 From: rrosenb1 at nd.edu (Robert Rosenbaum) Date: Sun, 11 Sep 2016 22:48:11 -0400 Subject: Connectionists: 3rd International Conference on Mathematical Neuroscience (ICMNS 2017) Message-ID: An HTML attachment was scrubbed... URL: From ahu at cs.stir.ac.uk Sun Sep 11 19:33:08 2016 From: ahu at cs.stir.ac.uk (Dr Amir Hussain) Date: Mon, 12 Sep 2016 00:33:08 +0100 Subject: Connectionists: Increased Impact Factor (2015/16) and Table of Contents Alert: Cognitive Computation journal (Springer Nature): Vol.8, No.4 / Aug 2016 Issue Message-ID: Dear Colleagues: (with advance apologies for any cross-postings) We are delighted to announce the publication of Volume 8, No.4 / Aug 2016 Issue, of (Springer Nature's) Cognitive Computation journal - www.springer.com/12559 ================================================================= Important News: Increased Impact Factor & Six bi-monthly Journal Issues since 2015 ================================================================= As you will know, Cognitive Computation was selected for coverage in Thomson Reuter?s products and services in 2011. Beginning with V.1 (1) 2009, this publication is now indexed and abstracted in: ? Science Citation Index Expanded (also known as SciSearch?) ? Journal Citation Reports/Science Edition ? Current Contents?/Engineering Computing and Technology ? Neuroscience Citation Index? Cognitive Computation received its first Impact Factor (IF) in 2011 The ISI IF for 2015/16 has increased to 1.933 (from 1.44 in 2014/15) - Thomson Reuters Journal Citation Reports? 2015 Many congratulations to the editors, reviewers and authors! Want to be part of the growing success? Visit the journal homepage ( http://springer.com/12559) for instructions on submitting your research. ================================= Quarterly to Bi-monthly Issues, since 2015!! ================================= Due to continuously growing number of high quality submissions, the number of Issues has increased from four (quarterly Issues) to six (bi-monthly Issues) each year, since Feb 2015! ================================= The August 2016 Issue comprises an OPEN ACCESS invited paper, by Yiyu Yao (titled: Three-Way Decisions and Cognitive Computing, available for free download from: http://link.springer.com/article/10.1007/s12559-016- 9397-5?view=classic ). This is followed by 16 regular papers. The full listing of published articles (Table of Contents) for this August 2016 Issue can be viewed here (and also at the end of this message, followed by an overview of the previous Issues/Archive listings): http://link.springer.com/journal/12559/8/4/ A list of the journal's Open Access articles can be found here: http://link.springer.com/search?query=&search-within= Journal&facet-journal-id=12559&package=openaccessarticles Other 'Online First' published articles not yet in a print issue can be viewed here: http://www.springerlink.com/content/121361/?Content+Status=Accepted All previous Volumes and Issues of the journal can be viewed here: http://link.springer.com/journal/volumesAndIssues/12559 ======================================== Reminder: Cognitive Computation "LinkedIn" Group: ======================================== To further strengthen the bonds amongst the interdisciplinary audience of Cognitive Computation, we have set-up a "Cognitive Computation LinkedIn group", which has over 800 members already! We warmly invite you to join us at: http://www.linkedin.com/groups?gid=3155048 For further information on the journal and to sign up for electronic "Table of Contents alerts" please visit the Cognitive Computation homepage: http://www.springer.com/12559 or follow us on Twitter at: http://twitter.com/CognComput for the latest On-line First Issues. For any questions with regards to LinkedIn and/or Twitter, please contact Springer's Publishing Editor: Marleen Moore: Marleen.Moore at springer.com Finally, we would like to invite you to submit short or regular papers describing original research or timely review of important areas - our aim is to peer review all papers within approximately six weeks of receipt. We also welcome relevant high quality multi-disciplinary proposals for Special Issues - three are already planned for 2016/17! (including an exciting new one titled: "Advances in Biologically Inspired Reservoir Computing" - submissions are now open, full CFP can be found here: http://static.springer.com/sgw/documents/1570471/ application/pdf/Advances+in+Biologically+Inspired+Reservoir+Computing.pdf ) With our very best wishes to all aspiring readers and authors of Cognitive Computation. Professor Amir Hussain, PhD (Editor-in-Chief: Cognitive Computation) E-mail: ahu at cs.stir.ac.uk (University of Stirling, Scotland, UK) Professor Igor Aleksander, PhD (Honorary Editor-in-Chief: Cognitive Computation) (Imperial College, London, UK) http://www.springer.com/12559 NEW: Open Access Springer Nature/BioMed Central (BMC) journal: Big Data Analytics (http://www.bdataanalytics.com/) - Now accepting submissions! NEW: Springer Series on Socio-Affective Computing: http://www.springer.com/series/13199 Also consider your work for a related forthcoming Book Series: Cognitive Computation Trends (emails us for details!) =========================================================== Table of Contents Alert -- Cognitive Computation Vol 8 No 4, August 2016 =========================================================== Invited Paper (Open Access) *Three-Way Decisions and Cognitive Computing* Yiyu Yao Regular Papers: *Learning the Semantics of Notational Systems with a Semiotic Cognitive Automaton* Valerio Targon *Detection and Extraction of Hot Topics on Chinese Microblogs* Liang Yang, Hongfei Lin, *Yuan Lin*, *Shengbo Liu* *Online Shopping Behavior Study Based on Multi-granularity Opinion Mining: China Versus America * Qingqing Zhou, Rui Xia, Chengzhi Zhang *On Identifying Minimal Absent and Unique Words: An Efficient Scheme* Aqil M. Azmi *Multi-Objective Model Selection (MOMS)-based Semi-Supervised Framework for Sentiment Analysis* Farhan Hassan Khan, Usman Qamar, Saba Bashir *A New Spatio-Temporal Saliency-Based Video Object Segmentation* Zhengzheng Tu, Andrew Abel, Lei Zhang, Bin Luo, Amir Hussain *Erratum to: A New Spatio-Temporal Saliency-Based Video Object Segmentation* Zhengzheng Tu, Andrew Abel, Lei Zhang, Bin Luo, Amir Hussain *A Neutrosophic Normal Cloud and Its Application in Decision-Making* Hong-yu Zhang, Pu Ji, Jian-qiang Wang, Xiao-hong Chen *A Likelihood-Based Qualitative Flexible Approach with Hesitant Fuzzy Linguistic Information* Zhang-peng Tian , Jing Wang , Jian-qiang Wang , Hong-yu Zhang *Deep Belief Networks for Quantitative Analysis of a Gold Immunochromatographic Strip* Nianyin Zeng , Zidong Wang , Hong Zhang , Weibo Liu , Fuad E. Alsaadi *A Novel Saliency Prediction Method Based on Fast Radial Symmetry Transform and Its Generalization* Jiayu Liang , Shiu Yin Yuen *Toward Self-Referential Autonomous Learning of Object and Situation Models* Florian Damerow , Andreas Knoblauch , Ursula K?rner , Julian Eggert ? *Self-adaptive Extreme Learning Machine Optimized by Rough Set Theory and Affinity Propagation Clustering* Li Xu , Shifei Ding , Xinzheng Xu , Nan Zhang *From Spin to Swindle: Identifying Falsification in Financial Text* Saliha Minhas , Amir Hussain *An Analytical Study on Reasoning of Extreme Learning Machine for Classification from Its Inductive Bias* Pak Kin Wong , Xiang Hui Gao , Ka In Wong , Chi Man Vong *Multilingual Sentiment Analysis: State of the Art and Independent Comparison of Techniques* Kia Dashtipour , Soujanya Poria , Amir Hussain , Erik Cambria ? *Erratum to: Multilingual Sentiment Analysis: State of the Art and Independent Comparison of Techniques* Kia Dashtipour , Soujanya Poria , Amir Hussain , Erik Cambria ? *A Bio-inspired Parallel-Framework Based Multi-gene Genetic Programming Approach to Denoise Biomedical Images* Syed Gibran Javed , Abdul Majid , Safdar Ali , Nabeela Kausar ----------------------------------------------- Previous Issues/Archive: Overview: ----------------------------------------------- All previous Volumes and Issues can be viewed here: http://link.springer.com/journal/volumesAndIssues/12559 Alternatively, the full listing of the Inaugural Vol. 1, No. 1 / March 2009, can be viewed here (which included invited authoritative reviews by leading researchers in their areas - including keynote papers from London University's John Taylor, Igor Aleksander and Stanford University's James McClelland, and invited papers from Ron Sun, Pentti Haikonen, Geoff Underwood, Kevin Gurney, Claudius Gross, Anil Seth and Tom Ziemke): http://www.springerlink.com/content/1866-9956/1/1/ The full listing of Vol. 1, No. 2 / June 2009, can be viewed here (which included invited reviews and original research contributions from leading researchers, including Rodney Douglas, Giacomo Indiveri, Jurgen Schmidhuber, Thomas Wennekers, Pentti Kanerva and Friedemann Pulvermuller): http://www.springerlink.com/content/1866-9956/1/2/ The full listing of Vol.1, No. 3 / Sep 2009, can be viewed here: http://www.springerlink.com/content/1866-9956/1/3/ The full listing of Vol. 1, No. 4 / Dec 2009, can be viewed here: http://www.springerlink.com/content/1866-9956/1/4/ The full listing of Vol.2, No. 1 / March 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/1/ The full listing of Vol.2, No. 2 / June 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/2/ The full listing of Vol.2, No. 3 / Aug 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/3/ The full listing of Vol.2, No. 4 / Dec 2010, can be viewed here: http://www.springerlink.com/content/1866-9956/2/4/ The full listing of Vol.3, No.1 / Mar 2011 (Special Issue on: Saliency, Attention, Active Visual Search and Picture Scanning, edited by John Taylor and Vassilis Cutsuridis), can be viewed here: http://www.springerlink.com/content/1866-9956/3/1/ The Guest Editorial can be viewed here: http://www.springerlink.com/content/hu2245056415633l/ The full listing of Vol.3, No.2 / June 2011 can be viewed here: http://www.springerlink.com/content/1866-9956/3/2/ The full listing of Vol. 3, No. 3 / Sep 2011 (Special Issue on: Cognitive Behavioural Systems, Guest Edited by: Anna Esposito, Alessandro Vinciarelli, Simon Haykin, Amir Hussain and Marcos Faundez-Zanuy), can be viewed here: http://www.springerlink.com/content/1866-9956/3/3/ The Guest Editorial for the special issue can be viewed here: http://www.springerlink.com/content/h4718567520t2h84/ The full listing of Vol. 3, No. 4 / Dec 2011 can be viewed here: http://www.springerlink.com/content/1866-9956/3/4/ The full listing of Vol. 4, No.1 / Mar 2012 can be viewed here: http://www.springerlink.com/content/1866-9956/4/1/ The full listing of Vol. 4, No.2 / June 2012 can be viewed here: http://www.springerlink.com/content/1866-9956/4/2/ The full listing of Vol. 4, No.3 / Sep 2012 (Special Issue on: Computational Creativity, Intelligence and Autonomy, Edited by: J. Mark Bishop and Yasemin J. Erden) can be viewed here: http://www.springerlink.com/content/1866-9956/4/3/ The full listing of Vol. 4, No.4 / Dec 2012 (Special Issue titled: "Cognitive & Emotional Information Processing", Edited by: Stefano Squartini, Bj?rn Schuller and Amir Hussain, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/4/4/page/1 The full listing of Vol. 5, No.1 / March 2013 Special Issue titled: Computational Intelligence and Applications Guest Editors: Zhigang Zeng & Haibo He, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/5/1/page/1 The full listing of Vol. 5, No.2 / June 2013 Special Issue titled: Advances on Brain Inspired Computing, Guest Editors: Stefano Squartini, Sanqing Hu & Qingshan Liu, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/5/2/page/1 The full listing of Vol. 5, No.3 / Sep 2013 Special Issue titled: In Memory of John G Taylor: A Polymath Scholar, Guest Editors: Vassilis Cutsuridis & Amir Hussain, which is followed by a number of regular papers), can be viewed here: http://link.springer.com/journal/12559/5/3/page/1 The full listing of Vol. 5, No.4 / Dec 2013, which includes regular papers (including an invited paper by Professor Ron Sun, Rensselaer Polytechnic Institute, USA, titled: Moral Judgment, Human Motivation, and Neural Networks), and a Special Issue titled: Advanced Cognitive Systems Based on Nonlinear Analysis. Guest Editors: Carlos M. Travieso and Jes?s B. Alonso, can be viewed here: http://link.springer.com/journal/12559/5/4/page/1 The full listing of Vol. 6, No.1 / Mar 2014, can be viewed here: http://link.springer.com/journal/12559/6/1/page/1 The full listing of Vol. 6, No.2 / June 2014, can be viewed here: http://link.springer.com/journal/12559/6/2/page/1 The full listing of Vol. 6, No.3 / Sep 2014, can be viewed here: http://link.springer.com/journal/12559/6/3/page/1 The full listing of Vol. 6, No.4 / Dec 2014 (Special Issue on Modeling emotion, behaviour and context in socially believable robots and ICT interfaces, Guest Editors: Anna Esposito, Leopoldina Fortunati, and Giuseppe Lugano) can be viewed here: http://link.springer.com/ journal/12559/6/4/page/1 The full listing of Vol. 7, No.1 / Feb 2015 can be viewed here: http://link.springer.com/journal/12559/7/1/ (with the first six papers part of a Special Issue on "Neural Signal Processing", Guest Edited by: Jordi Sole?-Casals, Francois-Benoit Vialatte, Justin Dauwels. The Guest Editorial titled: "Alternative Techniques of Neural Signal Processing in Neuroengineering" is available (for free download) here: http://link.springer.com/article/10.1007/s12559-015-9317-0) The full listing of Vol. 7, No. 2 / April 2015, can be viewed here: http://link.springer.com/journal/12559/7/2/ This comprises a Special Issue on "Sentic Computing", Guest Edited by: E. Cambria and A. Hussain. The Guest Editorial titled: "Sentic Computing" is available (for free download) here: http://link.springer.com/article/10.1007/s12559-015-9325-0 The full listing of Vol. 7, No. 3 / June 2015, can be viewed here: http://link.springer.com/journal/12559/7/3/ The full listing of Vol. 7, No. 4 / August 2015, can be viewed here: http://link.springer.com/journal/12559/7/4/ This comprises an invited paper by A. Vinciarelli and A. Esposito, et al. titled: Open Challenges in Modelling, Analysis and Synthesis of Human Behaviour in Human?Human and Human?Machine Interactions, which is followed by six regular papers. The full listing of Vol. 7, No. 5 / October 2015, can be viewed here: http://link.springer.com/journal/12559/7/5/ The full listing of Vol. 7, No.6 / December 2015, can be viewed here: http://link.springer.com/journal/12559/7/6/ This comprises a Special Issue titled: "Dealing with Big Data-Lessons from Cognitive Computing" (the Guest Editorial is available for free download here: http://link.springer.com/ article/10.1007/s12559-015-9364-6). This is followed by seven regular papers, including an invited paper by Hojjat Adeli et al. titled: "Nature Inspired Computing: An Overview and Some Future Directions" (free download available here: http://link.springer.com/article/10.1007/s12559-015-9370-8) The full listing of Vol. 8, No.1 / February 2016, can be viewed here: http://link.springer.com/journal/12559/8/1/ This comprises an invited paper by Ron Sun et al. titled: "Emotion: A Unified Mechanistic Interpretation from a Cognitive Architecture" (this is available for free download here: http://link.springer.com/content/pdf/10.1007%2Fs12559- 015-9374-4.pdf). This is followed by eight regular papers. The full listing of Vol. 8, No. 2 / April 2016, can be viewed here: http://link.springer.com/journal/12559/8/2/ This comprises two invited papers, the first by Yew-Soon Ong et al. (titled: Evolutionary Multitasking: A Computer Science View of Cognitive Multitasking) and the second by Zidong Wang et al. (titled: A Novel Switching Delayed PSO Algorithm for Estimating Unknown Parameters of Lateral Flow Immunoassay). These are followed by 10 regular papers, and finally a Special Issue titled: "Cognitively-Inspired Computing for Gerontechnology" (comprising five manuscripts, with the Guest Editorial available for free download here: http://link.springer.com/content/pdf/10.1007%2Fs12559-016-9392-x.pdf). The full listing of Vol. 8, No.3 / June 2016, can be viewed here: http://link.springer.com/journal/12559/8/3/ This Issue comprises two Open Access invited papers, the first by Hussein Abbass et al. (titled: "Trusted Autonomy and Cognitive Cyber Symbiosis: Open Challenges", available for free download from: http://link.springer.com/article/10.1007/s12559-015- 9365-5), and the second by Kevin Warwick et al. (titled: "Passing the Turing Test Does Not Mean the End of Humanity", available for free download from: http://link.springer.com/article/10.1007/s12559-015-9372-6). These are followed by 10 regular papers. -- The University achieved an overall 5 stars in the QS World University Rankings 2015 The University of Stirling is a charity registered in Scotland, number SC 011159. -------------- next part -------------- An HTML attachment was scrubbed... URL: From marco.baroni at unitn.it Sun Sep 11 13:50:22 2016 From: marco.baroni at unitn.it (Marco Baroni) Date: Sun, 11 Sep 2016 19:50:22 +0200 Subject: Connectionists: MAchine INtelligence @ NIPS: Call for abstracts and participation Message-ID: What: MAchine INtelligence workshop at NIPS 2016 (MAIN at NIPS) When and Where: Fri Dec 9th 2016, 9am-12.30pm and 2pm-5.30pm Where: Centre Convencions Internacional, Barcelona (Spain) (co-located with NIPS) Website: https://mainatnips.github.io/ *** Motivation *** Recent years have seen the success of machine learning systems, in particular deep learning architectures, on specific challenges such as image classification and playing Go. Nevertheless, machines still fail on hallmarks of human intelligence such as the flexibility to quickly switch between a number of different tasks, the ability to creatively combine previously acquired skills in order to perform a more complex goal, the capacity to learn a new skill from just a few examples, or the use of communication and interaction to extend one's knowledge in order to accomplish new goals. This workshop aims to stimulate theoretical and practical advances in the development of machines endowed with human-like general-purpose intelligence, focusing in particular on benchmarks to train and evaluate progress in machine intelligence. The workshop will feature invited talks by top researchers from machine learning, AI, cognitive science and NLP, who will discuss with the audience their ideas about what are the most pressing issues we face in developing true AI and the best methods to measure genuine progress. We are moreover calling for position statements from interested researchers to complement the workshop program (see below). The workshop will also introduce the new Environment for Communication-Based AI to the research community, encouraging discussion on how to make it the ultimate benchmark for machine intelligence. The Environment aims at being an interactive playground where systems can only succeed if they possess the hallmarks of intelligence we listed above. We will soon make a prototype of the Environment available, so that researchers interested in submitting position statements to the workshop can experiment with it and take it into account in their proposals. *** Call for abstracts *** We invite submission of 3-page abstracts (or shorter) presenting a position statement on what are the most important challenges to develop general machine intelligence (with special interest in communication-based intelligence), and what are the data and benchmarks we need to properly address such challenges. While all points of view are welcome, we encourage in particular critiques of the Environment for Communication-Based AI. To facilitate this, we will make a prototype of the Environment publicly available by Sunday, September 18th (downloading instructions will be posted on the workshop webpage: https://mainatnips.github.io/). Abstracts must be submitted in PDF format to main.at.nips2016 at gmail.com by Sunday, October 9th. We will notify acceptance by Sunday, October 23d. Authors of accepted abstracts are expected to present their ideas in an oral presentation at the workshop, and to take part in the panel discussions. *** Invited speakers *** * Emannuel Dupoux (Laboratoire de Sciences Cognitives et Psycholinguistique, Paris): http://www.lscp.net/persons/dupoux/ * Fernando Diaz (Microsoft Research, New York): http://msr.nyc/fdiaz/ * Raquel Fernandez (Institute for Logic, Language & Computation, Amsterdam): https://staff.fnwi.uva.nl/r.fernandezrovira/ * Arthur Szlam (Facebook Artificial Intelligence Reserch, New York): https://research.facebook.com/arthur-szlam * Josh Tenenbaum (MIT Department of Brain and Cognitive Sciences, Boston): http://web.mit.edu/cocosci/josh.html * Julian Togelius (NYU Game Innovation Lab, New York): http://julian.togelius.com/ *** Organizers *** Tomas Mikolov, Allan Jabri, Armand Joulin, Klemen Simonic (Facebook) Marco Baroni, Angeliki Lazaridou, Germ?n Kruszewski (University of Trento/Facebook) *** Program *** The workshop will feature oral presentations and two panel discussions. The program will be posted on the workshop website. *** Important dates *** * Sunday, September 18th: Release of Environment for Communication-Based AI prototype * Sunday, October 9th: Abstract submission deadline * Sunday, October 23d: Notification of acceptance * Friday, December 9th: Workshop *** Contact *** main.at.nips2016 at gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From thomas.wennekers at plymouth.ac.uk Mon Sep 12 08:13:26 2016 From: thomas.wennekers at plymouth.ac.uk (Thomas Wennekers) Date: Mon, 12 Sep 2016 13:13:26 +0100 Subject: Connectionists: FINAL CALL: Workshop on large-scale brain models, Manchester 7 Oct 2016 Message-ID: <201609121313.26899.thomas.wennekers@plymouth.ac.uk> Dear All This is the final call for an exciting workshop on large-scale models of embodied language. "BABEL -- Bioinspired Architectures for Brain Embodied Language" Workshop on large-scale brain models for embodied language on robots/iCub using SpiNNaker University of Manchester, Friday, 7th October 2016 AIM BABEL, short for "Bioinspired Architecture for Brain Embodied Language", is a research project jointly funded by the EPSRC and BBSRC. It aims at brain models for language that use SpiNNaker hardware on the iCub robot. The project abstract is included further below for detailed information. This open one day workshop concludes the BABEL project. It presents project results in the areas of robotics, spiking neuron hardware, the neurophysiology of language, and computational modeling. International experts in the fields of embodied cognition and robotics complement the list of speakers. SPEAKERS Lawrence Barsalou (University of Glasgow, UK) Chiara Bartolozzi (Italian Institute of Technology, Genoa, IT) Angelo Cangelosi (University of Plymouth, UK) Steve Furber (University of Manchester, UK) Marc Oliver Gewaltig (EPFL, Lausanne, Switzerland) Giorgio Metta (Italian Institute of Technology, Genoa, **) Friedemann Pulvermuller (Freie Universitaet Berlin, Germany) Paul Verschure (Universitat Pompeu Fabra, Barcelona, Spain) Thomas Wennekers (University of Plymouth, UK) (**) unconfirmed FEES Participation in the Workshop is free. A small fee for catering will be charged (Lunch, Tee&Coffee). IMPORTANT DATES Application Deadline 16 September 2016 Workshop 7 October 2016 APPLICATION To apply and for further information, please send email to twennekers at plymouth.ac.uk Spaces are limited and distributed on a first-come-first-serve basis. BABEL abstract Recent advances in behavioural and computational neuroscience, in cognitive robotics, and in the hardware implementation of large-scale neural networks, provide the opportunity for an accelerated understanding of brain functions and for the design of interactive robotic systems based on brain-inspired control systems. This is especially the case in the domain of action and language learning, given the significant scientific and technological developments in this field. This project aims at advancing the understanding of neural and behavioural mechanisms in word learning, the validation of these principles in neuroanatomically grounded models, and real-time implementations of brain language models within the SpiNNaker neuromorphic architecture that will support comparisons with neuroimaging experiments. The scientific hypotheses and cortical language model will also be validated by implementing a model of embodied active language learning on the humanoid robot iCub. Specifically, in the project we will develop, based on neuroscientific principles, a theory of language learning at the neural circuit level and build a neurocomputational model of the language cortex that implements the learning of words used to speak about objects and actions in large-scale neuronal circuits. This theoretical work will be supported by novel, hypothesis-driven brain imaging investigations using MEG, EEG and fMRI to identify the neural correlates and mechanisms of the learning of words for objects and actions. Imaging results will inform the improvement of the large-scale neuroanatomical models. These models will be implemented on the SpiNNaker software and hardware infrastructure, to implement a scaled-up real-time model of the language cortex using more realistic spiking activity. Finally, the project will translationally apply these neuro-anatomical models and SpiNNaker system as controllers for language and action learning simulations with the humanoid robot iCub, within the embodied and active learning context where the semantics of the language is directly driven by the context of object manipulation tasks. This is a highly interdisciplinary project that integrates essential expertise and methodologies from neuromorphic engineering, computational and experimental neuroscience, and cognitive robotics. The project is based around the unique and strategic partnership of applicants with an international track record in these areas of expertise and with previous collaborative experience. Furthermore, the project will benefit from an International Advisory Board, with both academic and industrial advisors, to foster the international dimension and impact of the project. ACKNOWLEDGEMENT The BABEL project is funded by the Engineering and Physical Sciences Research Council and the Biotechnology and Biological Sciences Research Council of the United Kingdom. ________________________________ [http://www.plymouth.ac.uk/images/email_footer.gif] This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form. From LT at dartmouth.edu Mon Sep 12 13:08:56 2016 From: LT at dartmouth.edu (Lorenzo Torresani) Date: Mon, 12 Sep 2016 13:08:56 -0400 Subject: Connectionists: Assistant Professor position in Machine Learning at Dartmouth Message-ID: <3408EB3D-91CD-44AB-A230-7DC4D6F04673@dartmouth.edu> The Dartmouth College Department of Computer Science invites applications for a tenure-track faculty position at the level of assistant professor. We seek candidates who will be excellent researchers and teachers in the area of machine learning. We particularly seek candidates who will help lead, initiate, and participate in collaborative research projects within Computer Science and beyond, including Dartmouth researchers from other Arts & Sciences departments, Geisel School of Medicine, Thayer School of Engineering, and Tuck School of Business. The Computer Science department is home to 21 tenured and tenure-track faculty members and two research faculty members. Research areas of the department encompass the areas of security, computational biology, machine learning, robotics, systems, algorithms, theory, digital arts, vision, and graphics. The Computer Science department is in the School of Arts & Sciences, and it has strong Ph.D. and M.S. programs and outstanding undergraduate majors. The department is affiliated with Dartmouth's M.D.-Ph.D. program and has strong collaborations with Dartmouth's other schools. Dartmouth College, a member of the Ivy League, is located in Hanover, New Hampshire (on the Vermont border). Dartmouth has a beautiful, historic campus, located in a scenic area on the Connecticut River. Recreational opportunities abound in all four seasons. We seek candidates who have a demonstrated ability to contribute to Dartmouth?s undergraduate diversity initiatives in STEM research, such as the Women in Science Program, E. E. Just STEM Scholars Program, and Academic Summer Undergraduate Research Experience (ASURE). We are especially interested in applicants with a demonstrated track record of successful teaching and mentoring of students from all backgrounds (including first-generation college students, low-income students, racial and ethnic minorities, women, LGBTQ, etc.). Applicants are invited to submit application materials via Interfolio at https://apply.interfolio.com/37189. Upload a CV, research statement, and teaching statement, and request at least four references to upload letters of recommendation, at least one of which should comment on teaching. Email Lorenzo.Torresani at Dartmouth.edu with any questions. Dartmouth College is an equal opportunity/affirmative action employer with a strong commitment to diversity and inclusion. We prohibit discrimination on the basis of race, color, religion, sex, age, national origin, sexual orientation, gender identity or expression, disability, veteran status, marital status, or any other legally protected status. Applications by members of all underrepresented groups are encouraged. Application review will begin January 1, 2017, and continue until the position is filled. From jacob.steinhardt at gmail.com Tue Sep 13 23:22:56 2016 From: jacob.steinhardt at gmail.com (Jacob Steinhardt) Date: Tue, 13 Sep 2016 20:22:56 -0700 Subject: Connectionists: CfP: NIPS workshop on Reliable Machine Learning Message-ID: *Call for PapersReliable Machine Learning in the Wild*Date: December 9th, 2016 Location: Barcelona, Spain (part of the NIPS 2016 workshops) Submission Deadline: November 1st, 2016 Website: https://sites.google.com/site/wildml2016nips/ How can we build systems that will perform well in the presence of novel, even adversarial, inputs? What techniques will let us safely build and deploy autonomous systems on a scale where human monitoring becomes difficult or infeasible? Answering these questions is critical to guaranteeing the safety of emerging high stakes applications of AI, such as self-driving cars and automated surgical assistants. This workshop will bring together researchers in areas such as human-robot interaction, security, causal inference, and multi-agent systems in order to strengthen the field of reliability engineering for machine learning systems. We are interested in approaches that have the potential to provide assurances of reliability, especially as systems scale in autonomy and complexity. We will focus on five aspects ? robustness, awareness, adaptation, value learning, and monitoring -- that can aid us in designing and deploying reliable machine learning systems. Some possible questions touching on each of these categories are given below, though we also welcome submissions that do not directly fit into these categories. *Robustness:* How can we make a system robust to novel or potentially adversarial inputs? What are ways of handling model mis-specification or corrupted training data? What can be done if the training data is potentially a function of system behavior or of other agents in the environment (e.g. when collecting data on users that respond to changes in the system and might also behave strategically)? *Awareness:* How do we make a system aware of its environment and of its own limitations, so that it can recognize and signal when it is no longer able to make reliable predictions or decisions? Can it successfully identify ?strange? inputs or situations and take appropriately conservative actions? How can it detect when changes in the environment have occurred that require re-training? How can it detect that its model might be mis-specified or poorly-calibrated? *Adaptation:* How can machine learning systems detect and adapt to changes in their environment, especially large changes (e.g. low overlap between train and test distributions, poor initial model assumptions, or shifts in the underlying prediction function)? How should an autonomous agent act when confronting radically new contexts? *Value Learning:* For systems with complex desiderata, how can we learn a value function that captures and balances all relevant considerations? How should a system act given uncertainty about its value function? Can we make sure that a system reflects the values of the humans who use it? *Monitoring:* How can we monitor large-scale systems in order to judge if they are performing well? If things go wrong, what tools can help? Organizers: Jacob Steinhardt (Stanford), Dylan Hadfield-Menell (Berkeley), Adrian Weller (Cambridge), David Duvenaud (Toronto), Percy Liang (Stanford) Sponsors: We gratefully acknowledge support from the Open Philanthropy Project, the Center for the Study of Existential Risk, and the Leverhulme Center for the Future of Intelligence. -------------- next part -------------- An HTML attachment was scrubbed... URL: From h.glotin at gmail.com Wed Sep 14 04:00:58 2016 From: h.glotin at gmail.com (Herve Glotin) Date: Wed, 14 Sep 2016 10:00:58 +0200 Subject: Connectionists: Phd and Postdoc positions in Deep Learning for Bio-Soundscape Representation Message-ID: Hi there, CNRS - french research center - is opening at LSIS Toulon 2 positions in Deep Learning in fall 2016: 1 PHD = 'DEEP LEARNING FOR NON HUMAN BIOACOUSTICS, applied to AUTOMATIC SPECIES IDENTIFICATION' 18 months+ POSTDOC = 'DEEP LEARNING for TRACKING OF ACOUSTIC SOURCES, applied to SUBMARINE BIOACOUSTICS' In both grants, the goal of your research will be to improve the current performance of soundscape / bioacoustic pattern detection and classification, at low signal to noise ratio. The objectives here are three-fold: (a) to make the signal representation more robust, (b) to develop classification model more efficient on complex bioacoustic patterns, with supervised and/or unsupervised approaches, and (c) to manage and collect large training data to better model the variability of object categories within terrestrial and/or submarine environments. The usual representations are based on Fourier descriptors, but have limits. We design mid-level or high-level features based on time-frequency segmentation, wavelet and discrete decomposition, compress sensing, non parametric bayesian representation, while developing specific CNN / LSTM Deep Representation Learning. The validation of the models are conducted on real complex soundscape analyses, from cetaceans to birds songs, from bats to dolphins biosonars... It can also include anthropic target. You'll be involved into citizen program, including associations on biodiversity / bird conservation. You'll be working on smartphone systems to integrate the software solution (online or deported). YOUR PROFILE: Machine learning / Data Science or Applied Mathematics / Computer Science, or Electrical Engineering / Signal Processing, Solid mathematics knowledge (especially linear algebra and statistics), Creative and highly motivated, good programming skill (Python, Matlab, C...), Smartphone applications LOCATION: University of Toulon, in the CNRS lab LSIS that is heading the SABIOD.org international project. Toulon campus provides scientific facilities and is located in the beautiful Provence area. LSIS lab actually gathers 260 researchers professors and PhD students in computer science, signal analysis and pattern recognition. Your research will be conducted within collaborations, like National Parks (Port-Cros, La Reunion, Alpin integral reserve...), international labs (CIBRA in Pavia univ., Brisbane univ. in Australia, Cornell univ. USA, Berlin Museum, Victoria univ. Canada, Queen Mary UK, Santiago univ, Chili...). LSIS-DYNI chaired several workshops on machine learning meetings bioacoustics at ICML 2013 and 2014, NIPS 2013, and ICDM 2015. SUBMIT YOUR APPLICATION (A SINGLE .PDF) OR INFORMAL INQUIRIES TO: Pr. Glotin (director): glotin at univ-tln.fr, h.glotin at gmail.com Screening of applications begins in mid sept 2016. Application materials should include a CV (university grades, honors / 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, web site demo, research manuscript / essay). Details / URL = http://sabiod.univ-tln.fr/jobs.html ----- -------------- next part -------------- An HTML attachment was scrubbed... URL: From info at ecmlpkdd2017.org Wed Sep 14 07:11:16 2016 From: info at ecmlpkdd2017.org (ECML-PKDD 2017) Date: Wed, 14 Sep 2016 13:11:16 +0200 Subject: Connectionists: ECML-PKDD 2017 - CALL FOR PAPERS - [Conference Research Track] Message-ID: ############################################################ European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) Skopje, Macedonia, September 18-22, 2017 (http://www.ecmlpkdd2017.org). ############################################################ Submissions are solicited for the 2017 edition of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2017). The conference provides an international forum for the discussion of the latest high-quality research results in all areas related to machine learning and knowledge discovery in databases and other innovative application domains. The 2017 conference will take place in Skopje, Macedonia, 18?22 September 2017. Submissions are invited on all aspects of machine learning, knowledge discovery and data mining, including real-world applications. Following the tradition of ECML-PKDD, we expect high-quality papers in terms of their scientific contribution, rigor, correctness, quality of presentation and reproducibility of experiments. Submission process Electronic submissions will be handled via CMT at the following address: https://cmt.research.microsoft.com/ECMLPKDD2017/. Please note that user accounts in each CMT conference are independent of other conferences, so you will need to create a new account. Abstracts need to be registered by Thursday April 13, 2017 and full submissions will be accepted until Thursday April 20, 2017. Papers must be written in English and formatted according to the Springer LNAI guidelines. Author instructions, style files and copyright form can be downloaded at: http://www.springer.de/comp/lncs/authors.html. The maximum length of papers is 16 pages in this format. Overlength papers will be rejected without review (papers with smaller page margins and font sizes than specified in the author instructions and set in the style files will also be treated as overlength). Up to 10 MB of additional materials (e.g. proofs, audio, images, video, data or source code) can be attached to the submission. Note that the reviewers and the program committee reserve the right to judge the paper solely on the basis of the 16 pages of the paper; looking at any additional material is up to the discretion of the reviewers and is not required. Reviewing process The review process is single-blind (authors identities known to reviewers). Submissions will be evaluated on the basis of technical quality, novelty, potential impact, and clarity. Authors will have the opportunity to point out factual errors, obvious mistakes, or misconceptions by reviewers during a rebuttal phase following the release of initial reviews. Dual submissions policy Papers submitted should report original work. ECML-PKDD 2017 will not accept any paper that, at the time of submission, is under review or has already been accepted for publication in a journal or another conference. Authors are also expected not to submit their papers elsewhere during the review period. The dual submissions policy applies during the whole ECML-PKDD 2017 reviewing period from April 20 to June 22, 2017. Reproducible research papers Authors are encouraged to adhere to the best practices of Reproducible Research (RR), by making available data and software tools for reproducing the results reported in their papers. Authors may flag their submissions as RR and make software and data accessible to reviewers and to the program committee who will verify the accessibility of software and data. Links to data and code will then be inserted in the final version of RR papers. For the sake of persistence and proper authorship attribution, we require the use of standard repository hosting services such as Dataverse, mldata.org, OpenML, etc. for data sets, and mloss.org, Bitbucket, GitHub, etc. for source code. If data or code gets updated after the paper is published, it is important to enable researchers to access the versions that were used to produce the results reported in the paper. Proceedings The conference proceedings will be published by Springer in the Lecture Notes in Artificial Intelligence series (LNAI). In addition to normal conference submissions, papers can be submitted to other tracks: Industrial, Governmental and NGO; Demo; Ph.D.; Nectar; journal track. Accepted papers in all the tracks, including journal track, will be presented at the conference. For information about other tracks, please see the separate call for papers. Important dates Abstract submission deadline: *Thursday April 13, 2017* Paper submission deadline: *Thursday April 20, 2017* Author notification: *Thursday June 22, 2017* Camera ready submission: *Thursday July 6, 2017* Contact For any additional questions you can contact the Program Chairs (Michelangelo Ceci, Jaakko Hollm?n, Ljup?o Todorovski, Celine Vens) at *pc_chairs at ecmlpkdd2017.org * -- Nikola Simidjievski & Dragi Kocev Production & Publicity Chairs of ECML-PKDD 2017 -------------- next part -------------- An HTML attachment was scrubbed... URL: From cgf at isep.ipp.pt Wed Sep 14 07:29:29 2016 From: cgf at isep.ipp.pt (Carlos Ferreira) Date: Wed, 14 Sep 2016 12:29:29 +0100 Subject: Connectionists: CFP: DATA STREAMS TRACK - ACM SAC 2017 (Submission deadline: September 15, 2016) Message-ID: ACM Symposium on Applied Computing The 31th Annual ACM Symposium on Applied Computing in Marrakech, Morocco, April 3 ? 7, 2017. http://www.acm.org/conferences/sac/sac2017/ Data Streams Track http://www.cs.waikato.ac.nz/~abifet/SAC2017/ Call for Papers The rapid development in Big Data information science and technology in general and in growth complexity and volume of data in particular has introduced new challenges for the research community. Many sources produce data continuously. Examples include the Internet of Things (IoT), Smart Cities, Urban Computing, sensor networks, wireless networks, radio frequency identification, health-care devices and information systems, customer click streams, telephone records, multimedia data, scientific data, sets of retail chain transactions, etc. These sources are called data streams. A data stream is an ordered sequence of instances that can be read only once or a small number of times using limited computing and storage capabilities. These sources of data are characterized by being open-ended, flowing at high-speed, and generated by non stationary distributions. TOPICS OF INTEREST We are looking for original, unpublished work related to algorithms, methods and applications on big data streams and large scale machine learning. Topics include (but are not restricted) to: * Real-Time Analytics * Big Data Mining * Data Stream Models * Large Scale Machine Learning * Languages for Stream Query * Continuous Queries * Clustering from Data Streams * Decision Trees from Data Streams * Association Rules from Data Streams * Decision Rules from Data Streams * Bayesian networks from Data Streams * Feature Selection from Data Streams * Visualization Techniques for Data Streams * Incremental on-line Learning Algorithms * Single-Pass Algorithms * Temporal, spatial, and spatio-temporal data mining * Scalable Algorithms * Real-Time and Real-World Applications using Stream data * Distributed and Social Stream Mining * Urban Computing, Smart Cities * Internet of Things (IoT) IMPORTANT DATES (strict) 1. Paper Submission: September 15, 2016 2. Author Notification: November 10, 2016 3. Camera?ready copies: November 25, 2016 PAPER SUBMISSION GUIDELINES Papers should be submitted in PDF. Authors are invited to submit original papers in all topics related to data streams. All papers should be submitted in ACM 2- column camera ready format for publication in the symposium proceedings. ACM SAC follows a double blind review process. Consequently, the author(s) name(s) and address(s) must NOT appear in the body of the submitted paper, and self-references should be in the third person. This is to facilitate double blind review required by ACM. All submitted papers must include the paper identification number provided by the eCMS system when the paper is first registered. The number must appear on the front page, above the title of the paper. Each submitted paper will be fully refereed and undergo a blind review process by at least three referees. The conference proceedings will be published by ACM. The maximum number of pages allowed for the final papers is 6 pages. There is a set of templates to support the required paper format for a number of document preparation systems at: http://www.acm.org/sigs/pubs/proceed/template.html Important notice: 1. Please submit your contribution via SAC 2017 Webpage. 2. Paper registration is required, allowing the inclusion of the paper, poster, or SRC abstract in the conference proceedings. An author or a proxy attending SAC MUST present the paper. This is a requirement for including the work in the ACM/IEEE digital library. No-show of registered papers, posters, and SRC abstracts will result in excluding them from the ACM/IEEE digital library. Student Research Competition Graduate students seeking feedback from the scientific community on their research ideas are invited to submit original abstracts of their research work in areas of experimental computing and application development related to SAC 2017 Tracks. The SRC program is designed to provide graduate students the opportunity to meet and exchange ideas with researcher and practitioners in their areas of interest. All research abstract submissions will be reviewed by researchers and practitioners with expertise in the track focus area to which they are submitted. Authors of selected abstracts will have the opportunity to give poster and oral presentations of their work and compete for three top wining places. The SRC committee will evaluate and select First, Second, and Third place winners. The winners will receive cash awards and SIGAPP recognition certificates during the conference banquet dinner. Authors of selected abstracts are eligible to apply to the SIGAPP Student Travel Award program for support. Graduate students are invited to submit research abstracts (minimum of two pages; maximum of four pages) following the instructions published at SAC 2017 website. Submission of the same abstract to multiple tracks is not allowed. Submissions must address original and unpublished research work related to a SAC track, with emphasis on the innovation behind the research idea. The submission should address the research problem being investigated, the proposed approach and research methodology, and sample preliminary results of the work. In addition, the abstract should reflect on the originality of the work, innovation of the approach, and applicability of the results to real-world problems. All abstracts must be submitted thought the START Submission system. If you encounter any problems with your submission, please contact the Program Coordinator. Carlos Ferreira ISEP | Instituto Superior de Engenharia do Porto Rua Dr. Ant?nio Bernardino de Almeida, 431 4249-015 Porto - PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail at isep.ipp.pt | www.isep.ipp.pt From info at ecmlpkdd2017.org Wed Sep 14 07:11:16 2016 From: info at ecmlpkdd2017.org (ECML-PKDD 2017) Date: Wed, 14 Sep 2016 13:11:16 +0200 Subject: Connectionists: ECML-PKDD 2017 - CALL FOR PAPERS - [Conference Research Track] Message-ID: ############################################################ European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) Skopje, Macedonia, September 18-22, 2017 (http://www.ecmlpkdd2017.org). ############################################################ Submissions are solicited for the 2017 edition of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2017). The conference provides an international forum for the discussion of the latest high-quality research results in all areas related to machine learning and knowledge discovery in databases and other innovative application domains. The 2017 conference will take place in Skopje, Macedonia, 18?22 September 2017. Submissions are invited on all aspects of machine learning, knowledge discovery and data mining, including real-world applications. Following the tradition of ECML-PKDD, we expect high-quality papers in terms of their scientific contribution, rigor, correctness, quality of presentation and reproducibility of experiments. Submission process Electronic submissions will be handled via CMT at the following address: https://cmt.research.microsoft.com/ECMLPKDD2017/. Please note that user accounts in each CMT conference are independent of other conferences, so you will need to create a new account. Abstracts need to be registered by Thursday April 13, 2017 and full submissions will be accepted until Thursday April 20, 2017. Papers must be written in English and formatted according to the Springer LNAI guidelines. Author instructions, style files and copyright form can be downloaded at: http://www.springer.de/comp/lncs/authors.html. The maximum length of papers is 16 pages in this format. Overlength papers will be rejected without review (papers with smaller page margins and font sizes than specified in the author instructions and set in the style files will also be treated as overlength). Up to 10 MB of additional materials (e.g. proofs, audio, images, video, data or source code) can be attached to the submission. Note that the reviewers and the program committee reserve the right to judge the paper solely on the basis of the 16 pages of the paper; looking at any additional material is up to the discretion of the reviewers and is not required. Reviewing process The review process is single-blind (authors identities known to reviewers). Submissions will be evaluated on the basis of technical quality, novelty, potential impact, and clarity. Authors will have the opportunity to point out factual errors, obvious mistakes, or misconceptions by reviewers during a rebuttal phase following the release of initial reviews. Dual submissions policy Papers submitted should report original work. ECML-PKDD 2017 will not accept any paper that, at the time of submission, is under review or has already been accepted for publication in a journal or another conference. Authors are also expected not to submit their papers elsewhere during the review period. The dual submissions policy applies during the whole ECML-PKDD 2017 reviewing period from April 20 to June 22, 2017. Reproducible research papers Authors are encouraged to adhere to the best practices of Reproducible Research (RR), by making available data and software tools for reproducing the results reported in their papers. Authors may flag their submissions as RR and make software and data accessible to reviewers and to the program committee who will verify the accessibility of software and data. Links to data and code will then be inserted in the final version of RR papers. For the sake of persistence and proper authorship attribution, we require the use of standard repository hosting services such as Dataverse, mldata.org, OpenML, etc. for data sets, and mloss.org, Bitbucket, GitHub, etc. for source code. If data or code gets updated after the paper is published, it is important to enable researchers to access the versions that were used to produce the results reported in the paper. Proceedings The conference proceedings will be published by Springer in the Lecture Notes in Artificial Intelligence series (LNAI). In addition to normal conference submissions, papers can be submitted to other tracks: Industrial, Governmental and NGO; Demo; Ph.D.; Nectar; journal track. Accepted papers in all the tracks, including journal track, will be presented at the conference. For information about other tracks, please see the separate call for papers. Important dates Abstract submission deadline: *Thursday April 13, 2017* Paper submission deadline: *Thursday April 20, 2017* Author notification: *Thursday June 22, 2017* Camera ready submission: *Thursday July 6, 2017* Contact For any additional questions you can contact the Program Chairs (Michelangelo Ceci, Jaakko Hollm?n, Ljup?o Todorovski, Celine Vens) at *pc_chairs at ecmlpkdd2017.org * -- Nikola Simidjievski & Dragi Kocev Production & Publicity Chairs of ECML-PKDD 2017 -------------- next part -------------- An HTML attachment was scrubbed... URL: From jong.de.edwin at gmail.com Wed Sep 14 16:16:33 2016 From: jong.de.edwin at gmail.com (Edwin de Jong) Date: Wed, 14 Sep 2016 22:16:33 +0200 Subject: Connectionists: New *sequence learning* data set available: MNIST digits as stroke sequences Message-ID: Dear colleagues, A new data set for the study of sequence learning algorithms is available as of today. The data set consists of pen stroke sequences that represent handwritten digits, and was created based on the MNIST handwritten digit data set. MNIST stroke sequence data set: https://github.com/edwin-de-jong/mnist-digits-stroke-sequence-data/wiki/MNIST-digits-stroke-sequence-data The code project that was used to create the data set is available as well: https://github.com/edwin-de-jong/mnist-digits-as-stroke-sequences/wiki/MNIST-digits-as-stroke-sequences-(code) The 70000 digit images were thresholded and thinned, yielding skeletons of the images. Using a TSP algorithm, hypothetical pen stroke sequences were then inferred. The resulting data set provides a sizeable and diverse test bed, and can serve as a benchmark data set for evaluating and comparing sequence learning algorithms. Further details can be found at the links above; please feel free to contact me in case of any questions or suggestions. Best regards, Dr. Edwin D. de Jong __ -------------- next part -------------- An HTML attachment was scrubbed... URL: From Michael.Zock at lif.univ-mrs.fr Wed Sep 14 16:11:13 2016 From: Michael.Zock at lif.univ-mrs.fr (Michael Zock) Date: Wed, 14 Sep 2016 22:11:13 +0200 Subject: Connectionists: 2nd and Final Call for 'Cognitive Aspects of the Lexicon (CogALex-V), workshop co-located with Coling Message-ID: <57D9AEE1.3020602@lif.univ-mrs.fr> 2nd and Final Call for CogALex Cognitive Aspects of the Lexicon (CogALex-V) https://sites.google.com/site/cogalex2016/home Workshop co-lated with COLING (the 26th International Conference on Computational Linguistics, Osaka, Japan), December 12, 2016 Invited speaker: Chris Biemann (LT + HCC, Universit?t Hamburg , Germany) We are pleased to announce the 5th Workshop on 'Cognitive Aspects of the Lexicon' (Cogalex-V), taking place just before COLING (Osaka, Japan), December 12, 2016. 1 Context and background The way we look at the lexicon (creation and use) has changed dramatically over the past 30 years. While in the past being considered as an appendix to grammar, the lexicon has now moved to centre stage. Indeed, there is hardly any task in NLP which can be conducted without it. Also, rather than considering it as a static entity (database view), dictionaries are now viewed as dynamic networks, akin to the human brain, whose nodes and links (connection strengths) may change over time. Linguists work on products, while psychologists and computer scientists deal with processes. They decompose the task into a set of subtasks, i.e. modules between which information flows. There are inputs, outputs and processes in between. A typical task in language processing is to go from meanings to sound or vice versa, the two extremes of language production and language understanding. Since this mapping is hardly ever direct, various intermediate steps or layers (syntax, morphology) are necessary. Most of the work done by psycholinguists has dealt with the information flow from meaning (or concepts) to sound or the other way around. What has not been addressed though is the creation of a map of the mental lexicon, that is a represention of the way how words are organized or connected. In this respect WordNet and Roget's Thesaurus are probably closest to what one can expect these days. This being said, to find a word in a resource one has to reduce the search space (entire lexicon) and this is done via the knowledge one has at the onset of search. While the information stored in the lexicon is a product, its access is clearly a (cognitive, i.e. knowledge-based) process. 1.1 Goal The goal of COGALEX is to provide a forum for researchers in NLP, psychologists, computational lexicographers and users of lexical resources to share their knowledge and needs concerning the construction, organization and use of a lexicon by people (lexical access) and machines (NLP, IR, data-mining). Like in the past (2004, 2008, 2010, 2012 and 2014), we will invite researchers to address various unsolved problems, by putting this time stronger emphasis though on distributional semantics (DS). Indeed, we would like to see work showing the relevance of DS as a cognitive model of the lexicon. The interest in distributional approaches has grown considerably over the last few year, both in computational linguistics and cognitive sciences. A further boost has been provided by the recent hype around deep learning and neural embeddings. While all these approaches seem to have great potential, their added value to address cognitive and semantic aspects of the lexicon still needs to be shown. This workshop is about possible enhancements of lexical resources and electronic dictionaries, as well as on any aspect relevant to the achieve a better understanding of the mental lexicon and semantic memory.We solicit contributions including but not limited to the topics listed here below, topics, which can be considered from any of the following points of view: * (computational, corpus) linguistics, * neuro- or psycholinguistics (tip of the tongue problem, associations), * network related sciences (sociology, economy, biology), * mathematics (vector-based approaches, graph theory, small-world problem), etc. We also plan to organize a ?friendly competition? for corpus-based models of lexical networks and navigation, i.e. lexical access (see below). 1.2 Possible Topics 1.2.1 Analysis of the conceptual input of a dictionary user * What does a language producer start out with and how does this input relate to the target form? (meaning, collocation, topically related, etc.) * What is in the authors' minds when they are generating a message and looking for a word? * What does it take to bridge the gap between this input and the desired output (target word)? 1.2.2 The meaning of words * Lexical representation (holistic, decomposed) * Meaning representation (concept based, primitives) * Distributional semantics (count models, neural embeddings, etc. ) * Neurocomputational theories of content representation. 1.2.3 Structure of the lexicon * Discovering structures in the lexicon: formal and semantic point of view (clustering, topical structure) * Evolution, i.e. dynamic aspects of the lexicon (changes of weights) * Neural models of the mental lexicon (distribution of information concerning words, organization of words) 1.2.4 Methods for crafting dictionaries or indexes * Manual, automatic or collaborative building of dictionaries and indexes (crowd-sourcing, serious games, etc.) * Impact and use of social networks (Facebook, Twitter) for building dictionaries, for organizing and indexing the data (clustering of words), and for allowing to track navigational strategies, etc. * (Semi-) automatic induction of the link type (e.g. synonym, hypernym, meronym, association, collocation, ...) * Use of corpora and patterns (data-mining) for getting access to words, their uses, combinations and associations 1.2.5 Dictionary access (navigation and search strategies), interface issues, * Search based on sound, meaning or associations * Search (simple query vs. multiple words) * Search-space determination based on user's knowledge, meta-knowledge and cognitive state (information available at the onset, knowledge concerning the relationship between the input and the target word, ...) * Context-dependent search (modification of users? goals during search) * Navigation (frequent navigational patterns or search strategies used by people) * Interface problems, data-visualization * Creative ways of getting access to and using word associations (reading between the lines, subliminal communication). 2 Description of the shared tasks associated with the workshop. As part of the workshop, we propose a shared task concerning the corpus-based identification of semantic relations. The goal of this ?competition between gentlemen" is less the discovery of the best system, as the testing of the relative efficiency of different distributional models and other corpus-based approaches on a challenging semantic task. We will provide the training and test data, and the participants are expected to submit a short paper (4 pages) describing their approach and evaluation results (using the official scoring scripts), together with the output produced by their system on the test data. For more details see : https://sites.google.com/site/cogalex2016/home/shared-task 3 INVITED SPEAKER /Chris Biemann/, well known among other things for his work on graph-based NLP, has kindly accepted to give the invited talk. Leader of the LT research group in Darmstadt, Chris is now affiliated with the Language Technology and Human-Centered Computing group of the university of Hamburg. 4 Deadlines. Workshop papers * September 25: Submission deadline forpapers * October 16: Author notification * October 30: Camera ready due by Authors * November 6: Proceedings due by Workshop Organisers to Workshop & Publication Chairs. * December 12 : Workshop Shared task * September 26: Expression ofinterest (send message to : esantus at gmail.com) * October 15: Submission of system description (4+1 pages) and system output * October 25: Author notification * October 30: Camera ready due by Authors 5 Submission The submissions should be written in English and be anonymized for review. They must comply with the style-sheets provided by Coling: http://coling2016.anlp.jp/#instructions * Long papers may consist of 8 pages of content, plus 2 pages for references; * Short paper may consist of up to 4 pages of content, plus 2 pages for references * The respective final versions may be up to 9 pages for long papers and 5 pages for short ones. In both cases the number of pages for references is limited to 3 pages. Papers should be in PDF format and have to be submitted electronically via the START submission system (https://www.softconf.com/coling2016/ CogALex-V/). You probably have to register first, and then choose: submission, i.e. (https://www.softconf.com/coling2016/CogALex-V/user/scmd.cgi?scmd=submitPaperCustom&pageid=0). 6 Organizers. * Michael Zock (LIF, CNRS, Aix-Marseille University, Marseille, France) * Alessandro Lenci (Computational Linguistics Laboratory, University of Pisa, Italy) * Stefan Evert (FAU, Erlangen-N?rnberg, Germany) 7 Contact persons For general questions, please get in touch with Michael Zock (michael.zock at lif.univ-mrs.fr), for questions concerning the shared task, send an e-mail to Stefan Evert (stefan.evert at fau.de). 8 Program committee * Bieman Chris (Universit?t Hamburg, Germany) * Babych, Bogdan (University of Leeds, UK) * Brysbaert, Marc (Experimental Psychology, Ghent University, Belgium) * Cristea Dan ("Al. I. Cuza" University, Iasi, Romania) * deDeyne Simon (University of Adelaide, Australia) * de Melo Gerard (IIIS, Tsinghua University, Beijing, China) * Evert, Stefan (University of Erlangen, Germany) * Ferret Olivier (CEA LIST, France) * Fontenelle Thierry (CDT, Luxemburg) * Gala Nuria (University of Aix-Marseille, France) * Geeraerts Dirk (University of Leuven, Belgium) * Granger Sylviane (Universit? Catholique de Louvain, Belgium) * Grefenstette Gregory (Inria, Paris, France) * Hirst Graeme (University of Toronto, Canada) * Hovy Ed (CMU, Pittsburgh, USA) * Hsieh, Shu-Kai (National Taiwan University, Taipei, Taiwan) * Joyce Terry (Tama University, Kanagawa-ken, Japan) * Lafourcade, Matthieu (LIRMM, universit? de Montepellier, France * Lapalme Guy (RALI, University of Montreal, Canada * Lebani Gianluca (University of Pisa, Italy) * Lenci Alessandro (University of Pisa, Italy) * L'Homme Marie Claude (University of Montreal, Canada) * Mititelu Verginica (RACAI, Bucharest, Romania) * Navigli, Roberto (Sapienza, Rome, Italy) * Paradis Carita (Centre for Languages and Literature Lund University, Sweden) * Pihlevar, Taher (university of Cambridge, UK) * Pirrelli, Vito (ILC, Pisa, Italy) * Polgu?re Alain (ATILF-CNRS, Nancy, France) * Purver, Matthew (King's College, London, UK) * Ramisch Carlos (AMU, Marseille, France) * Rayson Paul (UCREL, university of Lancaster, UK * Rosso, Paol (NLEL, Universitat Polit?cnica de Val?ncia, Spain) * Sahlgren, Magnus (Gavagai Inc. & SICS, Sweden) * Schulte im Walde Sabine (University of Stuttgart, Germany) * Schwab Didier (LIG, Grenoble, France) * Sharoff Serge (University of Leeds, UK) * Stella Massimo (Institute for Complex Systems Simulation, university of Southhampton, UK) * Tokunaga Takenobu (TITECH, Tokyo, Japan) * Tufis Dan (RACAI, Bucharest, Romania) * Zarcone, Alessandra (Saarland University, Germany) * Zock Michael (LIF-CNRS, Marseille, France) -- ------------------------------------------------ Michael ZOCK Aix-Marseille Universit?, CNRS & LIF, UMR 7279, 163 Avenue de Luminy F-13288 Marseille / France Mail: michael.zock at lif.univ-mrs.fr Tel.: +33 (0) 4 91 82 94 88 Secr.: +33 (0) 4 91 82 90 70 Fax: +33 (0) 4 91 82 92 75 Web: http://pageperso.lif.univ-mrs.fr/~michael.zock/ ------------------------------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From erik at oist.jp Thu Sep 15 03:28:35 2016 From: erik at oist.jp (Erik De Schutter) Date: Thu, 15 Sep 2016 07:28:35 +0000 Subject: Connectionists: Postdoctoral positions in reconstruction, analyzing and modeling dendritic morphology and growth Message-ID: <28381BA3-ED1B-4C99-8BA8-411067BCCD56@oist.jp> Postdoctoral researcher and staff scientist positions are available in the Computational Neuroscience Unit of Prof. Erik De Schutter at the Okinawa Institute of Science and Technology Graduate University , Japan. The project studies morphology and growth of neuronal dendrites in the olivocerebellar system from the perspective of neuron populations and considers the relations between neighboring dendrites explicitly (Context-aware modeling of neuronal morphologies ). One position for a postdoc with a neuroscience background to reconstruct neurons using semi-automated methods and analyze the morphologies obtained. Projects include reconstruction of single neurons based on STED microscopy and of populations of neurons using confocal imaging. Experience in neural reconstruction is essential, additional experience in microscopy and/or electrophysiology is a plus. One position for a postdoc with a computational neuroscience or computer science background to model of neural morphology and develop necessary software. Experience in modeling neurons with dendrites or in modeling growth in general required. Successful candidates will collaborate with scientists at OIST and abroad in addition to the daily interaction with other researchers and students in the lab who are working on cerebellar modeling projects, analyzing cerebellar recordings or developing software. We offer attractive financial and working conditions in an English language graduate university that emphasizes interdisciplinary research, located on the beautiful subtropical island of Okinawa. Send curriculum vitae, a summary of research interests and experience, and the names of three referees to Prof. Erik De Schutter at erik at oist.jp Prof. Erik De Schutter Computational Neuroscience Unit Okinawa Institute of Science and Technology 1919-1 Tancha, Onna-Son Okinawa 904-0495 JAPAN phone: +81-98-966-8727 fax: +81-98-966-8718 erik at oist.jp http://groups.oist.jp/cnu -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 3682 bytes Desc: not available URL: From martaruizcostajussa at gmail.com Thu Sep 15 04:11:33 2016 From: martaruizcostajussa at gmail.com (Marta Ruiz) Date: Thu, 15 Sep 2016 10:11:33 +0200 Subject: Connectionists: 1st Call for papers: special session on "Deep and kernel methods: best of two worlds" at ESANN 2017 Message-ID: Call for papers: special session on "Deep and kernel methods: best of two worlds" at ESANN 2017 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2017) *26-28 April 2017*, Bruges (Belgium) Multilayer neural networks have experienced a rebirth in the data analysis field, displaying impressive results, extending even to classical artificial intelligence domains, such as game playing, computer vision, natural language and speech processing. The versatility of such methods have lead deep (semi)-parametric models to get over well-established learning methods, like kernel machines or classical statistical techniques. However, their training is a delicate and costly optimization problem that raises many practical challenges. On the other hand, kernel methods usually involve solving a tractable convex problem and are able to handle non-vectorial data directly, leading to a higher expressive power. Their main drawback is arguably their complexity being dependent on the number of data points, both at training and model evaluation times. A natural and emerging field of research is given by their hybridization, which can done in many fruitful ways. Many ideas from the deep learning field can be transferred to the kernel framework and viceversa. This special session aims at all aspects of deep architectures, be theoretical or methodological developments, comparative analyses, or applications. A special emphasis is given to new ideas to bridge the gap between the fields of deep and kernel learning, as well as the understanding of their respective weak and strong points. The topics of the session include, but are not limited to, - Applications of deep architectures in data representation and analysis, including structured or non-vectorial inputs or outputs - Natural language and speech processing; structured relationships among data; scalability/efficiency of deep neural networks and large-scale kernel machines - Heterogeneous data and meta-data; applications in neuroscience, computer vision, (bio)acoustic signals and mechanisms - Statistical or stability analysis, visualization of learning, generalization bounds - Novel deep(er) architectures/algorithms for data representation and learning (using kernels or not) - Recursive and iterative kernels and their relation to deep neural architectures - Emulation of multilayer machines by shallow architectures and vice versa - Randomized (approximate) feature maps to scale-up kernel methods - Derivation of efficient layer-by-layer algorithms for training such networks; reductions in the computational complexity - Comparisons of deep architectures to shallow architectures SUBMISSION INFO Submitted papers will be reviewed according to the ESANN reviewing process and evaluated on their scientific value: originality, technical correctness, and clarity. Tutorial-like contributions are also welcome provided they add a new perspective on the field. IMPORTANT DATES: Paper submission deadline : 19 November 2016 Notification of acceptance : 31 January 2017 ESANN conference : 26-28 April 2017 ORGANISERS Llu?s A. Belanche, Marta R. Costa-juss? Universitat Polit?cnica de Catalunya (Barcelona, Spain) -------------- next part -------------- An HTML attachment was scrubbed... URL: From yashar at uoregon.edu Thu Sep 15 11:54:55 2016 From: yashar at uoregon.edu (Yashar Ahmadian) Date: Thu, 15 Sep 2016 08:54:55 -0700 Subject: Connectionists: Tenure-Track Position in Computational Neuroscience, University of Oregon Message-ID: *Tenure track position in Computational Neuroscience* University of Oregon Departments of Mathematics and Biology (http://math.uoregon.edu/ ht tp://biology.uoregon.edu/) Institute of Neuroscience (http://www.neuro.uoregon.edu/) The Departments of Biology and Mathematics and the Institute of Neuroscience at the University of Oregon announce a tenure track faculty position in computational neuroscience at the rank of assistant professor with ultimate department and institute affiliations flexible. Theorists seeking synergistic interactions with experimentalists in design, analysis and interpretation of research linking gene function, neuronal activity and behavior in model organisms and humans are especially encouraged to apply. This new position is part of an integrated effort to strengthen research at the nexus of mathematics and biology at the University of Oregon. It also advances a broader ?Neurons to Minds? initiative that includes multiple new positions in systems and cognitive neuroscience to accelerate discovery in the neuronal basis of behavior and cognition. Minimum qualifications for candidates are a Ph.D. in an appropriate field (e.g. neuroscience, biology, mathematics, physics, electrical engineering, statistics, computer science, etc.), commitment to excellent teaching at the undergraduate and graduate levels, and an outstanding research record. Candidates should have the ability to work effectively within a diverse community. Applications will be received online at https://www.mathjobs.org/jobs/UO/IONMATHBIO. Candidates are asked to submit a cover letter, a curriculum vitae including a publication list, a statement of research accomplishments and future research plans, a description of teaching experience and philosophy, and three letters of recommendation (sent independently). Submission of 1-3 selected reprints is encouraged. To be assured of consideration, application materials should be uploaded by *November 15, 2016, but the position will remain open until filled*. Requests for information can be sent to Dr. Shawn Lockery, Chair, Computational Neuroscience Search Committee (shawn at uoregon.edu). *The University of Oregon is an equal opportunity, affirmative action institution committed to cultural diversity and compliance with the ADA. The University encourages all qualified individuals to apply, and does not discriminate **on the basis of any protected status, including veteran and disability status.* *---------------------------------------------* *Yashar Ahmadian* *Institute of Neuroscience* Departments of Biology and Mathematics *University of Oregon* *http://uoneuro.uoregon.edu/ahmadian/index.php * -------------- next part -------------- An HTML attachment was scrubbed... URL: From dpal at yahoo-inc.com Fri Sep 16 10:26:01 2016 From: dpal at yahoo-inc.com (David Pal) Date: Fri, 16 Sep 2016 14:26:01 +0000 (UTC) Subject: Connectionists: New research positions at Yahoo Research in New York City References: <1685084051.899221.1474035961305.ref@mail.yahoo.com> Message-ID: <1685084051.899221.1474035961305@mail.yahoo.com> Yahoo Research is growing its strategic research teams to enable the company to build new products and platforms that our customers need, now and in the future. We have exciting job openings in several technical focus areas that are located in our New York City office located one block from Times Square. We hire the best scientific minds who like to roll up their sleeves, make new discoveries and contribute to the success of the business. We are looking for Research Scientists with a PhD degree in Computer Science, Electrical Engineering or Mathematical Optimization. Our scientists specialize in designing and building scalable and reliable distributed and parallel systems that serve all the aspects of big data like data mining, optimization, machine learning, computational economics and analytics. We design innovative algorithms to push the capacity, performance and reliability of our platforms, exploit novel hardware and software architectures, and evaluate the impact in Web-scale production settings. We actively contribute to the scientific and open source communities in foundations of Computer Science, Machine Learning, Mathematical Optimization and Computational Economics. Here are some reasons to explore this opportunity:1. We have a huge number of research problems to solve that lie on the intersection of Optimization, Machine Learning and Computational Economics. If you are an expert in one of these fields and want to expand your research profile this is an ideal place for you.2. We work on game changing products and solutions, you can quickly see how your research ideas and algorithms influence revenue and user engagement.3. We care about you continuing your fundamental research, publishing papers and keeping track of the latest technologies developed in your respective field. Responsibilities Include: ? Deep dive into the data to understand and apply patterns, while maintaining a sense of the big picture.? Work closely with colleagues on the engineering team to put research results into action.? Provide thought leadership to guide the direction of Yahoo products and services. ? Push your own research agenda and look to influence our products and services with your expertise. Required Skills and Qualifications:? PhD in Computer Science, Electrical Engineering or Mathematical Optimization.? Strong research track record (academic or industrial) in one of the following areas: Mathematical Optimization and Algorithm Design, Data Analytics, Machine Learning, Computational Economics (auctions, pricing, mechanism design) or related areas.? Strong design and implementation skills in Java or C++. Experience with large-scale production code development a plus. ? Ability to conduct research that is justified and guided by business opportunities.? Strong communication and presentation skills Please send your CV and a short letter of interest to Maxim Sviridenko (sviri at yahoo-inc dot com). ?David Pal Research Scientist M: +1 (646) 206-4832? 229 West 43rd Street, Floor 14, New York, NY 10036 ? -------------- next part -------------- An HTML attachment was scrubbed... URL: From bobak.shahriari at gmail.com Fri Sep 16 13:53:49 2016 From: bobak.shahriari at gmail.com (Bobak Shahriari) Date: Fri, 16 Sep 2016 17:53:49 +0000 Subject: Connectionists: [CFP] NIPS 2016 workshop on Bayesian optimization -- Submission deadline: October 16 In-Reply-To: References: Message-ID: Hello everyone, Apologies for inevitable cross-postings. We are pleased to announce another installment of the Bayesian optimization workshop! This year our theme is Black-box optimization and Beyond (see below for a description). Please visit http://bayesopt.com/ for more details. Hope to see you there! ============================================== Call for Papers Bayesian Optimization: Black-box Optimization and Beyond Date: December 10, 2016 Location: Barcelona, Spain (part of the NIPS 2016 workshops) Submission Deadline: *October 16, 2016* Website: http://bayesopt.com/ ============================================== ### Important dates: Submission deadline: 16 October (11:59 pm PST) Author notification: 2 November Camera-ready: 4 December ### Abstract: Classically, Bayesian optimization has been used purely for expensive single-objective black-box optimization. However, with the increased complexity of tasks and applications, this paradigm is proving to be too restricted. Hence, this year?s theme for the workshop will be ?black-box optimization and beyond?. Among the recent trends that push beyond BO we can briefly enumerate: - Adapting BO to not-so-expensive evaluations. - ?Open the black-box? and move away from viewing the model as a way of simply fitting a response surface, and towards modelling for the purpose of discovering and understanding the underlying process. For instance, this so-called grey-box modelling approach could be valuable in robotic applications for optimizing the controller, while simultaneously providing insight into the mechanical properties of the robotic system. - ?Meta-learning?, where a higher level of learning is used on top of BO in order to control the optimization process and make it more efficient. Examples of such meta-learning include learning curve prediction, Freeze-thaw Bayesian optimization, online batch selection, multi-task and multi-fidelity learning. - Multi-objective optimization where not a single objective, but multiple conflicting objectives are considered (e.g., prediction accuracy vs training time). ### Invited speakers and panelists: - Joshua Knowles (University of Birmingham) - Jasper Snoek (Twitter) - Marc Toussaint (University of Stuttgart) - Roman Garnett (Washington University in St. Louis) - Will Welch (University of British Columbia) - Katharina Eggensperger (University of Freiburg) ### Organizers: - Roberto Calandra (UC Berkeley) - Bobak Shahriari (University of British Columbia) - Javier Gonzalez (Amazon) - Frank Hutter (University of Freiburg) - Ryan P. Adams (Harvard University) Looking forward to seeing many of you in Barcelona! Roberto, Bobak, Javier, Frank, and Ryan -------------- next part -------------- An HTML attachment was scrubbed... URL: From mvzaanen at uvt.nl Sat Sep 17 04:37:44 2016 From: mvzaanen at uvt.nl (Menno van Zaanen) Date: Sat, 17 Sep 2016 10:37:44 +0200 Subject: Connectionists: Final call for participation ICGI 2016 Message-ID: <20160917083744.GD1401@pinball.uvt.nl> Apologies for cross-posting ================================ CALL FOR PARTICIPATION ICGI 2016 5-7 October 2016 ================================ icgi2016.tudelft.nl SCOPE AND LOCATION ICGI 2016 is the 13th edition of the International Conference on Grammatical Inference series, held every two years. The conference will be held at Delft University of Technology; in Delft, the Netherlands, from October 5-7, 2016. Delft is one of the most beautiful and historic cities in the world, situated in the central (western) part of the Netherlands. The city is directly accessible by train from Schiphol airport (a large international airport near Amsterdam). The conference will be hosted in the "Mekelzaal", a beautiful historic venue in a small science museum at the university campus. AREAS OF INTEREST The conference is on grammatical inference. Key interests are machine-learning methods applied to discrete combinatorial structures such as strings, trees, or graphs, and algorithms for learning symbolic models such as grammars, automata, Markov models, or pattern languages. The conference seeks to provide a forum for presentation and discussion of original research papers on all aspects of grammatical inference. A full program can be found on the website: icgi2016.tudelft.nl INVITED SPEAKERS - Borja Balle - Hendrik Blockeel - Valentin Spitkovsky CONFERENCE FORMAT The conference will include plenary, work in progress presentations, and invited talks. REGISTRATION http://icgi2016.tudelft.nl/#register We are looking forward to seeing you in Delft in October. Organizing committee: Rick Smetsers Sicco Verwer Menno van Zaanen From pkordjam at tulane.edu Sat Sep 17 22:01:08 2016 From: pkordjam at tulane.edu (Kordjamshidi, Parisa) Date: Sun, 18 Sep 2016 02:01:08 +0000 Subject: Connectionists: Postdoc in Machine Learning and NLP at Tulane University Message-ID: Dear Colleagues, I am looking for a postdoctoral fellow to work with me in the areas of machine learning and natural language processing, at the computer science department of Tulane university. The goal of this position is to develop structured machine learning models for extraction of spatial semantics form natural language and extending this to exploit the visual information, that is, images aligned with text. The models will be developed using a declarative learning based programming (DeLBP) framework using Java/Scala. The candidate, if interested, will collaborate in developing the DeLBP language itself too. This position entails excellent training opportunities in machine learning, natural language processing, combining various modalities and grounding language in perception. The current funding is for two years. QUALIFICATIONS Knowledge in machine learning, artificial intelligence, natural language processing, Publication record with peer-reviewed publications, PhD in computer science or related area, Experience/interest in open source software development and fluency in programming languages such as Java and Scala are preferred. APPLICATION INSTRUCTIONS Candidates must apply via Interfolio here https://apply.interfolio.com/37114, and provide the following: CV, cover letter, and at least three letters of recommendation. To receive full consideration, applications should be received by Friday, October 14th. Tulane University is an equal employment opportunity/affirmative action/persons with disabilities/veterans employer committed to excellence through diversity. Tulane will not discriminate against individuals with disabilities or veterans. All eligible candidates are encouraged to apply. I welcome any inquiries about the position, please Email me at pkordjam at tulane.edu. Thanks, Parisa Kordjamshidi, Assistant professor Departments of Computer Science Tulane University Homepage -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.biehl at rug.nl Sun Sep 18 04:17:08 2016 From: m.biehl at rug.nl (Michael Biehl) Date: Sun, 18 Sep 2016 10:17:08 +0200 Subject: Connectionists: CFP: special session on "Biomedical data analysis in translational research..." Message-ID: *Call for papers: Special Session at ESANN 2017* "Biomedical data analysis in translational research: integration of expert knowledge and interpretable models" *ESANN 2017,* *26-28 April 2017*, *Bruges (Belgium) * 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning *Session organizers* *Gyan Bhanot (Rutgers University, New Jersey, USA)* *Michael Biehl (University of Groningen, The Netherlands)* *Thomas Villmann (Univ. of Applied Sciences Mittweida, Germany)* *Dietlind Z?hlke (Seven Principles, Germany)* New technologies in various fields of biomedical research have led to a dramatic increase of the amount of electronic data that is available. Not only is the number of patients or amount of disease specific data increasing, but so is the structural complexity of the data, in terms of its dimensionality, multi-modality and inhomogeneity. A significant problem, recognized by both the bio-medical and computational community, is the lack of coordination among researchers in these disparate communities. On the one hand, integration of expert knowledge is instrumental for successful data analysis and modelling. On the other hand, methods and models should be transparent and interpretable in order to facilitate fruitful trans-disciplinary collaboration. This special session is meant to attract researchers who develop, investigate, or apply methods of machine learning and statistics in biomedical data analysis, experts from knowledge representation and integration as well as bio-medical researchers with a strong interest in computation and interpretable models. Topics include, but are not restricted to: ? Structured, inhomogeneous and multi-modal biomedical data ? Feature selection and identification of biomarkers ? Interpretable systems for diagnosis and classification ? Generative models of bio-medical processes ? Visual analytics and data mining ? Big data mining for clinical impact *Submission:* Submitted papers will be reviewed according to the ESANN reviewing process and evaluated based on their scientific value: originality, technical correctness, and clarity. For further information, see the conference web pages. *Important dates:* Paper submission deadline : 19 November 2016 Notification of acceptance : 31 January 2017 ESANN conference : 26-28 April 2017 ------------------------ Michael Biehl Johann Bernoulli Institute for Mathematics and Computer Science P.O. Box 407, 9700 AK Groningen The Netherlands www.cs.rug.nl/~biehl m.biehl at rug.nl -------------- next part -------------- An HTML attachment was scrubbed... URL: From jdrugo at gmail.com Sun Sep 18 12:15:02 2016 From: jdrugo at gmail.com (Jan Drugowitsch) Date: Sun, 18 Sep 2016 12:15:02 -0400 Subject: Connectionists: Postdoctoral fellowship in computational neuroscience at Harvard Message-ID: Dear all, Jan Drugowitsch (Department of Neurobiology, Harvard) and Sam Gershman (Department of Psychology, Harvard) are seeking a postdoctoral fellow to work on a project combining psychophysics, computational modeling, and clinical studies. The project focuses on visual structure discovery, using motion perception as a model system. Our goal is to understand how neural circuits represent and reason about complex combinatorial structures, and how these neural circuits break down in autism. Candidates must have a strong background in Bayesian modeling and computational neuroscience. Experience with visual psychophysics experiments is desirable but not essential. Applicants should send a CV and statement of research interests to Jan Drugowitsch (Jan_Drugowitsch at hms.harvard.edu). Applications will be reviewed until the position is filled. Best, Jan Drugowitsch Assistant Professor in Neurobiology Harvard Medical School From mklados at gmail.com Sun Sep 18 14:55:04 2016 From: mklados at gmail.com (Manousos Klados) Date: Sun, 18 Sep 2016 14:55:04 -0400 Subject: Connectionists: Online Webinar in Brain Networks (hands-on) Message-ID: Dear colleagues, please, accept my advanced apologies for any multiple cross-postings..., As a part of SAN 2016 conference (http://applied-neuroscience.org/san2016) I am organizing a hands-on workshop in Brain Networks on Thursday 6 OCT. This workshop aims to present some novel processing approaches, as well as different ways for visualizing the human connectome and some real studies. After participating in this workshop you will have the ability: - to analyze connectivity using graph theoretical models - to reduce the dimension and consequently the computation complexity of brain networks - to visualize with different ways the human connectome - to apply all these analyses to your data. Considering the huge amount of emails I received asking me for an online version of the workshop, I made an online webinar which is going to run in parallel with the live workshop. *After the first round of emails, few places are left and I am not planning to perform the same workshop in the near future. * You can reserve your seat as well as find more information about the programme in http://app.webinarsonair.com/register/?uuid=7961a35f44ab4cc2a3596492e7fc1ee1 If you need more information please don't hesitate to come in touch with me. Best wishes Manousos Klados -------------- next part -------------- An HTML attachment was scrubbed... URL: From d.goodman at imperial.ac.uk Sun Sep 18 22:33:18 2016 From: d.goodman at imperial.ac.uk (Dan Goodman) Date: Mon, 19 Sep 2016 03:33:18 +0100 Subject: Connectionists: Brian 2.0 release Message-ID: We are very pleased to announce the release of version 2.0 of the Brian neural network simulator. Brian is a free, open source simulator for spiking neural networks. It is written in the Python programming language and is available on almost all platforms. We believe that a simulator should not only save the time of processors, but also the time of scientists. Brian is therefore designed to be easy to learn and use, highly flexible and easily extensible. You can learn more about Brian at our website (http://briansimulator.org). You can also try out Brian from your web browser, without having to install any software, using our interactive demo (http://mybinder.org/repo/brian-team/brian2-binder/notebooks/demo.ipynb). Major new features in 2.0 ------------------------- * Much more flexible model definitions. The behaviour of all model elements can now be defined by arbitrary equations specified in standard mathematical notation. * Code generation as standard. Behind the scenes, Brian automatically generates and compiles C++ code to simulate your model, making it much faster. * "Standalone mode". In this mode, Brian generates a complete C++ project tree that implements your model. This can be then be compiled and run entirely independently of Brian. This leads to both highly efficient code, as well as making it much easier to run simulations on non-standard computational hardware, for example on robotics platforms. * Multicompartmental modelling. * Python 2 and 3 support. That's just a small fraction of the new features in 2.0. For the full list, see http://brian2.readthedocs.io/en/stable/introduction/release_notes.html. Upgrading from Brian 1.4 ------------------------ Brian 2 is a rewrite from scratch, and introduces some backwards incompatible changes. In most cases, these should be relatively simple. We've written a detailed guide on how to update your simulations: http://brian2.readthedocs.io/en/stable/introduction/changes.html. Note that you can have both Brian 1 and Brian 2 installed simultaneously, so you can switch gradually. Thanks ------ Brian 2 was written by Marcel Stimberg, Dan Goodman and Romain Brette. Do please remember to cite Brian if you use it for your research. We would also like to thank the large number of users (over 40) who contributed code, bug reports, etc. From dengdehao at gmail.com Mon Sep 19 06:27:43 2016 From: dengdehao at gmail.com (Teng Teck Hou) Date: Mon, 19 Sep 2016 18:27:43 +0800 Subject: Connectionists: [IJCNN 2017] Upcoming deadlines for Tutorials and Workshop Proposals Message-ID: <002d01d21260$7c93ff40$75bbfdc0$@gmail.com> [Apologies for cross-postings] ############################################################ International Joint Conference on Neural Networks May 14-19, 2017, Anchorage, Alaska, USA http://www.ijcnn.org/ ##################### Important Dates ###################### * Tutorial and Workshop Proposals October 15, 2016 * Paper Submission November 15, 2016 * Paper Decision Notification January 20, 2017 * Camera-Ready Submission ebruary 20, 2017 #################### UPCOMING DEADLINES #################### CALL FOR WORKSHOPS http://www.ijcnn.org/call-for-workshops CALL FOR TUTORIALS http://www.ijcnn.org/call-for-tutorials [UPCOMING DEADLINES 23.59hr UTC-10 on Saturday, 15 OCTOBER 2016] ############################################################ The 2017 International Joint Conference on Neural Networks (IJCNN 2017) will be held at the William A. Egan Civic and Convention Center in Anchorage, Alaska, USA, May 14-19, 2017. The conference is organized jointly by the International Neural Network Society and the IEEE Computational Intelligence Society, and is the premiere international meeting for researchers and other professionals in neural networks and related areas. It will feature invited plenary talks by world-renowned speakers in the areas of neural network theory and applications, computational neuroscience, robotics, and distributed intelligence. In addition to regular technical sessions with oral and poster presentations, the conference program will include special sessions, competitions, tutorials and workshops on topics of current interest For the latest updates, follow us on Facebook (https://fb.me/ijcnn2017/) and Twitter (@ijcnn2017). #################### Paper Submission is now Open #################### http://www.ijcnn.org/call-for-papers * Regular paper can have up to 8 pages in double-column IEEE Conference format * All papers are to be prepared using IEEE-compliant Latex or Word templates on paper of U.S. letter size. * All submitted papers will be checked for plagiarism through the IEEE CrossCheck system. * Papers with significant overlap with the authors own papers or other papers will be rejected without review. ##########################Call for Workshops########################## Post-conference workshops offer a unique opportunity for in-depth discussions of specific topics in neural networks and computational intelligence. The workshops should be moderated by scientists or professionals who has significant expertise and /or whose recent work has had a significant impact within their field. IJCNN 2017 will emphasize emerging and growing areas of computational intelligence. Each workshop has a duration of 3 or 6 hours. The format of each workshop will be up to the moderator, and can include interactive presentations as well as panel discussions among participants. These interactions should highlight exciting new developments and current research trends to facilitate a discussion of ideas that will drive the field forward in the coming years. Workshop organizers can prepare various materials including handouts or electronic resources that can be made available for distribution before or after the meeting. Researchers interested in organizing workshops are invited to submit a formal proposal including the following information as a single file (pdf, doc, etc.) to the workshop chair: * Title * Organizers and their short bio * Brief description of the scope and impact of the workshop * Timeliness of the topic * Confirmed and/or potential speakers * Half day (3 hours) or full day (6 hours) * Link to organizer's web page and/or workshop web site (optional) For further details, please refer http://www.ijcnn.org/call-for-workshops. Any questions regarding this proposal can be asked to the Workshop Chair: Lazaros Iliadis, Democritus University of Thrace, Greece. E-mail: liliadis at fmenr.duth.gr ##########################Call for Tutorials########################## IJCNN 2017 will feature pre-conference tutorials addressing fundamental and advanced topics in computational intelligence. Tutorial proposals should be emailed to the Tutorial Chair (see below). A tutorial proposal should include the * Title * Presenter/organizer name(s) and affiliations * Expected enrollment * Abstract (less than 300 words) * Additional outline if needed * Presenter/organizer biography * Links to the presenter/organizer web page or the tutorial page (optional) * The proposal should not exceed two pages in 1.5 space, Times 12 point font. The tutorial format (preliminary) is 1 hour and 45 minutes with a 10-minute break. Researchers interested in organizing workshops are invited to submit a formal proposal. For further details, please refer to http://www.ijcnn.org/call-for-tutorials. Any questions regarding this proposal can be asked to the Tutorials Chair: Asim Roy, Arizona State University, USA. E-mail: ASIM.ROY at asu.edu ##################Topics and Areas of Interest################## This conference solicits papers addressing original works in topics and areas of interest including, but are not limited to: NEURAL NETWORK MODELS * Feedforward neural networks * Recurrent neural networks * Self-organizing maps * Radial basis function networks * Attractor neural networks and associative memory * Modular networks * Fuzzy neural networks * Spiking neural networks * Reservoir networks (echo-state networks, liquid-state machines, etc.) * Large-scale neural networks * Other topics in artificial neural networks MACHINE LEARNING * Supervised learning * Unsupervised learning and clustering, (including PCA, and ICA) * Reinforcement learning * Probabilistic and information-theoretic methods * Support vector machines and kernel methods * EM algorithms * Mixture models, ensemble learning, and other meta-learning or committee algorithms * Bayesian, belief, causal, and semantic networks * Statistical and pattern recognition algorithms * Visualization of data * Feature selection, extraction, and aggregation * Evolutionary learning * Hybrid learning methods * Computational power of neural networks * Deep learning * Other topics in machine learning NEURODYNAMICS * Dynamical models of spiking neurons * Synchronization and temporal correlation in neural networks * Dynamics of neural systems * Chaotic neural networks * Dynamics of analog networks * Neural oscillators and oscillator networks * Dynamics of attractor networks * Other topics in neurodynamics COMPUTATIONAL NEUROSCIENCE * Connectomics * Models of large-scale networks in the nervous system * Models of neurons and local circuits * Models of synaptic learning and synaptic dynamics * Models of neuromodulation * Brain imaging * Analysis of neurophysiological and neuroanatomical data * Cognitive neuroscience * Models of neural development * Models of neurochemical processes * Neuroinformatics * Other topics in computational neuroscience NEURAL MODELS OF PERCEPTION, COGNITION AND ACTION * Neurocognitive networks * Cognitive architectures * Models of conditioning, reward and behavior * Cognitive models of decision-making * Embodied cognition * Cognitive agents * Multi-agent models of group cognition * Developmental and evolutionary models of cognition * Visual system * Auditory system * Olfactory system * Other sensory systems * Attention * Learning and memory * Spatial cognition, representation and navigation * Semantic cognition and language * Neural models of symbolic processing * Reasoning and problem-solving * Working memory and cognitive control * Emotion and motivation * Motor control and action * Dynamical models of coordination and behavior * Consciousness and awareness * Models of sleep and diurnal rhythms * Mental disorders * Other topics in neural models of perception, cognition and action NEUROENGINEERING * Brain-machine interfaces * Neural prostheses * Neuromorphic hardware * Embedded neural systems * Other topics in neuroengineering BIO-INSPIRED AND BIOMORPHIC SYSTEMS * Brain-inspired cognitive architectures * Embodied robotics * Evolutionary robotics * Developmental robotics * Computational models of development * Collective intelligence * Swarms * Autonomous complex systems * Self-configuring systems * Self-healing systems * Self-aware systems * Emotional computation * Artificial life * Other topics in bio-inspired and biomorphic systems APPLICATIONS * Bioinformatics * Biomedical engineering * Data analysis and pattern recognition * Speech recognition and speech production * Robotics * Neurocontrol * Approximate dynamic programming, adaptive critics, and Markov decision processes * Neural network approaches to optimization * Signal processing, image processing, and multi-media * Temporal data analysis, prediction, and forecasting; time series analysis * Communications and computer networks * Data mining and knowledge discovery * Power system applications * Financial engineering applications * Applications in multi-agent systems and social computing * Manufacturing and industrial applications * Expert systems * Clinical applications * Big data applications * Smart grid applications * Other applications CROSS-DISCIPLINARY TOPICS * Hybrid intelligent systems * Swarm intelligence * Sensor networks * Quantum computation * Computational biology * Molecular and DNA computation * Computation in tissues and cells * Artificial immune systems * Other cross-disciplinary topics ################## Organizing Committee ###################### The full organizing committee can be found at: http://www.ijcnn.org/organizing-committee General Chair * Yoonsuck Choe, Texas A and M University, USA Program Chair * Christina Jayne, Robert Gordon University, UK Technical Co-Chairs * Irwin King, The Chinese University of Hong Kong, China * Barbara Hammer, University of Bielefeld, Germany ##################Sponsoring Organizations################## * INNS - International Neural Network Society * IEEE - Computational Intelligence Society * BSCS - Budapest Semester in Cognitive Science -------------- next part -------------- An HTML attachment was scrubbed... URL: From JanHendrik.Metzen at de.bosch.com Mon Sep 19 07:21:14 2016 From: JanHendrik.Metzen at de.bosch.com (Metzen Jan Hendrik (CR/AEY2)) Date: Mon, 19 Sep 2016 11:21:14 +0000 Subject: Connectionists: Fully-funded PhD Position on "Automated Deep Learning" at Robert Bosch Corporate Research (Renningen, Germany) Message-ID: Applications for a PhD position focusing on the development of "Automated Deep Learning" methods are invited. The PhD position is funded by Robert Bosch GmbH and located at the company's new center for research and advance engineering in Renningen, Germany (www.bosch-renningen.de/en/). More details can be found below or under the URL https://www.bosch-career.de/bewerben/jobsearch/-/cui/job/ZRB_UNREG_SEARCH/en/567D863A01021EE69D97FB4FFB73DDF4. More details: Deep learning is currently one of the most exciting fields in machine learning and artificial intelligence. The number of impressive applications is increasing fast, for example in computer vision, speech recognition, but also in learning control. Besides applications, there are many challenging unsolved theoretical questions involved. At our machine learning group, practical as well as theoretical deep learning questions arise. Thus, the research direction of the PhD can be shaped according to the profile and interest of the PhD candidate. Established contacts to excellent academic institutes will be employed for PhD supervision. Part of the position are: ? Development and implementation of "automated machine learning" algorithms that support the process of devising, training, and deploying novel architectures for convolutional and recurrent deep neural networks. ? Extending methods for automated machine learning (e.g., Bayesian Optimization) such that they can optimize the structure of deep neural networks along with their hyperparameters ? Empirical evaluation of the developed methods on public and corporate datasets for image classification, semantic segmentation, action recognition, and time-series analysis ? Technical discussions and creation of new ideas & applications within the existing deep learning research team, strong collaboration within a diverse research team ? Publications at top tier conferences and journals ? Focus on PhD thesis ensured, no project work required What distinguishes you: ? Masters degree in Computer Science, Mathematics, Physics, Engineering or similar ? Profound knowledge of Machine Learning, preferably Deep Learning or Bayesian Optimization ? Good programming skills, preferably experience with the scientific Python stack and theano or tensorflow ? Personal commitment ? Teamplayer and flexibility ? Fluent spoken and written in English For applying to the announced position, please refer to https://www.bosch-career.de/bewerben/jobsearch/-/cui/job/ZRB_UNREG_SEARCH/en/567D863A01021EE69D97FB4FFB73DDF4. Mit freundlichen Gr??en / Best regards Dr. Jan Hendrik Metzen Cognitive Systems (CR/AEY2) Robert Bosch GmbH | Renningen | 70465 Stuttgart | GERMANY | www.bosch.com Tel. +49 711 81148904 | Mobil +49 172 7526499 | JanHendrik.Metzen at de.bosch.com Sitz: Stuttgart, Registergericht: Amtsgericht Stuttgart, HRB 14000; Aufsichtsratsvorsitzender: Franz Fehrenbach; Gesch?ftsf?hrung: Dr. Volkmar Denner, Dr. Stefan Asenkerschbaumer, Dr. Rolf Bulander, Dr. Stefan Hartung, Dr. Markus Heyn, Dr. Dirk Hoheisel, Christoph K?bel, Uwe Raschke, Dr. Werner Struth, Peter Tyroller -------------- next part -------------- An HTML attachment was scrubbed... URL: From nzhang at udc.edu Mon Sep 19 10:28:15 2016 From: nzhang at udc.edu (Zhang, Nian) Date: Mon, 19 Sep 2016 10:28:15 -0400 Subject: Connectionists: CFP: ISNN 2017, Sapporo, Hokkaido, Japan, June 21-23, 2017 Message-ID: <32596A4A154B2442BF6312975C518D00047E08489282@UDCMSGSTAFF-M.firebirds.udc.edu> Call for Papers The 14th International Symposium on Neural Networks (ISNN 2017) in Sapporo, Hokkaido, Japan, June 21-23, 2017 Conference Website: https://conference.cs.cityu.edu.hk/isnn/ Following the successes of previous events, the 14th International Symposium on Neural Networks (ISNN 2017) will be held in Sapporo, Hokkaido, Japan. Located in northern island of Hokkaido, Sapporo is the fourth largest Japanese city and a popular summer/winter tourist venue. The Sponsors/Organizers are Hokkaido University and City University of Hong Kong. The Technical Co-sponsors are IEEE Computational Intelligence Society, International Neural Network Society, and Japanese Neural Network Society. The Publishers are Springer and Lecture Notes in Computer Science. ISNN 2017 aims to provide a high-level international forum for scientists, engineers, and educators to present the state of the art of neural network research and applications in related fields. The symposium will feature plenary speeches given by world renowned scholars, regular sessions with broad coverage, and special sessions focusing on popular topics. Call for Papers and Special Sessions Prospective authors are invited to contribute high-quality papers to ISNN 2017. In addition, proposals for special sessions within the technical scopes of the symposium are solicited. Special sessions, to be organized by internationally recognized experts, aim to bring together researchers in special focused topics. Papers submitted for special sessions are to be peer-reviewed with the same criteria used for the contributed papers. Researchers interested in organizing special sessions are invited to submit formal proposals to ISNN 2017. A special session proposal should include the session title, a brief description of the scope and motivation, names, contact information and brief biographical information of the organizers. Important Dates Special session proposals December 1, 2016 Paper submission January 1, 2017 Notification of acceptance February 1, 2017 Camera-ready copy and author registration March 1, 2017 Conference June 21-23, 2017 From costa at informatik.uni-freiburg.de Mon Sep 19 13:25:45 2016 From: costa at informatik.uni-freiburg.de (Fabrizio Costa) Date: Mon, 19 Sep 2016 19:25:45 +0200 Subject: Connectionists: CFP NIPS 2016 Workshop on Constructive Machine Learning Message-ID: <05e84b8c-ae5e-9683-a617-96a7cff65686@informatik.uni-freiburg.de> Dear Colleagues, We are pleased to announce that the new edition of the Constructive Machine Learning workshop this year will be held at NIPS Barcelona, Spain, Sat Dec 10th. Please visit http://www.cs.nott.ac.uk/~psztg/cml for more details. Looking forward to seeing you there! Best Regards, Fabrizio Costa, Thomas G?rtner, Andrea Passerini, Fran?ois Pachet ============================================================== Call for Papers NIPS 2016 Workshop on Constructive Machine Learning (NIPS CML) http://www.cs.nott.ac.uk/~psztg/cml A workshop at the Twenty-Ninth Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona, Spain Sat Dec 10th 08:00 AM -- 06:30 PM IMPORTANT DATES: ----------------------------------------------------------------------------------------------- Nov 3, 2016: Submission Deadline Nov 24, 2016: Acceptance Notification Dec 1, 2016: Final papers due Dec 10, 2016: Workshop date ============================================================== ABSTRACT: ----------------------------------------------------------------------------------------------- In many real-world applications, machine learning algorithms are employed as a tool in a ''constructive process''. These processes are similar to the general knowledge-discovery process but have a more specific goal: the construction of one-or-more domain elements with particular properties. In this workshop we want to bring together domain experts employing machine learning tools in constructive processes and machine learners investigating novel approaches or theories concerning constructive processes as a whole. Interesting applications include but are not limited to: image synthesis, drug and protein design, computational cooking, generation of art (paintings, music, poetry). Interesting approaches include but are not limited to: deep generative learning, active approaches to structured output learning, transfer or multi-task learning of generative models, active search or online optimization over relational domains, and learning with constraints. Many of the applications of constructive machine learning, including the ones mentioned above, are primarily considered in their respective application domain research area but are hardly present at machine learning conferences. By bringing together domain experts and machine learners working on constructive ML, we hope to bridge this gap between the communities. SUBMISSION INSTRUCTIONS: ----------------------------------------------------------------------------------------------- We welcome contributions on both theory and applications related to constructive machine learning problems. We also welcome submissions containing previously published content in fields related to machine learning, especially descriptions of real-world problems and applications. We welcome work-in-progress contributions, demo and position papers, as well as papers discussing potential research directions. Submission of previously published work or work under review is allowed. However, preference will be given to novel work or work that was not yet presented elsewhere. All double submissions must be clearly declared as such! Submissions will be reviewed on the basis of relevance, significance, technical quality, and clarity. All accepted papers will be presented as posters and among them a few will be selected for the oral presentation. Submissions should use the NIPS style file, with a maximum of 4 pages (excluding references). Accepted papers will be made available online at the workshop website, but the workshop proceedings can be considered non-archival. Submissions need not be anonymous. All papers should be submitted via easychair at the following link: https://easychair.org/conferences/?conf=cml2016 INVITED SPEAKERS AND PANELISTS (to be confirmed): ----------------------------------------------------------------------------------------------- Ruslan Salakhutdinov (CMU, deep generative models) Thorsten Joachims (Cornell, coactive learning) Gisbert Schneider (ETH, de novo drug design) Simon Colton (Goldsmiths University of London, computational creativity) Douglas Eck (Google, music generation) Ross Goodwin (NYU ITP, computational creative writing) Florian Pinel (IBM, cognitive cooking) ORGANIZERS: ----------------------------------------------------------------------------------------------- Fabrizio Costa (University of Freiburg) Thomas G?rtner (University of Nottingham) Andrea Passerini (University of Trento) Fran?ois Pachet (SONY Computer Science Laboratory Paris) From gluck at pavlov.rutgers.edu Mon Sep 19 21:55:04 2016 From: gluck at pavlov.rutgers.edu (Mark Gluck) Date: Mon, 19 Sep 2016 21:55:04 -0400 Subject: Connectionists: Seeking Applicants to Behavioral & Neural Sciences Ph.D. Program at Rutgers University-Newark interested in Cognitive Neuroscience of Learning and Memory (Deadline: December 15th, 2016) Message-ID: <97FDE0E2-9A2B-4E88-9002-53214E8AF598@pavlov.rutgers.edu> Re: Seeking Students interested in Cognitive, Clinical, and Computational Neuroscience of Learning and Memory to Apply to the Behavioral & Neural Sciences Ph.D. Program at Rutgers University-Newark (Deadline: December 15th, 2016) Dear Colleagues: If you know of bright, well trained, and highly motivated graduating seniors or research assistants at your institution who are interested in pursuing a Ph.D. in cognitive and/or systems neuroscience, I would be obliged if you would pass this email on to them. I am especially interested in students interested in working with me on the cognitive, clinical, and computational neuroscience of learning, memory, and decision making. Current projects in my lab include (1) neuroimaging, computational, and behavioral studies of sleep and its impact on emotional cognition and insight learning (2) studies of psychiatric patients with clinical depression or post traumatic stress disorder (PTSD) and how learning and generalization in these patents is affected by pharmacological and behavioral interventions, and related to their clinical symptoms, (3) the effects of aerobic exercise and physical activity on brain function and cognition in older adults, (4) community-based participatory research on African-American brain health and health disparities (through our African-American Brain Health Initiative), (5) genetic influences on medial temporal lobe and striatal function in aging, (6) cognitive changes in Parkinson?s disease and how these are affected by clinical treatments and individual differences in motor symptoms. For additional details, lecture videos, an overview of current lab members, and downloadable publications and research summaries, see http://www.gluck.edu/ The Graduate Program in Behavioral and Neural Sciences (BNS) at Rutgers University-Newark prepares students for neuroscience careers in academia, industry, public administration, and scientific publishing by providing both general instruction across all areas of neuroscience as well as focused training within one area of specialization. BNS Students are supported financially by the graduate program (not by individual faculty) for five years; they receive full tuition remission and benefit from a comprehensive health insurance. A NIH Minority Biomedical Research Support (MBRS) training grant provides additional support services for students from under-represented minority groups or from disadvantaged backgrounds. The BNS curriculum offers a wide range of courses that provide a broad and in depth knowledge in neuroscience, including an intensive neuroscience ?Bootcamp? in the fall of their first year, and a comprehensive series of four core courses taught by all our faculty. Students in our graduate program are trained primarily to conduct independent research and to present and discuss their results orally and in written form. Students also gain experience in undergraduate and graduate teaching and mentoring. The integration of Rutgers University-Newark with our medical school (known now as Rutgers Behavioral and Health Sciences), provides our students with additional clinically-relevant training and research opportunities. The research interests of BNS faculty are diverse and span all levels of analysis in the neurosciences, from genes and molecules to microcircuits and complex systems. Their research methods are similarly varied as they combine electrophysiological, neurochemical, anatomical, imaging, behavioral, and neuropsychological methods to analyze how the brain works, develops, interacts with the environment, and is modified by experience in health and disease. 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 (many faculty, postdoctoral fellows, and students live in New York City). Key web links are: Faculty profiles and Rutgers-Newark info: http://www.neuroscience.newark.rutgers.edu Rutgers University Brain Imaging Center: http://rubic.rutgers.edu BNS Admissions (to apply online): http://www.bns.rutgers.edu The deadline for applications is December 15, 2016. Formal interviews and visits by the top US candidates usually take place at Rutgers-Newark in early February (international candidates may be interviewed via Skype or phone). Late applications may be considered on a case-by-case basis. In addition, I welcome promising applicants specifically interested in working in my lab to contact me to arrange an informal visit sometime during the fall to meet with my lab members and join us for lab meetings and research activities. The best day for this is usually a Wednesday when we have most of our meetings (Mondays sometimes also). Regards, Mark Gluck, Professor of Neuroscience ___________________________________ 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: From rsutton at ualberta.ca Mon Sep 19 17:48:15 2016 From: rsutton at ualberta.ca (Richard Sutton) Date: Mon, 19 Sep 2016 15:48:15 -0600 Subject: Connectionists: RLDM2017 Message-ID: <82C2FC62-5DFB-4C1F-89EA-C5672EFA8298@ualberta.ca> Dear friends and colleagues, I would like to call your attention to the upcoming Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) to be held next June 11-14 in Ann Arbor, Michigan. The special thing about this conference is that it is explicitly multidisciplinary, bringing together folks from all the different fields trying to figure out how learning and decision making work: neuroscience, artificial intelligence, control theory, psychology, operations research, economics, robotics, signal processing, and others. This will be the third time we have held this meeting. Last year, it was held in Edmonton at the University of Alberta, and in 2013 it was held in Princeton at Princeton University. It has been a smallish meeting, attended by a few hundred researchers, focused on what the different fields can learn from each other. I have found it extremely valuable, and I recommend the meeting to you for learning about what is going on in the attempt to understand the mind in the broadest possible terms. And if your own work might be of interest to other fields, why not submit a short paper describing it in cross-disciplinary terms? Submissions are due February 19, 2017. The conference itself will consist of invited talks of broad interest, talks selected from the submitted papers, and wonderful poster sessions where you can meet informally with like-minded people who are nevertheless working in different fields. The emphasis is on sharing of ideas across disciplines, so it is not a problem if the work you submit to this meeting has already been published within your discipline. There is a much wider world out there with which to share perspectives. -Rich Sutton p.s. for more information go to http://rldm.org. From mklados at gmail.com Mon Sep 19 18:08:08 2016 From: mklados at gmail.com (Manousos Klados) Date: Tue, 20 Sep 2016 00:08:08 +0200 Subject: Connectionists: =?utf-8?q?Society_of_Applied_Neuroscience_Biennia?= =?utf-8?b?bCBjb25mZXJlbmNlIChTQU4yMDE24oCPKSDigJMgZmluYWwgcHJvZ3Jh?= =?utf-8?q?mme?= Message-ID: Dear colleagues, I am proud to announce you that the final programme for SAN2016 is now online (http://www.applied-neuroscience.org/san2016/ index.php/conference-info/program) and a summarised snapshot with the its highlights is attached to this email. With this information we would also like to cordially invite you to participate in and attend SAN2016 (http://applied-neuroscience.org/san2016/), which is organised by the Society of Applied Neuroscience (SAN, http://www.applied-neuroscience.org/) in cooperation with the Medical School of the Aristotle University of Thessaloniki and the Department of Neurology of the Max Planck Institute for Human Cognitive and Brain Sciences. SAN2016 will be held October6-9, 2016 in Corfu Island, Greece. As you will see, there is an attractive list of planned hands-on workshops and conference symposia in place as well as, an attractive list of distinguished speakers Numerous special issues and research topics are also planned by Society members as per tradition. We look forward to seeing you in Corfu, Greece! Panos Bamidis John Gruzelier Manousos Klados -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: SAN2016_Brochure_Final.pdf Type: application/pdf Size: 593075 bytes Desc: not available URL: From ab8556 at coventry.ac.uk Tue Sep 20 04:56:04 2016 From: ab8556 at coventry.ac.uk (Abdulrahman Altahhan) Date: Tue, 20 Sep 2016 08:56:04 +0000 Subject: Connectionists: PhD in Machine Learning with Fund Message-ID: <703d516886304fefbe102253918596b4@GBCUEXCH02.coventry.ac.uk> Dear Colleagues, Please note that we have an opportunity for the following PhD in the area of Deep Reinforcement Learning at Coventry University http://www.coventry.ac.uk/research/research-students/research-studentships/robot-homing-deeply-reinforced-by-another-robot/ Please note that funding is also available for highly qualified candidates. Regards, _______________________________ Dr Abdulrahman Altahhan Course Director for MSc in Data Science School of Computing, Electronics and Maths Faculty of Engineering and Computing Coventry University Coventry, CV1 2JH UK +44 (0) 2477653088 -------------- next part -------------- An HTML attachment was scrubbed... URL: From cgf at isep.ipp.pt Tue Sep 20 06:15:43 2016 From: cgf at isep.ipp.pt (Carlos Ferreira) Date: Tue, 20 Sep 2016 11:15:43 +0100 Subject: Connectionists: EPIA 2017 -- Call for Journal Track Papers Message-ID: <022043a9-85ac-363a-9e05-9a3a72357a0c@isep.ipp.pt> ************************************************** CALL FOR JOURNAL TRACK PAPERS ************************************************** EPIA 2017 18th EPIA Conference on Artificial Intelligence http://www.fe.up.pt/epia2017 September 5-8, 2017 Porto -- Portugal ************************************************** Special Issue on Computational Models for Social and Technical Interactions The journal track invites high-quality submissions that present original work in the areas of computational models for understanding, modelling, and facilitating social interaction between people, organizations and systems. Topics covering intelligent socio-technical systems, adaptive and social-aware intelligent systems, evolving social systems, adaptive and reactive intelligent systems, Governance mechanisms, Organizational learning, Social media analysis, Social network analysis, Social robotics, smart cities, V2V, etc. are welcome. Accepted papers will be published in a special issue of the New Generation Computing journal and, moreover, a presentation slot at the EPIA 2017 conference will be assigned. Given the special nature of the EPIA 2017 journal track, only papers that naturally lend themselves to conference talks will be considered. For instance, journal versions of previously published conference papers, or survey papers will not be considered for the special issue. Such submissions might be submitted to the regular submission track of the journal. How to submit? To submit to EPIA?17 journal track, authors must send an e-mail to the Editor of NGC Dr.Masami Hagiya to ngcj at ohmsha.co.jpand CC to the e-mail epia2017 at fe.up.pt . The Subject of the e-mail should be ?Submission for the EPIA 2017 special issue?. Papers must be submitted in PDF format, using the style format of NGC. In the body of e-mail, authors should specify one of the six major fields (http://www.ohmsha.co.jp/ngc/information.htm#info-major) of the paper, and any previous publication with overlapping material. The EPIA 2017 Chairs will coordinate the review process. Authors who submit their work to the special EPIA 2017 journal track commit themselves to present their results at the EPIA conference in case of acceptance. If you are not interested in presenting your work at EPIA 2017, please do not submit to this special issue of the journal. Format It is recommended that submitted papers do not exceed 20 pages including references and appendices, formatted in the New Generation Computing journal style. This is a soft limit, but if a submission exceeds the limit, please provide a brief justification regarding the length in the cover letter. Important dates for the journal track Authors can submit at any time to this Special Issue. Once a paper is submitted, the review process starts. At least, two independent reviewers will review each paper. The expected review time is 2 months. We strongly suggest earlier submissions to accommodate the usual iterative review process. The very last date for submission is 1 April 2017. Notes on quality threshold The submissions will be treated as regular NGC journal submission with the same quality criteria; any paper accepted in the special issue will have to satisfy the high quality standards of the journal. Potential outcomes of the evaluation process Depending on the decisions of the handling editors, multiple outcomes are possible for a paper submitted to the journal track: Accept or Accept conditional to minor revisions in case the paper meets the journal acceptance criteria; if the final acceptance of the paper occurs before June 2017, a regular presentation slot for the paper will be allotted in the EPIA 2017 program. Reject in case the paper does not meet the quality criteria of the journal. In exceptional cases, the editors may decide that the research presented in the paper is not mature enough to be acceptable for the journal special issue, yet consider it, due to its originality and potential, a valuable asset for the EPIA 2017 conference. In such cases, the authors will be invited to revise and shorten their paper and submit to an EPIA 2017 regular track (in case the corresponding deadline can still be met), where the paper will be subject to a light reviewing process. The Journal Track Guest Editors Eugenio Oliveira, Jo?o Gama Carlos Ferreira ISEP | Instituto Superior de Engenharia do Porto Rua Dr. Ant?nio Bernardino de Almeida, 431 4249-015 Porto - PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail at isep.ipp.pt | www.isep.ipp.pt From cgf at isep.ipp.pt Tue Sep 20 06:57:54 2016 From: cgf at isep.ipp.pt (Carlos Ferreira) Date: Tue, 20 Sep 2016 11:57:54 +0100 Subject: Connectionists: Extended Deadline (Sept. 29): DATA STREAMS TRACK - ACM SAC 2017 Message-ID: ACM Symposium on Applied Computing The 31th Annual ACM Symposium on Applied Computing in Marrakech, Morocco, April 3 ? 7, 2017. http://www.acm.org/conferences/sac/sac2017/ Data Streams Track http://www.cs.waikato.ac.nz/~abifet/SAC2017/ Call for Papers The rapid development in Big Data information science and technology in general and in growth complexity and volume of data in particular has introduced new challenges for the research community. Many sources produce data continuously. Examples include the Internet of Things (IoT), Smart Cities, Urban Computing, sensor networks, wireless networks, radio frequency identification, health-care devices and information systems, customer click streams, telephone records, multimedia data, scientific data, sets of retail chain transactions, etc. These sources are called data streams. A data stream is an ordered sequence of instances that can be read only once or a small number of times using limited computing and storage capabilities. These sources of data are characterized by being open-ended, flowing at high-speed, and generated by non stationary distributions. TOPICS OF INTEREST We are looking for original, unpublished work related to algorithms, methods and applications on big data streams and large scale machine learning. Topics include (but are not restricted) to: * Real-Time Analytics * Big Data Mining * Data Stream Models * Large Scale Machine Learning * Languages for Stream Query * Continuous Queries * Clustering from Data Streams * Decision Trees from Data Streams * Association Rules from Data Streams * Decision Rules from Data Streams * Bayesian networks from Data Streams * Feature Selection from Data Streams * Visualization Techniques for Data Streams * Incremental on-line Learning Algorithms * Single-Pass Algorithms * Temporal, spatial, and spatio-temporal data mining * Scalable Algorithms * Real-Time and Real-World Applications using Stream data * Distributed and Social Stream Mining * Urban Computing, Smart Cities * Internet of Things (IoT) IMPORTANT DATES (strict) 1. Paper Submission: September 29, 2016 2. Author Notification: November 10, 2016 3. Camera?ready copies: November 25, 2016 PAPER SUBMISSION GUIDELINES Papers should be submitted in PDF. Authors are invited to submit original papers in all topics related to data streams. All papers should be submitted in ACM 2- column camera ready format for publication in the symposium proceedings. ACM SAC follows a double blind review process. Consequently, the author(s) name(s) and address(s) must NOT appear in the body of the submitted paper, and self-references should be in the third person. This is to facilitate double blind review required by ACM. All submitted papers must include the paper identification number provided by the eCMS system when the paper is first registered. The number must appear on the front page, above the title of the paper. Each submitted paper will be fully refereed and undergo a blind review process by at least three referees. The conference proceedings will be published by ACM. The maximum number of pages allowed for the final papers is 6 pages. There is a set of templates to support the required paper format for a number of document preparation systems at: http://www.acm.org/sigs/pubs/proceed/template.html Important notice: 1. Please submit your contribution via SAC 2017 Webpage. 2. Paper registration is required, allowing the inclusion of the paper, poster, or SRC abstract in the conference proceedings. An author or a proxy attending SAC MUST present the paper. This is a requirement for including the work in the ACM/IEEE digital library. No-show of registered papers, posters, and SRC abstracts will result in excluding them from the ACM/IEEE digital library. Student Research Competition Graduate students seeking feedback from the scientific community on their research ideas are invited to submit original abstracts of their research work in areas of experimental computing and application development related to SAC 2017 Tracks. The SRC program is designed to provide graduate students the opportunity to meet and exchange ideas with researcher and practitioners in their areas of interest. All research abstract submissions will be reviewed by researchers and practitioners with expertise in the track focus area to which they are submitted. Authors of selected abstracts will have the opportunity to give poster and oral presentations of their work and compete for three top wining places. The SRC committee will evaluate and select First, Second, and Third place winners. The winners will receive cash awards and SIGAPP recognition certificates during the conference banquet dinner. Authors of selected abstracts are eligible to apply to the SIGAPP Student Travel Award program for support. Graduate students are invited to submit research abstracts (minimum of two pages; maximum of four pages) following the instructions published at SAC 2017 website. Submission of the same abstract to multiple tracks is not allowed. Submissions must address original and unpublished research work related to a SAC track, with emphasis on the innovation behind the research idea. The submission should address the research problem being investigated, the proposed approach and research methodology, and sample preliminary results of the work. In addition, the abstract should reflect on the originality of the work, innovation of the approach, and applicability of the results to real-world problems. All abstracts must be submitted thought the START Submission system. If you encounter any problems with your submission, please contact the Program Coordinator. Carlos Ferreira ISEP | Instituto Superior de Engenharia do Porto Rua Dr. Ant?nio Bernardino de Almeida, 431 4249-015 Porto - PORTUGAL tel. +351 228 340 500 | fax +351 228 321 159 mail at isep.ipp.pt | www.isep.ipp.pt From tarek.besold at googlemail.com Tue Sep 20 09:21:44 2016 From: tarek.besold at googlemail.com (Tarek R. Besold) Date: Tue, 20 Sep 2016 15:21:44 +0200 Subject: Connectionists: 2nd CfP: Cognitive Computation - Integrating neural and symbolic approaches @ NIPS 2016 (December 9, Barcelona) Message-ID: **************************************************** Cognitive Computation: Integrating Neural and Symbolic Approaches (CoCo @ NIPS 2016) **************************************************** Workshop at NIPS 2016, Barcelona, Spain December 09, 2016 == WORKSHOP WEBPAGE == http://www.neural-symbolic.org/CoCo2016/ == KEYNOTE SPEAKERS == Barbara Hammer, Bielefed University Pascal Hitzler, Wright State University Risto Miikkulainen, University of Texas at Austin & Sentient Technologies, Inc. Dan Roth, University of Illinois at Urbana-Champaign Kristina Toutanova, Microsoft Research == PANELISTS == Yoshua Bengio, University of Montreal Marco Gori, University of Siena Alessio Lomuscio, Imperial College London Gary Marcus, New York University & Geometric Intelligence, Inc. == MISSION STATEMENT == While early work on knowledge representation and inference was primarily symbolic, the corresponding approaches subsequently fell out of favor, and were largely supplanted by connectionist methods. In this workshop, we will work to close the gap between the two paradigms, and aim to formulate a new unified approach that is inspired by our current understanding of human cognitive processing. This is important to help improve our understanding of Neural Information Processing and build better Machine Learning systems, including the integration of learning and reasoning in dynamic knowledge-bases, and reuse of knowledge learned in one application domain in analogous domains. The workshop brings together established leaders and promising young scientists in the fields of neural computation, logic and artificial intelligence, knowledge representation, natural language understanding, machine learning, cognitive science and computational neuroscience. Invited lectures by senior researchers will be complemented with presentations based on contributed papers reporting recent work (following an open call for papers) and a poster session, giving ample opportunity for participants to interact and discuss the complementary perspectives and emerging approaches. The workshop targets a single broad theme of general interest to the vast majority of the NIPS community, namely translations between connectionist models and symbolic knowledge representation and reasoning for the purpose of achieving an effective integration of neural learning and cognitive reasoning, called neural-symbolic computing. The study of neural-symbolic computing is now an established topic of wider interest to NIPS with topics that are relevant to almost everyone studying neural information processing. == KEYWORDS == The following list gives some (but by far not all) relevant keywords for the CoCo @ NIPS 2016 workshop: - neural-symbolic computing; - language processing and reasoning; - cognitive agents; - multimodal learning; - deep networks; - knowledge extraction; - symbol manipulation; - variable binding; - memory-based networks; - dynamic knowledge-bases; - integration of learning and reasoning; - explainable AI. == CALL FOR PAPERS == We invite submission of papers dealing with topics related to the research questions discussed in the workshop. The reported work can range from theoretical/foundational research to reports on applications and/or implemented systems. We explicitly also encourage the submission of more controversial papers which can serve as basis for open discussions during the event. Possible topics of interest include but are (by far!) not limited to: - The representation of symbolic knowledge by connectionist systems; - Neural Learning theory; - Integration of logic and probabilities, e.g., in neural networks, but also more generally; - Structured learning and relational learning in neural networks; - Logical reasoning carried out by neural networks; - Integrated neural-symbolic approaches; - Extraction of symbolic knowledge from trained neural networks; - Integrated neural-symbolic reasoning; - Neural-symbolic cognitive models; - Biologically-inspired neural-symbolic integration; - Applications in robotics, simulation, fraud prevention, natural language processing, semantic web, software engineering, fault diagnosis, bioinformatics, visual intelligence, etc. - Approaches/techniques making AI and/or Machine Learning systems/algorithms better explainable or increasing human comprehensibility. = Submission instructions = - Submissions have to be made via EasyChair (https://easychair.org/conferences/?conf=coconips2016) before the paper submission deadline indicated below. - Submissions are limited to at most eight pages, an additional ninth page containing only cited references is allowed. Still, also shorter papers are expressly welcomed. - Submissions have to use the NIPS 2016 submission format (see http://nips.cc/Conferences/2016/PaperInformation/StyleFiles). - Reviewing will be single-blind, i.e., you are free to indicate your name etc. on the paper. (Still, this is not an obligation.) Please note that at least one author of each accepted paper must register for the event and be available to present the paper at the workshop. =Publication= Accepted papers will be published in official workshop proceedings submitted to CEUR-WS.org. Authors of selected papers will be invited to submit a revised and extended version of their papers to a journal special issue after the workshop. == IMPORTANT DATES == - Deadline for paper submission: October 10, 2016 - Notification of paper acceptance: October 30, 2016 - Camera-ready paper due: November 14, 2016 - Workshop date: December 09 or 10, 2016 - NIPS 2015 main conference: December 5-8, 2016 == ADMISSION == The workshop is open to anybody, please register via NIPS 2016 (http://nips.cc ). == WORKSHOP ORGANIZERS == - Tarek R. Besold (University of Bremen, Germany) - Antoine Bordes (Facebook AI Research, USA) - Artur d'Avila Garcez (City University London, UK) - Greg Wayne (Google DeepMind, UK) == ADDITIONAL INFORMATION == - General questions concerning the workshop should be addressed to Tarek R. Besold at Tarek(dot)Besold(at)uni(hyphen)bremen(dot)de. - This workshop is conceptually related to the series of International Workshops on Neural-Symbolic Learning and Reasoning (NeSy). If interested, have a look at http://www.neural-symbolic.org - Please also feel free to join the neural-symbolic integration mailing list for announcements and discussions - it's a low traffic mailing list. If interested, register at http://maillists.city.ac.uk/mailman/listinfo/nesy. -- Digital Media Lab Center for Computing and Communication Technologies (TZI) University of Bremen Email: Tarek.Besold at uni-bremen.de Web: http://sites.google.com/site/tarekbesold/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From aw665 at cam.ac.uk Tue Sep 20 14:03:44 2016 From: aw665 at cam.ac.uk (Adrian Weller) Date: Tue, 20 Sep 2016 14:03:44 -0400 Subject: Connectionists: CfP: NIPS symposium on Machine Learning and the Law Message-ID: NIPS 2016 Symposium on Machine Learning and the Law ----------------------------------------------------------------------------- Please forward to others who may have interest. Important Dates ---------------------- Submission Deadline: Nov 3, 2016 Decision to Authors: Nov 18, 2016 Final Papers Due: Dec 1, 2016 (papers may be revised following the symposium) Symposium Date: Dec 8, 2016 Note that to come to any of the three NIPS symposia, you must be registered either for the main NIPS conference or for the workshops. Early registration with reduced pricing ends at 12:59am on October 6. Website www.MLandtheLaw.org Symposium on Machine Learning and the Law -------------------------------------------------------------- Advances in machine learning and artificial intelligence mean that predictions and decisions of algorithms are already in use in many important situations under legal or regulatory control, and this is likely to increase dramatically in the near future. Examples include deciding whether to approve a bank loan, driving an autonomous car, or even predicting whether a prison inmate is likely to offend again if released. This symposium will explore the key themes of privacy, liability, transparency and fairness specifically as they relate to the legal treatment and regulation of algorithms and data. Our primary goals are (i) to inform our community about important current and ongoing legislation (e.g. the EU?s GDPR https://en.wikipedia.org/wiki/General_Data_Protection_Regulation ); and (ii) to bring together the legal and technical communities to help form better policy in the future. We welcome machine learners, lawyers and anyone interested in social policy. Although the impact of machine learning on jobs in the legal profession is an important topic, that is not a key focus of this symposium. Call for Papers --------------------- Authors are invited to submit research abstracts on topics that relate broadly to the themes of machine learning and the law, including but not limited to issues of privacy, liability, transparency and fairness as they relate to algorithms and data. Submissions should be up to 6 pages in NIPS format (short submissions are welcome, longer submissions may be accepted, please contact us if this would help you). Submissions need not be anonymized. Given the novelty of the field, we welcome a wide range of submissions, whether technical, legal or careful thought pieces to stimulate debate and discussion. We are happy to consider submissions that survey and comment on relevant work that has been previously published. We aim to highlight a few submissions in spotlight presentations by authors at the symposium. All accepted papers will be made available on our symposium website, and will appear in an issue of JMLR Workshop and Conference Proceedings (unless authors prefer not). Please submit to submissions at mlandthelaw.org by Nov 3, 2016 (11:59PM PDT). Sponsors: We gratefully acknowledge support from the Center for the Study of Existential Risk, and the Leverhulme Center for the Future of Intelligence. ------------------------------ Adrian Weller From azahkm at gmail.com Tue Sep 20 21:51:05 2016 From: azahkm at gmail.com (Azah Kamilah Muda) Date: Wed, 21 Sep 2016 09:51:05 +0800 Subject: Connectionists: =?utf-8?q?CFP_=3A_The_16th_ISDA=E2=80=9916_=26_Th?= =?utf-8?q?e_6th_WICT=E2=80=9916_-_Springer_=E2=80=93_Porto=2C_Port?= =?utf-8?q?ugal_-_Extended_Date?= Message-ID: **We apologize in advance if you receive multiple copies of this CFP** Kindly help to distribute this CFP to your mailing list. -- Call For Papers --- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -- The 16th International Conference on Intelligent Systems Design and Applications (ISDA?16) -- http://www.mirlabs.org/isda16 http://www.mirlabs.net/isda16 -- The 6th World Congress on Information and Communication Technologies (WICT'16) -- http://www.mirlabs.org/wict16 http://www.mirlabs.net/wict16 ** Important Dates ** ---------------------------------- Paper submission due: September 20, 2016 Paper submission due (extended): October 10, 2016 Notification of paper acceptance: October 15, 2016 Notification of paper acceptance (extended): October 20, 2016 Registration and Final manuscript due: October 30, 2016 Conference: December 14 - 16, 2016 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ About ISDA?16 : ------------------------- The International Conference on Intelligent Systems Design and Applications (ISDA) is a major international conference bringing together researchers, engineers, and practitioners who work in the areas of intelligent systems and its applications in industry and the real world. Every year, ISDA attracts authors from over 30 countries. The conference will include workshops, special sessions and tutorials, along with prominent keynote speakers and regular paper presentations in parallel tracks. All accepted and registered papers will be included in the conference proceedings to expected be published by Springer. Topics ( not limited to ) ----------------------------- Intelligent Systems Architectures and Applications Intelligent Image and Signal Processing Intelligent Internet Modeling Intelligent Data mining Intelligent Business Systems Intelligent Control and Automation Intelligent Agents Intelligent Knowledge Management Innovative Information Security Innovative Networking and Communication Techniques Web Intelligence Intelligent Software Engineering About WICT'16 : ------------------------- WICT ?16 aims to provide an opportunity for the researchers from academia and industry to meet and discuss the latest solutions, scientific results and methods in the usage and applications of ICT in the real world. The conference programme includes workshops, special sessions and tutorials, along with prominent keynote speakers and regular paper presentations in parallel tracks. In the past century, our society has been through several periods of dramatic changes, driven by innovations such as transportation systems, telephone etc. Last few decades have experienced technologies that are evolving so rapidly, altering the constraints of space and time, and reshaping the way we communicate, learn and think. Rapid advances in information technologies and other digital systems are reshaping our ecosystem. Innovations in ICT allow us to transmit information quickly and widely, propelling the growth of new urban communities, linking distant places and diverse areas of endeavor i! n productive new ways, which a decade ago was unimaginable. All accepted and registered papers will be included in the conference proceedings to expected be published by Springer. Topics ( not limited to ) ----------------------------- Bioinformatics and Computational Biology Computer Graphics and Virtual Reality Data Mining e-Learning e-Business e-Government Artificial Intelligence Web Services and Semantic Web Grid and Cloud Computing Ambient Intelligence Body Sensor Networks Computational Finance and Economics Cybercrime (Legal and Technical Issues) Computer Network Security Data Mining for Information Security Academic Integrity, Plagiarism Detection and Software Misuse Intrusion Detection and Forensics Scheduling For Large Scale Distributed System Nature Inspired Optimization Algorithms and Their Applications The Role of Technology in Education and Health Data Management Collaborative Design in Knowledge-based Environment Software Engineering ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Submission Guidelines: ------------------------------------------------------ Submission of paper should be made through the submission page from the conference web page. Please refer to the conference website for guidelines to prepare your manuscript. Paper format templates: http://www.springer.com/series/11156 Proceedings are expected to be published by the Advances in Intelligent and Soft Computing, which is now indexed by ISI Proceedings, DBLP. Ulrich's, EI-Compendex, SCOPUS, Zentralblatt Math, MetaPress, Springerlink Proceedings will be made available during the conference. Expanded versions of selected papers will be published in special issues of internationally referred journals (indexed by SCI) and edited volumes. ISDA?16 Submission : https://easychair.org/conferences/?conf=isda2016 WICT?16 Submission : https://easychair.org/conferences/?conf=wict2016 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * Organizing Committee * ---------------------------------- General Chairs : Ana Maria Madureira, Instituto Superior de Engenharia do Porto, Portugal Ajith Abraham, Machine Intelligence Research Labs (MIR Labs), USA Technical Committee (Please refer website ) : http://www.mirlabs.net/isda16/committees.php http://www.mirlabs.net/wict16/committees.php For technical contact: ---------------------------------- Ajith Abraham Email: ajith.abraham at ieee.org -- Best Regards, Azah Muda -------------- next part -------------- An HTML attachment was scrubbed... URL: From marc.toussaint at informatik.uni-stuttgart.de Wed Sep 21 15:28:36 2016 From: marc.toussaint at informatik.uni-stuttgart.de (Marc Toussaint) Date: Wed, 21 Sep 2016 21:28:36 +0200 Subject: Connectionists: Group Leader Position in Machine Learning & Robotics @ Univ Stuttgart Message-ID: <5350baaf-d1c0-498b-883a-03f6c09238e6@informatik.uni-stuttgart.de> Dear PostDocs, the Stuttgart area is expanding in machine learning and robotics and will fund a new Research Group. We are seeking applications for a *Research Group Leader in* *Interactive Learning and Robotics* Topic-wise we are very open. Successful candidates should have an excellent early-career track record in one or more of the following areas: - Machine Learning - Robotics - Reinforcement Learning or Adaptive Control - Human-Robot Interaction and Cooperation Highlights of the position: - your position (E14) PLUS 1.5 PhD positions (E13) are funded - use a fully equipped robotics & HCI lab (PR2 + Baxter + OptiTrack) - cooperate with Stuttgart & MPI T?bingen (Toussaint, Schaal, Schmidt, Black, Lensch) - start up and running cost budgets Please see all job details at https://ipvs.informatik.uni-stuttgart.de/mlr/research-group-leader/ The application deadline is October 20th, 2016 Best, Marc Toussaint https://ipvs.informatik.uni-stuttgart.de/mlr/marc/ From m.plumbley at surrey.ac.uk Thu Sep 22 07:51:20 2016 From: m.plumbley at surrey.ac.uk (m.plumbley at surrey.ac.uk) Date: Thu, 22 Sep 2016 11:51:20 +0000 Subject: Connectionists: Lecturers (Assistant Professors) in: Machine Learning & Computer Vision; Robot Vision and Autonomous Systems Message-ID: [Please forward to anyone who may be interested. Apologies for cross-posting.] ------------------ Lecturers (Assistant Professors) in: Machine Learning & Computer Vision; Robot Vision & Autonomous Systems Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK Salary: GBP 39,324 to 46,924 per annum Closing Date: Monday 31 October 2016 https://jobs.surrey.ac.uk/070216 The University offers a unique opportunity for two individuals with outstanding research and leadership to join the Centre for Vision, Speech and Signal Processing (CVSSP). The successful candidate is expected to build a research project portfolio to complement existing CVSSP strengths. The centre seeks to appoint two individuals with an excellent research track-record and international profile to lead future growth of research activities in one or more of the following areas: * Machine Learning & Pattern Recognition * Computer Vision * Robot Vision & Autonomous Systems * Intelligent Sensing and Sensor Networks * Audio-Visual Signal and Media Processing * Big Visual Data Understanding * Machine Intelligence We now seek individuals with strong research track-records and leadership potential who can develop the existing activities of CVSSP and exploit the synergetic possibilities that exist within the centre, across the University and regionally with UK industry. You will possess proven management and leadership qualities, demonstrating achievements in scholarship and research at a national and international level, and will have experience of teaching within HE. CVSSP is one of the primary centres for computer vision & audio-visual signal processing in Europe with over 120 researchers, a grant portfolio of ?18M and a track-record of pioneering research leading to technology transfer in collaboration with UK industry. CVSSP forms part of the Department of Electronic Engineering, recognised as a top department for both Teaching and Research: surrey.ac.uk/ee. For an informal discussion, please contact Professor Adrian Hilton, Director of CVSSP (a.hilton at surrey.ac.uk). Further details of CVSSP: www.surrey.ac.uk/cvssp Interviews are expected to take place in the week commencing 21st November 2016. Further details: https://jobs.surrey.ac.uk/070216 We can offer a generous remuneration package, which includes relocation assistance where appropriate, an attractive research environment, the latest teaching facilities, and access to a variety of staff development opportunities. We acknowledge, understand and embrace diversity. -- 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 michel.verleysen at uclouvain.be Thu Sep 22 08:41:51 2016 From: michel.verleysen at uclouvain.be (Michel Verleysen) Date: Thu, 22 Sep 2016 12:41:51 +0000 Subject: Connectionists: ESANN 2017: announcement and call for papers Message-ID: <05e2cf4f02994ac19032143108eb9f18@ucl-mbx06.OASIS.UCLOUVAIN.BE> ESANN 2017 - 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges, Belgium, 26-27-28 April 2017 http://www.esann.org/ Call for papers The call for papers is available at http://www.esann.org/. The deadline for submitting papers is November 19, 2016. The ESANN conferences cover machine learning, artificial neural networks, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered. In addition to regular sessions, 7 special sessions will be organized on the following topics: - Randomized Machine Learning approaches: analysis and developments - Deep and kernel methods: best of two worlds - Algorithmic Challenges in Big Data Analytics - Machine Learning in Biomorphic Robots - Environmental signal processing: new trends and applications - Biomedical data analysis in translational research: integration of expert knowledge and interpretable models - Processing, Mining and Visualizing Massive Urban Data ESANN 2017 builds upon a successful series of conferences organized each year since 1993. ESANN has become a major scientific event in the machine learning, computational intelligence and artificial neural networks fields over the years. The conference will be organized in Bruges, one of the most beautiful medieval towns in Europe. Designated as the "Venice of the North", the city has preserved all the charms of the medieval heritage. Its centre, which is inscribed on the Unesco World Heritage list, is in itself a real open air museum. We hope to receive your submission to ESANN 2017 and to see you in Bruges next year! ======================================================== ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning http://www.esann.org/ * For submissions of papers, reviews, registrations: Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at uclouvain.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at uclouvain.be ======================================================== -------------- next part -------------- An HTML attachment was scrubbed... URL: From jamesdukephd at gmail.com Thu Sep 22 09:35:55 2016 From: jamesdukephd at gmail.com (James Duke) Date: Thu, 22 Sep 2016 16:35:55 +0300 Subject: Connectionists: How to Make Intelligent Robots That Understand the World Message-ID: Hi there, The ones of you interested in machine learning and AI, there is coming live Ask Me More session on 28th of September, together with neuroscientist Danko Nikolic, who presents his vision on "How to Make Intelligent Robots That Understand the World"-https://goo.gl/kb7Ubb Best wishes, Dr. James Duke -------------- next part -------------- An HTML attachment was scrubbed... URL: From r.pascanu at gmail.com Thu Sep 22 09:37:58 2016 From: r.pascanu at gmail.com (Razvan Pascanu) Date: Thu, 22 Sep 2016 14:37:58 +0100 Subject: Connectionists: =?utf-8?q?NIPS_workshop_on_=E2=80=9CContinual_Lea?= =?utf-8?q?rning_and_Deep_Networks=E2=80=9D_=5Bapologies_for_cross-?= =?utf-8?q?posting=5D?= Message-ID: TL;DR: We invite you to our workshop on Continual Learning and Deep Networks, at this year?s NIPS. Submission deadline for 4-page abstracts is October 21. Submission page: https://easychair.org/conferences/?conf=cldl2016 --------------------- Description: Humans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial "continual learning" agent that constructs a sophisticated understanding of the world from its own experience, through the autonomous incremental development of ever more complex skills and knowledge. Hallmarks of continual learning include: interactive, incremental, online learning (learning occurs at every moment, with no fixed tasks or data sets); hierarchy or compositionality (previous learning can become the foundation far later learning); "isolaminar" construction (the same algorithm is used at all stages of learning); resistance to catastrophic forgetting (new learning does not destroy old learning); and unlimited temporal abstraction (both knowledge and skills may refer to or span arbitrary periods of time). Continual learning is an unsolved problem which presents particular difficulties for the deep-architecture approach that is currently the favoured workhorse for many applications. Some strides have been made recently, and many diverse research groups have continual learning on their road map. Hence we believe this is an opportune moment for a workshop focusing on this theme. The goals would be to define the different facets of the continual-learning problem, to tease out the relationships between different relevant fields (such as reinforcement learning, deep learning, lifelong learning, transfer learning, developmental learning, computational neuroscience, etc.) and to propose and explore promising new research directions. Confirmed speakers: - Claudia Clopath (Imperial College London) - Eric Eaton (University of Pennsylvania) - Raia Hadsell (Google DeepMind) - Honglak Lee (University of Michigan) - Joelle Pineau (McGill University) - Satinder Singh Baveja (Cogitai and University of Michigan) - Alexander Stoytchev (University of Iowa) - Richard Sutton (University of Alberta) Dates: - Submission deadline: Friday October 21 - Workshop: Saturday December 10 Submission format: 4 page extended abstracts, which can include previously published work here https://easychair.org/conferences/?conf=cldl2016. Travel grants are available thanks to our sponsors: DeepMind, Cogitai, Sony ! More details at the website: https://sites.google.com/site/cldlnips2016/ We look forward to seeing you in December! Razvan Pascanu, Mark Ring and Tom Schaul. -------------- next part -------------- An HTML attachment was scrubbed... URL: From brian at thinktopic.com Thu Sep 22 14:12:27 2016 From: brian at thinktopic.com (Brian Mingus) Date: Thu, 22 Sep 2016 12:12:27 -0600 Subject: Connectionists: Deep Learning Software Engineer at ThinkTopic in Boulder, Co Message-ID: ThinkTopic in beautiful Boulder, Colorado is a deep learning-oriented software consultancy that is looking for world class machine learning experts who can help us raise the bar in bringing the latest advancements to market for our clients. As a Machine Learner you will help us build out our own functional deep learning library written in Clojure and help us stay up-to-date on the latest advancements in the field. We are interested in everything from functional automatic differentiation to highway networks to you-name-it and have already assembled a world class team of engineers to complement you and help you grow your skills. For more information on the position see the job posting on our website http://thinktopic.com and while there check out the awesome team of engineers you'll be working with. -- *Brian Mingus* *Software Engineer* 1050 Walnut St., Suite 500 Boulder, CO, USA, 80302 cell: (720) 587.9482 thinktopic.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Thu Sep 22 11:14:08 2016 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 22 Sep 2016 08:14:08 -0700 Subject: Connectionists: NEURAL COMPUTATION - October 1, 2016 In-Reply-To: Message-ID: Neural Computation - Volume 28, Number 10 - October 1, 2016 Available online for download now: http://www.mitpressjournals.org/toc/neco/28/10 ----- Article Energy-efficient Neuromorphic Classifiers Daniel Marti, Mattia Rigotti, Mingoo Seok, and Stefano Fusi Note A Note on Divergences Xiao Liang Letters Simulation Neurotechnologies for Advancing Brain Research: Parallelizing Large Networks in NEURON William W Lytton, Alexandra H Seidenstein, Salvador Dura Bernal, Robert A McDougal, Felix Schuermann, and Michael L. Hines Integrator or Coincidence Detector - a Novel Measure Based on the Discrete Reverse Correlation to Determine a Neuron's Operational Mode Jacob Kanev, Achilleas Koutsou, Chris Christodoulou, and Klaus Obermayer The Space-clamped Hodgkin-Huxley System With Random Synaptic Input: Inhibition of Spiking by Weak Noise and Analysis With Moment Equations Henry Tuckwell, Susanne Ditlevsenc Presynaptic Spontaneous Activity Enhances the Accuracy of Latency Coding Marie Levakovac., Massimiliano Tamborrino, Lubomir Kostal, and Petr Lansky Learning Polychronous Neuronal Groups Using Joint Weight-Delay Spike-Timing Dependent Plasticity Haoqi Sun, Olga Sourina, and Guang-Bin Huang Dimensionality-Dependent Generalization Bounds for K-Dimensional Coding Schemes Tongliang Liu, Dacheng Tao, and Dong Xu The Functional Segregation and Integration Model (FSIM): Mixture Model Representations of Consistent and Variable Group-level Connectivity in fMRI Nathan W. Chuchill, Kristoffer Madsen, and Morten Morup ------------ 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 Michael.Zock at lif.univ-mrs.fr Thu Sep 22 12:42:56 2016 From: Michael.Zock at lif.univ-mrs.fr (Michael Zock) Date: Thu, 22 Sep 2016 18:42:56 +0200 Subject: Connectionists: deadline extension for 'Cogalex' (Cognitive Aspects of the Lexicon), October 2nd, 2016 Message-ID: <57E40A10.2090407@lif.univ-mrs.fr> *** EXTENDED DEADLINE** * Last andFinal Call forCogALex-V ** *New **Paper Submission Deadline: October 2nd * *New **notification date: October 21st * Cognitive Aspects of the Lexicon (CogALex-V) https://sites.google.com/site/cogalex2016/home Workshop co-lated with COLING (the 26th International Conference on Computational Linguistics, Osaka, Japan), December 12, 2016 Invited speaker: Chris Biemann (LT + HCC, Universit?t Hamburg , Germany) We are pleased to announce the 5th Workshop on 'Cognitive Aspects of the Lexicon' (Cogalex-V), taking place just before COLING (Osaka, Japan), December 12, 2016. 1 Context and background The way we look at the lexicon (creation and use) has changed dramatically over the past 30 years. While in the past being considered as an appendix to grammar, the lexicon has now moved to centre stage. Indeed, there is hardly any task in NLP which can be conducted without it. Also, rather than considering it as a static entity (database view), dictionaries are now viewed as dynamic networks, akin to the human brain, whose nodes and links (connection strengths) may change over time. Linguists work on products, while psychologists and computer scientists deal with processes. They decompose the task into a set of subtasks, i.e. modules between which information flows. There are inputs, outputs and processes in between. A typical task in language processing is to go from meanings to sound or vice versa, the two extremes of language production and language understanding. Since this mapping is hardly ever direct, various intermediate steps or layers (syntax, morphology) are necessary. Most of the work done by psycholinguists has dealt with the information flow from meaning (or concepts) to sound or the other way around. What has not been addressed though is the creation of a map of the mental lexicon, that is a represention of the way how words are organized or connected. In this respect WordNet and Roget's Thesaurus are probably closest to what one can expect these days. This being said, to find a word in a resource one has to reduce the search space (entire lexicon) and this is done via the knowledge one has at the onset of search. While the information stored in the lexicon is a product, its access is clearly a (cognitive, i.e. knowledge-based) process. 1.1 Goal The goal of COGALEX is to provide a forum for researchers in NLP, psychologists, computational lexicographers and users of lexical resources to share their knowledge and needs concerning the construction, organization and use of a lexicon by people (lexical access) and machines (NLP, IR, data-mining). Like in the past (2004, 2008, 2010, 2012 and 2014), we will invite researchers to address various unsolved problems, by putting this time stronger emphasis though on distributional semantics (DS). Indeed, we would like to see work showing the relevance of DS as a cognitive model of the lexicon. The interest in distributional approaches has grown considerably over the last few year, both in computational linguistics and cognitive sciences. A further boost has been provided by the recent hype around deep learning and neural embeddings. While all these approaches seem to have great potential, their added value to address cognitive and semantic aspects of the lexicon still needs to be shown. This workshop is about possible enhancements of lexical resources and electronic dictionaries, as well as on any aspect relevant to the achieve a better understanding of the mental lexicon and semantic memory.We solicit contributions including but not limited to the topics listed here below, topics, which can be considered from any of the following points of view: * (computational, corpus) linguistics, * neuro- or psycholinguistics (tip of the tongue problem, associations), * network related sciences (sociology, economy, biology), * mathematics (vector-based approaches, graph theory, small-world problem), etc. We also plan to organize a ?friendly competition? for corpus-based models of lexical networks and navigation, i.e. lexical access (see below). 1.2 Possible Topics 1.2.1 Analysis of the conceptual input of a dictionary user * What does a language producer start out with and how does this input relate to the target form? (meaning, collocation, topically related, etc.) * What is in the authors' minds when they are generating a message and looking for a word? * What does it take to bridge the gap between this input and the desired output (target word)? 1.2.2 The meaning of words * Lexical representation (holistic, decomposed) * Meaning representation (concept based, primitives) * Distributional semantics (count models, neural embeddings, etc. ) * Neurocomputational theories of content representation. 1.2.3 Structure of the lexicon * Discovering structures in the lexicon: formal and semantic point of view (clustering, topical structure) * Evolution, i.e. dynamic aspects of the lexicon (changes of weights) * Neural models of the mental lexicon (distribution of information concerning words, organization of words) 1.2.4 Methods for crafting dictionaries or indexes * Manual, automatic or collaborative building of dictionaries and indexes (crowd-sourcing, serious games, etc.) * Impact and use of social networks (Facebook, Twitter) for building dictionaries, for organizing and indexing the data (clustering of words), and for allowing to track navigational strategies, etc. * (Semi-) automatic induction of the link type (e.g. synonym, hypernym, meronym, association, collocation, ...) * Use of corpora and patterns (data-mining) for getting access to words, their uses, combinations and associations 1.2.5 Dictionary access (navigation and search strategies), interface issues, * Search based on sound, meaning or associations * Search (simple query vs. multiple words) * Search-space determination based on user's knowledge, meta-knowledge and cognitive state (information available at the onset, knowledge concerning the relationship between the input and the target word, ...) * Context-dependent search (modification of users? goals during search) * Navigation (frequent navigational patterns or search strategies used by people) * Interface problems, data-visualization * Creative ways of getting access to and using word associations (reading between the lines, subliminal communication). 2 Description of the shared tasks associated with the workshop. As part of the workshop, we propose a shared task concerning the corpus-based identification of semantic relations. The goal of this ?competition between gentlemen" is less the discovery of the best system, as the testing of the relative efficiency of different distributional models and other corpus-based approaches on a challenging semantic task. We will provide the training and test data, and the participants are expected to submit a short paper (4 pages) describing their approach and evaluation results (using the official scoring scripts), together with the output produced by their system on the test data. For more details see : https://sites.google.com/site/cogalex2016/home/shared-task 3 INVITED SPEAKER /Chris Biemann/, well known (among things) for his work on graph-based NLP, has kindly accepted to give the invited talk. Leader of the LT research group in Darmstadt, Chris is now affiliated with the Language Technology group of the university of Hamburg. 4 Deadlines. Workshop papers * October, 2nd: Submission deadline forpapers * October 21: Author notification * October 30: Camera ready due by Authors * November 6: Proceedings due by Workshop Organisers to Workshop & Publication Chairs. * December 12 : Workshop Shared task * September 26: Expression ofinterest (send message to : esantus at gmail.com) * October 15: Submission of system description (4+1 pages) and system output * October 25: Author notification * October 30: Camera ready due by Authors 5 Submission The submissions should be written in English and be anonymized for review. They must comply with the style-sheets provided by Coling: http://coling2016.anlp.jp/#instructions * Long papers may consist of 8 pages of content, plus 2 pages for references; * Short paper may consist of up to 4 pages of content, plus 2 pages for references * The respective final versions may be up to 9 pages for long papers and 5 pages for short ones. In both cases the number of pages for references is limited to 3 pages. Papers should be in PDF format and have to be submitted electronically via the START submission system (https://www.softconf.com/coling2016/ CogALex-V/). You probably have to register first, and then choose: submission, i.e. (https://www.softconf.com/coling2016/CogALex-V/user/scmd.cgi?scmd=submitPaperCustom&pageid=0). 6 Organizers. * Michael Zock (LIF, CNRS, Aix-Marseille University, Marseille, France) * Alessandro Lenci (Computational Linguistics Laboratory, University of Pisa, Italy) * Stefan Evert (FAU, Erlangen-N?rnberg, Germany) 7 Contact persons For general questions, please get in touch with Michael Zock (michael.zock at lif.univ-mrs.fr), for questions concerning the shared task, send an e-mail to Stefan Evert (stefan.evert at fau.de). 8 Program committee For details see : https://sites.google.com/site/cogalex2016/home/ ** -- ------------------------------------------------ Michael ZOCK Aix-Marseille Universit?, CNRS & LIF, UMR 7279, 163 Avenue de Luminy F-13288 Marseille / France Mail: michael.zock at lif.univ-mrs.fr Tel.: +33 (0) 4 91 82 94 88 Secr.: +33 (0) 4 91 82 90 70 Fax: +33 (0) 4 91 82 92 75 Web: http://pageperso.lif.univ-mrs.fr/~michael.zock/ ------------------------------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From compsens at medizin.uni-tuebingen.de Fri Sep 23 05:29:08 2016 From: compsens at medizin.uni-tuebingen.de (Compsens) Date: Fri, 23 Sep 2016 11:29:08 +0200 Subject: Connectionists: POSTDOC / PHD POSITION in Neuroscience (University of Tuebingen, Germany) Message-ID: <20160923112908.Horde.iUMfNAOfkYEKasD7MkmIePl@webmail.uni-tuebingen.de> POSTDOC / PHD POSITION: NEURAL REPRESENTATION OF SOCIAL INTENTION (Hertie Institute / Center for Integrative Neuroscience, University of Tuebingen, Germany) ============================================================ The Section for Computational Sensomotorics at the Center for Integrative Neurosciences (CIN) and the Hertie Institute for Clinical Brain Research (HIH) at the University of Tuebingen invites applications for a Postdoc or a PhD student with a good mathematical background for a maximum duration of 3 years. The position is funded by a grant of the Human Frontiers Science Foundation (HFSP) in collaboration with the California Institute of Technology (CALTECH), and Ohio State University (OSU). The project will focus on the development of neural and deep/machine learning-based theories for the processing of social signals and social intention, and their verification by psychophysical, and (in collaboration) also electrophysio- logical and fMRI experiments. What we offer: -------------- * top scientific environment (HIH is among the top 3 European institutions for clinical brain research); the CIN is an Excellence Cluster as part of the German Excellence Initiative in science; multiple leading Max Planck Institutes for related topics in Tuebingen; total > 600 researchers on the Tuebingen Neuroscience Campus working on many different aspects of neuroscience * close collaborations with leading international partners in neuro- and computer science * possibility of teaching and taking courses at the Graduate Training Center for Neuroscience (> 40 courses in molecular, behavioral neuroscience, and neural information processing) What we are looking for: ------------------------- * person with Masters (or PhD) degree in Computational Neuroscience or a related discipline (Computer Science, Engineering, Physics, Mathematics, Cognitive Science, Mathematical Psychology, etc.) * highly-motivated individual with enthusiasm for research; motivation and capability of self-driven pursuit of difficult problems * strong mathematical background and programming skills (at least in C or Java); willingness to learn relevant techniques and software products (e.g. for computer animation, deep learning, or the simulation of neural networks) * interest in social neuroscience, computational vision, and neural circuits at the level of single cells * English speaking and writing skills. People with inappropriate backgrounds, or without enthusiasm for science who look for a temporary job at a German university are discouraged from applying. Committed to Equal Opportunities. Interested people should send their application, including a CV, all marks form studies, 2 letters of reference, and a research statement of about one half page (explaining how their skills might support a project about the understanding neural basis of the processing of social signals and intention) to: Prof. Dr. Martin Giese Section for Theoretical Sensomotorics Dept. for Cognitive Neurology Hertie Institute for Clinical Brain Research & Center for Integrative Neuroscience University of Tuebingen Otfried-M?ller Str. 25 D-72076 Tuebingen GERMANY Tel.: +49 7071 2989124 Fax: +49 7071 294790 Email: martin.giese at uni-tuebingen.de Web: http://www.compsens.uni-tuebingen.de/ ============================================== From t.heskes at science.ru.nl Fri Sep 23 04:19:25 2016 From: t.heskes at science.ru.nl (Tom Heskes) Date: Fri, 23 Sep 2016 10:19:25 +0200 Subject: Connectionists: postdoc position in machine learning at Radboud University Nijmegen Message-ID: <57E4E58D.4020301@science.ru.nl> [please forward to anyone you think may be interested and qualified; with apologies for cross-posting] ------- A postdoc position is available in the Data Science department of the Institute for Computing and Information Sciences, Radboud University Nijmegen. The group, headed by Prof. Tom Heskes, works on the development and understanding of (probabilistic) machine learning methods, with a keen eye on applications in other scientific domains as well as industry. Through various collaborations with clinicians, we have unique access to challenging real-world patient data, with the opportunity to make a tangible contribution to better patient care. This particular postdoc position is predominantly funded by the TOP ZonMW project Parkinson Precision Medicine, in collaboration with Prof. Bas Bloem (Radboudumc) and Prof. Anne Stiggelbout (Leiden University). Successful applicants will have a (nearly completed) PhD in computer science, statistics, or a related discipline. A strong background in mathematics and programming (e.g. Python, R, Matlab), and experience with machine learning, pattern analysis, or advanced statistics are essential. We offer a 2,5 year postdoc position, with competitive pay and excellent benefits, in a very friendly, interactive and international working environment, at the top computer science institute in the Netherlands. For more information and to apply see http://www.ru.nl/vacaturebeschrijving?recid=588061 From martaruizcostajussa at gmail.com Fri Sep 23 10:30:00 2016 From: martaruizcostajussa at gmail.com (Marta Ruiz) Date: Fri, 23 Sep 2016 16:30:00 +0200 Subject: Connectionists: DEADLINE EXTENSION: HyTra-6 Sixth Workshop on Hybrid Approaches to Translation (in conjunction with COLING) Message-ID: *HyTra-6: Sixth Workshop on Hybrid Approaches to Translation* **** NEW Paper submission October 2nd, 2016 **** The Sixth Workshop on Hybrid Approaches to Translation (HyTra-6), in conjunction with *COLING 2016*, intends to invite work contributions on integrating any type of data-driven and linguistic-based machine translation approaches. Nowadays, there are more paradigms competing in machine translation including statistical (phrase-based, hierarchical and syntax-based), neural-based and rule-based. Each of them has their own advantages and disadvantages which make it worth the research on hybridization, integration and/or combination of approaches. Given that academic and industry perspectives may differ on the opinion of which are the most suitable paradigms, HyTra gives a strong relevance to the participation of both in the workshop. The fact that machine translation is a highly interdisciplinary field (including engineers, computer scientists, mathematicians, translators, linguists?), specially in the research of hybridization, enriches the workshop in its discussions, proceedings, invited talks and, even, in one contributed volume published by Springer. In this edition, HyTRA will specially focus on motivating the cooperation and interaction between the different human components, as well as to foster innovation and creativity in the Hybrid Machine Translation research community. That is why we encourage the participation of the different integrating fields (engineers, computer scientists, mathematicians, translators, linguists either from academy or industry) to contribute to our special call of shared task proposals. Given the complementarity and mutual attractiveness of data-driven and rule-based MT, the appearance of new data-driven approaches (such as the neural-based one), the question is what the combined architecture should look like. We will solicit contributions including but not limited to the following topics: ? ways and techniques of hybridization ? architectures for the rapid development of hybrid MT systems ? applications of hybrid systems ? hybrid systems dealing with under-resourced languages ? hybrid systems dealing with morphologically rich languages ? using linguistic information (morphology, syntax, semantics) to enhance statistical MT (e.g. with hierarchical or factored models) ? bootstrapping rule-based systems from corpora ? extraction of dictionaries from parallel and comparable corpora ? induction of morphological, grammatical, and translation rules from corpora ? improving MT with statistical and rule-based computational linguistics methods (word sense disambiguation, information extraction, terminology mining, metaphor recognition, etc.) ? machine learning techniques for hybrid MT and complex data structures ? describing and using structural mappings between languages (e.g. tree-structures using synchronous/transduction grammars) ? system combination approaches such as multi-engine MT (parallel) or automatic post-editing (sequential) ? hybrid methods in spoken language translation ? heuristics for limiting the search space in hybrid MT ? translation of user generated contents ? alternative methods for the fair evaluation of the output of different types of MT systems (e.g. relying on linguistic criteria) ? use of word embeddings and continuous vector space representations in hybrid MT ? neural networks, deep learning and neural MT hybridization ? open source tools and free language resources for hybrid MT ? presentations of industrial hybrid MT systems and technologies which involve hybrid MT systems in commercial and professional applications *Call for shared task proposals* We solicit proposals for shared tasks relevant to hybrid translation with the potential to be conducted in future editions of the HyTra workshop series. Proposals should include: 1) A definition of the objectives of the shared task (e.g. user generated content translation) ; 2) A suggestion of a baseline system (if appropriate) ; 3) Data to conduct the shared task; 4) An evaluation measure Proposals should be different from those conducted elsewhere. We particularly welcome proposals which motivate the MT industry to participate. The proposals should be 2 pages long in the format required by the workshop. The best proposals will be published in the proceedings and discussed in a panel. The authors of convincing proposals will be invited to organize a shared task in conjunction with upcoming editions of the HyTra workshop series. Please send your proposals to patrik.lambert at gmail.com *Important Dates* *NEW Paper submission October 2nd, 2016* *Notification to authors* October 16th, 2016 *Camera-ready deadline* October 30th, 2016 *Workshop *December 11th, 2016 *Program Committee * ? Arianna Bisazza, University of Amsterdam, The Netherlands ? Bogdan Babych, University of Leeds, UK ? Rafael E. Banchs, Institute for Infocomm Research, Singapore ? Alexey Baytin, Yandex, Moscow, Russia ? Pierrette Bouillon, ISSCO/TIM/ETI, University of Geneva, Switzerland ? Marta R. Costa-jussa, UPC, Barcelona ? Josep Maria Crego, Systran, Paris, France ? Kurt Eberle, Lingenio GmbH, Heidelberg, Germany ? Cristina Espa?a, UPC, Barcelona ? Christian Federmann, Microsoft Research, Seattle, USA ? Jos? A. R. Fonollosa, UPC, Barcelona ? Maxim Khalilov, Berlin, Germany ? Udo Kruschwitz, University of Essex, UK ? Patrik Lambert, Pompeu Fabra University, Barcelona, Spain ? Maite Melero, Pompeu Fabra University, Barcelona, Spain ? Reinhard Rapp, Universities of Aix-Marseille, France, and Mainz, Germany ? George Tambouratzis, Institute for Language and Speech Processing, Greece ? J?rg Tiedemann, University of Uppsala, Sweden ? Grigori Sidorov, Instituto Polit?cnico Nacional, Mexico *Organizing Committee* Patrik Lambert, Bogdan Babych, Kurt Eberle, Rafael E. Banchs, Reinhard Rapp and Marta R. Costa-juss? *Contact* Patrik Lambert (patrik.lambert at gmail.com) -------------- next part -------------- An HTML attachment was scrubbed... URL: From hava at cs.umass.edu Sun Sep 25 08:38:14 2016 From: hava at cs.umass.edu (Hava Siegelmann) Date: Sun, 25 Sep 2016 08:38:14 -0400 Subject: Connectionists: DARPA for connectionists Message-ID: <57E7C536.3060300@cs.umass.edu> Hello friends and colleagues, I wanted to announce that I'm holding a post at DARPA now, see http://www.darpa.mil/staff/dr-hava-siegelmann I'll soon put an RFI (request for information) to find where the communtee's interest is, but meanwhile, if you have great ideas about transferring AI beyond the state of the art (life long learning, context-based learning, low energy learning, etc.) as well as great applications, and want to have an affect on shaping my upcoming programs, you may contact me with suggestions. All the best Hava -- 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 danko.nikolic at googlemail.com Sun Sep 25 08:30:54 2016 From: danko.nikolic at googlemail.com (=?UTF-8?Q?Danko_Nikoli=c4=87?=) Date: Sun, 25 Sep 2016 14:30:54 +0200 Subject: Connectionists: "ask me more session" on AI-Kindergarten Message-ID: <9c908228-20b3-19aa-4534-610ff77c3c8e@gmail.com> Dear connectionists, This is to inform you about the upcoming "ask me more" session at guaana.com that will host this time the concept of AI-Kinderarten (which is itself founded in the theory of practopoiesis): https://www.guaana.com/ask-me-more/ZPGyLZefsTehcgknP This is a perfect opportunity to ask further questions. The session takes place on this Wednesday. Best, Danko -- Prof. Dr. Danko Nikoli? Web: http://www.danko-nikolic.com ---------------------------- From csutton at inf.ed.ac.uk Sun Sep 25 16:33:26 2016 From: csutton at inf.ed.ac.uk (Charles Sutton) Date: Sun, 25 Sep 2016 21:33:26 +0100 Subject: Connectionists: CFP: NIPS 2016 Workshop on Artificial Intelligence for Data Science Message-ID: ==================================================== CALL FOR PAPERS NIPS 2016 Workshop on Artificial Intelligence for Data Science (AI4DataSci) Saturday 10 December 2016, Barcelona, Spain Submission deadline: 1 November 2016 http://workshops.inf.ed.ac.uk/nips2016-ai4datasci/ ==================================================== We invite researchers to submit recent work on artificial intelligence methods to support the practical process of data analytics. Submissions should take the form of extended abstracts of approximately two pages in NIPS format. Please see workshop web site (above) for submission instructions. WORKSHOP DESCRIPTION Machine learning methods have been applied beyond their origins in artificial intelligence to a wide variety of data analysis problems in fields such as science, health care, technology, and commerce. Previous research in machine learning, perhaps motivated by its roots in AI, has primarily aimed at fully-automated approaches for prediction problems. But predictive analytics is only one step in the larger pipeline of data science, which includes data wrangling, data cleaning, exploratory visualization, data integration, model criticism and revision, and presentation of results to domain experts. An emerging strand of work aims to address all of these challenges in one stroke is by automating a greater portion of the full data science pipeline. This workshop will bring together experts in machine learning, data mining, databases and statistics to discuss the challenges that arise in the full end-to-end process of collecting data, analysing data, and making decisions and building new methods that support, whether in an automated or semi-automated way, more of the full process of analysing real data. Considering the full process of data science raises interesting questions for discussion, such as: What aspects of data analysis might potentially be automated and what aspects seem more difficult? Statistical model building often emphasizes interpretability and human understanding, while machine learning often emphasizes predictive modeling --- are ML methods truly suitable for supporting the full data analysis pipeline? Do recent advances in ML offer help here? Finally, are there low hanging fruit, i.e., how much time is wasted on routine tasks in scientific data analysis that could be automated? Specific topics of interest include: data cleaning, exploratory data analysis, semi-supervised learning, active learning, interactive machine learning, model criticism, automated and semi-automated model construction, usable machine learning, interpretable prediction methods and automatic methods to explain predictions. We are especially interested in contributions that take a broader perspective, i.e., that aim toward supporting the process of data science more holistically. CONFIRMED SPEAKERS Thomas Dietterich, Oregon State University Carlos Guestrin, University of Washington Others TBC WORKSHOP ORGANIZERS James Geddes, The Alan Turing Institute Zoubin Ghahramani, Cambridge University Padhraic Smyth, University of California Irvine Charles Sutton, University of Edinburgh Chris Williams, University of Edinburgh KEY DATES Paper submission: 1 November 2016 Acceptance notification: 16 November 2016 Workshop: 10 December 2016 -- Charles Sutton * Reader in Machine Learning * University of Edinburgh Director, EPSRC CDT in Data Science * http://datascience.inf.ed.ac.uk/ Faculty Fellow, Alan Turing Institute * http://turing.ac.uk/ Please excuse brevity: http://theoatmeal.com/comics/email_monster The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From yang at maebashi-it.org Mon Sep 26 01:35:40 2016 From: yang at maebashi-it.org (Yang) Date: Mon, 26 Sep 2016 14:35:40 +0900 Subject: Connectionists: [BIH-WI 2016] Call for Participation Message-ID: [Apologies if you receive this more than once] =============================================== CALL FOR PARTICIPATION The 2016 International Conference on Brain Informatics & Health (BIH'16) IEEE/WIC/ACM International Conference on Web Intelligence 2016 (WI'16) A Celebration of the 60th Anniversary of AI October 13-16, 2016, Hilton Omaha, USA Homepage: http://wibih.unomaha.edu/ ================================================ ************************************************************* On-line registration (and more information) at https://wibih.unomaha.edu/bih/register Book your hotel room with a discount rate at Hilton Omaha https://wibih.unomaha.edu/bih/accomodation ************************************************************* BIH'16 Keynote Skeakers +++++++++++++++++++++++ Dr. Stephen Smith, Allen Institute for Brain Science Shotgun Connectomic Analysis of Cortical Synaptic Networks Dr. Ivan Soltesz, Stanford School of Medicine Mechanisms of Network Oscillations in Data-driven Full-scale and Rationally Derived Simple Models of the Hippocampus WI'16 Keynote Skeakers ++++++++++++++++++++++ Dr. Leslie Valiant (Turing Award 2010), Harvard University A Computational Model and Theory of Cortex Dr. Butler Lampson (Turing Award 1992), Microsoft Corporation and MIT Personal Control of Data BIH'16 Feature Talks ++++++++++++++++++++ Dr. Steven Schiff, Pennsylvania State University Model-based Observation and Control for the Brain: >From Control of Seizures and Migraines, to Reducing Infant Brain Infections in Africa Dr. Kristen Harris, University of Texas at Austin Analytical Challenges to Understanding Subcellular Resource Allocation for Synaptic Plasticity and Homeostasis Dr. Giulio Tononi, University of Wisconsin-Madison Consciousness: From Theory to Practice Dr. Bob Jacobs, Colorado College Cortical Neuromorphology Beyond Rodents and Primates: A Personal Journey Dr. Partha Mitra, Cold Spring Harbor Laboratory Neuron Trees in the Brain Jungle: Mapping Brainwide Connectivity Dr. Paola Pergami, George Washington University Big Data and Advanced Imaging in Clinical Decision Making: Are We There Yet? WI'16 Feature Talks +++++++++++++++++++ Dr. Naren Ramakrishnan, Virginia Tech Forecasting Significant Societal Events using Open Source Indicators Dr. Vijay Raghavan, University of Louisiana at Lafayette Triangular Spatial Relationships Based Protein 3-D Comparison Dr. Marek Rusinkiewicz, New Jersey Institute of Technology Towards Smarter Cyber Security Dr. Daniel Siewiorek, Carnegie Mellon University Converting Mobile Sensing into Data and Data into Action Dr. Chris Welty, Google Towards an Embedded Theory of Truth BIH'16-WI'16 Joint Panel ~~~~~~~~~~~~~~~~~~~~~~~~ Connecting Network and Brain with Big Data Chairs: Yong Shi and Ning Zhong Panelits: Giorgio Ascoli, George Mason University Butler Lampson, Microsoft & MIT Hanchuan Peng, Allen Institute for Brain Science Paola Pergami, George Washington University Vijay Raghavan, University of Louisiana at Lafayette Ivan Soltesz, Stanford University Leslie Valiant, Harvard University Chris Welty, Google Research ------------- The two conferences will be co-located and have a joint opening, keynotes and invited talks, panel, reception and banquet. Attendees only need to register for one conference and can attend workshops, sessions, keynote/invited talks, panel and tutorials across the two conferences. ************************************************************* On-line registration (and more information) at https://wibih.unomaha.edu/bih/register Book your hotel room with a special discount at Hilton Omaha https://wibih.unomaha.edu/bih/accomodation ************************************************************* Regular registration (non-authors) covers all events of technical program (plenary talks, tutorials, workshops, parallel sessions, industry/demo sessions, etc.), the reception, coffee breaks and lunches. Schedule Outline ++++++++++++++++ October 13: Workshop & Tutorial Day October 14: BIH'16-WI'16 Joint Day October 15-16: Feature Talks, Special-sessions, and Presentations of Accepted Papers in parallel sessions TUTORIALS +++++++++ T1: Context-Awareness in Information Retrieval and Recommender Systems Yong Zheng, Illinois Institute of Technology, USA T2: Ontology Learning and Population from Text Background Rosario Girardi, Federal University of Maranh o, Brasil WORKSHOPS & SPECIAL SESSIONS ++++++++++++++++++++++++++++ BIH'16: ~~~~~~~ B1: International Workshop on Brain and Artificial Intelligence (BAI 2016) B2: International Workshop on Services and Data Modeling in Life Sciences (SDMLS 2016) B3: International Workshop on Brain Big Data Based Wisdom Service B4: International Workshop on Neuromorphic Computing and Algorithms B5: International Workshop on Big Data Neuroimaging Analytics for Brain and Mental Health B6: Special Session on BigNeuron Project WI'16: ~~~~~~ W1: The International Workshop on Web Personalization and Social Media W2: The Second Workshop on Complex Methods for Data and Web Mining W3: International Workshop on Educational Recommender Systems W4: The First International Workshop on the Internet of Agents (IoA) W5: The 1st International Workshop on Platforms and Applications for Social Problem Solving and Collective Reasoning W6: International Workshop on Advanced Methods in Optimization and Machine Learning SOCIAL PROGRAM ++++++++++++++ October 13, 18:00-20:00 Pre-Conference Reception (with hors d'oeuvres) at the Conference Hotel (Sponsored by Hilton) October 14, 17:00-19:00 -- Tour of the Henry Doorly Zoo 19:00-21:00 -- Welcome Reception (with dinner) sponsored by the Greater Omaha Convention & Visitors Bureau Durham TreeTops Restaurant at the Henry Doorly Zoo October 15, 18:30 to 21:00 -- UNO Jazz Quintet 19:00 to 21:00 -- Banquet and Awards Ceremony in the Conference Hotel You can also enjoy the city of Omaha. More information about the conference hotel, visas and local information can be obtained from the conference homepage: http://wibih.unomaha.edu/ CONTACT INFORMATION +++++++++++++++++++ Deepak Khazanchi Bettina Lechner -------------- next part -------------- An HTML attachment was scrubbed... URL: From marcusg at itee.uq.edu.au Mon Sep 26 02:40:27 2016 From: marcusg at itee.uq.edu.au (Marcus Gallagher) Date: Mon, 26 Sep 2016 16:40:27 +1000 Subject: Connectionists: Lecturer/Senior Lecturer/Associate Professor in Data Science, The University of Queensland Message-ID: ================== Lecturer (Level B)/Senior Lecturer (Level C)/Associate Professor (Level D) in Data Science The University of Queensland The remuneration package will be in the range $89,459 - $106,232 per annum (Level B); $109,587 - $126,360 per annum (Level C); and $131,951 - $145,370 per annum (Level D), plus employer superannuation contributions of up to 17% (total package will be in the range $104,667 - $124,292 (Level B); $128,217 - $147,841 (Level C); $154,383 - $170,083 (Level D) per annum. =================== The University of Queensland is developing a new Master of Data Science Program, to be offered from 2017. This is a joint initiative of the School of Information Technology and Electrical Engineering and the School of Mathematics and Physics at UQ. Four continuing (tenure-track) positions are available (two in each School). Full details are available here: School of ITEE positions: http://jobs.uq.edu.au/caw/en/job/499451/lecturersenior-lecturerassociate-professor School of Maths and Physics positions: http://jobs.uq.edu.au/caw/en/job/499490/lecturersenior-lecturerassociate-professor-in-data-science Cheers, Marcus. -- A/Prof Marcus Gallagher Complex & Intelligent Systems, School of ITEE University of Queensland 4072 Australia http://www.itee.uq.edu.au/~marcusg | +61 7 3365 6197 | CRICOS No. 00025B From leonel.rozo at iit.it Mon Sep 26 03:41:55 2016 From: leonel.rozo at iit.it (Leonel Rozo) Date: Mon, 26 Sep 2016 09:41:55 +0200 Subject: Connectionists: [journals] CfP - AURO Special Issue on Learning for Human-Robot Collaboration Message-ID: [Apologies for cross-posting] Dear colleagues, We are pleased to announce the Call for Papers of the AURO special Issue on "Learning for Human-Robot Collaboration". Please see all the details below. /Autonomous Robots Journal/ Special Issue: *Learning for Human-Robot Collaboration* Deadline: _November 30th, 2016_ Once isolated behind safety fences, the new emerging generation of robots endowed with more precise and sophisticated sensors, as well as better actuators, are materializing the idea of having robots working alongside people not only on manufacturing production lines, but also in spaces such as houses, museums, and hospitals. In this context, one of the next frontiers is the collaboration between humans and robots, which raises new challenges for robotics. A collaborative robot must be able to assist humans in a large diversity of tasks, understand its collaborator's intentions as well as communicate its own, predict human actions to adapt its behavior accordingly, and decide when it can lead the task or when just follow its human counterpart. All these aspects demand the robot to be endowed with an adaptation capability so that it can satisfactorily collaborate with humans. In this sense, learning is a crucial feature for creating robots that can execute different tasks, and rapidly adapt to its human partner's actions and requirements. The goal of this special issue is to document and highlight recent progress in the use of machine learning for human-robot collaboration tasks. In recent years, various interesting approaches and systems have been proposed that tackle different aspects of human-robot collaboration. This journal special issue will therefore present the state-of-the-art in the field and discuss future challenges and research opportunities. List of topics: Papers addressing one or more of the topics below in the context of human-robot collaboration are of particular interest: * Learning from demonstration * Reinforcement learning * Active learning * Force and impedance control * Physical human-robot interaction * Human-robot coordination * Recognition and prediction of human actions * Reactive and proactive behaviors * Roles allocation * Haptic communication * Cooperative human-human interaction * Human activity understanding * Learning from tactile experiences * Human-robot collaborative tasks in manufacturing Important Dates: * Paper submission deadline: November 30th, 2016 * Notification to authors: January 15, 2017 * Final manuscript due: February 1st, 2017 * Final decision: February 15th, 2017 Guest editors: Heni Ben Amor (hbenamor at asu.edu) - Assistant Professor (Arizona State University) Leonel Rozo (leonel.rozo at iit.it) - Senior postdoctoral fellow (Italian Institute of Technology IIT) Sylvain Calinon (sylvain.calinon at idiap.ch) - Permanent Researcher (IDIAP research institute) Dongheui Lee (dhlee at tum.de) - Assistant Professor (Technical University of Munich) Anca Dragan (anca at berkeley.edu) - Assistant Professor (UC Berkeley) Submission: Papers must be prepared in accordance with AURO guidelines. All papers will be reviewed following the regular reviewing procedure of the journal. More information at: http://static.springer.com/sgw/documents/1576377/application/pdf/AURO+CFP+-+Human-Robot+Collaboration.pdf -- Leonel Rozo, Senior postdoctoral researcher Advanced Robotics Department Istituto Italiano di Tecnologia (IIT) http://leonelrozo.weebly.com/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From joseph.austerweil at gmail.com Sun Sep 25 15:46:33 2016 From: joseph.austerweil at gmail.com (Joseph Austerweil) Date: Sun, 25 Sep 2016 15:46:33 -0400 Subject: Connectionists: Fwd: Interdisciplinary Cognitive Science / Computational Cognition Assistant Prof @ Berkeley In-Reply-To: References: <304A2EAA-35D5-4344-925E-DD1CCD2AB81F@berkeley.edu> Message-ID: On Behalf of Tania Lombrozo (lombrozo at berkeley.edu) at UC Berkeley, Dear Colleagues, This year we have a search for an Assistant Professor in Interdisciplinary Cognitive Science / Computational Cognition at UC Berkeley. I would very much appreciate your help in circulating this ad to promising candidates who work within cognition / cognitive science, especially those with a formal or computational bent. We are eager to recruit a broad and diverse set of applicants. We are accepting applications through November 15. You can find a copy of the job description and application instructions at https://aprecruit.berkeley.edu/apply/JPF01118, with the job description additionally pasted below. Thank you for your time! Sincerely, Tania Lombrozo ----- The Department of Psychology and the Cognitive Science Program seek to fill a tenure- track assistant professor faculty position in the area of computational cognitive science, with an anticipated start date of July 1, 2017. We are interested in candidates with exceptional promise who are conducting research in cognition from an interdisciplinary perspective. Research interests may include but are not limited to memory, learning, reasoning, problem solving, and decision-making. We are especially interested in applicants taking an interdisciplinary approach that bridges psychology and another discipline within cognitive science, such as computer science, philosophy, linguistics, anthropology, biology, or education, and in applicants with skills in computational modeling, data science, or other formal approaches. The position will be within Psychology, but teaching commitments will be distributed across Psychology and the Cognitive Science Program. The department is interested in candidates who will contribute to diversity and equal opportunity in higher education through their teaching. The University is committed to supporting employees as they balance work and family. Ph.D. or equivalent degree is required by date of hire. Candidates must have completed all degree requirements except the dissertation at the time of application. The department is interested in candidates who will contribute to diversity and equal opportunity in higher education through their teaching, research, and service. To apply, please go to the following link: https://aprecruit.berkeley.edu /apply/JPF01118 Applicants should submit a cover letter, curriculum vitae, statement of research, summary of teaching experience and interests, a brief statement addressing past and/or potential contributions to diversity through research, teaching, and/or service, and two to five reprints or preprints. Applicants should also arrange for the online submission of three to five letters of recommendation. All letters will be treated as confidential per University of California policy and California state law. Please refer potential referees, including when letters are provided via a third party (i.e., dossier service or career center), to the UC Berkeley statement of confidentiality (http://apo.berkeley.edu/evalltr.html) prior to submitting their letters. Applications must be received by November 15, 2016. Please direct questions to psychsearch at berkeley.edu, and include ?Interdisciplinary Approaches to Cognition? in the subject line. The University is committed to addressing the family needs of faculty, including dual career couples and single parents. For information about potential relocation to Berkeley, or career needs of accompanying partners and spouses, please visit: http://ofew.berkeley.edu/new- faculty 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, sexual orientation, gender identity, national origin, disability, age or protected veteran status. For the complete University of California nondiscrimination and affirmative action policy see: http://policy.ucop.edu/doc/400 0376/NondiscrimAffirmAct. -- Tania Lombrozo Associate Professor Department of Psychology University of California, Berkeley http://cognition.berkeley.edu http://www.npr.org/blogs/13.7/ -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From niebur at jhu.edu Mon Sep 26 12:26:00 2016 From: niebur at jhu.edu (Ernst Niebur) Date: Mon, 26 Sep 2016 12:26:00 -0400 Subject: Connectionists: Systems Neuroscience Faculty Position at Johns Hopkins University In-Reply-To: References: Message-ID: > > The Johns Hopkins Mind/Brain Institute (MBI) invites applications for a > tenure-track faculty position (any rank) in the Neuroscience Department of > the Johns Hopkins University School of Medicine (JHUSOM). Applicants will > be expected to conduct an independent research program in systems > neuroscience, focused on high-level perceptual and/or cognitive brain > mechanisms. MBI emphasizes the application of state-of-the-art experimental > and analytical methods in mammalian models including non-human primates. We > are committed to hiring candidates who will contribute to diversity and > excellence in the field of neuroscience through research, teaching, and/or > service. > > The Mind/Brain Institute was established in 1994, with a generous gift > from Zanvyl Krieger, to address the great scientific question of the 21st > century: How does neural activity in the brain give rise to mental > phenomena? Our goal is to understand, at the most fundamental, algorithmic > level, how the brain processes information about the world to generate > perception, knowledge, decision, and action. Our researchers hold academic > appointments in the JHUSOM Neuroscience Department. We interact extensively > with faculty and students in other departments, including Biomedical > Engineering, Psychological and Brain Sciences, and Cognitive Science. > > Johns Hopkins University is committed to active recruitment of a diverse > faculty and student body. The University 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. Consistent with the University?s goals of > achieving excellence in all areas, we will assess the comprehensive > qualifications of each applicant, beginning December 1, 2016. Applicants > should submit a PDF file comprising a cover letter, CV, and research > statement to the address below and arrange for three reference letters to > be sent to the same address. > > > Charles E. Connor > > Chair, MBI Search Committee > > Johns Hopkins University > > 3400 N Charles St > > Baltimore, Maryland 21218 > > *NeuroSearchMBI at jhu.edu * > > An EEO/AA employer > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From jizhengp at gmail.com Tue Sep 27 01:44:18 2016 From: jizhengp at gmail.com (Ji Zhengping) Date: Mon, 26 Sep 2016 22:44:18 -0700 Subject: Connectionists: Jobs: Deep Learning and Computer Vision Position at Samsung Pasadena Lab Message-ID: [Apologies for cross-posting] Samsung Pasadena Lab is hiring the talents in deep learning and computer vision. Please see https://www.linkedin.com/jobs/view/140716679 for brief requirement and feel free to contact zhengp.ji at samsung.com for more details. -------------- next part -------------- An HTML attachment was scrubbed... URL: From marco.baroni at unitn.it Mon Sep 26 16:11:32 2016 From: marco.baroni at unitn.it (Marco Baroni) Date: Mon, 26 Sep 2016 22:11:32 +0200 Subject: Connectionists: CommAI-env release Message-ID: We are happy to announce the release of the first prototype of CommAI-env, an environment meant to stimulate the development of communication-based AI. The environment and related documentation are available at the following link: https://github.com/facebookresearch/CommAI-env We'd love to hear your feedback on how to improve CommAI-env. In particular, we welcome critiques of the environment in the form of abstracts submitted to the Machine Intelligence at NIPS Workshop, deadline October 9th: https://mainatnips.github.io/ -- Marco Baroni Center for Mind/Brain Sciences (CIMeC) University of Trento http://clic.cimec.unitn.it/marco -------------- next part -------------- An HTML attachment was scrubbed... URL: From pascal.fua at epfl.ch Tue Sep 27 10:44:12 2016 From: pascal.fua at epfl.ch (Pascal Fua) Date: Tue, 27 Sep 2016 16:44:12 +0200 Subject: Connectionists: Post-doctoral Position in Computer Vision at EPFL Message-ID: EPFL's Computer Vision Laboratory (http://cvlab.epfl.ch/) has an opening for a post-doctoral fellow. The position is initially offered for 1 year and can be extended for up to 4 years total. Description: CVLab is collaborating with PSA (https://www.groupe-psa.com/fr/) in Paris on the theme of self-driving vehicles. The goal of this project is to design and develop efficient algorithms that produce in real-time a 3D model of the scene around a car from cameras mounted on the vehicle. In addition to performing Simultaneous Localization and Mapping (SLAM), our algorithms will estimate a semantic class label for each reconstructed 3D point. Altogether, this will allow us to provide an accurate 3D map of the car's surroundings, potentially depicted from various viewpoints, and to reason about obstacles and free space in 3D rather than in the images. Position: The Computer Vision Laboratory offers a creative international environment, a possibility to conduct competitive research on a global scale and involvement in teaching. There will be ample opportunities to cooperate with some of the best groups in Europe and elsewhere. EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers away from the city of Geneva. Salaries for post-doctoral fellows start from CHF 81,400 per year, the precise amount to be determined by EPFL's department of human resources. Education: Applicants are expected to have finished, or be about to finish their Ph.D. degrees, to have a strong background in Computer Vision and Statistical Machine Learning, and to have a track record of publications in top conferences and journals. Strong programming skills (C or C++) are a plus. French language skills are not required, English is mandatory. Application: Applications must be sent by email to Ms. Staudenmann (ariane.staudenmann at epfl.ch). They must contain a statement of interest, a CV, a list of publications, and the names of three references. From schapire at microsoft.com Tue Sep 27 10:56:49 2016 From: schapire at microsoft.com (Robert Schapire) Date: Tue, 27 Sep 2016 14:56:49 +0000 Subject: Connectionists: postdoc positions at Microsoft Research NYC Message-ID: Microsoft Research NYC seeks outstanding applicants for a postdoctoral researcher in the area of machine learning or a related field. DEADLINE FOR FULL CONSIDERATION: November 27, 2016. Application instructions are at the end of this email. More information about postdoc and researcher positions can also be found at: https://www.microsoft.com/en-us/research/group/machine-learning-nyc. Microsoft Research offers an exhilarating and thriving environment for cutting-edge, multidisciplinary research, both theoretical and applied, with access to an extraordinary diversity of big and small data sources, an open publications policy, and close links to top academic institutions around the world. We seek applicants from all areas of machine learning and related fields with a passion and demonstrated ability for independent research, including a strong publication record at top research venues. The start date for this position is July 3, 2017. Postdoc positions at Microsoft Research provide emerging scholars an opportunity to develop their research careers as members of a very active machine learning community at a world-class research organization. Postdocs in our lab are encouraged to define their own research agenda and to demonstrate their ability to drive forward an effective program of research. They may also get the chance to see their ideas realized in products and services that will be used worldwide. Microsoft Research New York City is the newest MSR lab, comprising thirty full-time researchers and postdocs working in machine learning, systems, computational social science, algorithmic economics, information retrieval, and social media. The lab is highly collaborative and interdisciplinary, and is actively engaged with the local academic and tech communities. The machine learning group includes Alekh Agarwal, Miroslav Dud?k, John Langford, Robert Schapire, Alex Slivkins, Jenn Wortman Vaughan, and Hanna Wallach. Examples of current machine learning projects and directions include: ? Active learning. ? Bayesian latent variable modeling. ? Contextual bandits, exploration and incentives. ? Ethics of machine learning. ? Logarithmic-time prediction for problems with extremely large label sets. ? Online learning and game theory. ? Prediction markets and auction design. ? Reinforcement learning for large complex environments, such as Minecraft. ? Structured prediction, including applications to NLP. A sampling of recent publications can be found at: https://www.microsoft.com/en-us/research/group/machine-learning-nyc. Postdocs receive a competitive salary and benefits package, and are eligible for relocation expenses. Postdocs are typically hired for a two-year term appointment following the academic calendar, starting in July 2017. Applicants must have completed the requirements for a PhD, including final submission of their dissertation, prior to joining Microsoft Research. Applicants with tenure-track offers from other institutions will be considered, provided they are able to defer their start date to accept our position. HOW TO APPLY To apply, submit an online application on the Microsoft Research Careers website at: https://careers.research.microsoft.com. To be assured of full consideration, all materials, including reference letters, need to be received by November 27, 2016. Applications received after that date may or may not be considered. In completing your application, please be sure to follow these additional instructions: 1. In addition to submitting your CV and the names of three referees (including your dissertation advisor) as required by the online application, please also upload the following three attachments: ? two conference or journal articles, book chapters, or equivalent writing samples (uploaded as two separate attachments); ? an academic research statement (approximately 3-4 pages) that outlines your research achievements and agenda. 2. Indicate that your research area of interest is "Machine Learning, Adaptation, and Intelligence" and that your location preference is "New York." Include "Robert Schapire" as the name of a Microsoft Research contact (you may include additional contacts as well). NOTE: IF YOU DO NOT MARK THESE PREFERENCES, IT IS VERY UNLIKELY THAT WE WILL RECEIVE YOUR APPLICATION. After you submit your application, a request for letters will be sent to your list of referees on your behalf. Note: The application system will not request reference letters until after you have submitted your application. You may wish to alert your letter writers in advance so that they will be ready to submit your letter by our application deadline of November 27, 2016. You can check the progress on individual reference requests by clicking the status tab within your application page. -------------- next part -------------- An HTML attachment was scrubbed... URL: From schapire at microsoft.com Tue Sep 27 13:35:50 2016 From: schapire at microsoft.com (Robert Schapire) Date: Tue, 27 Sep 2016 17:35:50 +0000 Subject: Connectionists: full-time researcher positions at Microsoft Research NYC Message-ID: Microsoft Research NYC seeks outstanding and experienced applicants for full-time researcher positions in machine learning or a related field, such as statistics, computer vision, natural language processing, or other subfields of artificial intelligence. We welcome applicants at all levels, especially those with several years of experience as a professor, researcher or equivalent. We particularly seek applicants with expertise that is complementary to our own. DEADLINE FOR FULL CONSIDERATION: November 27, 2016. Application instructions are at the end of this email. More information about postdoc and researcher positions can also be found at: https://www.microsoft.com/en-us/research/group/machine-learning-nyc. Microsoft Research offers an exhilarating and thriving environment for cutting-edge, multidisciplinary research, both theoretical and applied, with access to an extraordinary diversity of big and small data sources, an open publications policy, and close links to top academic institutions around the world. We seek applicants from all areas of machine learning and related fields with a passion and demonstrated ability to craft and pursue an independent research program, including a strong publication record at top research venues and significant research experience beyond the doctorate or post-doctorate level. We especially welcome candidates who complement our efforts to expand the scope and effectiveness of machine learning approaches to both new and existing domains. Researchers in our lab define their own research agenda, driving forward an effective program of basic and applied research. In addition to working on challenging and fundamental problems, they have the potential to realize their ideas in products and services used worldwide. Microsoft Research New York City is the newest MSR lab, comprising roughly thirty full-time researchers and postdocs working in machine learning, systems, computational social science, algorithmic economics, information retrieval, and social media. The lab is highly collaborative and interdisciplinary, and is actively engaged with the local academic and tech communities. The machine learning group includes Alekh Agarwal, Miroslav Dud?k, John Langford, Robert Schapire, Alex Slivkins, Jenn Wortman Vaughan, and Hanna Wallach. A sampling of recent publications can be found at: https://www.microsoft.com/en-us/research/group/machine-learning-nyc. The ideal candidate for this position will have: ? a PhD in computer science, electrical engineering, statistics, mathematics, or a related field; ? significant research experience beyond the doctorate or post-doctorate level (although stellar junior candidates may also be considered); ? a well-established research program demonstrated, for example, by journal and conference publications, and participation on program committees, editorial boards, etc.; ? strong communication skills; ? the ability to work in a highly collaborative and interdisciplinary environment; ? demonstrated leadership; ? complementary expertise. HOW TO APPLY To apply, submit an online application on the Microsoft Research Careers website at: https://careers.research.microsoft.com. To be assured of full consideration, all materials, including reference letters, need to be received by November 27, 2016. Applications received after that date may or may not be considered. In completing your application, please be sure to follow these additional instructions: 1. In addition to submitting your CV and the names of at least three referees, as required by the online application, please also upload the following three attachments: o two conference or journal articles, book chapters, or equivalent writing samples (uploaded as two separate attachments); o an academic research statement (approximately 3-4 pages) that outlines your research achievements and agenda. 2. Indicate that your research area of interest is "Machine Learning, Adaptation, and Intelligence" and that your location preference is "New York." Include "Robert Schapire" as the name of a Microsoft Research contact (you may include additional contacts as well). NOTE: IF YOU DO NOT MARK THESE PREFERENCES, IT IS VERY UNLIKELY THAT WE WILL RECEIVE YOUR APPLICATION. After you submit your application, a request for letters may be sent to your list of referees on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance so they will be ready to submit your letter by our application deadline of November 27, 2016. You can check the progress on individual reference requests by clicking the status tab within your application page. -------------- next part -------------- An HTML attachment was scrubbed... URL: From francois.fleuret at idiap.ch Tue Sep 27 15:51:21 2016 From: francois.fleuret at idiap.ch (Francois Fleuret) Date: Tue, 27 Sep 2016 21:51:21 +0200 Subject: Connectionists: Two PhD positions in deep machine learning (Idiap, Switzerland, affiliated to EPFL) Message-ID: <22506.52665.421068.507453@swan.fleuret.org> The Idiap Research Institute, affiliated with ?cole Polytechnique F?d?rale de Lausanne, seeks two PhD students in machine learning to develop new techniques to speed up the training of deep architectures using importance sampling, and to learn automatically network architectures from data. The starting date is early 2017. http://www.idiap.ch/~fleuret/hiring.html These positions are funded by the Swiss National Science Foundation, and the candidates will be doctoral students at EPFL. Research will be conducted in the Computer Vision and Learning group at the Idiap research institute, under the supervision of Dr. Fran?ois Fleuret. * Summary Large neural networks demonstrate excellent performance for applications such as image classification, object detection, speech processing, and natural language processing. They are currently the standard machine-learning tool to deal with such problems when large training sets are available. Two key issues remain. The first is the computational effort during training which is often the limiting factor in practice. The second is the need for a careful design of the architecture, for which very few heuristics exist. The two lines of research we will pursue aim at addressing the first through the development of novel importance-sampling strategies that focus the computational effort over the samples which influence the parameter optimization the most. The second point will be addressed by revisiting variants of the Boosting algorithm in the context of deep architectures. This work will mix theoretical developments in machine learning with the implementation and benchmarking of algorithms on real-world data. Applicants must imperatively be self-sufficient programmers and have a strong background in mathematics. They should be familiar with several of the following topics: probabilities, applied statistics, information theory, signal processing, optimization, algorithmic, and development with some of the modern "deep learning" frameworks (e.g. Torch, Theano, TensorFlow) Please contact francois.fleuret at idiap.ch for additional information. * About Idiap Idiap is an independent, non-profit research institute recognized and supported by the Swiss Government, and affiliated with the Ecole Polytechnique F?d?rale de Lausanne (EPFL). It is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within close proximity to Geneva and Lausanne. Although Idiap is located in the French part of Switzerland, English is the working language. Free French lessons are provided. Idiap offers competitive salaries and conditions at all levels in a young, dynamic, and multicultural environment. Idiap is an equal opportunity employer and is actively involved in the "Advancement of Women in Science" European initiative. The Institute seeks to maintain a principle of open competition (on the basis of merit) to appoint the best candidate, provides equal opportunity for all candidates, and equally encourage both genders to apply. -- Francois Fleuret http://www.idiap.ch/~fleuret/ From simone.scardapane at uniroma1.it Wed Sep 28 06:33:29 2016 From: simone.scardapane at uniroma1.it (Simone Scardapane) Date: Wed, 28 Sep 2016 12:33:29 +0200 Subject: Connectionists: Final CfP: Advances in Biologically Inspired Reservoir Computing [EXTENDED DEADLINE] Message-ID: <7627e576-7b4e-9e45-8579-0857eae4f73b@uniroma1.it> [Apologies if you receive multiple copies of this CFP] -------------------------------------------------------------------------- Call for papers: Cognitive Computation Special Issue ADVANCES IN BIOLOGICALLY INSPIRED RESERVOIR COMPUTING Submission deadline [EXTENDED]: 31th October, 2016 http://ispac.diet.uniroma1.it/cognitive-computation-special-issue/ -------------------------------------------------------------------------- Scope and motivations -------------------------------------------------------------------------- Reservoir computing is a family of techniques for training and analyzing recurrent neural networks, wherein the recurrent portion of the network is assigned before the training process, typically via stochastic assignment of its weights. The non-linear reservoir acts as a high-dimensional kernel space, which generates complex dynamics characterized by sharp transitions between ordered and chaotic regimes. The behavior of this model emulates the functioning of many biological (complex) systems, among which the brain. Driven by the conceptual simplicity of the reservoir and by links with neuroscience, computer science and systems? theory, researchers have achieved remarkable breakthroughs, both in theory and in practice. These include dynamical models for explaining the working behavior of reservoirs, unsupervised strategies for the adaptation of the network, and the design of unconventional computing architectures for its execution. The recent upsurge of interest in fully adaptable recurrent networks, far from shifting the attention from the field, has brought renewed interest in reservoir computing models. In our era of extreme computational power and sophisticated problems, it is essential to understand the limits and the potentialities of simple (both deterministic and random) collections of processing units. For this reason, many fundamental questions remain open, including the design of optimal task-dependent reservoirs in a stable fashion, novel investigations on the memory and power capabilities of reservoir devices, and their applicability in an ever-increasing range of domains. In light of this, the aim of this special issue is to provide a unified platform for bringing forth and advancing the state-of-the-art in reservoir computing approaches. Researchers are invited to submit innovative works on the theory and implementation of this family of techniques, in order to provide an up-to-date overview on the field. Topics -------------------------------------------------------------------------- The topics of interest to be covered by this Special Issue include, but are not limited to: * Theoretical analyses on the computational power of reservoir computing. * Deep reservoir models. * Techniques for the automatic adaptation of the reservoir and the readout. * Supervised, unsupervised and semi-supervised training criteria. * Non-conventional substrates for the implementations of reservoirs. * Parallel and distributed algorithms for reservoir computing. * Comparisons between reservoir computing and standard (deep) neural networks. * Reservoir computing for reinforcement learning problems. * Fundamental links between reservoir computing and neuroscientific findings. * Investigation of reservoir dynamic in a phase space of reduced dimensionality. Applicative papers in all areas (including robotics, industrial control, etc.) are welcome, as well as outstanding surveys on specific aspects of the field. Paper submission -------------------------------------------------------------------------- All papers should follow the manuscript preparation requirements for the Springer Cognitive Computation submissions, see http://www.springer.com/biomed/neuroscience/journal/12559. The authors are requested to submit their manuscripts via the online submission manuscript system, available at http://www.editorialmanager.com/cogn/. During submission, authors should explicitly choose the title of the special issue in the Subject line. Should there be any further enquiries, please feel free to address them to the lead guest editor: Simone Scardapane (simone.scardapane at uniroma1.it) Important dates -------------------------------------------------------------------------- * Paper submission deadline: October 31, 2016 [EXTENDED] * First notification of acceptance: November 30, 2016 * Submission of revised papers: January 15, 2017 * Final notification to the authors: January 31, 2017 * Submission of final/camera-ready papers: February 15, 2017 * Publication of special issue: TBD Organizers -------------------------------------------------------------------------- * Simone Scardapane (Sapienza University of Rome) - simone.scardapane at uniroma1.it * John B. Butcher (Keele University) - j.b.butcher at keele.ac.uk * Filippo M. Bianchi (UiT, Troms?) - filippo.m.bianchi at uit.no * Zeeshan K. Malik (University of Stirling) - zkm at cs.stir.ac.uk From melahi at kth.se Wed Sep 28 08:30:38 2016 From: melahi at kth.se (Mehdi Elahi) Date: Wed, 28 Sep 2016 12:30:38 +0000 Subject: Connectionists: New Dataset of Stylistic Visual Features of Movie Trailers References: <4128DE33-39D8-4C45-B42D-C2E35B69619F@kth.se> Message-ID: <5F0BC536-9088-4FBA-9479-10BE4B3CA9D9@kth.se> DATASET RELEASE ======================================================================================= POLIMI at RECSYS research group is delighted to announce the release of the Mise-en-Sc?ne Dataset: Stylistic Visual Features of Movie Trailers This dataset is intended to serve the community for research on multimedia retrieval, multimedia recommender systems, and computer vision. SUMMARY ======================================================================================= This dataset provides a set of 7 low-level VISUAL features extracted from more than 13K movie trailers. The movie IDs are in agreement with the movie IDs provided by another movie rating dataset, that contains millions of ratings and thousands of tags (visit the links below for more details). DOWNLOAD ======================================================================================= Description: https://www.researchgate.net/publication/305682388_Mise-en-Scene_Dataset_Stylistic_Visual_Features_of_Movie_Trailers_description Download: https://www.researchgate.net/publication/305682269_Mise-en-Scene_Dataset_Stylistic_Visual_Features_of_Movie_Trailers_dataset Homepage: http://recsys.deib.polimi.it -------------- next part -------------- An HTML attachment was scrubbed... URL: From lchen at udc.edu Tue Sep 27 09:13:46 2016 From: lchen at udc.edu (Chen, Li) Date: Tue, 27 Sep 2016 09:13:46 -0400 Subject: Connectionists: Data Science Book information RE: Connectionists Digest, Vol 499, Issue 1 Message-ID: <32596A4A154B2442BF6312975C518D00047E08441C17@UDCMSGSTAFF-M.firebirds.udc.edu> Dear Connectionists, Would like to share with you our recent book on Data Science and BigData: Chen, Su, Jiang, Mathematical Problems in Data Science, Springer 2015, http://www.springer.com/gp/book/9783319251257. It is already having a very good chapter download record. From amir.aly at em.ci.ritsumei.ac.jp Wed Sep 28 10:10:12 2016 From: amir.aly at em.ci.ritsumei.ac.jp (Amir Aly) Date: Wed, 28 Sep 2016 23:10:12 +0900 Subject: Connectionists: 2 Available PhD Positions in Artificial Intelligence and Neuro-Cognitive Robotics, Ritsumeikan University, Japan Message-ID: **Apologies for Cross Posting ** *2 Available PhD Positions in Artificial Intelligence and Neuro-Cognitive Robotics at the Emergent Systems Laboratory, Ritsumeikan University, Japan* The Emergent Systems Laboratory [Link ] at Ritsumeikan University in Japan (nearby Kyoto) announces 2 available PhD positions in artificial intelligence and neuro-cognitive robotics as a part of the new project: *"*Comparison and Fusion of Artificial Intelligence and Brain Science*"*. The successful PhD candidates will be involved in research about: *Understanding Neural Computation for Double Articulation Analysis Bridging Sensory-motor Information and Natural Language in Human Brain*, under the supervision of Tadahiro Taniguchi (Project Coordinator) [ Link ]. *I. Positions Description * Human brain can analyze a two-layer hierarchical structure embedded in speech signal called *double articulation structure* (i.e., speech signal is segmented into words and phonemes in a hierarchical manner). However, the computational process of double articulation analysis in human brain has not been revealed in neuroscience. In artificial intelligence and developmental robotics, we have not developed - yet - a robot that can automatically learn language from human-robot and sensorimotor real-world interactions in an unsupervised manner. This project aims to contribute to : - Understanding the neural mechanism supporting human and robot language acquisition involving double articulation analysis. - Developing unsupervised machine learning methods for building the next-generation communicative robots. - Developing deep learning and Bayesian probabilistic models integrating language, planning, and sensorimotor behaviors. - Investigating theories bridging between deep learning and Bayesian nonparametrics. Each PhD candidate is expected to contribute to a part of the project. *II. Candidate Profile* - Good mathematical background. - English communication skill for daily discussion and writing papers: IELTS 6 (TOEIC 740). - Programming skills in C++, Python, or Matlab for machine learning and intelligent robot. - Applicants are expected to be interested in natural language, language acquisition, and the human cognitive neural system of social behavior. *III. Application* Please send your application to (adm at em.ci.ritsumei.ac.jp) no later than *31 October 2016*, including: - List of publications. - Copies of 2 major publications. - Outline of past research (free format). - Motivation letter (free format). - Outline of prospective research (free format). - 2 Reference letters. Further details about the available positions and admission procedures are available on: *PhD Positions in Artificial Intelligence and Neuro-Cognitive Robotics * . Ritsumeikan University is a fast growing international research environment with interdisciplinary research areas, and is the biggest private university in the west of Japan. The College of Information Science and Engineering is the biggest college in the field of Information Science in Japan, and the Graduate School is receiving a large number of KAKENHI Japanese governmental research grants. *IV. Related Papers* [1] Tadahiro Taniguchi, Shogo Nagasaka, Ryo Nakashima, Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals, IEEE Transactions on Cognitive and Developmental Systems, Vol. PP (99) .(2016) DOI: 10.1109/TCDS.2016.2550591 [2] Tadahiro Taniguchi, Takayuki Nagai, Tomoaki Nakamura, Naoto Iwahashi, Tetsuya Ogata, and Hideki Asoh, Symbol Emergence in Robotics: A Survey, Advanced Robotics, Vol.30, (11-12) pp. 706-728 .(2016) DOI:10.1080/01691864.2016.1164622 ---------------------------------------------- Amir Aly, Ph.D. Postdoctoral Research Associate Emergent Systems Laboratory College of Information Science and Engineering - Ritsumeikan University 1-1-1 Noji Higashi, Kusatsu, Shiga 525-8577 Japan -------------- next part -------------- An HTML attachment was scrubbed... URL: From florian.roehrbein at in.tum.de Wed Sep 28 11:29:06 2016 From: florian.roehrbein at in.tum.de (Florian Roehrbein) Date: Wed, 28 Sep 2016 17:29:06 +0200 Subject: Connectionists: [jobs] PhD student TUM, Germany Message-ID: <2D7025B1-4163-4DB6-9B3F-74C1CAA8B686@in.tum.de> We are seeking an enthusiastic and talented PhD student to join the Robotics and Embedded Systems group in the Department of Informatics at the Technical University of Munich (TUM). The successful candidate is supposed to extract the adjacency matrix describing the functional connectivity of the spinal cord circuitry. While our general project is based on electrophysiological patch clamp measurements, the candidate will focus on graph theoretical analysis. The results are expected to be integrated into the Human Brain Project, a ?1bn flagship project of the European Commission, as an interface that connects brain simulations with robotic platforms. The student will work in an enriching, interdisciplinary, and international collaborative framework at the leading department of informatics in Germany (cf. the Shanghai and the QS ranking). Partners of our project include the chair of Sensor Based Robotic Systems and Intelligent Assistance Systems at TUM, members of The Human Brain Project, and the Institute of Robotics and Mechatronics at the German Aerospace Center (DLR). The student is furthermore expected to complete some of his work in the Department of Experimental Medical Science at Lund University. Requirements: - master?s degree in mathematics, computer science, physics, or similar - knowledge in graph theory and its application to measured data - very good programming skills - fluent in written and spoken English - ability to work independently as well as in international teams Helpful skills: - knowledge in (computational) neuroscience and neural networks - Matlab and Python skills We offer a competitive funding at 100% on the German employee scale TV-L 13. Interested applicants should provide florian.roehrbein at in.tum.de with a cover letter, a CV and the contact information of reference letter writers. Please don?t hesitate to contact us in case of questions. Start date: about 2 months after acceptance Application Deadline: until position is filled Priv.-Doz. Dr. Florian Roehrbein Program Director HBP Neurorobotics http://neurorobotics.net/ http://www.frontiersin.org/Neurorobotics -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 4851 bytes Desc: not available URL: From julian.mcauley at gmail.com Thu Sep 29 00:42:13 2016 From: julian.mcauley at gmail.com (Julian McAuley) Date: Wed, 28 Sep 2016 21:42:13 -0700 Subject: Connectionists: Final CFP: SoCal Machine Learning Symposium: Friday Nov 18 @ Caltech Message-ID: Please remember to submit your abstracts by *next Tuesday* (Oct. 4) to the Southern California Machine Learning Symposium! Key info and our CFP appears below: Symposium: Nov 18 @ Caltech Abstract submission (Oct 4): https://easychair.org/conferences/?conf=scmls16 Registration and further information: http://dolcit.cms.caltech.edu/scmls/ Yisong Yue, Julian McAuley ===== Original CFP below ==== We are pleased to invite you to the Southern California Machine Learning Symposium, on Friday November 18 at Caltech! http://dolcit.cms.caltech.edu/scmls/ The SoCal ML Symposium brings together students and faculty to promote machine learning in the Southern California region. The workshop serves as a forum for researchers from a variety of fields working on machine learning to share and discuss their latest findings. Topics to be covered at the symposium include, but are not limited to: + Machine learning with graphs, social networks, and structured data. + Active learning, reinforcement learning, crowdsourcing. + Learning with images and natural language. + Learning with high-dimensional data. + Neural networks, deep learning, and graphical models. + Learning dynamic and streaming data. + Applications to interesting new domains. + Addressing each of these issues at scale. The majority of the workshop will be focused on student contributions, in the form of contributed talks and posters. We invite submissions in the form of 1-2 page extended absracts, to be presented as posters and oral presentations at the symposium. Submissions may be made on our easychair page: https://easychair.org/conferences/?conf=scmls16 A $500 first-prize and a $250 runner-up prize, sponsored by Google Research, will be awarded for the best student presentations. Timeline: Oct 4: Abstract submission Oct 14: Notification Nov 11: Registration deadline Nov 18: Symposium For more details, including submission and registration instructions, visit our symposium webpage: http://dolcit.cms.caltech.edu/scmls/ and please help distribute our flyer: http://dolcit.cms.caltech.edu/scmls/scmls.pdf Hope to see you there! Yisong Yue, Julian McAuley -------------- next part -------------- An HTML attachment was scrubbed... URL: From davrot at neuro.uni-bremen.de Thu Sep 29 06:17:54 2016 From: davrot at neuro.uni-bremen.de (David Rotermund) Date: Thu, 29 Sep 2016 12:17:54 +0200 Subject: Connectionists: Open PhD Position in Neuroscience at the University of Bremen, Germany Message-ID: The Institute for Theoretical Physics at the University of Bremen, headed by Prof. Dr. Klaus Pawelzik, offers a PhD position in the field of Complex Adaptive Systems. Successful candidates will join an international research group that is located in the field of Complex Adaptive Systems with a specialization in Econophysics, Psychophysics and Computational Neuroscience. In the latter we work on Attention, Neuronal Dynamics, Learning and Neurotechnology. The project funded by the DFG is entitled: ?Dynamic instabilities from information annihilation in neuronal networks? Many Complex Adaptive Systems, including human balancing behavior, financial markets, and neuronal networks, exhibit complex spatio-temporal activity. Interestingly, all these systems feature a dynamic balance of opposing influences. In this project we will investigate the consequences of simple but biologically realistic mechanisms that yield a balance of excitatory and inhibitory inputs into neurons. In particular, we will determine the conditions where this balance does not result in simple equilibria but causes complex temporal dynamics and power-law distributed avalanches of activity in recurrent networks. This topic is part of a long term research program where we investigate whether a single general principle, by which criticality emerges from an efficient absorption of information, can account for these observations in a wide range of systems. The position is funded with a salary comparable to a 65 % TVL13 position and comes with support for 3 years and direct supervision by the principal investigator. Ideal candidates have a MSc degree in Physics or Mathematics. In any case they must have a strong background in physics and/or computational neuroscience and solid programming skills. Above all, they must have a strong motivation, a sense for responsibility, interest for detailed analysis, and a distinct desire to learn. Fluency in English is required (both written and spoken). If you are interested, please send your complete application by 23th October 2016 by e-mail (see detailed instructions below) to ajanssen at neuro.uni-bremen.de. Severely disabled applicants and women with essentially identical and personal suitability will be preferentially selected. Detailed instructions for applicants ===================== Your application must comprise: Motivation letter -------------------- Your 1-2 page essay should reply the following questions: What is your background? In which fields have you worked before and how do you think this can be useful for the present job? What attracts you to the field of neuroscience? Which problem(s) in neuroscience are you most interested in? Which kind of person are you (e.g. creative, analytic, communicative, pragmatic, etc.) and how do you approach a research problem? What are your plans for your future career? Curriculum Vitae --------------------- Send a classical tabular CV with your contact details, your date-of-birth, a current photograph, and all stages of education and employment. List of skills, awards, publications List your skills, especially proficiency in languages (including the level of proficiency), that you think might be useful for the job. Also list awards you might have got and peer-reviewed papers, in case there are some. Contact details of two academic references -------------------------------------------------------- One of the references should be your MSc advisor. Please contact the references prior to listing their names so that they are not surprised if they get contacted. Your application can be in English or German, whatever language you are more familiar with. Please send your application to ajanssen at neuro.uni-bremen.de by 23th October 2016! All documents must be in PDF format and must not be compressed. Combine all documents to a single PDF file or at least name the separate files appropriately. If we find your application interesting, we will let you know within two weeks and potentially ask for more documents. -------------- next part -------------- An HTML attachment was scrubbed... URL: From h.spiers at ucl.ac.uk Thu Sep 29 07:20:00 2016 From: h.spiers at ucl.ac.uk (Spiers, Hugo) Date: Thu, 29 Sep 2016 11:20:00 +0000 Subject: Connectionists: Advert for a post-doc position at UCL Message-ID: <14AE20C8-7C41-4AA1-956D-BC3486F6F56B@ucl.ac.uk> Dear Connectionists mail list, please can you send round the following details about a post-doc position available at UCL: Post-doctoral Position available at UCL Applications are invited for the post of Research Associate in the Department of Experimental Psychology UCL to work with Dr Hugo Spiers and Prof Michael Hornberger (University of East Anglia) in collaboration with Dr Ricardo Silva (UCL), Dr Ed Manley (UCL), Dr Jan Wiener (University of Bournemouth), Dr Ruth Dalton (University of Northumbria), Prof Christoph Hoelscher (ETH Zurich) and Veronique Bohbot (McGill University). This project is investigating human spatial navigation using data collected from the mobile video game app ?Sea Hero Quest?. The post is funded by Alzheimer?s Research UK and Deutsche Telekom. The applicant will be involved in analyzing the data collected from the app, contribute to the writing of manuscripts and presentation of the data at international conferences. Data from > 2 million participants will be analyzed which contains coordinate and orientation tracking data during checkpoint and radial maze levels, and accuracy measures during flare levels (see www.seaheroquest.com for details). Applicants must hold a PhD, or have submitted their thesis, in a field with experience of analyzing time series or large data sets. An interest in spatial cognition and the ability to work as part of a research team is essential. Experience with analyzing trajectory data, knowledge of SQL, Python or R is desirable. A background in Machine Learning, Statistics, Mathematics, or Computer Science is also desirable for this post. Applications should include a covering letter, CV and the names and addresses of three referees. Shortlisted applicants will be interviewed in early October 2016. Interested candidates can familiarize themselves with other work in the lab at http://www.ucl.ac.uk/spierslab or contact Dr Hugo Spiers (h.spiers at ucl.ac.uk). To apply see: https://atsv7.wcn.co.uk/search_engine/jobs.cgi?owner=5041416&ownertype=fair&jcode=1585787&vt_template=965&adminview=1 Best wishes, Hugo Spiers -------------- next part -------------- An HTML attachment was scrubbed... URL: From S.M.Bohte at cwi.nl Thu Sep 29 07:29:11 2016 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Thu, 29 Sep 2016 13:29:11 +0200 Subject: Connectionists: CFP NIPS 2016 Workshop: Computing with Spikes [EXTENDED DEADLINE] Message-ID: ** EXTENDED DEADLINE: NOVEMBER 1 ** CALL FOR PAPERS NIPS 2016 Workshop: Computing with Spikes https://www.cwi.nl/computing-spikes-nips-2016-workshop The first NIPS Workshop Computing with Spikes will be held at NIPS 2016 in Barcelona, Spain, Saturday December 10. =================================== We invite you to submit new work on computing with spiking neurons. Submissions should be in the NIPS 2016 format with a maximum of eight pages. Author names need not be anonymized and references can extend beyond the 8 pages as far as needed; the usual NIPS policy on supplementary information applies. Accepted submissions will get a spotlight and a poster presentation; a small subset will be selected for contributed talks. The submission deadline is *November 1* (midnight), and decisions will be sent out on *November 7*. Please submit papers by email to this address: =================================== Despite remarkable computational success, artificial neural networks ignore the spiking nature of neural communication that is fundamental for biological neuronal networks. Understanding how spiking neurons process information and learn remains an essential challenge. It concerns not only neuroscientists studying brain function, but also neuromorphic engineers developing low-power computing architectures, or machine learning researchers devising new biologically-inspired learning algorithms. Unfortunately, despite a joint interest in spike-based computation, the interactions between these subfields remains limited. The workshop aims to bring them together and to foster the exchange between them by focusing on recent developments in efficient neural coding and spiking neurons' computation. The discussion will center around critical questions in the field, such as "what are the underlying paradigms?" "what are the fundamental constraints?", and "what are the measures for progress??, that benefit from varied perspectives. The workshop will combine invited talks reviewing the state-of-the-art and short contributed presentations, and it will conclude with a panel discussion. =================================== Invited Speakers Sophie Deneve (Ecole Normale Superieure) Wolfgang Maass (U. Graz) Steve Furber (U. Manchester) Tobi Delbrueck (ETH Zurich, INI) Terry Steward (U Waterloo) Paul Merolla (IBM Truenorth team) =================================== Organizers: Cristina Savin (IST), Thomas Nowotny (U Sussex), Davide Zambrano (CWI) Sander Bohte (CWI). -------------- next part -------------- An HTML attachment was scrubbed... URL: From djork-arne.clevert at bayer.com Thu Sep 29 08:13:43 2016 From: djork-arne.clevert at bayer.com (Djork-Arne Clevert) Date: Thu, 29 Sep 2016 12:13:43 +0000 Subject: Connectionists: "Computational Life Sciences @ Bayer" a workshop for doctoral candidates and postdoctoral scientists Message-ID: Dear all, Bayer is accepting applications for the Workshop "Computational Life Sciences @ Bayer" in Berlin, Germany. This workshop, which will take place on November 16-18, 2016, is an excellent opportunity to discuss Bayer's recent developments and research & development projects, present your own scientific work and explore specific job opportunities in Bayer's R&D organization. Deadline for applications is October 16th, 2016. Participation is free of charge and Bayer is covering costs for travel and accommodation. Space is limited, so please apply soon! Looking forward to meeting you in Berlin! Djork Clevert Full Call for Participation: Bayer is a global enterprise with core competencies in the fields of health care and agriculture. As an innovation company, it sets trends in research-intensive areas. Bayer's products and services are designed to benefit people and improve their quality of life. Workshop "Computational Life Sciences @ Bayer" November 16th - 18th, 2016 in Berlin DO YOU WANT TO IMPROVE LIFE WITH YOUR RESEARCH? Bayer invites you to a scientific networking event. It includes a poster session where you have a chance to present your current scientific research, case studies and group sessions to foster lively discussion about relevant scientific issues. It also includes talks about computational life sciences at Bayer. There is ample time for all participants to talk to representatives from the different divisions, i.e. Pharmaceuticals as well as Crop Science. Alongside the workshop sessions, time is allocated for networking. WHO YOU ARE You should be experienced, enthusiastic and deeply committed to one or more fields of computational life science: bioinformatics (ideally familiar with machine learning techniques like deep learning), biometrics, biostatistics, bioanalysis, systems biology or or pharmacology, pharmacometrics, structural bioinformatics, mathematics, physics, biology, pharmacology, medicine, engineering, chemistry or other related fields with a focus on theory and / or application of computational methods, supported by a sound track record of scientific achievements and a Master / PhD degree. HOW TO APPLY If you are interested please submit your application via our career website including your CV, cover letter, relevant certificates (Bachelor / Master / Diploma and PhD) as well as abstracts of scientific research (if applicable) by October 16th, 2016. Travel and accommodation costs will be covered by Bayer for all participants. Find out more: Workshop "Computational Life Sciences @ Bayer" http://karriere.bayer.de/en/working-at-bayer/entrylevel/postdocs/Computational_Life_Sciences_Workshop/index.html ______________________________________________ Djork-Arn? Clevert, PhD Senior Scientist Bayer Pharma Aktiengesellschaft GDD-GTRG-CIPL-Bioinformatics M?llerstr. 178, Building S190/328 13353 Berlin, Germany Phone: +49 30 468 196745 E-mail: djork-arne.clevert at bayer.com Web: http://www.bayer.com Vorstand: Dieter Weinand, Vorsitzender | Hartmut Klusik, Manfred Vehreschild Vorsitzender des Aufsichtsrats: Michael K?nig Sitz der Gesellschaft: Berlin | Eintragung: Amtsgericht Charlottenburg HRB 283 B -------------- next part -------------- An HTML attachment was scrubbed... URL: From dwang at cse.ohio-state.edu Thu Sep 29 11:59:05 2016 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Thu, 29 Sep 2016 11:59:05 -0400 Subject: Connectionists: NEURAL NETWORKS, Oct. 2016 Message-ID: Neural Networks - Volume 82, October 2016 http://www.journals.elsevier.com/neural-networks Global oscillation regime change by gated inhibition August Romeo, Hans Super A new EEG synchronization strength analysis method: S-estimator based normalized weighted-permutation mutual information Dong Cui, Weiting Pu, Jing Liu, Zhijie Bian, Qiuli Li, Lei Wang, Guanghua Gu A local Vapnik-Chervonenkis complexity Luca Oneto, Davide Anguita, Sandro Ridella Event-triggered H_infinity image filter design for delayed neural network with quantization Jinliang Liu, Jia Tang, Shumin Fei Boundedness and convergence analysis of weight elimination for cyclic training of neural networks Jian Wang, Zhenyun Ye, Weifeng Gao, Jacek M. Zurada Stability analysis of switched cellular neural networks: A mode-dependent average dwell time approach Chuangxia Huang, Jie Cao, Jinde Cao Micro-level dynamics of the online information propagation: A user behavior model based on noisy spiking neurons Ilias N. Lymperopoulos, George D. Ioannou From levitan at oxy.edu Thu Sep 29 17:03:09 2016 From: levitan at oxy.edu (Carmel Levitan) Date: Thu, 29 Sep 2016 14:03:09 -0700 Subject: Connectionists: open-rank position in computer science with contributions to cognitive science Message-ID: I am pleased to announce that my department has an open-rank search that is now live: http://www.oxy.edu/cognitive-science/computer-scientist-search The Department of Cognitive Science at Occidental College invites applications for an open-rank faculty position in Computer Science. We seek a computer scientist who has a strong interest in building Occidental?s Computer Science program and who can also contribute to Cognitive Science. We have a preference for candidates with research interests at the intersection of computer science and cognitive science (broadly construed), including such areas as computational neuroscience, artificial intelligence, computer vision, computational linguistics, human-computer/robotic interactions, computer science education, and game design. Applicants should have a Ph.D. in Computer Science or related field, and a strong commitment to educating undergraduates through teaching and research. The successful candidate is expected to: 1. teach introductory and advanced courses in computer science; 2. participate in team-teaching our introduction to cognitive science course; 3. offer additional courses in computer science and/or cognitive science to enhance our current offerings; 4. develop a rigorous research program involving undergraduates; 5. advise students across the College who may be interested in computing; 6. work in consultation with the Computer Science Advisory Committee to develop a vision for expansion of our current computer science program beyond a minor, and 7. participate in regular service to the department and the College. Occidental College is a nationally-ranked small liberal arts institution situated in Los Angeles. Occidental is located in the culturally-rich neighborhoods of Eagle Rock and Highland Park, near Caltech, the Jet Propulsion Lab, the Natural History Museum, and other major research institutions. The College is committed to academic excellence in a diverse community and supporting interdisciplinary and multicultural academic programs that provide a gifted and diverse group of students with an educational experience that prepares them for leadership in a pluralistic world. We, therefore, strongly encourage applications from candidates who will further Occidental?s mission of excellence and equity in their teaching, scholarship, and/or service. Applicants should submit the following: (1) a cover letter detailing your interest in teaching in a liberal arts environment; (2) a statement of teaching philosophy, including how you will support and enhance the College?s goal of building a strong educational environment in classrooms that have an ethnically, socio-economically, and culturally diverse student body (include teaching evaluations, evidence of effective advising, or other data, if available); (3) a statement of research interests and experience, including how students will participate in or benefit from your research; (4) a curriculum vitae; and (5) three confidential letters of recommendation (request writers to send separately). Electronic application materials should be addressed to Dr. Andrew Shtulman, Chair, Computer Science Search, and sent by email to Patricia Micciche at micciche at oxy.edu. Review of applications will begin on November 15, 2016. Occidental College is an Equal Opportunity Employer and does not discriminate against employees or applicants because of race, religious creed, color, national origin, ancestry, physical and mental disability, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, age, or sexual orientation, or any other characteristic protected by State or Federal Law. We strongly encourage all underrepresented candidates, especially women and persons of color, to apply. -------------- next part -------------- An HTML attachment was scrubbed... URL: From yulia.sandamirskaya at ini.rub.de Fri Sep 30 10:05:41 2016 From: yulia.sandamirskaya at ini.rub.de (Yulia Sandamirskaya) Date: Fri, 30 Sep 2016 16:05:41 +0200 Subject: Connectionists: EUCog 2016 - 'European Society for Cognitive Systems' Message-ID: <7230EAC1-BEEF-47ED-AB45-41AE7476BCCF@ini.rub.de> LAST CALL FOR CONTRIBUTIONS ?Cognitive Robot Architectures? EUCog 2016 - ?European Society for Cognitive Systems? December 8th-9th, 2016 TU Vienna, Karlsplatz 13, 1040 Vienna http://www.eucognition.org/index.php?page=2016-vienna-general-info Updated Abstract submission date: 01.Oct 2016 For over a decade, the EUCognition network (EUCog) has brought together academic researchers and industrial partners with a common interest in the design and construction of artificial cognitive systems in ways that are informed by, or attempt to explain, biological cognition. The emphasis is on systems that are autonomous, robust, flexible and self-improving in pursuing their goals in real environments. EUCog not only includes researchers who use insights from natural cognition in creating artificial cognitive systems for robotic and other technical applications but also those interested in using artificial cognitive systems to understand natural cognition. The field includes computer science, robotics, cognitive science, neuroscience, and philosophy as its core disciplines. EUCog will hold its next meeting this coming December in Vienna. The focus of the event will be community building, as well as presenting cutting-edge research in the field of artificial cognitive systems. The meeting is open to all: one need not be a past or current member of the EUCog network to attend. ========================================= INVITED SPEAKERS: David Vernon (Sk?vde) http://www.vernon.eu Paul F.M.J. Verschure (UPF Barcelona) http://specs.upf.edu/people/paul-fmj-verschure ========================================= ORGANISERS Ron Chrisley (University of Sussex) Vincent C. M?ller (Anatolia College/ACT & University of Leeds) Yulia Sandamirskaya (University of Zurich & ETH Z?rich) Markus Vincze (Technical University of Vienna) ========================================= THEME: COGNITIVE ARCHITECTURES The theme of this meeting will be cognitive architectures, raising such questions/debates as: ? What makes an architecture a cognitive architecture? A good cognitive architecture? ? Implementation-independent architectures vs strongly embodied architectures ? Should/could there be a common framework for comparing cognitive architectures? ? What are the tradeoffs of various architectural features? ? What are the best examples of architecture-based designs of cognitive systems? ? What is the role of architecture in the design-implement-evaluate cycle? Key issues to be explored at the meeting include: ? The role of cognitive architectures in robotic systems ? The role of neural networks in the design of cognitive architectures ? The role of cognitive science in the design of robotic architectures ? Embodiment and robotic architectures ? Architectures for robotic perception (esp. vision, audition, haptics, proprioception, kinaesthesia, interoception) ? Architectures for motor control and behavioural organisation ? Architectures for planning and mapping ? Architectures for HRI ? Machine learning and robotic architectures ? Architectures for developmental robotics ? Embodied deliberative architectures ? Embodied reflective architectures ========================================= ABSTRACTS We invite submissions for papers and posters. For papers, we invite anonymous long abstracts of 600-1000 words (excluding references) in plain text or PDF. For posters, we require a short abstract of 120 words. Accepted papers and posters will be presented at the conference and published in the proceedings. All submissions will be double-blind reviewed by at least two members of the programme committee. Please, submit online at EasyChair: https://easychair.org/conferences/?conf=eucog2016 (please submit your long abstract as ?paper? on that site). ========================================= PUBLICATION The proceedings of the meeting will be published - most likely in the ?Springer Series in Cognitive and Neural Systems?. ========================================= REGISTRATION Online registration will open in September. Participation fee - including lunch & coffee breaks, and conference dinner: ?160; reduced ?75 (students, privately paying participants) ========================================= KEY DATES Deadline for submission of abstracts and long abstracts: 01.10.2016 Decisions announced: 15.10.2016 Conference: 08.-09.12.16 Deadline for submission of posters/papers for publication: 11.11.16 ========================================= We look forward to seeing you in Vienna in December! -------------- next part -------------- An HTML attachment was scrubbed... URL: