From evarist.planet at epfl.ch Sat Sep 1 02:17:43 2018 From: evarist.planet at epfl.ch (Planet Letschert Evarist) Date: Sat, 1 Sep 2018 06:17:43 +0000 Subject: Connectionists: [Jobs] Senior Data Scientist Message-ID: <86A467E1-4722-4E6A-AF3B-08C10677D89F@epfl.ch> The EPFL Laboratory of Virology and Genetics (headed by prof. Didier Trono) is looking for a senior data scientist with sound experience in Machine Learning techniques. The team is part of the EPFL School of Life Sciences and offers a challenging and stimulating environment with outstanding career opportunities and excellent benefits. The candidate will apply his/her advanced knowledge of ML algorithms over several huge cancer related datasets. This is a very applied field, with possible impact of data science on genomics and more broadly on personalized health / precision medicine. The selected candidate will be located at the Health 2030 Genome Center (at Campus Biotech in Geneva) and at the EPFL campus in Lausanne. S/he will also collaborate closely with the Swiss Data Science Center (SDSC https://datascience.ch). Main duties and responsibilities include : The candidate must be highly motivated, like programming and be Unix-proficient. S/he will apply his/her practical experience in cleaning, mining and analysing huge volumes of data to develop Machine Learning solutions in the field of personalized health and precision medicine. Candidates are expected to possess deep experience in solving complex problems using data-driven methods. The ideal candidate also has good background in Big Data technologies. Your profile : Title: Master?s degree or PhD in Machine Learning, Statistics, Computer Sciences or Electrical Engineering. Attitude: -Highly motivated -Excellent communication skills -Proactive Technical skills: -Deep understanding of ML algorithms -Unix and shell scripting -Good programming ability. Fluent in python and/or R -Knowledge of statistics and data modeling Languages: -English (French is a plus) Ideal skills: -Knowledge of Apache Spark -Knowledge in biology in general and cancer biology in particular Please apply here: https://recruiting.epfl.ch/Vacancies/645/Description/2 Evarist Planet Bioinformatician/Biostatistician Bioinformatician at TronoLab Laboratory of Virology and Genetics Phone +41 21 69 30902 evarist.planet at epfl.ch -------------- next part -------------- An HTML attachment was scrubbed... URL: From msn2018 at mail.neu.edu.cn Sat Sep 1 04:28:38 2018 From: msn2018 at mail.neu.edu.cn (MSN2018) Date: Sat, 1 Sep 2018 16:28:38 +0800 (GMT+08:00) Subject: Connectionists: [msn2018] CFP: Mobile Ad-hoc and Sensor Networks 2018 Message-ID: <12e280c8.6bad.165943f8f99.Coremail.msn2018@mail.neu.edu.cn> Apologies for any cross posting 14th Int. Conference on Mobile Ad-hoc and Sensor Networks Shenyang, China Dec. 6- 8, 2018 http://conf.neu.edu.cn/msn2018 You are cordially invited to submit your contribution until September 15, 2018. Final manuscripts should be prepared according to IEEE Computer Society Proceedings Format (double column, 10pt font) and submitted via the EasyChair system in PDF file format. The manuscript should be no longer than 6 pages. Up to two additional pages are permitted if the authors are willing to pay an over-length charge at the time of publication (manuscripts should not exceed 8 pages in total). Final manuscripts should not be previously published in or be under consideration for publication in another conference or journal. To submit your contribution visits the submission page (https://easychair.org/conferences/?conf=msn2018). ? Papers will be included in the conference proceedings edited by IEEE ? Extended versions will be invited for publication in special issues of international journals: o IEEE Transactions on Industrial Informatics edited by IEEE o IET Networks edited by IET o IEEE Wireless Communications edited by IEEE o Sensors edited by MDPI Topics include, but are not limited to: o Ad Hoc Networks o Vehicular Networks o Intelligent Sensor Networks o Urban Computing o Internet of Things o Edge and Fog Computing/Networking o 5G networks o Cognitive Radio Networks o Mobile Social Networks o Mobile Crowdsensing and Computing o Smart Networks o Knowledge Centric Networks o Delay Tolerant and Opportunistic Networking o Network Security and Privacy o Artificial Intelligence for Networking and Communications o Novel Applications and Architecture Steering Committee Co-Chairs Xiaohua Jia, City University of Hong Kong Jiannong Cao, Hong Kong Polytechnic University General Co-Chairs Xingwei Wang, Northeastern University, China Vincenzo Piuri, University of Milan, Italy TPC Co-Chairs Ruiyun Yu, Northeastern University, China Hongyi Wu, Old Dominion University, USA Dieter Hogrefe, University of Goettingen, Germany Publication Chair Guangtao Xue, Shanghai Jiao Tong University, China Xu Yuan, University of Louisiana at Lafayette, USA Yuanguo Bi, Northeastern University, China Yuan Liu, Northeastern University, China Publicity Chair Guangjie Han, Dalian University of Technology, China Cong Wang, Old Dominion University, USA Jie Jia, Northeastern University, China Jie Li, Northeastern University, China Financial Chair Lianbo Ma, Northeastern University, China Local arrangement Chair Zhenhua Tan, Northeastern University, China Web Chair Yu Wang, Northeastern University, China -------------- next part -------------- An HTML attachment was scrubbed... URL: From thang.buivn at gmail.com Sat Sep 1 09:11:22 2018 From: thang.buivn at gmail.com (Thang Bui) Date: Sat, 1 Sep 2018 23:11:22 +1000 Subject: Connectionists: CFP: 1st Symposium on Advances in Approximate Bayesian Inference (AABI 2018) Message-ID: We invite researchers in machine learning and statistics to participate in the: 1st Symposium on Advances in Approximate Bayesian Inference Sunday December 2 2018, Montreal, Canada www.approximateinference.org Submission deadline: *19 October 2018* *1. Call for Participation* We invite researchers to submit their recent work on the development, analysis, or application of approximate Bayesian inference. A submission should take the form of an extended abstract of 2-4 pages in PDF format using the PMLR one-column style [ http://approximateinference.org/pmlr/aabi_template.zip ]. For questions and troubleshooting, visit CTAN [ https://ctan.org/tex-archive/macros/latex/contrib/jmlr ]. Author names do not need to be anonymized and references may extend as far as needed beyond the 4 page upper limit. If authors' research has previously appeared in a journal, workshop, or conference (including the NIPS 2018 conference), their symposium submission should extend that previous work. Submissions may include a supplement/appendix, but reviewers are not responsible for reading any supplementary material. All submissions will be reviewed by at least three reviewers from the field. Accepted submissions will be accepted to presentation only. The authors of selected submissions will be invited to publish their paper in a PMLR volume. We aim to keep a general inclusive nature of the symposium for presentations. However, we will only invite the top-rated accepted papers to be published through PMLR. Papers should be submitted by 19 October through easychair [ https://easychair.org/conferences/?conf=aabi2018 ]. Final versions of the symposium submissions are due by 1 December and will be posted on the symposium website. If you have any questions, please contact us at aabisymposium2018 at gmail.com. *2. Symposium Overview* Probabilistic modeling is a useful tool to analyze and understand real-world data. Central to the success of Bayesian modeling is posterior inference, for which approximate inference algorithms are typically needed in most problems of interest. The two pillars of approximate Bayesian inference are variational and Monte Carlo methods. In the recent years, there have been numerous advances in both methods, which have enabled Bayesian inference in increasingly challenging scenarios involving complex probabilistic models and large datasets. In this symposium, besides recent advances in approximate inference, we will discuss the impact of Bayesian inference, connecting approximate inference methods with other fields. In particular, we encourage submissions that relate Bayesian inference to the fields of reinforcement learning, causal inference, decision processes, Bayesian compression, or differential privacy, among others. We also encourage submissions that contribute to connecting different approximate inference methods, such as variational inference and Monte Carlo. This symposium can be seen as a continuation of previous workshops at NIPS: + NIPS 2017 Workshop: Advances in Approximate Bayesian Inference + NIPS 2016 Workshop: Advances in Approximate Bayesian Inference + NIPS 2015 Workshop: Advances in Approximate Bayesian Inference + NIPS 2014 Workshop: Advances in Variational Inference *3. Key Dates* Paper submission: *19 October 2018 (11:55pm GMT)* Acceptance notification: 13 November 2018 Final paper submission: 1 December 2018 Symposium organizers: Cheng Zhang (Microsoft Research) Dawen Liang (Netflix) Francisco Ruiz (University of Cambridge / Columbia University) Thang Bui (University of Sydney) Advisory committee: Christian Robert (Universit? Paris Dauphine / University of Warwick) David Blei (Columbia University) Dustin Tran (Google Brain / Columbia University) James McInerney (Spotify) Stephan Mandt (Disney Research) -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Sun Sep 2 05:29:13 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Sun, 2 Sep 2018 12:29:13 +0300 Subject: Connectionists: ENTER 2019 eTourism Conference: Last Call for Papers In-Reply-To: References: <0B8845F2-4D38-4F72-883C-8011F7853750@cs.ucy.ac.cy> <661201BE-6D0D-4C29-B078-E681845BDE26@cs.ucy.ac.cy> Message-ID: <03BFF210-760C-4ADF-BE58-09E21097F117@cs.ucy.ac.cy> ENTER 2019: The 26th Annual eTourism Conference "eTourism: Towards a Sustainable Digital Society" Hilton Cyprus, Nicosia, Cyprus, 30 January - 1 February, 2019 https://www.enter2019.org *** Last Call for Research Papers *** *** Submission Deadline: September 10, 2018 (extended) *** (Proceedings published by Springer - Journal special issue in JITT, Springer) Every year, hundreds of tourism academics, industry representatives, government officials, students and entrepreneurs come together to share, discuss and challenge latest developments in information technology in the fields of travel, tourism and hospitality. With the theme "eTourism: Towards a Sustainable Digital Society" the ENTER 2019 conference will focus on exploring the ways in which technology and tourism together can make our society more sustainable. We call for latest research and case studies on emergent and cutting-edge information and communication technology concepts, applications, and business models to be shared in the conference. Organized by the International Federation for Information Technology and Travel & Tourism (IFITT), the ENTER 2019 conference provides a unique venue for various tourism stakeholders to understand the application of information and communication technologies to travel and tourism, with a special focus on how eTourism can contribute to the sustainability of the society. The ENTER 2019 research track is divided into three major topics that all contribute to our capabilities in building a sustainable digital society: Tourism Business and Technology, Governance, Sustainability and Education, and Computer Science and Information Systems. Issues to be covered at the conference include, but are not limited, to the following areas in the travel, tourism and hospitality context: Tourism Business and Technology ? ICT and Tourism Experience ? Augmented and Virtual Reality ? Platform Economy ? Website Design and Evaluation ? Digital Marketing and Social Media Strategies ? Digital Distribution and Social Selling ? Social Networking, Social Media and Social Inspiration ? Gaming and Gamification ? ICT Adoption and Value Creation ? E-strategy and eBusiness Models ? ICT for Innovation and Service Design ? Digital Nomads ? Consumer Behaviour in Digital Space ? Robotics and Automation in Travel and Hospitality Governance, Sustainability and Education ? ICT for Regional Development and Sustainability ? Advanced Distribution Systems and Strategies, Dynamic Packaging ? ICT-enabled Partnership and Collaboration ? E-Learning, Life-long Learning and MOOCs ? E-Government and Public Policy in Tourism ? Digital Divide and Socio-economic Development ? Privacy and Internet Security ? Legal, Ethical and Social Aspects of ICT Computer Science and Information Systems ? Big Data and Large-scale Systems ? Artificial Intelligence, Machine Learning and Deep Learning ? Data Mining, Analytics and Measurement ? Text and Concept Mining, Sentiment Analysis ? Recommender Systems and Personalization ? User Modeling and Decision Making ? Human-Computer Interaction ? Emotions and Personality-based Systems ? Social Network Analysis ? Location-based Services and Context-Aware Systems ? Mobile Services and Wearable Technologies ? Semantic Web, Tourism Ontologies and Linked Open Data ? Data Standards and Data Integration ? Travel Information Search and Retrieval ? Internet-of-Things ? Smart Destinations ? Travel Chatbots ? Blockchain and Other Emerging Technologies Welcoming Academics and the Industry The conference brings together the research community and industry, and it is organized in three streams, namely industry track, destinations track, and research track. If you are representing tourism industry or destinations, please see suitable calls for presentations at https://www.enter2019.org . The conference also features six to eight world-class keynote speakers discussing the most pressing topics within eTourism. Location The 26th edition of ENTER will take place in Nicosia, Cyprus. Nicosia is the capital of Cyprus; a status it has enjoyed for 1000 years since the 10th century, though its beginnings date back 5000 years to the Bronze Age. Nicosia is a sophisticated and cosmopolitan city, rich in history and culture that combines its historic past with the amenities of a modern city. Cyprus is an island drenched in sun and mythology, at the crossroads of ancient civilizations. 9,000 years of history gathered on one island. Cyprus packs a remarkable array of sights and attractions, museums and archaeological parks, throbbing beach resorts, pine covered mountains, medieval fortresses and ancient temples. Over the last few years, it has become one of the top touristic European destinations breaking in consecutive years the record of tourist arrivals. It is expected that in 2018, more than 3.6 million tourists will visit Cyprus and plans target a steady intake of 5 million tourists per year. More information about Nicosia and Cyprus as well as what the island and its capital offer can be found on the conference web site. Call for Research Papers We invite research papers across the widest spectrum of Information and Communication Technologies in Travel and Tourism to be presented at the ENTER 2019 conference. All submissions to the research track are rigorously evaluated for novelty, significance, and soundness. Papers should clearly state the background, introduction, purpose, theory, methodology, results, conclusions and managerial/industry/social implications of the study, and be fully referenced with appropriate citations. The authors of full papers and research notes will have the opportunity to present their research orally supported by PowerPoint slides. Full technical details will be provided with the acceptance of the paper. The proceedings of recently held ENTER conferences are listed by ISI's Conference Proceedings Citation Index - Science (CPCI-S). ENTER 2019 proceedings will follow a similar indexing process for ISI and other major indices. A) Full Papers Full papers should be innovative, so to advance the knowledge base of related fields. These papers present major contributions to the field and should be up to 12 pages in length. The conference proceedings https://www.springer.com/la/book/9783319729220 (to be published by Springer International Publishing) will include all accepted full papers. An award for the best full paper will be presented during the conference. B) Research Notes Research notes of up to 5 pages are invited. These papers represent new ideas not developed enough at the scale of a full paper, findings that restate known research, descriptions of prototypes, or research that is limited in scope. All research notes will be published by the e-Review of Tourism Research (eRTR) at http://ertr.tamu.edu/ (Editor of eRTR: Cody Morris Paris, Middlesex University Dubai, United Arab Emirates). C) Organized Sessions Proposals for organizing technical or other research-oriented sessions are invited. Proposals will include details of potential participants, topics, and presenters. Session Chairs are expected to attend ENTER 2019, set the order of presentations, and chair their session/s. Deadline for session chairs to submit their proposals to Research Track Chairs is September 3, 2018 (please submit proposal by e-mail to the research track chairs found at the end of the document). Submission Please refer to the "Author Advice" (http://www.enter2019.org/wp-content/uploads/2018/06/enter2019authoradvice_2.docx ) document as a style guide for standards to follow in the preparation of manuscripts. Please also see Springer guidelines for conference proceedings: https://www.springer.com/gb/authors-editors/conference-proceedings/conference-proceedings-guidelines , especially for Latex submissions. Papers must be uploaded to the online reviewing platform: Easy Chair for ENTER2019 (https://easychair.org/conferences/?conf=enter2019 ). All papers will be double-blind peer-reviewed by experienced researchers who are members of the scientific review committee. Final acceptance will depend on whether the author(s) can adequately address review comments to the satisfaction of the reviewers. Authors must submit their revised manuscripts by the deadline (October 22, 2018) and must register for the conference by November 12, 2018 in order to have their papers included in the Conference Proceedings or eRTR. Time Schedule ? Submission closes: September 10, 2018 (extended) ? Notification of acceptance/rejection/revision: October 8, 2018 ? Deadline to submit revised version: October 22, 2018 ? Final acceptance: October 29, 2018 ? End of Early Bird registration: November 2, 2018 ? Registration deadline to be published later: November 12, 2018 ? Conference: January 30 - February 1, 2018 Conference organizers reserve the right to modify the paper submission schedule. Submission Guideline and Presentation Template Please download the "Author Advice" document as a style guide for Word here: http://www.enter2019.org/wp-content/uploads/2018/06/enter2019authoradvice_2.docx and for Latex here: ftp://ftp.springernature.com/cs-proceeding/svproc/templates/ProcSci_TeX.zip . A presentation template for your presentation during ENTER2019 Conference will be sent to the authors after acceptance. Fast Track Journal of Information Technology and Tourism (JITT) Best papers' authors will be invited to submit an extended version of their article to Journal of Information Technology and Tourism (Springer). These articles will be reviewed under a special fast track in order to assure a timely publication. JITT website: http://bit.ly/ITTJournal . Research Track Chairs ? Juho Pesonen, University of Eastern Finland (juho.pesonen[at]uef.fi) ? Julia Neidhardt, TU Wien, Austria (julia.neidhardt[at]ec.tuwien.ac.at) -------------- next part -------------- An HTML attachment was scrubbed... URL: From msn2018 at mail.neu.edu.cn Mon Sep 3 01:50:21 2018 From: msn2018 at mail.neu.edu.cn (MSN2018) Date: Mon, 3 Sep 2018 13:50:21 +0800 (GMT+08:00) Subject: Connectionists: CFP: Mobile Ad-hoc and Sensor Networks 2018 Message-ID: <479cb179.7509.1659dfb5f3d.Coremail.msn2018@mail.neu.edu.cn> Apologies for any cross posting 14th Int. Conference on Mobile Ad-hoc and Sensor Networks Shenyang, China Dec. 6- 8, 2018 http://conf.neu.edu.cn/msn2018 You are cordially invited to submit your contribution until September 15, 2018. Final manuscripts should be prepared according to IEEE Computer Society Proceedings Format (double column, 10pt font) and submitted via the EasyChair system in PDF file format. The manuscript should be no longer than 6 pages. Up to two additional pages are permitted if the authors are willing to pay an over-length charge at the time of publication (manuscripts should not exceed 8 pages in total). Final manuscripts should not be previously published in or be under consideration for publication in another conference or journal. To submit your contribution visits the submission page (https://easychair.org/conferences/?conf=msn2018). ? Papers will be included in the conference proceedings edited by IEEE ? Extended versions will be invited for publication in special issues of international journals: o IEEE Transactions on Industrial Informatics edited by IEEE o IET Networks edited by IET o IEEE Wireless Communications edited by IEEE o Sensors edited by MDPI Topics include, but are not limited to: o Ad Hoc Networks o Vehicular Networks o Intelligent Sensor Networks o Urban Computing o Internet of Things o Edge and Fog Computing/Networking o 5G networks o Cognitive Radio Networks o Mobile Social Networks o Mobile Crowdsensing and Computing o Smart Networks o Knowledge Centric Networks o Delay Tolerant and Opportunistic Networking o Network Security and Privacy o Artificial Intelligence for Networking and Communications o Novel Applications and Architecture Steering Committee Co-Chairs Xiaohua Jia, City University of Hong Kong Jiannong Cao, Hong Kong Polytechnic University General Co-Chairs Xingwei Wang, Northeastern University, China Vincenzo Piuri, University of Milan, Italy TPC Co-Chairs Ruiyun Yu, Northeastern University, China Hongyi Wu, Old Dominion University, USA Dieter Hogrefe, University of Goettingen, Germany Publication Chair Guangtao Xue, Shanghai Jiao Tong University, China Xu Yuan, University of Louisiana at Lafayette, USA Yuanguo Bi, Northeastern University, China Yuan Liu, Northeastern University, China Publicity Chair Guangjie Han, Dalian University of Technology, China Cong Wang, Old Dominion University, USA Jie Jia, Northeastern University, China Jie Li, Northeastern University, China Yang Liu, Beijing University of Posts and Telecommunications, China Financial Chair Lianbo Ma, Northeastern University, China Local arrangement Chair Zhenhua Tan, Northeastern University, China Web Chair Yu Wang, Northeastern University, China -------------- next part -------------- An HTML attachment was scrubbed... URL: From bremeseiro at uniovi.es Mon Sep 3 05:23:00 2018 From: bremeseiro at uniovi.es (BEATRIZ REMESEIRO LOPEZ) Date: Mon, 3 Sep 2018 09:23:00 +0000 Subject: Connectionists: CFP ESANN'19 - Special Session on "Parallel and Distributed Machine Learning: Theory and Applications" Message-ID: [Apologies if you receive multiple copies of this CFP] Call for papers: special session on "Parallel and Distributed Machine Learning: Theory and Applications" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019) 24-26 April 2019, Bruges (Belgium) - http://www.esann.org Parallel and Distributed Machine Learning: Theory and Applications Organized by: Beatriz Remeseiro (Universidad de Oviedo, Spain), Ver?nica Bol?n-Canedo, Jorge Gonz?lez-Dom?nguez, Amparo Alonso-Betanzos (Universidade da Coru?a, Spain) The spread of Internet and the technological advances have resulted in huge volumes of data, very valuable for different agents in the industrial world that are interested in analyzing them for different purposes. Machine Learning (ML) algorithms play a key role in this context, being able to learn from and make predictions on data. Their increasing complexity, since they have to deal now with millions of parameters, as well as their computational cost lead to new research opportunities and technical challenges. This continuous increase of data involved in ML analyses leads to a growing interest in the design and implementation of parallel and distributed ML algorithms. The efficient exploitation of the vast aggregate main memory and processing power of High Performance Computing (HPC) resources such as multicore CPUs, hardware accelerators (GPUs, Intel Xeon Phi coprocessors, FPGAs, etc.), clusters or cloud-based systems can significantly accelerate many ML algorithms. However, the development of efficient parallel algorithms is not trivial, as we must pay much attention to the data organization and decomposition strategy in order to balance the workload among resources while minimizing data dependencies as well as synchronization and communication overhead. We invite papers on both practical and theoretical issues about incorporating parallel and distributed approaches into ML problems, as well as review papers with the state-of-art techniques and the open challenges encountered in this field. In particular, topics of interest include, but are not limited to: - Development of parallel ML algorithms on multicore and manycore architectures: multithreading, GPUs, Intel Xeon Phi coprocessor, FPGAs, etc. - Exploitation of cloud, grid and distributed-memory systems to accelerate ML algorithms: Spark, Hadoop, MPI, etc. - Deep learning models trained across multicore CPUs, GPUs or clusters of computers. - Development of distributed ML algorithms. - Novel programming paradigms to support HPC for ML. - Middleware, programming models, tools, and environments for HPC in ML. - Caching, streaming, pipelining, and other optimization techniques for data management in HPC for ML. - Benchmarking and performance studies of high-performance ML applications. - Parallel databases and I/O systems to store ML data. - Applications and services: bioinformatics, medicine, multimedia, video 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 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24-26 April 2019 -------------- next part -------------- An HTML attachment was scrubbed... URL: From weng at cse.msu.edu Mon Sep 3 12:23:06 2018 From: weng at cse.msu.edu (Juyang Weng) Date: Mon, 3 Sep 2018 12:23:06 -0400 Subject: Connectionists: Brains do not code time Message-ID: <0e5ea4ec-ae37-a210-5055-809cb8ab5e17@cse.msu.edu> I saw that Nature publisehd an Article by Albert Tsao et al. titled ?Integrating time from experience in the lateral entorhinal cortex?.? The authors are from Stanford University, (USA), NTNU of Norway, and Johns Hopkins University (USA).?? Nature has published many such papers that show incremental advances in biology. The abstract of the Article reads ?in freely foraging rats that temporal information is robustly encoded across time scales from seconds to hours within the overall population state of the lateral entorhinal cortex.? These claims by the authors are definitely wrong, because of authors? great lack of overwarching understanding about how brains work and the severe limitations of their experiments.? The authors have designed very restricted task settings (in a box of four walls with two continuous sections of colors, black and white; the top section wall?s center has one color and the ramaining walls have the other color) and forced repeated experience (12 trials) onto the animal (rats)?s brains.? Therefore, they greatly distorted what the multilemodal areas such as hippocampus do.?? This is a severe disgrace to brain intelligence, contrary to what authors intended to do.? This Article is not an isolated case in terms of a narrow-minded approach to studying hippocampus or other brain areas.? Currently prevailing in biology, physiology, and medicine, this narrow-minded approach to studying brains is not going to lead us anywhere interesting. In particular, none of the brains areas in general,? hippocampal areas in particular, code time at all!? They only deal with sensorimotor events like an emergent Turing machine.?? The brains must deal with time-warping, like an automata, not directly encoding time!?? However, I am afraid none of the authors are familiar with emergent Turing machines. June 13, 2017, we submitted two joint Letters to Nature: Juyang Weng, ?A Model for Auto-Programming for General Purposes?, and Juyang Weng, Zejia Zheng, Juan L. Castro-Garcia, Xiang Wu, Qian Guo, and Xiaofeng Wu, ?Some Experiments towards Auto-Programming for General Purposes?.? Nature rejected both Letters June 20, 2017. The email from Nature?s Senior Editor Leonie Mueck stated: ?I regret that we are unable to publish it in Nature.? As you may know, we decline a substantial proportion of manuscripts without sending them to referees, so that they may be sent elsewhere without delay. In such cases, even if referees were to certify the manuscript as technically correct, we do not believe that it represents a development of sufficient scientific impact to warrant publication in Nature. These editorial judgements are based on such considerations as the degree of advance provided, the breadth of potential interest to researchers and timeliness. ? ?In this case, we do not feel that your paper has matched our criteria for further consideration. We therefore feel that the paper would find a more suitable outlet in another journal.? There are no paper specific comments in the review.? In particular, none of the comments in the email address the major contributions of the papers at all. The cover letter of our first Letter to Nature provided a 100 word or less summary indicating on scientific grounds why the paper should be considered for a wide-ranging journal like Nature instead of a more narrowly focused journal: ?The results here have wide-front implications to computer science and engineering.?? The Turing Machine theory has yet to be tightly associated with brain-like network computation.?? While a Universal Turing Machine is considered for general purposes, a human must program it for each purpose.?? It was not known that a non-human machine can automatically program for general purposes, only a human adult can. In this sense, the new machine is a general-purpose self-programming Turing Machine, different from the (irrational number capability, or from rational numbers to real numbers) sense of Hava Siegelman 1995 published in? Science.? ?? those who like to duplicate and expand the simulation results on machines must read this theoretical letter because it is impossible to duplicate the results without understanding the theory.?? The same seems to be true if one likes to biologically verify the theory here. ? After much writing improvements, January 2, 2018 we submitted two joint reports to the Science Magazine but the worse events have happened: Not only did Science not provide any review comments at all, after the rejection by Science Magazine our web site was cyber-attacked probably because the site criticized that Science Magazine violated COPE rules!? Please watch the YouTube video: ?BMTalk 3D Episode 2: Science Magazine Rejected GENISAMA Super Turing Machines?, https://youtu.be/Qf8qjgBMasc It is unfornate that human scientists are too narrow-minded for the subjects that they study, blocked by cross-disciplinary journals like Science and Nature.? Those who do research on biological brains do not really care how brains compute overall; those who do artificial intelligence do not really care how brains work.?? Much taxpayers? money have been spent wastefully on many such narrow-minded and shallow projects, while our brain-model GENISAMA Turing Machines and experimental works have already explained, shown, and demosntrated how brains work.? Yet, the Science and Nature journals presistently block much needed cross-disciplinaery scientific communications. Again, brains do not represent time, but sensorimotor events instead.?? The human race took over two decades to wake up for the first deep learning network (Cresceptron 1992, 1993) with which we started general-purpose visual learning from 3D worlds.? How many more decades does the human race needs before it wakes up and accepts this much? greater breakthrough in Natural Intelligence and Artificial Intelligence?GENISAMA Super Turing Machines?? What should I do?? What should scientists do? -- -- Juyang (John) Weng ------------------- Work --------------------- ---- Technology Transfer ---- Professor Founder Department of Computer Science and Engineering GENISAMA LLC MSU Cognitive Science Program Okemos, MI 48864 USA and MSU Neuroscience Program Tel: 517-980-6270 428 S Shaw Ln Rm 3115 Web: genisama.com Michigan State University --------- Outreach ---------- East Lansing, MI 48824 USA Founder Tel: 517-353-4388 Brain-Mind Institute Fax: 517-432-1061 Web: brain-mind-institute.org Email: weng at cse.msu.edu Brain-Mind Magazine Web: http://www.cse.msu.edu/~weng/ Web: brain-mind-magazine.org ---------------------------------------------- ----------------------------- From msn2018 at mail.neu.edu.cn Mon Sep 3 21:58:51 2018 From: msn2018 at mail.neu.edu.cn (MSN2018) Date: Tue, 4 Sep 2018 09:58:51 +0800 (GMT+08:00) Subject: Connectionists: [msn2018] CFP: Mobile Ad-hoc and Sensor Networks 2018 Message-ID: <4287f502.7b9f.165a24dcaa1.Coremail.msn2018@mail.neu.edu.cn> Apologies for any cross posting 14th Int. Conference on Mobile Ad-hoc and Sensor Networks Shenyang, China Dec. 6- 8, 2018 http://conf.neu.edu.cn/msn2018 You are cordially invited to submit your contribution until September 15, 2018. Final manuscripts should be prepared according to IEEE Computer Society Proceedings Format (double column, 10pt font) and submitted via the EasyChair system in PDF file format. The manuscript should be no longer than 6 pages. Up to two additional pages are permitted if the authors are willing to pay an over-length charge at the time of publication (manuscripts should not exceed 8 pages in total). Final manuscripts should not be previously published in or be under consideration for publication in another conference or journal. To submit your contribution visits the submission page (https://easychair.org/conferences/?conf=msn2018). ? Papers will be included in the conference proceedings edited by IEEE ? Extended versions will be invited for publication in special issues of international journals: o IEEE Transactions on Industrial Informatics edited by IEEE o IET Networks edited by IET o IEEE Wireless Communications edited by IEEE o Sensors edited by MDPI Topics include, but are not limited to: o Ad Hoc Networks o Vehicular Networks o Intelligent Sensor Networks o Urban Computing o Internet of Things o Edge and Fog Computing/Networking o 5G networks o Cognitive Radio Networks o Mobile Social Networks o Mobile Crowdsensing and Computing o Smart Networks o Knowledge Centric Networks o Delay Tolerant and Opportunistic Networking o Network Security and Privacy o Artificial Intelligence for Networking and Communications o Novel Applications and Architecture Steering Committee Co-Chairs Xiaohua Jia, City University of Hong Kong Jiannong Cao, Hong Kong Polytechnic University General Co-Chairs Xingwei Wang, Northeastern University, China Vincenzo Piuri, University of Milan, Italy TPC Co-Chairs Ruiyun Yu, Northeastern University, China Hongyi Wu, Old Dominion University, USA Dieter Hogrefe, University of Goettingen, Germany Publication Chair Guangtao Xue, Shanghai Jiao Tong University, China Xu Yuan, University of Louisiana at Lafayette, USA Yuanguo Bi, Northeastern University, China Yuan Liu, Northeastern University, China Publicity Chair Guangjie Han, Dalian University of Technology, China Cong Wang, Old Dominion University, USA Jie Jia, Northeastern University, China Jie Li, Northeastern University, China Financial Chair Lianbo Ma, Northeastern University, China Local arrangement Chair Zhenhua Tan, Northeastern University, China Web Chair Yu Wang, Northeastern University, China -------------- next part -------------- An HTML attachment was scrubbed... URL: From nguyensmai at gmail.com Mon Sep 3 16:40:24 2018 From: nguyensmai at gmail.com (Nguyen, Sao Mai) Date: Mon, 3 Sep 2018 22:40:24 +0200 Subject: Connectionists: [journals] CfP : Special Issue on Continual Unsupervised Sensorimotor Learning Message-ID: Dear Colleagues, IEEE Transactions on Cognitive and Developmental Systems is currently running a Special Issue entitled " Continual Unsupervised Sensorimotor Learning". Dr. Jos? Antonio Iglesias Mart?nez, Assoc. Prof. We would like to invite you to prepare a research article or a comprehensive review to be published in this special issue. AIM AND SCOPE Although machine learning algorithms continue to improve at a rapid pace enabling technologies and products such as autonomous driving cars and sophisticated image and speech recognition, it is often forgotten that these applications represent tailored solutions to specific tasks. Thus it is not clear if or how these autonomous systems can pave the road to general purpose machines envisioned by many. The pursuit for higher levels of autonomy and versatility in robotics is arguably lead by two main factors. Firstly, as we push robots out of the labs and productions lines, it becomes increasingly difficult to design for all possible scenarios that a particular robot might encounter. Secondly, the cost of designing, manufacturing, and maintaining such systems becomes prohibitive. As the algorithms for learning single tasks in restricted environments are improving, new challenges have gained relevance in order to get more autonomous artificial systems. These challenges include multi-task learning, multimodal sensorimotor learning and lifelong adaptation to injury, growth and ageing. Addressing these challenges promise higher levels of autonomy and versatility of future robots. This special issue on Continual Unsupervised Sensorimotor Learning is primarily concerned with the developmental processes involved in unsupervised sensorimotor learning in a life-long perspective, and in particular the emergence of representations of action and perception in humans and artificial agents in continual learning. These processes include action-perception cycle, active perception, continual sensory-motor learning, environmental-driven scaffolding, and intrinsic motivation. The special issue will highlight behavioural and neural data, and cognitive and developmental approaches to research in the areas of robotics, computer science, psychology, neuroscience, etc. Contributions might focus on mathematical and computational models to improve robot performance and/or attempt to unveil the underlying mechanisms that lead to continual adaptation to changing environment or embodiment and continual learning in open-ended environments. Contributions from multiple disciplines including cognitive systems, cognitive robotics, developmental and epigenetic robotics, autonomous and evolutionary robotics, social structures, multi-agent and artificial life systems, computational neuroscience, and developmental psychology, on theoretical, computational, application-oriented, and experimental studies as well as reviews in these areas are welcome. THEMES This special issue aims to report state-of-the-art approaches and recent advances on Continual Unsupervised Sensorimotor Learning with a cross-disciplinary perspective. Topics relevant to this special issue include but are not limited to: Emergence of representations via continual interaction Continual sensory-motor learning Action-perception cycle Active perception Environmental-driven scaffolding Intrinsic motivation Neural substrates, neural circuits and neural plasticity Human and animal behaviour experiments and models Reinforcement learning and deep reinforcement learning for life-long learning Multisensory robot learning Multimodal sensorimotor learning Affordance learning Prediction learning SUBMISSION Manuscripts should be prepared according to the ?Information for Authors? of the journal found at http://cis.ieee.org/component/content/article/7/131-ieee-transactions-on-autonomous-mental-development-information-for-authors.html. Submissions must be done through the IEEE TCDS Manuscript center: https://mc.manuscriptcentral.com/tcds-ieee. Please select the category ?SI: Continual Unsupervised Sensorimotor Learning?. IMPORTANT DATES 6th January 2019 ? Paper submission deadline 15th March 2019 ? Notification for authors 31st May 2019 ? Deadline revised papers submission 30th June 2019 ? Final notification for authors 31st July 2019 ? Deadline for camera-ready versions September 2019 ? Expected publication date More information on Continual Unsupervised Sensorimotor Learning http://projects.au.dk/socialrobotics/news-events/show/artikel/special-issue-on-continual-unsupervised-sensorimotor-learning/ GUEST EDITORS Nicol?s Navarro-Gerrero Aarhus University, Aarhus, Denmark nng at eng.au.dk Sao Mai Nguyen IMT Atlantique, Francenguyensmai at gmail.com Erhan ?ztop ?zye?in University, Turkeyerhan.oztop at ozyegin.edu.tr Junpei Zhong National Institute of Advanced Industrial Science and Technology (AIST), Japanjoni.zhong at aist.go.jp ---- Nguyen Sao Mai nguyensmai at gmail.com Researcher in Cognitive Developmental Robotics http://nguyensmai.free.fr -------------- next part -------------- An HTML attachment was scrubbed... URL: From nguyensmai at gmail.com Mon Sep 3 17:16:33 2018 From: nguyensmai at gmail.com (Nguyen, Sao Mai) Date: Mon, 3 Sep 2018 23:16:33 +0200 Subject: Connectionists: [meetings] Call for Participation : Workshop on Continual Unsupervised Sensorimotor Learning - Tokyo - September 17th Message-ID: Call for Participation Workshop on Continual Unsupervised Sensorimotor Learning at IEEE ICDL-Epirob 2018 - Tokyo - September 17th Website : http://conferences.au.dk/icdl-epirob-2018-workshop/ ============================================================ Invited Speakers - Jochen Triesch, Frankfurt Institute of Advanced Studies, Germany - David Ha, Google Brain - Lorenzo Jamone, Queen Mary University of London, UK Scope As the algorithms for learning single tasks in restricted environments are improving, new challenges have gained relevance. They include multi-task learning, multimodal sensorimotor learning in open worlds and lifelong adaptation to injury, growth and ageing. In this workshop we will discuss the developmental processes involved in the emergence of representations of action and perception in humans and artificial agents in continual learning. These processes include action-perception cycle, active perception, continual sensory-motor learning, environmental-driven scaffolding, and intrinsic motivation. The discussion will be strongly motivated by behavioural and neural data. We hope to provide a discussion friendly environment to connect with research with similar interest regardless of their area of expertise which could include robotics, computer science, psychology, neuroscience, etc. We would also like to devise a roadmap or strategies to develop mathematical and computational models to improve robot performance and/or to attempt to unveil the underlying mechanisms that lead to continual adaptation to changing environment or embodiment and continual learning in open-ended environments. The primary list of topics covers the following (but not limited to): - Emergence of representations via continual interaction - Continual sensory-motor learning - Action-perception cycle - Active perception - Environmental-driven scaffolding - Intrinsic motivation - Neural substrates, neural circuits and neural plasticity - Human and animal behaviour experiments and models - Reinforcement learning and deep reinforcement learning for life-long learning - Multisensory robot learning - Multimodal sensorimotor learning - Affordance learning - Prediction learning Organizers: - Nicol?s Navarro-Guerrero, Aarhus University, Aarhus, Denmark - Sao Mai Nguyen, IMT Atlantique, France - Erhan ?ztop, ?zye?in University, Turkey - Junpei Zhong, National Institute of Advanced Industrial Science and Technology (AIST), Japan Nguyen Sao Mai nguyensmai at gmail.com Researcher in Cognitive Developmental Robotics http://nguyensmai.free.fr -------------- next part -------------- An HTML attachment was scrubbed... URL: From mark.humphries at manchester.ac.uk Tue Sep 4 08:29:08 2018 From: mark.humphries at manchester.ac.uk (Mark Humphries) Date: Tue, 4 Sep 2018 12:29:08 +0000 Subject: Connectionists: Fully-funded UK/EU PhD studentship in neural data science, deadline 26th September Message-ID: <7E954275ED82B9468C2C731FB72522F5013E0F9A6C@MBXP09.ds.man.ac.uk> A fully-funded EU/UK PhD studentship is available in the lab of Prof Mark Humphries at the University of Nottingham, on a project entitled "Inferring the connectome using voltage imaging". This project will develop computational techniques to accurately infer wiring between neurons from the next generation of imaging techniques that directly record neuron voltages. The project will combine development of algorithms, simulations of neural circuits as test-beds, and analysis of real imaging data from neural populations. For a primer on the problem of finding the wiring between neurons, read our piece here: https://medium.com/the-spike/mindlessly-mapping-the-brain-1dec092a404d Find out more about the lab and its interests here: https://www.humphries-lab.org/ More details, eligibility, and application instructions here: https://www.findaphd.com/search/ProjectDetails.aspx?PJID=97729 Deadline: 26th September 2018 Start date: January 2019 To discuss this or other projects, please contact Prof Mark Humphries (mark.humphries at nottingham.ac.uk). Professor Mark Humphries | MRC Senior non-Clinical Fellow | Chair in Computational Neuroscience humphries-lab.org [0da17e2a-9ed5-496a-b161-9fd4491ce5c7]@markdhumphries Public blog: https://medium.com/the-spike -------------- next part -------------- An HTML attachment was scrubbed... URL: From rajeev.raizada at gmail.com Tue Sep 4 13:14:53 2018 From: rajeev.raizada at gmail.com (Rajeev Raizada) Date: Tue, 4 Sep 2018 13:14:53 -0400 Subject: Connectionists: Job ad: tenure-track open rank faculty positions in Cognitive Science In-Reply-To: <2973038610487523.WA.rajeev.raizadagmail.com@www.jiscmail.ac.uk> References: <2973038610487523.WA.rajeev.raizadagmail.com@www.jiscmail.ac.uk> Message-ID: http://www.sas.rochester.edu/bcs/jobs/faculty.html Cognitive Scientist, Open Rank, University of Rochester The Department of Brain and Cognitive Sciences at the University of Rochester is seeking to hire multiple faculty members in the area of decision making and cognitive or sensorimotor planning at the Assistant (tenure-track) or Associate Professor level. Areas of interest include the roles of learning, prediction, memory, and attention in guiding goal-directed behavior, especially within complex, naturalistic environments. We are primarily interested in candidates using neuroimaging, computational (e.g., Bayesian decision theory, reinforcement learning), behavioral (including technology-driven approaches such as virtual reality), and/or developmental approaches. Both individuals and teams are encouraged to apply. Successful candidates will join a dynamic department with interests in the study of perception, motor control, learning, cognition, language, and development through combined neurobiological, computational, and behavioral research (http://www.sas.rochester.edu/bcs/); she or he will also be part of a university?wide community engaged in graduate and undergraduate education. Candidates should hold a PhD degree (or equivalent) in cognitive science, psychology, neuroscience, or another relevant domain, and should have considerable research experience. Applicants should submit a CV, a statement of research and teaching interests, and contact information for three referees via the following website: http://www.rochester.edu/faculty-recruiting. In addition, team applications should include a joint statement that describes the research synergies of the team. Questions concerning this position can be addressed to Robert Jacobs (rjacobs at ur.rochester.edu) and Duje Tadin (dtadin at ur.rochester.edu), co-chairs of the search committee. Review of applications will begin on November 1, 2018. The University of Rochester is an Equal Opportunity Employer with a strong commitment to diversity, and actively encourages applications from candidates from groups underrepresented in higher education. EOE / Minorities / Females / Protected Veterans / Disabled -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Tue Sep 4 15:19:35 2018 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 4 Sep 2018 15:19:35 -0400 Subject: Connectionists: High Performance Computing workshop at SFN 2018 meeting Message-ID: <80966c3f-37bb-d8ba-3835-c942562ab280@yale.edu> This year's workshop on High Performance Computing Resources for Parallel Simulations and Data Analysis will be held on Saturday, Nov. 3, from 8:30 AM to 12:30 PM in downtown San Diego as a satellite to the 2018 meeting of the Society for Neuroscience. It will feature presentations from developers and users of powerful hardware and software tools for dealing with computationally-intensive modeling and data analysis tasks. For more information and a link to the registration form, see https://neuron.yale.edu/neuron/static/courses/nsg2018/nsg2018.html The registration deadline for this workshop is Friday Oct. 12, but you should sign up early because space is limited. --Ted From ted.carnevale at yale.edu Tue Sep 4 22:12:38 2018 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 4 Sep 2018 22:12:38 -0400 Subject: Connectionists: NEURON Course at SFN 2018 meeting Message-ID: Space is still available for the NEURON course at this year's meeting of the Society for Neuroscience. Are you a lab director trying to decide whether to add computational modeling to your research program? A grad student or postdoc who is just getting started in modeling? An established NEURON user who wants to find out about NEURON's latest features? If so, this one-day course is for you! The course starts with a practical introduction that reviews basic concepts and presents a workflow for building and using models of cells and networks, and moves on to topics that include: --how to speed up simulations --how to use Python with NEURON (and take advantage of NEURON's GUI!) --how to model reaction-diffusion with the RxD class For more information and the registration form, see https://neuron.yale.edu/neuron/static/courses/sd2018/sd2018.html --Ted From luca.oneto at unige.it Wed Sep 5 05:42:09 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Wed, 5 Sep 2018 11:42:09 +0200 Subject: Connectionists: ESANN 2019 SS - Societal Issues in Machine Learning: When Learning from Data is Not Enough Message-ID: [Apologies if you receive multiple copies of this CFP] Call for papers: special session on "Societal Issues in Machine Learning: When Learning from Data is Not Enough" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019). 24-26 April 2019, Bruges, Belgium - http://www.esann.org DESCRIPTION: It has been argued that Artificial Intelligence (AI) is experiencing a fast process of commodification. This characterization is on the interest of big IT companies, but it correctly reflects the current industrialization of AI. This phenomenon means that AI systems and products are reaching the society at large and, therefore, that societal issues related to the use of AI and Machine Learning (ML) cannot be ignored any longer. Designing ML models from this human-centered perspective means incorporating human-relevant requirements such as safety, fairness, privacy, and interpretability, but also considering broad societal issues such as ethics and legislation. These are essential aspects to foster the acceptance of ML-based technologies, as well as to be able to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. This special session aims to put forward the state-of-the-art on these increasingly relevant topics among ML theoretician and practitioners. For this purpose, we welcome both solid contributions and preliminary relevant results showing the potential, the limitations and the challenges of new ideas, refinements, or contaminations between the different fields of research, ML, and related approaches in facing real-world problems involving societal issues. We welcome works on ML theory, applications to topics listed below as well as other topics of social relevance. Studies stemming from major research initiatives and projects focusing on the session topics are particularly welcome. TOPICS OF INTEREST: - Fairness as an element in the development of ML techniques; - Ethical issues in the application of ML and related techniques in areas of social impact; - Privacy as a challenge in ML application to problems in the social domain; - Interpretability and explainability of ML and related approaches; - Safety and Security of ML and related methods in safety critical contexts; - Legislative challenges to the use of ML and related methods; - The challenge of complex data for ML and related methods; - Transparency and open data. SUBMISSION: Prospective authors must submit their paper through the ESANN portal following the instructions provided in https://www.elen.ucl.ac.be/esann/index.php?pg=submission Each paper will undergo a peer reviewing process for its acceptance. Authors should send as soon as possible an e-mail with the tentative title of their contribution to the special session organisers. IMPORTANT DATES: Submission of papers: 19 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Davide Bacciu, University of Pisa (Italy) Battista Biggio, University of Cagliari (Italy) Jos? D. Mart?n, Universitat de Val?ncia (Spain) Luca Oneto, University of Genoa (Italy) Alfredo Vellido, Universitat Polit?cnica de Catalunya (Spain) Paulo J. G. Lisboa, Liverpool John Moores University (UK) ----------------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: Luca.Oneto at unige.it SmartLab Laboratory e-mail: Luca.Oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145 Genoa ITALY Phone: +39-010-3532192 www.smartlab.ws ----------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From luca.oneto at unige.it Wed Sep 5 07:26:43 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Wed, 5 Sep 2018 13:26:43 +0200 Subject: Connectionists: INNSBDDL2019 - List of Confirmed Tutorials & Student Paper Awards Message-ID: Apologies for cross-posting. INNS BIG DATA AND DEEP LEARNING 2019 SESTRI LEVANTE, GENOA, ITALY, 16-18 APRIL 2019 HTTPS://INNSBDDL2019.ORG/ CONFIRMED TUTORIALS https://innsbddl2019.org/tutorial/ - Davide Bacciu (University of Pisa), Deep Learning for Graphs - Silvia Chiappa (DeepMind), Luca Oneto (University of Genoa), Fairness in Machine Learning - Claudio Gallicchio (University of Pisa), Simone Scardapane (Sapienza University of Rome), Deep Randomized Neural Networks - V?ra K?rkov? (Czech Academy of Sciences), Complexity of Shallow and Deep Networks - Danilo P. Mandic, Ilia Kisil, and Giuseppe G. Calvi (Imperial College London), Tensor Decompositions and Applications. Blessing of Dimensionality - German I. Parisi and Stefan Wermter (University of Hamburg), Continual Lifelong Learning with Neural Networks STUDENT PAPER AWARDS https://innsbddl2019.org/awards/ Two best student paper awards (financed by AI*IA). The two students which will receive the prize will be selected by the INNS BDDL 2019 PC. The two winner students will have to register to the AI*IA, if they are not members yet, and their student registration fees will be refunded by the AI*IA. ----------------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: Luca.Oneto at unige.it SmartLab Laboratory e-mail: Luca.Oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145 Genoa ITALY Phone: +39-010-3532192 www.smartlab.ws ----------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Wed Sep 5 12:04:58 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Wed, 5 Sep 2018 19:04:58 +0300 Subject: Connectionists: The 34th ACM Symposium on Applied Computing (SAC 2019): Final Combined Call for Papers In-Reply-To: <31C24FFB-0CFA-4FDA-A707-4F88A4937121@cs.ucy.ac.cy> References: <31C24FFB-0CFA-4FDA-A707-4F88A4937121@cs.ucy.ac.cy> Message-ID: *** FINAL COMBINED CALL FOR PAPERS *** The 34th ACM Symposium on Applied Computing (SAC 2019) St. Raphael Resort, Limassol, Cyprus, April 8-12, 2019 https://www.sigapp.org/sac/sac2019 *** Submission Deadline: September 24, 2018 (extended) *** For the past thirty-three years the ACM Symposium on Applied Computing (SAC) has been a primary and international forum for applied computer scientists, computer engineers and application developers to gather, interact and present their work. The ACM Special Interest Group on Applied Computing (SIGAPP) is the sole sponsor of SAC. The conference proceedings are published by ACM and are also available online through ACM's Digital Library. The 34th Annual SAC meeting will be held in April 2019 in Limassol, Cyprus, and is hosted by the University of Cyprus. The conference features the following tracks: ? Intelligent Robotics and Multi-Agent Systems (IRMAS) ? Knowledge Representation and Reasoning (KRR) ? Information Access and Retrieval (IAR) ? Software Verification and Testing (SVT) ? Computational Intelligence and Video & Image Analysis (CIVIA) ? Social Network and Media Analysis (SONAMA) ? Selected Areas of Wireless Communications and Networking (WCN) ? Recommender Systems: Theory and Applications (RS) ? Computer Security (SEC) ? Web-based Technologies for Interactive Computing Education (WICE) ? Data Mining (DM) ? Usability Engineering (UE) ? Cloud Computing (CC) ? Privacy by Design in Practice (PDP) ? Advances in COMputational Biomedical Imaging (COMBI) ? Operating Systems (OS) ? Software Platforms (SP) ? Decentralized Applications (DAPP) with Blockchain, DLT and Crypto-Currencies (DAPP) ? Databases and Big Data Management (DBDM) ? Requirements Engineering (RE) ? Cyber-Physical Systems (CPS) ? Software Architecture: Theory, Technology, and Applications (SA-TTA) ? Internet of Things (IoT) ? Sustainability of Fog/Edge Computing Systems (SFECS) ? Software-intensive Systems-of-Systems (SiSoS) ? Data Streams (DS) ? Programming Languages (PL) ? Business Process Management & Enterprise Architecture (BPMEA) ? Microservices, DevOps, and Service-Oriented Architecture (MiDOS) ? Health Informatics (HI) ? Dependable, Adaptive, and Secure Distributed Systems (DADS) ? GeoInformation Analytics (GIA) ? Knowledge and Language Processing (KLP) ? KomIS: Knowledge Discovery meets Information Systems (KomIS) ? Next Generation Programming Paradigms and Systems (NGPS) ? Communication, Computing and Networking in Internet of Vehicles (CCNIV) ? Bioinformatics (BIO) ? Embedded Systems (EMBS) ? Digital Life for Human Well-being (DLHWB) ? Networking (NET) ? Semantic Web and Applications (SWA) ? Mobile Computing and Applications (MCA) ? Software Engineering (SE) ? Variability and Software Product Line Engineering (VSPLE) ? Smart Human Computer Interaction (HCI) ? Web Technologies (WT) ? Machine Learning and its Applications (MLA) More information about the topics covered by each track and submission instructions are available on the conference web site and the web sites of the tracks themselves (accessible from the conference web site). Important Dates ? Sept 24, 2018: Submission of papers (extended) ? Nov 10, 2018: Author notification ? Nov 25, 2018: Camera-ready copies ? Dec 10, 2018: Author registration Committees https://www.sigapp.org/sac/sac2019/organization.html -------------- next part -------------- An HTML attachment was scrubbed... URL: From r.pascanu at gmail.com Wed Sep 5 12:56:11 2018 From: r.pascanu at gmail.com (Razvan Pascanu) Date: Wed, 5 Sep 2018 17:56:11 +0100 Subject: Connectionists: CfP -- Continual Learning workshop at NIPS 2018 Message-ID: TL;DR: We invite you to our workshop on Continual Learning at this year?s NIPS. Submission deadline for 4-page abstracts is October 19th. --------------------- Continual learning (CL) is the ability to learn continually from a stream of experiential data, building on what was learnt previously, while being able to reapply, adapt and generalize it to new situations. CL is a fundamental step towards artificial intelligence, as it allows the learning agent to continually extend its abilities and adapt them to a continuously changing environment, a hallmark of natural intelligence. It also has implications for supervised or unsupervised learning. For example, if a dataset is not randomly shuffled, or the input distribution shifts over time, a learned model might overfit to the most recently seen data, forgetting the rest -- a phenomenon referred to as catastrophic forgetting, which is a core issue CL systems aim to address. Continual learning is characterized in practice by a series of desiderata. A non-complete list of which includes: - Online learning -- learning occurs at every moment, with no fixed tasks or data sets and no clear boundaries between tasks; - Presence of transfer (forward/backward) -- the learning agent should be able to transfer and adapt what it learned from previous experience, data, or tasks to new situations, as well as make use of more recent experience to improve performance on capabilities learned earlier; - Resistance to catastrophic forgetting -- new learning should not destroy performance on previously seen data; - Bounded system size -- the agent?s learning capacity should be fixed, forcing the system to use its resources intelligently, gracefully forgetting what it has learned so as to minimize potential loss of future reward; - No direct access to previous experience -- while the model can remember a limited amount of experience, a continual learning algorithm cannot assume direct access to all of its past experience or the ability to rewind the environment (i.e., t=0 exactly once). In the first (2016) meeting of this workshop, the focus was on defining a complete list of desiderata of what a continual learning (CL) enabled system should be able to do. The focus of the 2018 workshop will be on: 1. how to evaluate CL methods; and 2. how CL compares with related ideas (e.g., life-long learning, never-ending learning, transfer learning, meta-learning) and how advances in these areas could be useful for continual learning. In particular, different desiderata of continual learning seem to be in opposition (e.g., fixed model capacity vs non-catastrophic forgetting vs the ability to generalize and adapt to new situations), which also raises the question of what a successful continual learning system should be able to do. What are the right trade-offs between these different opposing forces? How do we compare existing algorithms in the face of conflicting objectives? What metrics are most useful to report? In some cases, trade-offs will be tightly defined by the way we choose to test the algorithms. What would be the right benchmarks, datasets or tasks for productively advancing this topic? We encourage submission of four-page abstracts describing work in progress or completed work on topics (1) and (2) above, including work beneficial to the advancement of CL from related areas, such as: - Transfer learning - Multi-task learning - Meta learning - Lifelong learning - Few-shot learning Finally, we will also encourage presentation of both novel approaches to CL and implemented systems, which will help concretize the discussion of what CL is and how to evaluate CL systems. Confirmed speakers: - Marc?Aurelio Ranzato (Facebook AI Research) - John Schulman (OpenAI) - Raia Hadsell (DeepMind) - Chelsea Finn (Berkeley & Google Brain) - Yarin Gal (Oxford) - Juergen Schmidhuber (IDSIA/NNAISENSE) Dates: - Submission deadline: Friday October 19 - Workshop: Friday December 7th Submission format: 4 page extended abstracts, which can include previously published work. More details at the website: https://sites.google.com/corp/view/continual2018/ Submissions will be managed through EasyChair here: https://easychair.org/conferences/?conf=cl20180 We look forward to seeing you in December! Razvan Pascanu, Yee Whye Teh, Mark Ring and Marc Pickett. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ian.r.oakley at gmail.com Wed Sep 5 19:44:58 2018 From: ian.r.oakley at gmail.com (Ian Oakley) Date: Thu, 6 Sep 2018 08:44:58 +0900 Subject: Connectionists: ICMI 18 Call for Participation Message-ID: ********** International Conference on Multimodal Interaction (ICMI) Boulder, Colorado, October 16-20th, 2018 https://icmi.acm.org/2018/ Call for Participation Early-bird registration: Sep 14, 2018, ACM members: $575, students: $375. Regular registration: Oct 13, 2018, ACM members: $675, students: $475. Onsite registration: ACM members: $725, students: $525. Full details and pricing: https://icmi.acm.org/2018/index.php?id=registration ********** ICMI 2018 Call for Participation The 20th International Conference on Multimodal Interaction (ICMI 2018) will be held in Boulder, Colorado. ICMI is the premier international forum for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, and system development. The conference focuses on theoretical and empirical foundations, component technologies, and combined multimodal processing techniques that define the field of multimodal interaction analysis, interface design, and system development. The ICMI 2018 program includes an exciting set of events and speakers. Highlights include Keynotes: - A multimodal approach to understanding human vocal expressions and beyond by Prof. Shrikanth (Shri) Narayanan - Using Technology for Health and Wellbeing by Dr. Mary Czerwinski - Reinforcing, reassuring, and roasting: The forms and functions of the human smile by Prof. Paula M. Niedenthal Plenary Paper Sessions: - Six plenary oral sessions with 28 technical full and short papers - Two poster sessions with 35 posters Tutorials: - Multimodal-Multisensor Behavioral Analytics: Going Deeper into Human-Centered Design by Prof. Sharon Oviatt - Deep Learning for Multimodal and Multisensorial Interaction by Prof. Bj?rn W. Schuller Workshops: - Multi-sensorial Approaches to Human-Food Interaction (MHFI) - Group Interaction Frontiers in Technology (GIFT) - Modeling Cognitive Processes from Multimodal Data (MCPMD) - Human-Habitat for Health (H3) - Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction (MA3HMI) Grand Challenges: - The ICMI Eating Analysis & Tracking Challenge (ICMI 2018 EAT) - 6th Emotion Recognition in the Wild Challenge (EmotiW) Panels: - Panel on Future Challenges for Multimodal Interaction in Groups - Panel: Future roadmap to multimodal research Other Events: - Doctoral Consortium - Late Breaking Papers - Demos/Exhibits There is also available funding to Broaden Participation under a SIGCHI Conference Development Fund - submissions due by 20th Sept: https://icmi.acm.org/2018/index.php?id=cdf Keep up to date with the program as it is finalized online: https://icmi.acm.org/2018/index.php?id=schedule Come join us in Boulder in October 16-20, 2018! Sincerely, ICMI 2018 co-chairs Sidney D'Mello (CU Boulder) Stefan Scherer (USC) Panayiotis (Panos) Georgiou (USC) -------------- next part -------------- An HTML attachment was scrubbed... URL: From dnoelle at ucmerced.edu Thu Sep 6 00:59:04 2018 From: dnoelle at ucmerced.edu (David Noelle) Date: Thu, 6 Sep 2018 04:59:04 +0000 Subject: Connectionists: Four Open Faculty Positions in Cognitive and Information Sciences at the University of California, Merced Message-ID: Four Open Faculty Positions Assistant Professor of Cognitive and Information Sciences University of California, Merced The Department of Cognitive and Information Sciences (CIS) at the University of California, Merced seeks applicants for four (4) tenure-track faculty positions at the Assistant Professor level. CIS is a highly interdisciplinary group offering bachelor?s degrees in Cognitive Science and Philosophy as well as an intensive research-based PhD in Cognitive and Information Sciences. We seek outstanding scholars who will establish and maintain creative research paradigms, participate actively in the development of interdisciplinary programs, and teach and mentor effectively at both the undergraduate and graduate levels. Applicants must have either a strong research record or evidence of the potential to develop an independent and innovative research program. We are especially seeking candidates whose research involves one or more of the following areas: (1) Cognitive and Data Science, (2) Language, Communication, and Culture, and (3) Applied Ethics. Applicants must hold a PhD in a relevant discipline, such as Cognitive Science, Psychology, Philosophy, Neuroscience, Linguistics, Computer Science, or Anthropology, by the position start date, which is anticipated to be July 1, 2019. Applications must be received no later than November 15, 2018 to be considered. For further information, please visit ?https://aprecruit.ucmerced.edu/apply/JPF00699?. -------------- next part -------------- An HTML attachment was scrubbed... URL: From m_e_alper at yahoo.com.tr Thu Sep 6 02:56:56 2018 From: m_e_alper at yahoo.com.tr (Ege A) Date: Thu, 6 Sep 2018 06:56:56 +0000 (UTC) Subject: Connectionists: Post-doc ad on Gaussian Process Emulators References: <1287708031.976747.1536217016070.ref@mail.yahoo.com> Message-ID: <1287708031.976747.1536217016070@mail.yahoo.com> Dear correspondent, The attached ad might be of interest. Regards,Muzaffer Ege Alper, PhD in Statistics and Applied Probability Post-doc researcher at Finnish Meteorological Institute -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Post-doctoral position on statistical emulation of a cloud-scale model_fmi_AD.pdf Type: application/pdf Size: 212285 bytes Desc: not available URL: From richard.jiang at northumbria.ac.uk Thu Sep 6 05:13:45 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Thu, 6 Sep 2018 09:13:45 +0000 Subject: Connectionists: Call for Book Chapters on Deep Biometrics In-Reply-To: References: Message-ID: Dear Colleagues, We would like to invite you to contribute a chapter for the upcoming volume entitled Deep Biometrics to be published by Springer, the largest global scientific, technical, and medical ebook publisher. The volume will be available both in print and in ebook format by late 2018/early 2019 on SpringerLink, one of the leading science portals that includes more than 8 million documents, an ebook collection with more than 160,000 titles, journal archives digitized back to the first issues in the 1840s, and more than 30,000 protocols and 290 reference works. Below is a short description of the volume: Recent development in machine learning, particularly deep learning, has brought out drastic impact on Biometrics, which is a classic topic to utilize Machine Learning for biometric identification. Particularly, Deep Learning can benefit from the training with large unlabelled datasets via semi-supervised or unsupervised learning. This book aims to highlight recent research advances in biometrics using semi-supervised and unsupervised new methods such as Deep Neural Networks, Deep Stacked Autoencoder, Convolutional Neural Networks, Generative Adversary Networks, and so on, and exploit these new methods in the emerging new areas such as privacy and security issues, cancellable biometrics and soft biometrics, smart cities, big biometric data, biometric banking, medical biometrics, and healthcare biometrics, etc.. The goal of this volume is to summarize the recent advances in using Deep Learning in the area of biometric security and privacy. Topics of interest include: (but not limited to) ? Deep Learned Biometric Features ? Convolutional Neural networks ? Deep Stacked Autoencoder ? Biometrics in Cybersecurity ? Biometrics in Cognitive Robot ? Healthcare Biometrics ? Medical Biometrics ? Biometrics in Social Computing ? Privacy and Security Issues ? Deep Face Detection ? Deep Face Recognition ? Iris, Fingerprints, DNA, Palmprints ? Gait, EEG, Heart rates ? Multimodal Fusion ? Soft Biometrics ? Cancellable Biometrics with Deep Learning ? Big data issues in Biometrics ? Biometrics for Internet of things Each contributed chapter is expected to present a novel research study, a comparative study, or a survey of the literature. Note that there will be no publication fees for accepted chapters. Important Dates Submission of abstracts Nov 15, 2018 Notification of initial editorial decisions Nov 20, 2018 Submission of full-length chapters Dec 15, 2018 Notification of final editorial decisions Jan 15, 2019 Submission of revised chapters Feb 15, 2019 All submissions should be done via EasyChair: https://easychair.org/conferences/?conf=deepbio2019 Original artwork and a signed copyright release form will be required for all accepted chapters. For author instructions, please visit: http://www.springer.com/authors/book+authors?SGWID=0-154102-12-417900-0 Please feel free to contact us via email (perceptualscience at outlook.com, or any editors below) regarding your chapter ideas. Editorial Board * Dr Richard Jiang Computer and Information Sciences, Northumbria University, United Kingdom Web: http://bit.ly/2n5glEx * Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark * Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia * Professor Christophe Rosenberger Computer Security ENSICAEN ? GREYC, France Contact All questions about submissions can be emailed to Dr Richard Jiang (perceptualscience at outlook.com, or richard.jiang at unn.ac.uk). This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender?s explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. -------------- next part -------------- An HTML attachment was scrubbed... URL: From richard.jiang at northumbria.ac.uk Thu Sep 6 05:13:45 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Thu, 6 Sep 2018 09:13:45 +0000 Subject: Connectionists: [visionlist] Call for Book Chapters on Deep Biometrics In-Reply-To: References: Message-ID: <7762_1536241605_w86Dkh32013780_WM!8926f42c656d15f3fd7a257112cfb3e21c01486d971d647467ed26b779148f45d3a5979901ca77a0e8433aa1d4cce9ac!@defcon3.northumbria.ac.uk> Dear Colleagues, We would like to invite you to contribute a chapter for the upcoming volume entitled Deep Biometrics to be published by Springer, the largest global scientific, technical, and medical ebook publisher. The volume will be available both in print and in ebook format by late 2018/early 2019 on SpringerLink, one of the leading science portals that includes more than 8 million documents, an ebook collection with more than 160,000 titles, journal archives digitized back to the first issues in the 1840s, and more than 30,000 protocols and 290 reference works. Below is a short description of the volume: Recent development in machine learning, particularly deep learning, has brought out drastic impact on Biometrics, which is a classic topic to utilize Machine Learning for biometric identification. Particularly, Deep Learning can benefit from the training with large unlabelled datasets via semi-supervised or unsupervised learning. This book aims to highlight recent research advances in biometrics using semi-supervised and unsupervised new methods such as Deep Neural Networks, Deep Stacked Autoencoder, Convolutional Neural Networks, Generative Adversary Networks, and so on, and exploit these new methods in the emerging new areas such as privacy and security issues, cancellable biometrics and soft biometrics, smart cities, big biometric data, biometric banking, medical biometrics, and healthcare biometrics, etc.. The goal of this volume is to summarize the recent advances in using Deep Learning in the area of biometric security and privacy. Topics of interest include: (but not limited to) ? Deep Learned Biometric Features ? Convolutional Neural networks ? Deep Stacked Autoencoder ? Biometrics in Cybersecurity ? Biometrics in Cognitive Robot ? Healthcare Biometrics ? Medical Biometrics ? Biometrics in Social Computing ? Privacy and Security Issues ? Deep Face Detection ? Deep Face Recognition ? Iris, Fingerprints, DNA, Palmprints ? Gait, EEG, Heart rates ? Multimodal Fusion ? Soft Biometrics ? Cancellable Biometrics with Deep Learning ? Big data issues in Biometrics ? Biometrics for Internet of things Each contributed chapter is expected to present a novel research study, a comparative study, or a survey of the literature. Note that there will be no publication fees for accepted chapters. Important Dates Submission of abstracts Nov 15, 2018 Notification of initial editorial decisions Nov 20, 2018 Submission of full-length chapters Dec 15, 2018 Notification of final editorial decisions Jan 15, 2019 Submission of revised chapters Feb 15, 2019 All submissions should be done via EasyChair: https://easychair.org/conferences/?conf=deepbio2019 Original artwork and a signed copyright release form will be required for all accepted chapters. For author instructions, please visit: http://www.springer.com/authors/book+authors?SGWID=0-154102-12-417900-0 Please feel free to contact us via email (perceptualscience at outlook.com, or any editors below) regarding your chapter ideas. Editorial Board * Dr Richard Jiang Computer and Information Sciences, Northumbria University, United Kingdom Web: http://bit.ly/2n5glEx * Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark * Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia * Professor Christophe Rosenberger Computer Security ENSICAEN ? GREYC, France Contact All questions about submissions can be emailed to Dr Richard Jiang (perceptualscience at outlook.com, or richard.jiang at unn.ac.uk). This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender?s explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- _______________________________________________ visionlist mailing list visionlist at visionscience.com http://visionscience.com/mailman/listinfo/visionlist_visionscience.com From M.Gillies at gold.ac.uk Fri Sep 7 12:39:16 2018 From: M.Gillies at gold.ac.uk (Marco Gillies) Date: Fri, 7 Sep 2018 16:39:16 +0000 Subject: Connectionists: Post-Doctoral Position in modelling and generating real-time social interactions In-Reply-To: References: , Message-ID: Apologies for cross posting Applications are invited for the position of post-doctoral research associate. The post-holder will be expected to carry out interdisciplinary research in computing and social neuroscience, as part of a project which aims to measure, model and generate natural face-to-face behaviours. The focus of this post is on building real-time interactions between people and virtual characters. https://www.jobs.ac.uk/job/BMB900/research-associate-social-neuroscience The post-holder will be based in Marco Gillies laboratory at Goldsmiths College and in Antonia Hamilton's laboratory at the UCL Institute of Cognitive Neuroscience, and will spend time in both locations. The start date for the post will be 1st December 2018 or a close to that date as possible. This post is funded by a Leverhulme grant and is available for 1.2 years in the first instance. The successful applicant should hold a PhD in computer science or a closely related area. Knowledge of a range of research techniques useful to virtual reality and/or interactive agents and extensive research experience in computing and data analysis are essential. Dr Marco Gillies Academic Director - Distance Learning Teaching and Learning Innovation Centre Department of Computing Embodied Audio-Visual Interaction Group 15 Laurie Grove, Room 4 Goldsmiths, University of London, UK T: +44 (0) 207 717 3378 @marcogillies http://www.doc.gold.ac.uk/~mas02mg/MarcoGillies/ https://goldsmithstalic.wordpress.com/ @goldsmithstalic www.gold.ac.uk/computing Subscribe to our blog | Follow us on Twitter -------------- next part -------------- An HTML attachment was scrubbed... URL: From boubchir at ai.univ-paris8.fr Fri Sep 7 06:55:16 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Fri, 7 Sep 2018 12:55:16 +0200 Subject: Connectionists: CFP: The 1st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) Message-ID: <208c282c-929e-70d5-f457-23361e2fd845@ai.univ-paris8.fr> _________________________________ *The 1st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) * Madrid, Spain, December 3-6, 2018 in conjunction with the IEEE International Conference on Bioinformatics and Biomedicine http://orienta.ugr.es/bibm2018/ _________________________________ Overview EEG signal processing involves the analysis and treatment of the electrical activity of the brain measured with Electroencephalography, or EEG, in order to provide useful information on which decisions can be made. The recent advances in signal processing and machine learning for EEG data processing have brought an impressive progress to solve several practical and challenging problems in many areas such as healthcare, biomedicine, biomedical engineering, BCI and biometrics. The aim of this workshop is to present and discuss the recent advances in machine learning for EEG signal analysis and processing. We are inviting original research work, as well as significant work-in-progress, covering novel theories, innovative methods, and meaningful applications that can potentially lead to significant advances in EEG data analytics. This workshop is an opportunity to bring together academic and industrial scientists to discuss the recent advances. The topics of interest include but not limited to: - EEG signal processing and analysis - Time-frequency EEG signal analysis - Signal processing for EEG Data - EEG feature extraction and selection - Machine learning for EEG signal processing - EEG classification and clustering - EEG abnormalities detection (e.g. Epileptic seizure, Alzheimer's disease, etc.) - Machine learning in EEG Big Data - Deep Learning for EEG Big Data - Neural Rehabilitation Engineering - Brain-Computer Interface - Neurofeedback - Biometrics with EEG data - Related applications Program Chair: - Assoc. Prof. Larbi Boubchir (LIASD - University of Paris 8, France) Program Committee: - Prof. Boubaker Daachi (LIASD - University of Paris 8, France) - Prof. Mohamad Sawan (Polytechnique Montr?al, Canada) - Prof. Geraldine Boylan (University College Cork, Ireland) - Prof. Lei Ding (University of Oklahoma, USA) Important Dates: - Sept. 30, 2018 (11:59 pm CST): Due date for full workshop papers submission - Oct. 27, 2018: Notification of paper acceptance to authors - Nov. 15, 2018: Camera-ready of accepted papers - Dec. 3-6, 2018: Workshops Paper Submission: - Please submit a full-length paper (up to 8 page IEEE 2-column format) or short paper (3-6 pages) through the online submission system. You can download the format instruction here: http://www.ieee.org/conferences_events/conferences/publishing/templates.html - Electronic submissions in PDF format are required. - Online Submission: https://wi-lab.com/cyberchair/2018/bibm18/ Publication: All accepted papers will be published in the BIBM proceedings and IEEE Xplore Digital Library. Journal Special Issue: Selected high-quality papers will be invited for publication in a special issue in highly respected journal. Contact: Please email workshop chair: Larbi Boubchir (larbi.boubchir[at]ai.univ-paris8.fr) Please find the call for papers and more information at the workshop webpage: http://www.ai.univ-paris8.fr/~boubchir/Workshop/MLESP2018/home.htm -- _____________________________________________________ Larbi Boubchir, PhD, SMIEEE Associate Professor LIASD - University of Paris 8 2 rue de la Libert?, 93526 Saint-Denis, France Tel. (+33) 1 49 40 67 95 Email. larbi.boubchir at ai.univ-paris8.fr http://www.ai.univ-paris8.fr/~boubchir/ _____________________________________________________ -------------- next part -------------- An HTML attachment was scrubbed... URL: From kerstin.ritter at bccn-berlin.de Fri Sep 7 04:34:29 2018 From: kerstin.ritter at bccn-berlin.de (Kerstin Ritter) Date: Fri, 7 Sep 2018 10:34:29 +0200 (CEST) Subject: Connectionists: PhD scholarship for "Deep learning in clinical neuroimaging", Charite University Medicine Berlin, Germany In-Reply-To: <383427793.344904.1536309152473.JavaMail.root@comms> Message-ID: <1512821640.345116.1536309269723.JavaMail.root@comms> Dear all, we will offer a PhD scholarship at Charite University Medicine Berlin and Bernstein Center for Computational Neuroscience for "Deep learning in clinical neuroimaging", starting in October/November 2018 (initially for 2 years). Please see announcement below: ______________________________________________________________ Deep Learning in clinical neuroimaging PhD scholarship (starting October/November 2018, initially for 2 years; Promotionsstipendium II at Charit?) At the Berlin Center for Advanced Neuroimaging and Bernstein Center for Computational Neuroscience (Charit?), we are looking for a motivated and highly talented PhD student for various research questions within the interdisciplinary field of deep learning and clinical neuroimaging. In particular, we employ convolutional neural networks for finding new representations from neuroimaging data in order to predict disease conversion and future clinical disability in neurological as well as psychiatric diseases. Whereas previous disease decoding approaches mostly relied on expert-based extraction of features in combination with standard classification algorithms and thus strongly depend on the choice of data representation, convolutional networks are capable of learning hierarchical information directly from raw imaging data. By this, they have a great potential for finding unexpected and latent data characteristics and might perform as a real ?second reader?. A major focus will be on visualization techniques to make the learned content of convolutional neural networks visible. Requirements for the PhD student: - Very good degree in computer science, mathematics, physics, psychology, computational neuroscience or related subject. - Very good programming skills (e.g. Python) - Experience in machine learning - Good writing and communication skills (in English) Please send your application (motivation+CV) in one pdf-file (in English or German) to: Dr. Kerstin Ritter Berlin Center for Advanced Neuroimaging, Bernstein-Zentrum f?r Computational Neuroscience Charit? - Universit?tsmedizin Berlin Sauerbruchweg 4, Charit?platz 1, 10117 Berlin Tel.: + 49 30 450 539364; Email: kerstin.ritter at bccn-berlin.de _______________________________________________ From xaq at rice.edu Fri Sep 7 12:47:54 2018 From: xaq at rice.edu (xaq pitkow) Date: Fri, 7 Sep 2018 09:47:54 -0700 Subject: Connectionists: postdoc positions in statistical neuroscience Message-ID: <828573F5-4F6A-46EA-AEA9-F04589350746@rice.edu> POSITION: We seek several highly motivated postdoctoral research fellows for a collaborative team project building statistical tools for interpreting large scale neural recordings. The fellows will develop new methods and applications of probabilistic graphical models to infer statistical interactions amongst neurons and with their environment. The tools will be validated in neural network simulations, tested in physiological recordings, and made widely available to the neuroscience community for understanding data from next-generation experiments. TEAM: Fellows will join principal investigators and theorists Kre?imir Josi?, Genevera Allen, Xaq Pitkow, Ankit Patel, and Robert Rosenbaum. The team will interact closely with experimentalists including co-Investigator Andreas Tolias and several other labs interested in applying novel methods we develop. Fellows will also be members of the new Center for Neuroscience and Artificial Intelligence housed at the Baylor College of Medicine and supported in part by the NSF NeuroNex program. The Center brings together interdisciplinary researchers from across Houston, including members from Baylor College of Medicine, Rice University, University of Houston, and University of Texas Health Sciences. Researchers at the Center contribute diverse expertise in fields including neuroscience, machine learning, statistics, physics, computer science, electrical engineering, and applied mathematics. QUALIFICATIONS: Candidates must have outstanding mathematical skills, a PhD in a relevant quantitative discipline, and expertise in probabilistic graphical models or statistical machine learning. APPLYING: Applicants should email a letter of research interests and CV to Camila Lopez (Camila.Lopez at bcm.edu), along with contact information for three references. We look forward to hearing from you! From t.j.prescott at sheffield.ac.uk Fri Sep 7 07:05:42 2018 From: t.j.prescott at sheffield.ac.uk (Tony Prescott) Date: Fri, 7 Sep 2018 13:05:42 +0200 Subject: Connectionists: Job Opportunity: Two robotics/compneuro/ML posts at the University of Sheffield Message-ID: Dear Connectionists, We are seeking motivated biomimetic roboticists, computational neuroscientists and/or machine learning researchers to help develop and extend a systems level computational model of the mammalian brain architecture and to evaluate this model within the control system of animal-like robots. Up to* two posts* are available. This is an exciting opportunity to join a dynamic disciplinary team, led by Professor Tony Prescott , that has been working on embodied (robotic) models of the vertebrate brain for over two decades. The current project is supported as part of the Europe-wide FET Flagship Human Brain Project with Sub-project 3 on Systems and Computational Neuroscience . Successful candidates would join Sheffield Robotics , one of the UK's leading interdisciplinary institutes for robotics research. The positions allow a high degree of autonomy and include considerable scope for creativity and international collaboration with world-class scientists and engineers. The work extends from developing novel models of memory systems on the mammalian brain, to embedding and testing these models within specialised neuromorphic hardware onboard biomimetic robots including the animal-like companion robot MiRo and a novel whiskered robot developed in partnership with Bristol Robotics Lab. Successful candidates should have a PhD in computational neuroscience, brain-based/bio-inspired robotics, machine learning or in related discipline, with experience in systems neuroscience and neural network modelling. Fore further details see g.co/kgs/G2y55x or email t.j.prescott at sheffield.ac.uk with enquiries. Closing date mid-september 2018. -------------- next part -------------- An HTML attachment was scrubbed... URL: From msn2018 at mail.neu.edu.cn Fri Sep 7 22:38:48 2018 From: msn2018 at mail.neu.edu.cn (MSN2018) Date: Sat, 8 Sep 2018 10:38:48 +0800 (GMT+08:00) Subject: Connectionists: [msn2018] CFP: Mobile Ad-hoc and Sensor Networks 2018 Message-ID: <31f9c629.a276.165b70bce59.Coremail.msn2018@mail.neu.edu.cn> Apologies for any cross posting 14th Int. Conference on Mobile Ad-hoc and Sensor Networks Shenyang, China Dec. 6- 8, 2018 http://conf.neu.edu.cn/msn2018 You are cordially invited to submit your contribution until September 15, 2018. Final manuscripts should be prepared according to IEEE Computer Society Proceedings Format (double column, 10pt font) and submitted via the EasyChair system in PDF file format. The manuscript should be no longer than 6 pages. Up to two additional pages are permitted if the authors are willing to pay an over-length charge at the time of publication (manuscripts should not exceed 8 pages in total). Final manuscripts should not be previously published in or be under consideration for publication in another conference or journal. To submit your contribution visits the submission page (https://easychair.org/conferences/?conf=msn2018). ? Papers will be included in the conference proceedings edited by IEEE ? Extended versions will be invited for publication in special issues of international journals: o IEEE Transactions on Industrial Informatics edited by IEEE o IET Networks edited by IET o IEEE Wireless Communications edited by IEEE o Sensors edited by MDPI Topics include, but are not limited to: o Ad Hoc Networks o Vehicular Networks o Intelligent Sensor Networks o Urban Computing o Internet of Things o Edge and Fog Computing/Networking o 5G networks o Cognitive Radio Networks o Mobile Social Networks o Mobile Crowdsensing and Computing o Smart Networks o Knowledge Centric Networks o Delay Tolerant and Opportunistic Networking o Network Security and Privacy o Artificial Intelligence for Networking and Communications o Novel Applications and Architecture Steering Committee Co-Chairs Xiaohua Jia, City University of Hong Kong Jiannong Cao, Hong Kong Polytechnic University General Co-Chairs Xingwei Wang, Northeastern University, China Vincenzo Piuri, University of Milan, Italy TPC Co-Chairs Ruiyun Yu, Northeastern University, China Hongyi Wu, Old Dominion University, USA Dieter Hogrefe, University of Goettingen, Germany Publication Chair Guangtao Xue, Shanghai Jiao Tong University, China Xu Yuan, University of Louisiana at Lafayette, USA Yuanguo Bi, Northeastern University, China Yuan Liu, Northeastern University, China Publicity Chair Guangjie Han, Dalian University of Technology, China Cong Wang, Old Dominion University, USA Jie Jia, Northeastern University, China Jie Li, Northeastern University, China Financial Chair Lianbo Ma, Northeastern University, China Local arrangement Chair Zhenhua Tan, Northeastern University, China Web Chair Yu Wang, Northeastern University, China -------------- next part -------------- An HTML attachment was scrubbed... URL: From luca.oneto at unige.it Mon Sep 10 09:16:48 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Mon, 10 Sep 2018 15:16:48 +0200 Subject: Connectionists: [INNSBDDL2019] - Submission system is now open & Updates Message-ID: Apologies for the cross postings. INNS BIG DATA AND DEEP LEARNING 2019 SESTRI LEVANTE, GENOA, ITALY, 16-18 APRIL 2019 HTTPS://INNSBDDL2019.ORG/ WEBSITE https://innsbddl2019.org/ SUBMISSION SYSTEM (CMT) IS NOW OPEN https://innsbddl2019.org/submissions/ VENUE & ORGANIZATION The 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) conference will be held in Sestri Levante, Italy, April 16?18, 2019. The conference is organized by the International Neural Network Society, with the aim of representing an international meeting for researchers and other professionals in Big Data, Deep Learning and related areas. It will feature invited plenary talks by world-renowned speakers in the area, in addition to regular and special technical sessions with oral and poster presentations. Moreover, workshops and tutorials will also be featured. IMPORTANT DATES Deadline of full paper submission: October 31, 2018 Notification of paper acceptance: December 31, 2018 Camera-ready submission: January 31, 2019 Early registration deadline: January 15, 2019 Registration deadline: January 31, 2019 Conference date: April 16-18, 2019 INVITED SPEAKERS - Paolo Ferragina, University of Pisa, Italy - Guang-Bin Huang, Nanyang Technological University, Singapore TUTORIALS - Davide Bacciu (University of Pisa), Deep Learning for Graphs - Silvia Chiappa (DeepMind), Luca Oneto (University of Genoa), Fairness in Machine Learning - Claudio Gallicchio (University of Pisa), Simone Scardapane (Sapienza University of Rome), Deep Randomized Neural Networks - V?ra K?rkov? (Czech Academy of Sciences), Complexity of Shallow and Deep Networks - Danilo P. Mandic, Ilia Kisil, and Giuseppe G. Calvi (Imperial College London), Tensor Decompositions and Applications. Blessing of Dimensionality - German I. Parisi and Stefan Wermter (University of Hamburg), Continual Lifelong Learning with Neural Networks SCOPE We solicit both solid contributions or preliminary results which show the potentiality and the limitations of new ideas, refinements, or contaminations in any aspect of Big Data and Deep Learning. Both theoretical and practical results are welcome. Example topics of interest includes but is not limited to the following: Big Data Science and Foundations - Novel Theoretical Models for Big Data - New Computational Models for Big Data - Data and Information Quality for Big Data Big Data Mining - Social Web Mining - Data Acquisition, Integration, Cleaning, and Best Practices - Visualization Analytics for Big Data - Computational Modeling and Data Integration - Large-scale Recommendation Systems and Social Media Systems - Cloud/Grid/StreamData Mining - Big Velocity Data - Link and Graph Mining - Semantic-based Data Mining and Data Pre-processing - Mobility and Big Data - Multimedia and Multi-structured Data-Big Variety Data Modern Practical Deep Networks - Deep Feedforward Networks - Regularization for Deep Learning - Optimization for Training Deep Models - Convolutional Networks - Sequence Modeling: Recurrent and Recursive Nets - Practical Methodology Deep Learning Research - Linear Factor Models - Autoencoders - Representation Learning - Structured Probabilistic Models for Deep Learning - Monte Carlo Methods - Confronting the Partition Function - Approximate Inference - Deep Generative Models PROCEEDINGS & SPECIAL ISSUE Works submitted as a regular paper will be published in a serie indexed by Scopus. Submitted papers will be reviewed by some PC members based on technical quality, relevance, originality, significance and clarity. At least one author of an accepted submission should register to present their work at the conference. Selected papers presented at INNS BDDL 2019 will be included in special issues of top journals in the field (prospected journals: Big Data Research, Transaction on Neural Networks and Learning System, Neurocomputing, etc). --------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: luca.oneto at unige.it SmartLab Laboratory e-mail: luca.oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145, Genoa, Italy Phone: +39-010-3532192 www.smartlab.ws --------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From zatyen at yahoo.com Mon Sep 10 17:34:48 2018 From: zatyen at yahoo.com (Satyen Kale) Date: Mon, 10 Sep 2018 21:34:48 +0000 (UTC) Subject: Connectionists: Algorithmic Learning Theory (ALT) 2019 call for papers References: <986731012.2592793.1536615288192.ref@mail.yahoo.com> Message-ID: <986731012.2592793.1536615288192@mail.yahoo.com> Dear all, Please find below the call for papers for ALT 2019. The submission deadline is?Friday, September 28, 2018, 4:59PM EST. The submission server is now open for submissions at?https://easychair.org/conferences/?conf=alt2019. Thanks, Satyen Kale and Aur?lien GarivierALT 2019 program chairs The ALT 2019 conference is dedicated to all theoretical and algorithmic aspects of machine learning. We invite submissions with contributions to new or existing learning problems including, but not limited to:* Design and analysis of learning algorithms. * Statistical and computational learning theory.* Online learning algorithms and theory.* Optimization methods for learning.* Unsupervised, semi-supervised, online and active learning.* Connections of learning with other mathematical fields.* Artificial neural networks, including deep learning.* High-dimensional and non-parametric statistics.* Learning with algebraic or combinatorial structure.* Bayesian methods in learning.* Planning and control, including reinforcement learning.* Learning with system constraints: e.g. privacy, memory or communication budget.* Learning from complex data: e.g., networks, time series, etc.* Interactions with statistical physics.* Learning in other settings: e.g. social, economic, and game-theoretic. We are also interested in papers that include viewpoints that are new to the ALT community. We welcome experimental and algorithmic papers provided they are relevant to the focus of the conference by elucidating theoretical results, or by pointing out an interesting and not well understood behavior that could stimulate theoretical analysis.Paper submission deadline: Friday, September 28, 2018, 4:59PM EST.? Authors can submit their papers electronically via the submission page which will be opened a few weeks before the conference submission deadline. AWARDSALT 2018 will have both a best student paper award (E.M. Gold Award) and a best paper award. Authors must indicate at submission time if they wish their paper to be eligible for a student award. This does not preclude the paper to be eligible for the best paper award. The paper can be co-authored by other researchers. TUTORIALSWe also invite proposals for a tutorial presentation. These should be dealing with a learning theory topic covered within two hours. Proposals are limited to 2 pages and should include a one page abstract as well as links to any relevant material such as existing slides or other teaching material.Tutorials Submission Deadline : October 19, 2018. VENUEThe conference will be held in Chicago, IL, USA from March 22-24, 2019. CONTACTAll questions about submissions should be emailed to the PC chairs at alt2019pc at gmail dot com. -------------- next part -------------- An HTML attachment was scrubbed... URL: From tomas.hromadka at gmail.com Mon Sep 10 19:43:50 2018 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Tue, 11 Sep 2018 01:43:50 +0200 Subject: Connectionists: COSYNE 2019: Call for workshop proposals Message-ID: <01a39e12-0b27-7b0a-15fe-c72b11ad839c@gmail.com> ================================================= Computational and Systems Neuroscience 2019 (Cosyne) MAIN MEETING 28 February - 03 March 2019 Lisbon, Portugal WORKSHOPS 04 - 05 March 2019 Cascais, Portugal www.cosyne.org ================================================= ----------------------------------------------------------------------- CALL FOR WORKSHOP PROPOSALS ----------------------------------------------------------------------- PRE-PROPOSAL DEADLINE: 30 September 2018 FULL PROPOSAL DEADLINE: 31 October 2018 PRE-PROPOSALS In an effort to coordinate submissions, the organizers are *strongly encouraged* to submit a pre-proposal by *30 September 2018.* Pre-proposals will be shared among submitters. Pre-proposals are not mandatory, but workshops with a pre-proposal will have priority. The organizers may submit the full proposal by its deadline. A series of workshops will be held after the main Cosyne meeting (www.cosyne.org). The goal is to provide an informal forum for the discussion of important research questions and challenges. Controversial issues, open problems, comparisons of competing approaches, and alternative viewpoints are encouraged. The overarching goal of all workshops should be the integration of empirical and theoretical approaches, in an environment that fosters collegial discussion and debate. Preference will be given to proposals that differ substantially in content, scope, and/or approach from workshops of recent years (examples available at Cosyne.org -> Workshops). Relevant topics include, but are not limited to: sensory processing; motor planning and control; functional neural circuits; motivation, reward and decision making; learning and memory; adaptation and plasticity; neural coding; neural circuitry and network models; and methods in computational or systems neuroscience. In order to foster discussion within Workshops and reduce overlap between workshops, organizers should inform invited speakers that a single person should not speak in more than one of the Workshops taking place on the same day. WORKSHOP DETAILS - There will be 4-8 workshops/day, running in parallel. - Each workshop is expected to draw between 15 and 80 people. - The workshops will be split into morning (8.00-11.00 AM) and afternoon (4.30-7.30 PM) sessions. - Workshops will be held at Cascais, a coastal village ~34 km west of Lisbon. Buses from the main conference will be provided. . SUBMISSION INSTRUCTIONS Submission instructions for workshop (pre)-proposals are available at Cosyne.org -> Workshops. PRE-PROPOSALS should include: - Name(s) and email address(es) of the organizers (no more than 2 organizers per session, please). A primary contact should be designated. - A title. - A brief description of 1) what the workshop will address and accomplish, 2) why the topic is of interest, 3) who is the targeted group of participants. - Names of potential invitees, with indication of confirmed speakers. Preference will be given to workshops with the most confirmed speakers. - Proposed workshop length (1 or 2 days). Most workshops will be limited to a single day. If you think your workshop needs two days, please explain why. - A brief resume of the workshop organizer along with a short list of workshop-relevant publications (about half a page total). FULL PROPOSALS should include the list of confirmed speakers in addition to components required for a pre-proposal. Workshop organizer responsibilities include coordinating workshop participation and content, scheduling all speakers and submitting a final schedule for the workshop program, and moderating the discussion. Organizers can be speakers but need not speak depending on scheduling constraints. SUGGESTIONS Experience has shown that the best discussions during a workshop are those that arise spontaneously. A good way to foster these is to have short talks and long question periods (e.g. 30+15 minutes), and have plenty of breaks. We recommend fewer than 10 talks. When preparing pre-proposals and full proposals, the organizers are encouraged to: - address timeliness of workshop in the proposal: what new insights have been generated (new papers, data, techniques, whatever) over the past few years that make now the right time for discussing them and for presenting them to the wider community? - directly describe how speakers address the central topic, e.g. which are the big question(s), which speakers represent different viewpoints on the same question, which experimentalist addresses the theories addressed by which theoretician (and vice versa); - address controversies and bring together speakers from different ?camps? in the same field, or from different fields that you think should talk more to each other for whatever reason; WORKSHOP COSTS Detailed registration costs, etc, will be available at www.cosyne.org. Please note: Cosyne does NOT provide travel funding for workshop speakers. All workshop speakers are expected to pay for workshop registration fees. Participants are encouraged to register early, in order to qualify for discounted registration rates. One complementary (free) organizer registration is provided per workshop. For workshops with 2 organizers, the free registration can be given to one of the organizers or split evenly between them. COSYNE 2019 WORKSHOP CHAIRS Catherine Hartley (NYU) and Ralf Haefner (University of Rochester) QUESTIONS email: workshops [at] cosyne.org 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 alessandro.lulli at dibris.unige.it Tue Sep 11 04:03:58 2018 From: alessandro.lulli at dibris.unige.it (Alessandro Lulli) Date: Tue, 11 Sep 2018 10:03:58 +0200 Subject: Connectionists: ReForeSt an Apache Spark Library (Random Forests, Random Rotation Ensembles, and Model Selection) Message-ID: Apologies for the cross postings. We are pleased to announce the first stable version of our ReForeSt library. https://github.com/alessandrolulli/reforest which is made available under the Apache License 2.0 on GitHub Key features - Implemented in Scala to be fully distributed on Apache Spark - Implements Random Forests [1] - Implements Random Rotation Ensembles [2] - Implements an efficient Model Selection strategy [3] - similar API to MLlib Random Forest but up to 6x faster and up to 10x less memory requirements [3] ReForeSt is a distributed, Apache Spark based scalable implementation of the Random Forest learning algorithm targeting a fast and memory efficient processing written in Scala. The distinguishing features of ReForeSt are the ability to support arbitrary large datasets ranging from millions of samples to millions of features, categorical features and missing values, different data distributions models, Random Rotations, and automatic hyperparameters selection. ReForeSt is a simple alternative to MLlib since it shares very similar API. It covers the lack of MLlib in providing results for dataset having million of features. ReForeSt is always faster and requires less memory with respect to MLlib. MS is a useful tool to retrieve the best performing hyperparameters and may help users when there is low knowledge about the problem or to test multiple hyperparameters in less time. [1] Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. [2] Blaser, R., & Fryzlewicz, P. (2016). Random rotation ensembles. The Journal of Machine Learning Research, 17(1), 126-151. [3] Lulli, A., Oneto, L., & Anguita, D. (2017, December). Crack random forest for arbitrary large datasets. In Big Data (Big Data), 2017 IEEE International Conference on (pp. 706-715). IEEE. -------------- next part -------------- An HTML attachment was scrubbed... URL: From salah at boun.edu.tr Tue Sep 11 19:59:50 2018 From: salah at boun.edu.tr (Albert Ali Salah) Date: Wed, 12 Sep 2018 02:59:50 +0300 Subject: Connectionists: Call for Special Sessions, Workshops, and Tutorials - IEEE FG 2019, Lille, 14-18 May 2019 Message-ID: Call for Special Sessions, Workshops, and Tutorials - IEEE FG 2019, Lille, 14-18 May 2019. ------------------------ We invite special sessions, workshop, and tutorial proposals for the 2019 IEEE Conference on Automatic Face and Gesture Recognition in Lille, France. Accepted workshops and tutorials will be held on either May 14 or May 18, 2019, in the same venue as the FG 2019 main conference, namely, Lille Grand Palais. Special sessions will be held with the main conference, 15-17 May. We solicit workshop and tutorial proposals on any topic of interests to the FG community. We especially encourage workshops relating to emerging new fields or new application domains of face and gesture analysis and synthesis. The tutorials should complement and enhance the scientific program of FG 2019 by providing authoritative and comprehensive overviews of growing themes that are of sufficient relevance with respect to the state-of-the-art and the conference topics. Workshop and tutorial organizers who have a strong track record in the field are strongly encouraged to submit a proposal. The tutorials are half-day events (3 to 4 hours including breaks). For Special Sessions, we particularly encourage proposals that highlight emerging new fields, application domains and challenges related to face and gesture as well as interdisciplinary topics that bring new perspectives to the FG community. These Special Sessions will emphasize ?Frontiers in FG? in the face and gesture recognition research field. It is possible to propose panels in this category. Proposers should have a strong record in the proposed field. If the Special Session is accepted, proposers will act as area chairs and supervise the reviewing process of the papers marked for the Special Session. The workshop paper submission, review, acceptance notification, and final manuscript due must all be handled until February 15, 2019 (camera-ready workshop paper due date). Financial support from the main conference is not guaranteed and depends on the budget. IMPORTANT DATES Special Session proposals due: September 21, 2018 Special Session proposal notification: October 10, 2018 Special Session papers due: 9 December, 2018 Workshop proposals due: September 21, 2018 Workshop acceptance decisions: October 10, 2018 Workshop camera-ready papers due: February 15, 2019 Tutorial proposals due: January 14, 2019 Tutorial decisions: February 4, 2019 The main conference will provide rooms, equipment, and coffee breaks for the workshops and tutorials. If necessary, poster facilities will be offered. For each workshop one complimentary registration for a keynote speaker is available. For any additional questions please contact the workshop, tutorial, and special session chairs. All workshop, tutorial, and special session proposals should be sent via email to FG 2019 Workshop, Tutorial, and Special Session Co-chairs, Stefano Berretti (stefano.berretti at unifi.it) and Albert Ali Salah (salah at boun.edu.tr), with the subject field ?FG 2019 [type] Proposal: [title of session]? where [type] should be replaced with one of the following: "Workshop", "Tutorial", "Special Session", or "Panel". WORKSHOP PROPOSAL SUBMISSION A proposal should include the following information to facilitate the decision process: Workshop title -Workshop motivation, expected outcomes and impact -List of organizers including affiliation, email address, and short bio -Tentative length of the workshop (half day or full day) -Tentative paper submission and review schedule -Planned advertisement means, website hosting -Paper submission procedure (submission via web site, via email, etc.) if applicable -Paper review procedure (single/double-blind, internal/external, solicited/invited-only, pool of reviewers, etc.) -Specify the relationship, if any, to previous workshops -Describe difference with most relevant previous workshops -Tentative program committee, and invited speakers, if any -Estimated number of submissions and acceptance rate -Special space or equipment requests, if any -Specify if there will be non-peer reviewed invited paper, if so, how many? TUTORIAL PROPOSAL SUBMISSION A proposal should include the following information to facilitate the decision process: -Tutorial title -Proposer?s contact information and short CV -Names of any additional lecturers and short CV -Tutorial description and description of relevance to the FG community and an evaluation plan -References and experience of the instructors with respect to the proposed tutorial topic -Planned length of the tutorial -List of relevant tutorials recently presented in other conferences -Requirements (e.g., facilities, Internet access, etc.) -Other useful information (e.g., estimated attendance, slides/notes available, etc.). Tutorial proposals will be evaluated on the basis of their estimated benefit for the community and their fit within the tutorials program as a whole. Factors to be considered include: relevance, timeliness, importance, and audience appeal; suitability for presentation in a half or full day format; past experience and qualifications of the instructors. Selection will also be based on the overall distribution of topics, expected attendance, and specialties of the intended audiences. SPECIAL SESSION PROPOSAL SUBMISSION A proposal must include the following information: -The title of the proposed Special Session or Panel. -A brief description of the topic, including how it stands apart from the regular FG topics/sessions. -Contact information and short bio of the organizers. -For a Special Session: a list of proposed contributions to the special session (including authors, title, and short abstract). -For a Panel: a list of proposed panelists and their expected perspectives/contributions. Paper preparation and review details. Special Session papers will be part of the conference proceedings and will be reviewed along with the regular conference submissions. Papers submitted to a Special Session should describe original work and should follow the general FG submission guidelines. For your reference, below is a list of workshops, tutorials, and special sessions held in conjunction with FG 2018: Workshops: -8th Int. Workshop on Human Behavior Understanding in conjunction with 2nd Int. Workshop on Automatic Face Analytics for Human Behavior Understanding (HBU 2018) -Latest developments of FG technologies in China -First Workshop on Large-scale Emotion Recognition and Analysis (LERA 2018) -IEEE FG 2018 Workshop on Dense 3D Reconstruction of 2D Face Images in the Wild -Face and Gesture Analysis for Health Informatics (FGAHI 2018) -Facial Micro-Expression Grand Challenge (MEGC): Methods and Datasets -The 1st International Workshop on Real-World Face and Object Recognition from Low-Quality Images (FOR-LQ) Tutorials: -Person Re-Identification: Recent Advances and Challenges -Representation Learning for Face Alignment and Recognition -Reading Hidden Emotions from Micro-Expression Analysis -Active Authentication in Mobile Devices: Role of Face and Gesture -Introduction to Deep Learning for Facial Understanding -Sign Language Recognition and Gesture Analysis -Physiological Measurement from Images And Videos -Statistical Methods for Affective Computing -Ms-Celeb-1M: Large Scale Face Recognition Challenge Tutorial Special Sessions: -Perception, Cognition and Psychophysiology of Gesture Interaction -Is Deep Learning Always the Best Solution for Face Recognition? -Face and Gesture Recognition on Mobile Devices -Kinect-based Kinematic Data Analysis and Evaluation for Clinical Applications -Measurable Social Impact Systems and Applications -Generalized Face Spoofing Detection in Real-World Applications -Automatic Kinship Verification from Face -- Dr. Albert Ali Salah http://www.cmpe.boun.edu.tr/~salah/ Bogazici University, Computer Engineering Dept. & Cognitive Science MA Program http://www.cogsci.boun.edu.tr -------------- next part -------------- An HTML attachment was scrubbed... URL: From bdoiron at pitt.edu Wed Sep 12 21:59:36 2018 From: bdoiron at pitt.edu (Brent Doiron) Date: Wed, 12 Sep 2018 21:59:36 -0400 Subject: Connectionists: Faculty positions in computational neuroscience and mathematical biology Message-ID: Dear Connectionists community The Dietrich School at the University of Pittsburgh invites applications for two tenure-track faculty positions at the Assistant Professor level in *Mathematical and Computational Life Sciences *to begin in the fall term of 2019. Successful candidates will be placed in the departments most suitable for their backgrounds and research programs from among the Departments of Mathematics, Biology, Neuroscience, Physics, and Chemistry. We seek outstanding scientists who will enhance and complement our existing strengths and who will collaborate with members of our sizable neuroscience, biology, biophysics, and biochemistry communities. One position is in *Mathematical and Computational Neuroscience. *Candidates working on the following topics are especially encouraged to apply: - Circuits and information flow in neuroscience - Neuronal and population dynamics - Synaptic mechanisms and dynamics - Neuronal membrane properties and ion channel function The other position is in *Mathematics and Theory of Biological Processes*. Candidates working on the following topics are especially encouraged to apply: - Mathematical ecology - Evolutionary theory - Cellular sensing and signal processing - Epigenetic and gene network dynamics The University of Pittsburgh is an active center for interdisciplinary research in the life sciences offering exciting opportunities for collaborations across departments as well as with our highly ranked medical school. The University is currently ranked third in the nation in total NIH funding, and the city of Pittsburgh is often voted ?most livable? in the nation. These positions represent part of a vision to grow our community of researchers at the interface of mathematics, physics, chemistry and the life sciences. Successful candidates will have a Ph.D. and should demonstrate substantial research accomplishment and dedication to teaching. They will be expected to establish an extramurally funded research program, train graduate students, and actively participate in undergraduate education. *Review of applications will begin on October 23, 2018, *and will continue until the positions are filled*. *Applicants can apply online at: https://facultysearch.as.pitt.edu/apply/index/MjQy. Candidates should submit (a) a cover letter, (b) a CV, (c) a statement of research accomplishments and future plans, (d) a brief description of teaching interests, (e) a brief description of how your research, teaching or service demonstrates a commitment to diversity and inclusion, and (f) at least three letters of reference (for each reference, you will have the opportunity to input an email address through Interfolio?s Online Application system and a notification will be sent to the designated address with instructions). The positions are pending budgetary approval. The University of Pittsburgh is an Affirmative Action/Equal Opportunity Employer and values equality of opportunity, human dignity and diversity. EEO/AA/M/F/Vets/Disabled. Person to Contact: Erika Carpio 139 University Place Room 302 Pittsburgh, PA 15206 412-624-8361 -- Professor of Mathematics Center for the Neural Basis of Cognition University of Pittsburgh 301 Thackeray Hall Pittsburgh, PA, 15260 www.math.pitt.edu/~bdoiron -------------- next part -------------- An HTML attachment was scrubbed... URL: From r.jolivet at ucl.ac.uk Thu Sep 13 08:17:31 2018 From: r.jolivet at ucl.ac.uk (Jolivet, Renaud) Date: Thu, 13 Sep 2018 12:17:31 +0000 Subject: Connectionists: PhD school in Life Sciences of the Faculties of Medicine and Science, University of Geneva Message-ID: <35AD6644-B0A0-4F2D-B7F6-611FB54FF838@ucl.ac.uk> Dear Colleagues, The University of Geneva Faculties of Medicine and Science join their forces to offer an outstanding study and research environment in Life Sciences. Highly motivated students with a Master?s degree or equivalent are welcome to apply to one or two of its six innovative doctoral programmes. Apply at https://lifesciencesphd.unige.ch/ before Oct 1st 2018! Best wishes, Renaud ? Prof. Renaud Jolivet University of Geneva, Physics Section CERN, Experimental Physics Department MCAA, Board Member +41 79 830 2129 (mobile) +41 22 379 6275 (UNIGE) +41 75 411 8134? (CERN) renaud.jolivet at unige.ch linkedin.com/in/renaud-jolivet-63b5534 http://unige.ch/dpnc/en/groups/renaud-jolivet/home/ https://scholar.google.ch/citations?user=9Ozwv7EAAAAJ&hl=en -------------- next part -------------- An HTML attachment was scrubbed... URL: From r.jolivet at ucl.ac.uk Thu Sep 13 08:10:01 2018 From: r.jolivet at ucl.ac.uk (Jolivet, Renaud) Date: Thu, 13 Sep 2018 12:10:01 +0000 Subject: Connectionists: Geneva Life Sciences PhD School first intake Message-ID: A non-text attachment was scrubbed... Name: Flyer A3-PhDLifeSciences-2018.pdf Type: application/pdf Size: 435538 bytes Desc: Flyer A3-PhDLifeSciences-2018.pdf URL: From boubchir at ai.univ-paris8.fr Thu Sep 13 11:51:15 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Thu, 13 Sep 2018 17:51:15 +0200 Subject: Connectionists: CFP: The 1st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) In-Reply-To: <88329ae3-6226-b1e4-6c2d-24c8a3f30f96@ai.univ-paris8.fr> References: <2689b21c-c7b5-ed06-ca47-4ea4e30c47a7@ai.univ-paris8.fr> <88329ae3-6226-b1e4-6c2d-24c8a3f30f96@ai.univ-paris8.fr> Message-ID: <12907daa-7dc8-c8ec-50b7-776b8a066a5d@ai.univ-paris8.fr> Dear colleagues, Please feel free to share this CFP with anyone that may find it of interest. Apologies if you receive multiple copies of this CfP. Best regards, Larbi Boubchir -- _____________________________________________________ Larbi Boubchir, PhD, SMIEEE Associate Professor LIASD - University of Paris 8 2 rue de la Libert?, 93526 Saint-Denis, France Tel. (+33) 1 49 40 67 95 Email. larbi.boubchir at ai.univ-paris8.fr http://www.ai.univ-paris8.fr/~boubchir/ _____________________________________________________ -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: CfP-MLESP2018.pdf Type: application/pdf Size: 823016 bytes Desc: not available URL: From m.biehl at rug.nl Thu Sep 13 13:10:22 2018 From: m.biehl at rug.nl (Michael Biehl) Date: Thu, 13 Sep 2018 19:10:22 +0200 Subject: Connectionists: 2nd CFP (reminder) Message-ID: Apologies in advance for multiple postings. *Second call for papers (reminder): *Special Session *"Statistical Physics of Learning and Inference" at ESANN 2019*Deadline for submission of papers: November 19, 2018. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN2019). 24-26 April 2019, Bruges, Belgium http://www.esann.org Description: This special session is meant to attract researchers who exploit analogies and concepts from statistical physics in the context of machine learning, inference, optimization, and related fields. The exchange of ideas between statistical physics and computer science has been very fruitful and is currently gaining momentum again as a consequence of the revived interest in neural networks, machine learning and inference in general. Statistical physics methods complement other approaches to the theoretical understanding of machine learning processes and inference in stochasic modeling. They facilitate, for instance, the study of dynamical and equilibrium properties of randomized training processes in model situations. At the same time, the approach inspires novel and efficient algorithms and facilitates interdisciplinary applications in a variety of scientific and technical disciplines. The tools and concepts applied in this context include information theory, the mathematical analysis of stochastic differential equations, methods borrowed from the statistical mechanics of disorder, mean field theory, variational calculus, renormalization group and other methods. Potential topics include, but are not limited to: - Probabilistic inference in, e.g., stochastic dynamical systems and complex networks - Learning in Deep Networks and other architectures - Complex optimization problems - Emergent behavior in societies of agents - Transient dynamics and equilibrium phenomena in machine learning - The relation of statistical mechanics with information theory and mathematical statistics - Applications, for instance in: - systems biology and bioinformatics - neuroscience - environmental modelling - social systems - signal processing - complex optimization SUBMISSION: Authors must submit their paper through the ESANN portal following the instructions provided at https://www.elen.ucl.ac.be/esann/index.php?pg=submission We encourage authors to contact the organizers of the session beforehand. Each paper will undergo a peer reviewing process for its acceptance. IMPORTANT DATES: Submission of papers: 19 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Michael Biehl, University of Groningen, The Netherlands Nestor Caticha, University of Sao Paulo, Brazil Manfred Opper, Technical University Berlin, Germany Thomas Villmann, University of Applied Sciences Mittweida, Germany ---------------------------------------------------------- Prof. Dr. Michael Biehl Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence P.O. Box 407, 9700 AK Groningen The Netherlands Tel. +31 50 363 3997 www.cs.rug.nl/~biehl m.biehl at rug.nl -------------- next part -------------- An HTML attachment was scrubbed... URL: From cezarykaliszyk at gmail.com Fri Sep 14 01:03:43 2018 From: cezarykaliszyk at gmail.com (Cezary Kaliszyk) Date: Fri, 14 Sep 2018 07:03:43 +0200 Subject: Connectionists: PhD and Postdoc Positions at the University of Innsbruck Message-ID: We invite candidates for PhD student and Postdoc positions to start in 2018 or early 2019 in Innsbruck. The 5-year ERC project "SMART" aims to combine modern machine learning techniques with formal reasoning to provide proof advice and assistance. The starting date can be negotiated. PhD student positions like Postdoc positions are formal employment in Austria, with a regular salary and benefits. A background in machine learning, or formal proof is an advantage. Knowledge of German is not required, the group is international and the language of communication is English. Candidates for a PhD position must hold a MSc in computer science or mathematics and candidates for the postdoctoral position hold a PhD degree in computer science or mathematics. Applications and informal inquiries are welcome, please contact Cezary Kaliszyk (cezary.kaliszyk at uibk.ac.at). Applications should include a CV and names and contact details of two references. For the Postdoc positions please include a brief research statement. The city of Innsbruck, which hosted the Olympic Winter Games in 1964, 1976 and 2012 (YOG), is superbly located in the beautiful surroundings of the Tyrolean Alps. The combination of the Alpine environment and urban life in this historic town provides a high quality of living. More information about the project, the group, and the university see: http://cl-informatik.uibk.ac.at/cek/smart/ -- Cezary Kaliszyk, University of Innsbruck, http://cl-informatik.uibk.ac.at/cek/ From tarek.besold at googlemail.com Thu Sep 13 13:31:09 2018 From: tarek.besold at googlemail.com (Tarek R. Besold) Date: Thu, 13 Sep 2018 19:31:09 +0200 Subject: Connectionists: ML/AI Research Engineers @ Alpha Health in Barcelona (Spain) Message-ID: Dear all, for our fledgling Alpha Health AI Lab (http://alpha.company) we are still searching for one or two AI/ML Research Engineers. We are a translational research team, developing solutions and system prototypes addressing foundational questions relating to Trustworthy/Explainable AI, Empathic AI, and Distributed & Anonymous ML out of beautiful Barcelona (Spain). If you are interested, please have a look at https://jobs.lever.co/alpha/4c8e4883-53f8-4da7-a82c-cd4868644065 Cheers, Tarek. -------------- next part -------------- An HTML attachment was scrubbed... URL: From bernstein.communication at fz-juelich.de Fri Sep 14 04:06:57 2018 From: bernstein.communication at fz-juelich.de (Nikola Schwarzer) Date: Fri, 14 Sep 2018 10:06:57 +0200 Subject: Connectionists: PhD scholarship for "Deep learning in clinical neuroimaging", Charite University Medicine Berlin, Germany In-Reply-To: <1512821640.345116.1536309269723.JavaMail.root@comms> References: <1512821640.345116.1536309269723.JavaMail.root@comms> Message-ID: > On 7. Sep 2018, at 10:34, Kerstin Ritter wrote: > > Dear all, > > we will offer a PhD scholarship at Charite University Medicine Berlin and Bernstein Center for Computational Neuroscience for "Deep learning in clinical neuroimaging", starting in October/November 2018 (initially for 2 years). Please see announcement below: > > ______________________________________________________________ > Deep Learning in clinical neuroimaging > > PhD scholarship (starting October/November 2018, initially for 2 years; Promotionsstipendium II at Charit?) > > At the Berlin Center for Advanced Neuroimaging and Bernstein Center for Computational Neuroscience (Charit?), we are looking for a motivated and highly talented PhD student for various research questions within the interdisciplinary field of deep learning and clinical neuroimaging. In particular, we employ convolutional neural networks for finding new representations from neuroimaging data in order to predict disease conversion and future clinical disability in neurological as well as psychiatric diseases. Whereas previous disease decoding approaches mostly relied on expert-based extraction of features in combination with standard classification algorithms and thus strongly depend on the choice of data representation, convolutional networks are capable of learning hierarchical information directly from raw imaging data. By this, they have a great potential for finding unexpected and latent data characteristics and might perform as a real ?second reader?. A major focus w! > ill be on visualization techniques to make the learned content of convolutional neural networks visible. > > Requirements for the PhD student: > - Very good degree in computer science, mathematics, physics, psychology, computational neuroscience or related subject. > - Very good programming skills (e.g. Python) > - Experience in machine learning > - Good writing and communication skills (in English) > > Please send your application (motivation+CV) in one pdf-file (in English or German) to: > > Dr. Kerstin Ritter > Berlin Center for Advanced Neuroimaging, > Bernstein-Zentrum f?r Computational Neuroscience > Charit? - Universit?tsmedizin Berlin > Sauerbruchweg 4, Charit?platz 1, 10117 Berlin > Tel.: + 49 30 450 539364; Email: kerstin.ritter at bccn-berlin.de > > > _______________________________________________ > > ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Juelich GmbH 52425 Juelich Sitz der Gesellschaft: Juelich Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender), Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt, Prof. Dr. Sebastian M. Schmidt ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ From nguyensmai at gmail.com Fri Sep 14 10:42:58 2018 From: nguyensmai at gmail.com (Nguyen, Sao Mai) Date: Fri, 14 Sep 2018 16:42:58 +0200 Subject: Connectionists: [meetings] Call for Participation : Workshop on Continual Unsupervised Sensorimotor Learning - Tokyo - September 17th Message-ID: *Call for Participation* Workshop on Continual Unsupervised Sensorimotor Learning at IEEE ICDL-Epirob 2018 - Tokyo - September 17th Website : http://conferences.au.dk/icdl-epirob-2018-workshop/ ============================================================ *Updated list of Invited Speakers* - Jochen Triesch, Frankfurt Institute of Advanced Studies, Germany Title: Active Efficient Coding - David Ha, Google Brain Title: Generative World Models - Kathryn Kasmarik, University of New South Wales, Australian Defence Force Academy (UNSW Canberra), Australia Title: Computational Motivation for Learning, Optimisation and Decision Making *Schedule* 09:50 ? 10:10 Welcome and introduction 10:10 ? 10:50 *Invited talk: **David Ha* Title: Generative World Models 10:50 ? 11:10 Coffee break *Inference and Representations* 11:10 ? 11:30 *Where do I move my sensors? Emergence of an internal representation from the sensorimotor flow*Valentin Marcel, Sylvain Argentieri and Bruno Gas 11:30 ? 11:50 *Active inference in continual learning* Pablo Lanillos *Sensorimotor Learning* 11:50 ? 12:10 *Towards Biological Plausibility of Sensorimotor Learning Models: a Short Review* Silvia Pagliarini, Arthur Leblois, and Xavier Hinaut 12:10 ? 12:30 *A Computational Model For Action Prediction Development* Serkan Bugur, Yukie Nagai, Erhan Oztop, and Emre Ugur *Application/Tools* 12:30 ? 12:50 *Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning* Hugo Caselles-Dupr?, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz, and David Filliat 12:50 ? 14:10 Lunch break 14:10 ? 14:50 *Invited talk. Jochen Triesch* Title: Active Efficient Coding *Intrinsic Motivation and alike* 14:50 ? 15:10 *Learning Sequences of Policies by using an Intrinsically Motivated Learner and a Task Hierarchy* Nicolas Duminy, Alexandre Manoury, Sao Mai Nguyen, C?dric Buche, and Dominique Duhaut 15:10 ? 15:30 *Emergent emotion as a regulatory mechanism for a cognitive task implemented on the iCub robot* Murat Kirtay, Lorenzo Vannucci, Egidio Falotico, Cecilia Laschi, and Erhan Oztop *Application/Tools* 15:30 ? 15:50 *Towards Life Long Learning: Multimodal Learning of MNIST Handwritten Digits* Eli Sheppard, Hagen Lehmann, G. Rajendran, Peter E. McKenna, Oliver Lemon, and Katrin S. Lohan 15:50 ? 16:10 Coffee break 16:10 ? 16:40 *Invited talk: Kathryn Kasmarik* Title: Computational Motivation for Learning, Optimisation and Decision Making 16:40 ? 17:40 Discussion 17:40 ? 18:00 Conclusions and farewell ============================================================ *Scope* As the algorithms for learning single tasks in restricted environments are improving, new challenges have gained relevance. They include multi-task learning, multimodal sensorimotor learning in open worlds and lifelong adaptation to injury, growth and ageing. In this workshop we will discuss the developmental processes involved in the emergence of representations of action and perception in humans and artificial agents in continual learning. These processes include action-perception cycle, active perception, continual sensory-motor learning, environmental-driven scaffolding, and intrinsic motivation. The discussion will be strongly motivated by behavioural and neural data. We hope to provide a discussion friendly environment to connect with research with similar interest regardless of their area of expertise which could include robotics, computer science, psychology, neuroscience, etc. We would also like to devise a roadmap or strategies to develop mathematical and computational models to improve robot performance and/or to attempt to unveil the underlying mechanisms that lead to continual adaptation to changing environment or embodiment and continual learning in open-ended environments. The primary list of topics covers the following (but not limited to): - Emergence of representations via continual interaction - Continual sensory-motor learning - Action-perception cycle - Active perception - Environmental-driven scaffolding - Intrinsic motivation - Neural substrates, neural circuits and neural plasticity - Human and animal behaviour experiments and models - Reinforcement learning and deep reinforcement learning for life-long learning - Multisensory robot learning - Multimodal sensorimotor learning - Affordance learning - Prediction learning *Organizers:* Nicol?s Navarro-Guerrero, Aarhus University, Aarhus, Denmark Sao Mai Nguyen, IMT Atlantique, France Erhan ?ztop, ?zye?in University, Turkey Junpei Zhong, National Institute of Advanced Industrial Science and Technology (AIST), Japan ============================================================ Nguyen Sao Mai nguyensmai at gmail.com Researcher in Cognitive Developmental Robotics http://nguyensmai.free.fr -------------- next part -------------- An HTML attachment was scrubbed... URL: From aonken at inf.ed.ac.uk Fri Sep 14 06:31:30 2018 From: aonken at inf.ed.ac.uk (Arno Onken) Date: Fri, 14 Sep 2018 11:31:30 +0100 Subject: Connectionists: PhD student position in neural data analysis, University of Edinburgh (Arno Onken) Message-ID: A fully funded PhD position is available in the group of Arno Onken at the University of Edinburgh, on the development and application of novel methods for analysing multi-modal and multi-scale neural recordings. The group collaborates closely with the experimental groups of Nathalie Rochefort (University of Edinburgh, joint EPSRC-funded project to start in March) and Shuzo Sakata (University of Strathclyde). Potential projects are interdisciplinary, bridging computational neuroscience, statistical modelling and machine learning. The successful applicant will join the Institute for Adaptive and Neural Computation (http://www.anc.ed.ac.uk/) which hosts strong research groups in the relevant fields. Applicants should have a strong quantitative background (e.g. math, statistics, computer science, physics, computational neuroscience), good programming skills and a keen interest in interdisciplinary research. A background in neuroscience is desirable, but not essential. The position is available to UK/EU applicants. Other excellent applicants may be eligible for international postgraduate scholarships - please get in touch. The start date is flexible. Interested applicants should submit their application to the Institute for Adaptive and Neural Computation: https://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&edition=2018&id=489 For further information, please contact Arno Onken (aonken at inf.ed.ac.uk). -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From auke.ijspeert at epfl.ch Sat Sep 15 08:00:00 2018 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Sat, 15 Sep 2018 14:00:00 +0200 Subject: Connectionists: AMAM 2019, Adaptive motion in animals and machines, Aug 19-23 2019, EPFL, Lausanne, Switzerland Message-ID: AMAM 2019, Adaptive Motion in Animals and Machines, Aug 19-23 2019, EPFL, Lausanne, Switzerland https://amam2019.epfl.ch/ Mark the date and first call for abstracts Investigating how animals and humans excel at adaptive movements can help engineers to improve the adaptive capabilities of robots. In return, robots can serve as scientific tools to explore the basic principles of biological systems, in particular the neuromechanical mechanisms underlying their fascinating motor abilities. AMAM 2019 is the 9th international symposium dedicated to stimulate fruitful interactions among biologists and engineers interested in adaptive motion. It aims at bringing together researchers in robotics, biomechanics, neuroscience, sports science, and other fields related to motor behavior in biological and artificial systems. Previous symposia were held in Montreal, Canada (2000); Kyoto, Japan (2003); Ilmenau, Germany (2005); Cleveland, USA (2008); Awaji, Japan (2011); Darmstadt, Germany (2013); Cambridge, USA (2015); and Sapporo, Japan (2017). Abstract contributions are invited from all areas pertaining to adaptive motion in animals and machines. Accepted abstracts are presented in either oral or poster sessions based on assessed suitability by the program committee. Invited talks and some selected speakers will be presented in oral sessions in a single track. We also encourage participants to contribute hardware demonstrations, as part of the ?Robot Zoo?@AMAM2019. Important dates: * Jan 18th, 2019?????? Opening of the extended abstract submission * March 8th, 2019??? Deadline of extended abstracts submission * April 12th, 2019??? Notification of acceptance for extended abstracts * May 31st, 2019 ??? Deadline of submission for Robot Zoo (Robot Demos) * August 19-23, 2019? Conference Program Committee: * Hitoshi Aonuma, Hokkaido University, Japan * Jordan Boyle, Leeds University, UK * Monica Daley, Royal Veterinary College, UK * Koh Hosoda, Osaka University, Japan * Fumiya Iida, Cambridge, UK * Auke Ijspeert, EPFL, Lausanne, Switzerland * Akio Ishiguro, Tohoku University, Japan * Masato Ishikawa, Osaka University, Japan * Takeshi Kano, Tohoku University, Japan * Sangbae Kim, MIT, USA * Jun Nishii, Yamaguchi University, Japan * Dai Owaki, Tohoku University, Japan * Andre Seyfarth, TU Darmstadt, Germany * Emily Standen, University of Ottawa, Canada * Dagmar Sternad, Northeastern University, USA * Barry Trimmer, Tufts University, USA * Eric Tytell, Tufts University, USA * Hartmut Witte, TU Ilmenau, Germany General Chair: * Auke Ijspeert, EPFL, Lausanne, Switzerland -- ----------------------------------------------------------------- Prof Auke Jan Ijspeert Biorobotics Laboratory EPFL-STI-IBI-BIOROB, ME D1 1226, Station 9 EPFL, Ecole Polytechnique F?d?rale de Lausanne CH 1015 Lausanne, Switzerland Office: ME D1 1226 Tel: +41 21 693 2658 Fax: +41 21 693 3705 www:http://biorob.epfl.ch Email:Auke.Ijspeert at epfl.ch ----------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From npark9 at gmu.edu Sat Sep 15 15:55:31 2018 From: npark9 at gmu.edu (Noseong Park) Date: Sat, 15 Sep 2018 15:55:31 -0400 Subject: Connectionists: GRA positions of George Mason University in deep learning, machine learning, and constrained optimization Message-ID: The Center for Secure Information Systems (CSIS) at the George Mason University is seeking multiple PhD students who will work as GRAs in the field of deep learning, machine learning, constrained optimization, and their applications to cybersecurity. Please refer to our recent publications listed below and GRA students will be working for similar topics, including but not limited to i) enhancing generative models such as generative adversarial networks, ii) enhancing knowledge graph embedding for scalability and accuracy, iii) solving optimization problems in cybersecurity and social networks (e.g., optimally allocating security analysts against security alarms, finding a set of social sensors to detect outbreaks in social media, etc.). They will also conduct many practical research projects for cybersecurity applications, such as fake data synthesis. Below is a list of recent publications on these topics. Generative adversarial networks and their application to data privacy: 1. Noseong Park, Mahmoud Mohammadi, Kshitij Gorde, Sushil Jajodia, "Data Synthesis based on Generative Adversarial Networks ," the 44th International Conference on Very Large Data Bases (VLDB), 2018 2. David K. Park, Seungjoo Yoo, Hyojin Bahng, Jaegul Choo, Noseong Park, "MEGAN: Mixture of Experts of Generative Adversarial Networks for Image Generation for Multimodal Image Generation ," the 27th International Joint Conference on Artificial Intelligence (IJCAI), 2018 3. Noseong Park, Ankesh Anand, Joel Ruben Antony Moniz, Kookjin Lee, Jaegul Choo, David K. Park, Tanmoy Chakraborty, Hongkyu Park, and Youngmin Kim, "MMGAN: Manifold Matching Generative Adversarial Network for Generating Images ," the 24th International Conference on Pattern Recognition (ICPR), 2018 Knowledge graph query processing and embedding: 1. Hyunjoong Kang, Sanghyun Hong, Kookjin Lee, Noseong Park and Soonhyun Kwon, "On Integrating Knowledge Graph Embedding into SPARQL Query Processing ," the 25th IEEE International Conference on Web Services (ICWS), 2018 2. Francesco Parisi, Noseong Park, Andrea Pugliese, V.S. Subrahmanian, "Top-k User-Defined Vertex Scoring Queries in Edge-Labeled Graph Databases ," to appear in ACM Transactions on the WEB, 2018 Constrained optimization and prediction-drive optimization: 1. Bo An, Haipeng Chen, Noseong Park, and V.S. Subrahmanian, "Data-Driven Frequency-Based Airline Profit Maximization ," ACM Transactions on Intelligent Systems and Technology, vol. 8, no. 4, 2017 2. Bo An, Haipeng Chen, Noseong Park, and V.S. Subrahmanian, "MAP: Maximizing Airline Profits using an Ensemble Game-Theoretic Forecasting Approach ," ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2016 3. Noseong Park, Edoardo Serra, Tom Snitch, and V.S. Subrahmanian, ?APE: A Data-Driven, Behavioral Model Based Anti-Poaching Engine, ? IEEE Transactions on Computational Social Systems, vol. 2, no. 2, pp. 1-23, 2015 [NBC Nightly News] Successful candidates should have at least one proven record of experience on the posted fields and be capable of solving research problems. Detailed advice will be provided but preference will be given to self-motivated students who can perform literature survey and design algorithms by themselves beyond the advice. Successful candidates may also have mature programming skills for Python (with various machine learning and data mining libraries such as Scikit-Learn), Tensorflow, and/or Java. The initial GRA contract will be for one year but can be extended until the end of PhD study depending on performance. The GRA support will consists of the standard support package of Volgenau School of Engineering. GRAs will be advised by Dr. Noseong Park (npark9 at gmu.edu; https://sites.google.com/view/npark ). Please send your CV if interested. ------------------------------------------------- Noseong Park, PhD *| *Assistant Professor Center for Secure Information Systems Information Sciences and Technology 424, Research Hall George Mason University npark9 at gmu.edu* | * Visit Homepage ------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From stefan.haufe at charite.de Sun Sep 16 16:16:34 2018 From: stefan.haufe at charite.de (Stefan Haufe) Date: Sun, 16 Sep 2018 23:16:34 +0300 Subject: Connectionists: =?utf-8?q?PhD_positions_in_machine_learning/neuro?= =?utf-8?q?imaging_available_at_Charit=C3=A9_-_University_Medicine_Berlin?= Message-ID: <38932658-240d-af84-85c4-277310b7cb2d@charite.de> Dear all, PhD positions for highly motivated graduate students are available in the ERC funded research group of Stefan Haufe at the Berlin Center for Advanced Neuroimaging (BCAN) of the Charit? - University Medicine Berlin, Germany. The group will develop machine learning and signal processing methods for the analysis of non-invasive brain signals (primarily EEG/MEG) and apply these methods to patient data with the aim of better understanding neurological diseases such as Parkinson's and Alzheimer?s disease. Appointments can be made for up to four years starting from January 2019 or later. Remuneration is based on the German pay scale TVL E13 (65% working time). Candidates are required to hold a very good MSc or equivalent degree in a relevant field and are expected to demonstrate extraordinary skills in at least one of the following core areas A: Mathematics and quantitative data analysis/modeling (machine learning, signal processing, statistics, numerical optimization, etc.). Experience with efficient algorithms and large data sets. B: Neuroscience (psychology, cognitive science). Knowledge of general research practices and experience in the design, execution, and statistical evaluation of studies. C: Computer science. Experience in software development, programming in Matlab/Python/C, system administration. Further required are excellent communication skills in English (written and spoken), and a genuine interest in interdisciplinary work. Prior experience with functional neuroimaging data is a plus. Successful candidates will work at Charit?'s historic Mitte campus in the center of Berlin, and will be embedded in a stimulating research environment. Applications should be sent by email to stefan.haufe at charite.de quoting the reference number DM.143.18b. In addition to cv and cover letter, applicants are encouraged to include further documentation such as references, transcripts, copies of bachelor/master theses/research papers (in English or German), links to github repositories, etc. . All documents should be contained in a single pdf. From inesdomingues at gmail.com Mon Sep 17 16:46:03 2018 From: inesdomingues at gmail.com (=?UTF-8?Q?In=C3=AAs_Domingues?=) Date: Mon, 17 Sep 2018 21:46:03 +0100 Subject: Connectionists: Special Issue Call for Papers - Multimedia Systems and Applications in Biomedicine Message-ID: -------------------------------------------------------------------------------- Please re-distribute (Apologies for cross posting) -------------------------------------------------------------------------------- -------------------------------------------------------------------------------- CALL FOR PAPERS Special Issue Call for Papers - ?Multimedia Systems and Applications in Biomedicine? -------------------------------------------------------------------------------- Aims and Scope -------------------------------------------------------------------------------- Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization (http://www.tandfonline.com/toc/tciv20/current) invites submissions to the Special Issue on ?Multimedia Systems and Applications in Biomedicine?. Advances in computing techniques, data acquisition technology, hardware, and networks have mutually promoted the development of multimedia analysis approaches. Many machine learning, signal/image processing, and data mining algorithms have been successfully developed for multimedia analysis. WIthin the multimedia domain, medical data analysis has attracted considerable attention due in part to the increase of imaging modalities. Consider the assessment of the functioning of the heart. Physicians have multiple resources and modalities available, including: auscultation which can produce a report in text format; electrocardiograms which result in time series, x-rays saved as images; volumes provided through angiography; temporal information given by echocardiograms, and 4D information extracted through flow MRI. Since gathering medical data is now easier than ever before, existing multimedia learning methods are expected to embrace new challenges to deal with large-scale medical data that may share totally different data distributions or may continuously change over time. This special issue will serve as a way to set the state of the art in the advances in multimedia learning methods for various medical applications. -------------------------------------------------------------------------------- Topics of Interest -------------------------------------------------------------------------------- Topics appropriate for this special issue include (but are not limited to): - 2D/3D Image reconstruction - Computational Bio-imaging and Visualization - Computer-Aided diagnostic systems - Data acquisition - Data Processing and Analysis - Devices for Imaging and Visualization - Disease recognition, classification and retrieval - Human Perception in Imaging and Visualization - Image denoising and enhancement - Image Processing and Analysis - Image registration and calibration - Imaging and Visualization in Biomedical Engineering - Landmark/structure detection - Large scale 3D data indexing - Medical Image Representation - Medical Image Understanding - Medical Imaging and Visualization - Multi-modal Imaging and Visualization - Multiscale Imaging and Visualization - Scientific Visualization - Segmentation/labeling - Software Development for Imaging and Visualization - Surgical and interventional systems - Telemedicine Systems and Applications - Virtual Reality - Visual Data Mining and Knowledge Discovery - Visualization and visual synthesis Manuscripts must clearly delineate the role of multimedia systems and applications in Biomedicine. The manuscript should include new contributions beyond those made in earlier publications. Review works will also be considered in this special issue. Contributions should be described in sufficient detail to be reproducible on the basis of the material and references presented in the paper. -------------------------------------------------------------------------------- Important Dates -------------------------------------------------------------------------------- Manuscript Due : December 10, 2018 First Decision Date : February 11, 2019 Second Revision Due : April 15, 2019 Final Decision Date : June 10, 2019 Camera Ready Version Due : August 12, 2019 -------------------------------------------------------------------------------- PAPER SUBMISSION -------------------------------------------------------------------------------- The paper should be submitted at https://mc.manuscriptcentral.com/tciv, choosing on step 5, the option ?Multimedia Systems and Applications in Biomedicine? -------------------------------------------------------------------------------- Guest Editorial Board -------------------------------------------------------------------------------- In?s Domingues Ana F. Sequeira Carla Pinto ?lvaro Rocha -------------- next part -------------- An HTML attachment was scrubbed... URL: From emmanuel.vincent at inria.fr Mon Sep 17 02:38:28 2018 From: emmanuel.vincent at inria.fr (Emmanuel Vincent) Date: Mon, 17 Sep 2018 08:38:28 +0200 Subject: Connectionists: R&D Technical Project Manager - H2020 project on Speech and Language Processing Message-ID: Dear list, Inria is seeking a Technical Project Manager for a new European (H2020 ICT) collaborative project called COMPRISE. COMPRISE is a 3-year Research and Innovation Action (RIA) aiming at new cost-effective, multilingual, privacy-driven voice interaction technology. This will be achieved through research advances in privacy-driven machine/deep learning, personalized training, automatic data labeling, and tighter integration of speech and dialog processing with machine translation. The technology will be based on existing software toolkits (Kaldi speech-to-text, Platon dialog processing, Tilde text-to-speech), as well as new software resulting from these research efforts. The consortium includes academic and industrial partners in France (Inria, Netfective Technology), Germany (Ascora, Saarland University), Latvia (Tilde), and Spain (Rooter). The successful candidate will be part of the Multispeech team at Inria Nancy (France). As the Technical Project Manager of H2020 COMPRISE, he/she will be responsible for animating the consortium in daily collaboration with the project lead. This includes orchestrating scientific and technical collaborations as well as reporting, disseminating, and communicating the results. He/she will also lead Inria?s software development and demonstration tasks. Besides the management of COMPRISE, the successful candidate will devote half of his/her time to other activities relevant to Inria. Depending on his/her expertise and wishes, these may include: management of R&D projects in other fields of computer science, involvement in software and technology development and demonstration tasks, building of industry relationships, participation in the setup of academic-industry collaborations, support with drafting and proofreading new project proposals, etc. Ideal profile: - MSc or PhD in speech and language processing, machine learning, or a related field - at least 5 years' experience after MSc/PhD, ideally in the private sector - excellent software engineering, project management, and communication skills Application deadline: October 12, 2018 Starting date: December 1, 2018 or January 1, 2019 Duration: 3 years (renewable) Location: Nancy, France Salary: from 2,300 to 3,700 EUR net/month, according to experience For more details and to apply: https://jobs.inria.fr/public/classic/en/offres/2018-01033 -- Emmanuel Vincent Multispeech Project-Team Inria Nancy - Grand Est 615 rue du Jardin Botanique, 54600 Villers-l?s-Nancy, France Phone: +33 3 8359 3083 - Fax: +33 3 8327 8319 Web: http://members.loria.fr/evincent/ From cgf at isep.ipp.pt Mon Sep 17 16:25:03 2018 From: cgf at isep.ipp.pt (Carlos Ferreira) Date: Mon, 17 Sep 2018 21:25:03 +0100 Subject: Connectionists: CFP: DATA STREAMS TRACK - ACM SAC 2019 (Submission deadline: September 24, 2018) Message-ID: <0d5081e9-daf3-e035-81e5-ef82bd0a006a@isep.ipp.pt> *ACM Symposium on Applied Computing * The 34th ACM/SIGAPP Symposium on Applied Computing in Limassol, Cyprus April 8 ? 12, 2019 https://www.sigapp.org/sac/sac2019/ *Data Streams Track * https://www.cs.waikato.ac.nz/~abifet/SAC2019/ *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 * Neural Networks for 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 24, 2018 2. Author Notification: November 24, 2018 3. Camera?ready copies: December 10, 2018 *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 2019 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. 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 recruitment at bioinf.jku.at Tue Sep 18 04:10:49 2018 From: recruitment at bioinf.jku.at (Recruitment) Date: Tue, 18 Sep 2018 10:10:49 +0200 Subject: Connectionists: Research Fellow in Machine Learning / Deep Learning, Hochreiter Group, Linz, Austria Message-ID: Research Fellow in Machine Learning / Deep Learning, Hochreiter Group, Linz, Austria Johannes Kepler University Linz (JKU), Austria, is looking for two post-doctoral research fellows to advance machine learning and deep learning research with Sepp Hochreiter. These six year positions are affiliated both with the newly established LIT AI Lab and the Institute for Machine Learning. Job description: ???? conduct independent research in the field, ?? ? collaborate in machine learning and deep learning projects, ???? publish in renowned international journals and conferences, ???? supervise students; prepare and hold lectures; support study programs. Requirements: ???? PhD degree, ???? track record in machine learning (e.g. deep learning, reinforcement learning, kernel methods, probabilistic modeling, meta-learning, attention models), ???? knowledge in one or more of the following application domains is a plus: signal processing, vision, speech, natural language processing, physics, bio-/chemoinformatics, computational medicine, autonomous driving, ???? willingness and ability to work in a team and to support students and junior researchers. About the group: Within the last years, Sepp Hochreiter (who is best known for the invention of LSTM, for the Vanishing Gradient problem, ?Flat Minima?, and ?Learning to Learn?) has built up a dynamic team of more than 20 researchers. The group has recently achieved widely acclaimed contributions and successes, such as, winning the NIH?s Tox21 toxicity prediction challenge with deep learning, the invention of the ELU activation function, Self-Normalizing Networks, and providing a convergence proof for GAN learning. The group has many international collaborations and receives funding from national and international research programs as well as from companies, such as, Johnson&Johnson, Merck, Bayer, Zalando and from joined labs like the Audi.JKU Deep Learning Center. About the location: The area offers an excellent quality of living in the heart of Europe ? close to the alps between Vienna, Salzburg, Prague and Munich. Linz provides a superb cultural environment, most famous for the Ars Electronica Festival, the Brucknerfest, and the nearby Salzburg Festival. The picturesque and versatile landscape provides countless options for recreation and sports in nature (skiing, hiking, climbing, cycling, and many more). If you have questions, please contact: Prof. Dr. Sepp Hochreiter, +43 732 2468 4520, recruitment at bioinf.jku.at. Prospective applicants interested in this position are requested to electronically send an application via the online portal http://jku.at/application. Please include ?Job Reference Number 3578? (deadline: Dec 12, 2018). From juliustch at gmail.com Tue Sep 18 10:24:37 2018 From: juliustch at gmail.com (Chenhao Tan) Date: Tue, 18 Sep 2018 08:24:37 -0600 Subject: Connectionists: Postdoctoral associate in natural language processing and computational social science Message-ID: *Postdoctoral associate in natural language processing and computational social science* Department of Computer Science, University of Colorado Boulder Applicants are invited to apply for a postdoctoral associate position to work on natural language processing, computational social science, human-centered machine learning with Dr. Chenhao Tan at the Department of Computer Science, University of Colorado Boulder. Dr. Tan's research interests include language and social dynamics, multi-community engagement, and human-centered machine learning. His work has been covered by many news media outlets, such as the New York Times and the Washington Post. He also won a Facebook fellowship and a Yahoo! Key Scientific Challenges award. Successful applicants are expected to have a PhD degree in Computer Science, Information Science, or social sciences with demonstrated technical capability. Interested applicants should submit their application materials through the following website: https://jobs.colorado.edu/ jobs/JobDetail/?jobId=13076&emailCampaignId=168. Applicants are also welcome to send Dr. Tan emails for inquiries; please attach a resume. Dr. Tan's email address is chenhao.tan at colorado.edu and his homepage is athttps://chenhaot.com. For more information check https://chenhaot.com/pubs/postdoc_ad.pdf -------------- next part -------------- An HTML attachment was scrubbed... URL: From latorre at lsi.uji.es Tue Sep 18 04:49:09 2018 From: latorre at lsi.uji.es (Pedro Latorre Carmona) Date: Tue, 18 Sep 2018 10:49:09 +0200 Subject: Connectionists: Automatic Generation Groundtruth Bounding Boxes Person Tracking Message-ID: Dear *connectionist* members, I was wondering if any of you is aware of (and might recommend) a MATLAB *GUI* or similar that allows to *easily* create the *bounding boxes* of a person on a video for *ground truth* generation purposes. Any information from your side would be very welcome. Pedro Latorre Carmona. -------------- next part -------------- An HTML attachment was scrubbed... URL: From richard.jiang at northumbria.ac.uk Tue Sep 18 06:46:38 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Tue, 18 Sep 2018 10:46:38 +0000 Subject: Connectionists: Call for Book Chapters on Deep Biometrics In-Reply-To: References: Message-ID: Dear Colleagues, We would like to invite you to contribute a chapter for the upcoming volume entitled "Deep Biometrics" to be published by Springer, the largest global scientific, technical, and medical ebook publisher. The volume will be available both in print and in ebook format by late 2018/early 2019 on SpringerLink, one of the leading science portals that includes more than 8 million documents, an ebook collection with more than 160,000 titles, journal archives digitized back to the first issues in the 1840s, and more than 30,000 protocols and 290 reference works. Below is a short description of the volume: Recent development in machine learning, particularly deep learning, has brought out drastic impact on Biometrics, which is a classic topic to utilize Machine Learning for biometric identification. Particularly, Deep Learning can benefit from the training with large unlabelled datasets via semi-supervised or unsupervised learning. This book aims to highlight recent research advances in biometrics using semi-supervised and unsupervised new methods such as Deep Neural Networks, Deep Stacked Autoencoder, Convolutional Neural Networks, Generative Adversary Networks, Ensemble Methods, and so on, and exploit these novel methods in the emerging new areas such as privacy and security issues, cancellable biometrics and soft biometrics, smart cities, big biometric data, biometric banking, medical biometrics, and healthcare biometrics, etc.. The goal of this volume is to summarize the recent advances in using Deep Learning in the area of biometric security and privacy. Topics of interest include: (but not limited to) * Deep Learned Biometric Features * Convolutional Neural networks * Deep Stacked Autoencoder * Deep Face Detection * Deep Gait Recognition * Biometrics in Cybersecurity * Biometrics in Cognitive Robot * Healthcare Biometrics * Medical Biometrics * Biometrics in Social Computing * Biometric Block Chain * Privacy and Security Issues * Iris, Fingerprints, DNA, Palmprints * Gait, EEG, Heart rates * Multimodal Fusion * Soft Biometrics * Cancellable Biometrics * Big data issues in Biometrics * Biometrics for Internet of things Each contributed chapter is expected to present a novel research study, a comparative study, or a survey of the literature. Note that there will be no publication fees for accepted chapters. Important Dates: Submission of abstracts Nov 15, 2018 Notification of initial editorial decisions Nov 20, 2018 Submission of full-length chapters Dec 15, 2018 Notification of final editorial decisions Jan 15, 2019 Submission of revised chapters Feb 15, 2019 All submissions should be done via EasyChair: https://easychair.org/conferences/?conf=deepbio2019 Original artwork and a signed copyright release form will be required for all accepted chapters. For author instructions, please visit: http://www.springer.com/authors/book+authors?SGWID=0-154102-12-417900-0 Please feel free to contact us via email (perceptualscience at outlook.com, or any editors below) regarding your chapter ideas. Editorial Board * Dr Richard Jiang Computer and Information Sciences, Northumbria University, United Kingdom Email: richard.jiang at unn.ac.uk * Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark Email: weme at dtu.dk * Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia Email: chli at csu.edu.au * Professor Christophe Rosenberger Computer Security ENSICAEN - GREYC, France Email: christophe.rosenberger at ensicaen.fr Contact: All questions about submissions can be emailed to perceptualscience at outlook.com or any editor in the board. Many thanks! Kind Regards, Editors of the Book This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender's explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. -------------- next part -------------- An HTML attachment was scrubbed... URL: From kyunghyun.cho at nyu.edu Tue Sep 18 09:23:13 2018 From: kyunghyun.cho at nyu.edu (Kyunghyun Cho) Date: Tue, 18 Sep 2018 09:23:13 -0400 Subject: Connectionists: [CFP] 2nd NIPS Workshop on Emergent Communication Message-ID: 2nd NIPS Workshop on Emergent Communication [EmComm2] Submission via https://cmt3.research.microsoft.com/EMECOMNIPS2018 Website: https://sites.google.com/site/emecom2018/ Sat Dec 8th 08:45 AM -- 06:30 PM, Montreal, Canada Mission Statement: To bring together a variety of researchers from a range of different backgrounds interested in the topic of (emergent) communication. Abstract Communication is one of the most impressive human abilities. The question of how communication arises has been studied for many decades, if not centuries. However, due to computational and representational limitations, past work was restricted to low dimensional, simple observation spaces. With the rise of deep reinforcement learning, this question can now be studied in complex multi-agent settings, which has led to flourishing activities in the area over the past years. In these settings, agents learn to communicate in grounded multimodal environments using rich, emergent communication protocols. Last year?s workshop was a great success, but there still are many open questions. For example, most work in the field so far has focused on fully cooperative settings, while the more challenging and realistic use cases come from situations where agents do not have fully aligned interests and goals. How can we have credible communication amongst self-interested agents where each agent maximizes its own individual rewards rather than a joint team reward? This is a new computational modeling challenge for the community. Due to the recent exploding popularity of machine learning, there is a tendency for researchers to have an arguably too narrow focus only on recent machine learning-based approaches. This often leads to reinventing the wheel. In order to avoid this issue and broaden our view on emergent communication, we take an interdisciplinary approach to emergent communication by inviting scientists from a broad set of disciplines, including machine learning, game theory, evolutionary biology, linguistics, cognitive science and programming languages, while focusing on the question of communication and emergent language. Call for Papers We invite submissions in the following and related areas: - deep multi-agent learning - language evolution - multi-agent communication - strategic communication - modeling of other agents - understanding emergent protocols - grounding emergent protocols - Any other area related to the subject of the workshop All accepted submissions will be made available on the workshop website and included in the poster session during the workshop. As this does not constitute an archival publication or formal proceedings, authors are free to submit and publish their extended work elsewhere. Since NIPS sold out early, authors of accepted papers at the workshop may be able to register for the workshop through access to a dedicated pool of tickets. Submission Format An abstract should be 2-4 pages of content in the NIPS format, with an unlimited number of pages for references. We also encourage the submission of a recently published, accepted or submitted paper, without any page limit. Submissions Link Please submit your manuscripts via: *https://cmt3.research.microsoft.com/EMECOM2018* Important Dates Submission Deadline: Nov 2 2018 Author Notification: Nov 18 2018 Workshop: Dec 8 2018 -------------- next part -------------- An HTML attachment was scrubbed... URL: From jesus.m.cortes at gmail.com Tue Sep 18 07:34:21 2018 From: jesus.m.cortes at gmail.com (Jesus Cortes) Date: Tue, 18 Sep 2018 13:34:21 +0200 Subject: Connectionists: 1-year position for an engineer to work in Parkinson, in the frontiers of imaging and machine learning (Bilbao, Spain) Message-ID: We are looking for an Engineer with skills in computer vision, programming and machine learning to collaborate in the research project entitled: "Study of the retina and the visual pathway by neuroimaging in genetic and aggressive idiopathic synucleinopathies as a model to identify phenotypes and prognostic biomarkers in idiopathic Parkinson's disease" (Principal Investigator: I?igo Gabilondo, MD, PhD) led by the Neurodegenerative Diseases Group. The data to analyse are multimodal and longitudinal, with a sample size bigger than N=100 and consisting in retina OCT, neuroimaging (structural, functional, tensor tensor and spectroscopy), neuropsychology and clinical scales. The engineer also will work in close collaboration with the Computational Neuroimaging Group, led by Prof. Jesus M Cortes. For further information about the groups, visit: https://biocrucesbizkaia.org/web/biocruces/bc5.01and https://biocrucesbizkaia.org/bc5.08 Requirements: - Bachelor of Engineering - Good academic marks (average score higher than 7 over 10) - Experience in computer vision, programming j(Matlab, Python and / or R), machine learning and other artificial intelligence techniques - Experience with the magnetic resonance imaging analysis packages SPM, FSL and Freesurfer - Advanced English level (demonstrable with official degree - C1) - Intention to develop a PhD in Biomedicine. The contract is for 1 year, but exists the possibility to extend it to finalize the PhD Working conditions: - Duration: 12 months (extendable) - Full working day (100%) (1592 annual hours) - Estimated annual gross salary: 23,004 euros per year - Expected start date: As soon as possible Interested candidates send 2 reference letters and updated CV to igabilon at gmail.com and/or jesus.m.cortes at gmail.com -- http://www.jesuscortes.info https://neurokafe.github.io/ https://thesciencebridge.org/ http://neurolagun.eus/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From emmanuel.vincent at inria.fr Tue Sep 18 16:22:32 2018 From: emmanuel.vincent at inria.fr (Emmanuel Vincent) Date: Tue, 18 Sep 2018 22:22:32 +0200 Subject: Connectionists: Three postdoctoral positions on machine learning and speech processing Message-ID: <735d23aa-e9b4-7336-1f83-57d4e5e8e0be@inria.fr> Inria is seeking 3 postdoctoral researchers for a new European (H2020 ICT) collaborative project called COMPRISE. COMPRISE is a 3-year Research and Innovation Action (RIA) aiming at new cost-effective, multilingual, privacy-driven voice interaction technology. This will be achieved through research advances in privacy-driven machine learning, personalized training, automatic data labeling, and tighter integration of speech and dialog processing with machine translation. The technology will be based on existing software toolkits (Kaldi speech-to-text, Platon dialog processing, Tilde text-to-speech), as well as new software resulting from these research efforts. The consortium includes academic and industrial partners in France (Inria ,Netfective Technology ), Germany (Ascora ,Saarland University ), Latvia (Tilde ), and Spain (Rooter ). The successful candidates will be part of theMultispeech team in Nancy or theMagnet team in Lille. Both teams will work in tight collaboration. Topics include: * weakly-supervised, semi-supervised learning, learning with partial feedback * theoretical aspects and formal guarantees in private machine learning, * representation learning and deep learning for speech processing, * learning on the edge, federated learning and personalized learning. Both theoretical and practical aspects will be developed, possibly by different candidates depending on their skills. *Desired profile:* Two alternative profiles are welcome, either: * strong background in mathematics, machine learning, statistics and algorithms, or * strong experience with implementation and experimentation, speech processing, natural language processing, user modeling. *Application deadline:* October 19, 2018 *Starting date:* January 1, 2019 or later *Duration:* 2 years (renewable) *Location:* Nancy or Lille, France *Salary:* from 2,130 to 2,520 EUR net/month, according to experience *For more details and to apply:* https://jobs.inria.fr/public/classic/en/offres/2018-01045 https://jobs.inria.fr/public/classic/en/offres/2018-01044 https://jobs.inria.fr/public/classic/en/offres/2018-01038 -- Emmanuel Vincent Multispeech Project-Team Inria Nancy - Grand Est 615 rue du Jardin Botanique, 54600 Villers-l?s-Nancy, France Phone: +33 3 8359 3083 - Fax: +33 3 8327 8319 Web: http://members.loria.fr/evincent/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Tue Sep 18 17:58:28 2018 From: ted.carnevale at yale.edu (Carnevale, Nicholas) Date: Tue, 18 Sep 2018 21:58:28 +0000 Subject: Connectionists: NEURON Course at SFN 2018 Message-ID: The registration deadline for the NEURON course at the SFN 2018 meeting is Friday, October 12--less than a month from now. The online registration form is at https://neuron.yale.edu/neuron/static/courses/sd2018/sd2018.html This course is suitable for applicants with a wide range of interests and expertise, ranging from experimentalists who have never done any computational modeling, to advanced modelers who want to know the latest tips for using NEURON with Python. Topics that will be covered include: --using Python and NEURON's graphical tools to build and work with models of individual cells --using the Import3d tool to import detailed anatomical neuronal data from NeuroLucida and SWC files --using the CellBuilder to specify the biophysical properties of model cells with detailed anatomical structure --expanding NEURON's library of ion channels and other biophysical mechanisms --analyzing models with the Model View tool --building network models --speeding up simulations on parallel hardware --Ted From george at cs.ucy.ac.cy Wed Sep 19 10:31:33 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Wed, 19 Sep 2018 17:31:33 +0300 Subject: Connectionists: The 34th ACM Symposium on Applied Computing (SAC 2019): Combined Call for Papers - Last Mile In-Reply-To: References: <31C24FFB-0CFA-4FDA-A707-4F88A4937121@cs.ucy.ac.cy> Message-ID: <6978C684-25CD-4FF6-BD9A-4AA340EF7189@cs.ucy.ac.cy> Department of Computer Science Office: +357-22892693 University of Cyprus Mobile: +357-99433817 1 University Avenue Fax: +357-22892701 Aglantzia, CY-2109 Email: george at cs.ucy.ac.cy Nicosia, Cyprus > On 05 Sep 2018, at 19:04, George Angelos Papadopoulos wrote: > > *** FINAL COMBINED CALL FOR PAPERS *** > > The 34th ACM Symposium on Applied Computing (SAC 2019) > > St. Raphael Resort, Limassol, Cyprus, April 8-12, 2019 > > https://www.sigapp.org/sac/sac2019 > > *** Submission Deadline: September 24, 2018 (extended) *** > > > For the past thirty-three years the ACM Symposium on Applied Computing > (SAC) has been a primary and international forum for applied computer > scientists, computer engineers and application developers to gather, > interact and present their work. The ACM Special Interest Group on > Applied Computing (SIGAPP) is the sole sponsor of SAC. The conference > proceedings are published by ACM and are also available online through > ACM's Digital Library. > > The 34th Annual SAC meeting will be held in April 2019 in Limassol, Cyprus, > and is hosted by the University of Cyprus. The conference features the > following tracks: > > ? Intelligent Robotics and Multi-Agent Systems (IRMAS) > ? Knowledge Representation and Reasoning (KRR) > ? Information Access and Retrieval (IAR) > ? Software Verification and Testing (SVT) > ? Computational Intelligence and Video & Image Analysis (CIVIA) > ? Social Network and Media Analysis (SONAMA) > ? Selected Areas of Wireless Communications and Networking (WCN) > ? Recommender Systems: Theory and Applications (RS) > ? Computer Security (SEC) > ? Web-based Technologies for Interactive Computing Education (WICE) > ? Data Mining (DM) > ? Usability Engineering (UE) > ? Cloud Computing (CC) > ? Privacy by Design in Practice (PDP) > ? Advances in COMputational Biomedical Imaging (COMBI) > ? Operating Systems (OS) > ? Software Platforms (SP) > ? Decentralized Applications (DAPP) with Blockchain, DLT and Crypto-Currencies (DAPP) > ? Databases and Big Data Management (DBDM) > ? Requirements Engineering (RE) > ? Cyber-Physical Systems (CPS) > ? Software Architecture: Theory, Technology, and Applications (SA-TTA) > ? Internet of Things (IoT) > ? Sustainability of Fog/Edge Computing Systems (SFECS) > ? Software-intensive Systems-of-Systems (SiSoS) > ? Data Streams (DS) > ? Programming Languages (PL) > ? Business Process Management & Enterprise Architecture (BPMEA) > ? Microservices, DevOps, and Service-Oriented Architecture (MiDOS) > ? Health Informatics (HI) > ? Dependable, Adaptive, and Secure Distributed Systems (DADS) > ? GeoInformation Analytics (GIA) > ? Knowledge and Language Processing (KLP) > ? KomIS: Knowledge Discovery meets Information Systems (KomIS) > ? Next Generation Programming Paradigms and Systems (NGPS) > ? Communication, Computing and Networking in Internet of Vehicles (CCNIV) > ? Bioinformatics (BIO) > ? Embedded Systems (EMBS) > ? Digital Life for Human Well-being (DLHWB) > ? Networking (NET) > ? Semantic Web and Applications (SWA) > ? Mobile Computing and Applications (MCA) > ? Software Engineering (SE) > ? Variability and Software Product Line Engineering (VSPLE) > ? Smart Human Computer Interaction (HCI) > ? Web Technologies (WT) > ? Machine Learning and its Applications (MLA) > > More information about the topics covered by each track and submission > instructions are available on the conference web site and the web sites > of the tracks themselves (accessible from the conference web site). > > > Important Dates > > ? Sept 24, 2018: Submission of papers (extended) > ? Nov 10, 2018: Author notification > ? Nov 25, 2018: Camera-ready copies > ? Dec 10, 2018: Author registration > > > Committees > > https://www.sigapp.org/sac/sac2019/organization.html > -------------- next part -------------- An HTML attachment was scrubbed... URL: From maneesh+connectionists at gatsby.ucl.ac.uk Wed Sep 19 05:54:54 2018 From: maneesh+connectionists at gatsby.ucl.ac.uk (Maneesh Sahani) Date: Wed, 19 Sep 2018 10:54:54 +0100 Subject: Connectionists: Machine Learning faculty position (open rank) at the Gatsby Unit, UCL Message-ID: The Gatsby Computational Neuroscience Unit at University College London invites applications for an academic position in machine learning or statistics at the rank of Lecturer, Reader/Associate Professor, or Professor. We especially seek candidates whose work addresses fundamental probabilistic or statistical machine learning. The appointment will be made at a rank appropriate to the experience and international standing of the successful candidate. Established in 1998 through a generous grant from the Gatsby Charitable Foundation, the Gatsby Unit has been a pioneering centre for both machine learning and theoretical neuroscience. We have core funding to support six positions, associated postdocs and PhD students, and computational resources. Faculty may raise additional funds through grants from national and international funding bodies and charities. We have no undergraduate programme, so only graduate-level teaching and supervision is required. The Unit is located in London's vibrant West End, sharing a new purpose-built home with the Sainsbury Wellcome Centre for Neural Circuits and Behaviour, near the Gower street campus. We are close to cognate groups in the departments of Computer Science and Statistical Science, as well as the Alan Turing Institute. The Unit offers internationally competitive salaries. We particularly welcome female applicants and those from an ethnic minority, as they are under-represented within UCL at this level. For informal enquiries, please contact Maneesh Sahani (maneesh at gatsby.ucl.ac.uk). All applications received before 30 November 2018 will be reviewed together. If the position remains unfilled following this review, further rounds of application will be considered. For more information, and a link to the online application portal, please visit http://www.gatsby.ucl.ac.uk/vacancies/ UCL vacancy reference: 1731589 -- Maneesh Sahani, Ph.D. Professor of Theoretical Neuroscience and Machine Learning, Director, Gatsby Computational Neuroscience Unit UCL, 25 Howland Street, London W1T 4JG From t.hospedales at ed.ac.uk Wed Sep 19 09:40:12 2018 From: t.hospedales at ed.ac.uk (Timothy Hospedales) Date: Wed, 19 Sep 2018 14:40:12 +0100 Subject: Connectionists: Postdoctoral Research Associate Position in Deep Learning Message-ID: Applications are invited for the position of Postdoctoral Research Associate in the EPSRC and DSTL funded UDRC Phase 3 project. This is a large project with several open positions, including one within the Machine Intelligence Group at the School of Informatics in the University of Edinburgh. The particular focus of this post is on certifying and verifying deep neural networks. As Deep Neural Networks (DNNs) are deployed in increasingly many and increasingly mission-critical applications, it becomes more important to be confident that their outputs can be relied upon for decision-making. This is a particularly salient concern when DNN-based systems are deployed and exposed to new, unexpected, and potentially adversarial inputs. The researcher will develop novel methods for certifying and verifying that DNNs are fit for purpose, even when extrapolating in the presence of novel inputs. Potential techniques to explore include both formal and meta-learning based approaches to increasing reliability to out of sample data, as well as explainable AI approaches to allow reasoning to be manually checked for validity. The competitive candidate will have a strong track record of publications in venues such as ICML, NIPS, ICLR, CVPR and ICCV. This fixed-term post is available for a period of 2.5 years from January 2019. The closing date for applications is 04 October 2018. International applicants are welcome. Further details and a link to the online application portal are available at https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=045067. Informal enquiries may be directed to Dr Timothy Hospedales at t.hospedales at ed.ac.uk. --- Timothy Hospedales Reader (Associate Professor) School of Informatics, University of Edinburgh http://mig.inf.ed.ac.uk/ -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From thomas.kleinbauer at lsv.uni-saarland.de Thu Sep 20 04:15:30 2018 From: thomas.kleinbauer at lsv.uni-saarland.de (Thomas Kleinbauer) Date: Thu, 20 Sep 2018 10:15:30 +0200 (CEST) Subject: Connectionists: PhD position and Post-doc position: Privacy-respecting dialog systems Message-ID: <453068483.185228.1537431330149.JavaMail.zimbra@lsv.uni-saarland.de> PhD position and Post-doc position: Privacy-respecting dialog systems ===================================================================== (Computational Linguistics, Computer Science or similar) Conversational interfaces based on deep learning are becoming more and more ubiquitous. However, the massive amounts of stored speech and text data that is needed for training state-of-the-art models raises serious privacy concerns for its users. Each spoken message may potentially reveal information about the user's personality, may contain critical information (credit card numbers, passwords, etc.), and may convey sensitive information (ethnicity, age, health status, etc.). Voice recordings may even be malevolently used to build synthesized voiced to impersonate users. The Spoken Language Systems group at Saarland University is seeking new ways to provide dialog technology that is "private by design" by means such as e.g. privacy-preserving machine learning. To this end, we are anticipating the availability of a PhD position and a Post-Doc position starting at the beginning of 2019. Ideal candidates for either position would have: 1. A good understanding of not just NLP, but of dialog phenomena in particular. Here, an understanding of how privacy-relevant information may arise as a result of dialog behavior (rather than as part of a single utterance) is desirable. 2. Excellent knowledge of machine learning, experience with weakly-supervised methods a plus. 3. Knowledge of and experience with scientific evaluation methodologies. 4. Excellent programming skills, experience with RESTful APIs a plus. 5. Experience with architecting large, heterogeneous, modular and distributed systems. 6. Knowledge of the European General Data Protection Regulation (GDPR) Salaries: The PhD position will be 75% of full time on the German E13 scale (TV-L). The Post-Doc position will be 100% of the full time on the German E13 scale (TV-L). The appointments will be for three years with possible extensions subject to follow-up funding. About the department: The department of Language Science and Technology is one of the leading departments in the speech and language area in Europe. The flagship project at the moment is the CRC on Information Density and Linguistic Encoding. Furthermore, the department is involved in the cluster of excellence Multimodal Computing and Interaction. It also runs a significant number of European and nationally funded projects. In total it has seven faculty and around 50 postdoctoral researchers and PhD students. How to apply: Please send us: * a letter of motivation, * your CV, * your transcripts, * a list of publications, * and the names and contact information of at least two references, as a single PDF or a link to a PDF if the file size is more than 3 MB. Please apply by October 10th, 2018. Contact: Applications and any further inquiries regarding the project should be directed to: * Thomas.Kleinbauer at lsv.uni-saarland.de * Dietrich.Klakow at lsv.uni-saarland.de From Alessandro.Gozzi at iit.it Thu Sep 20 02:18:05 2018 From: Alessandro.Gozzi at iit.it (Alessandro Gozzi) Date: Thu, 20 Sep 2018 06:18:05 +0000 Subject: Connectionists: Postdoctoral fellow - systems and computational neuroscience Message-ID: The Functional Neuroimaging Laboratory, at Istituto Italiano di Tecnologia, Rovereto, Italy, is seeking postdoctoral researchers interested in studying the neural basis of connectivity disruption in brain disorders. Our research, funded by the European Research Council (ERC - project "DisConn"), is aimed at identifying the general neural and cellular principles governing the assembly of spontaneous neural activity, and its breakdown in developmental disorders. We address these questions at the level of identified cell types by combining cutting-edge functional MRI methods with neural manipulations in the living mouse. This research sits at the intersection of computational neuroscience, neurobiology and neuroimaging. The successful candidate will have a PhD in neuroscience, biotechnology, computer science, physics, or equivalent. Training in experimental neuroscience is desirable, but not mandatory. The IIT center in Rovereto (http://cncs.iit.it/) is actively expanding its infrastructure and space for system-level neuroscience research. The center is inserted both in the vibrant community of the IIT (http://www.iit.it) and of the CIMeC center of the University of Trento (http://www.cimec.unitn.it), which specializes in cognitive neuroscience. Rovereto is conveniently located near Trento and Verona, two of the most important "Citta d'Arte" in Italy. The Trentino area is a region of Northern Italy nestled in the Dolomite Mountains, offering spectacular natural beauty, vibrant culture and exceptional quality of life. Please send your application (full CV, research statement, and names of 2 referees) by email to mailto:alessandro.gozzi at iit.it. Applications will be examined until the positions are filled. https://www.iit.it/careers/openings/opening/846-postdoctoral-positions-in-neuroimaging-and-circuit-physiology Alessandro Gozzi, PhD Senior Scientist, Group Leadel Functional Neuroimaging Laboratory Istituto Italiano di Tecnologia Center for Neuroscience and Cognitive Systems @ UNITN Corso Bettini 31, 38068 Rovereto, Italy Tel: +39 0464 808 701 -------------- next part -------------- An HTML attachment was scrubbed... URL: From zhaoping at gatsby.ucl.ac.uk Wed Sep 19 16:04:39 2018 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Wed, 19 Sep 2018 21:04:39 +0100 (BST) Subject: Connectionists: A mini-course (of video lectures) available on computational vision Message-ID: Dear colleagues, A mini-course (of introductory video lectures) on computational vision, based on the book "Understanding Vision: theory, models, and data" (Oxford University Press, 2014), is available at http://www0.cs.ucl.ac.uk/staff/Zhaoping.Li/VideoLectures_ForBook.html The lecture topics include: visual encoding, visual decoding, and visual attention. Feedback and comments welcome! Zhaoping -- Li Zhaoping Author of "Understanding Vision: theory, models, and data", Oxford University Press, 2014 http://www.cs.ucl.ac.uk/staff/Zhaoping.Li/VisionBook.html Moving from University College London to University of Tuebingen and Max Planck Institute of Biological Cybernetics on Oct. 1st, 2018 From axel.soto at cs.uns.edu.ar Thu Sep 20 13:52:43 2018 From: axel.soto at cs.uns.edu.ar (Axel Soto) Date: Thu, 20 Sep 2018 14:52:43 -0300 Subject: Connectionists: ACM Intelligent User Interfaces - IUI 2019: Last CFP (Oct 1st, Abstract due) Message-ID: *** ACM IUI 2019: Call for Papers *** Los Angeles, CA, USA March 17-20, 2019 http://iui.acm.org/2019/ ACM IUI 2019 is the 24rd annual meeting of the intelligent interfaces community and serves as a premier international forum for reporting outstanding research and development on intelligent user interfaces. ACM IUI is where the Human-Computer Interaction (HCI) community meets the Artificial Intelligence (AI) community, with contributions from related fields such as psychology, behavioral science, cognitive science, computer graphics, design, the arts, and more. Our focus is to improve the interaction between humans and machines, by leveraging both HCI approaches and state-of-the art AI techniques from machine learning, natural language processing, data mining, knowledge representation and reasoning. ACM IUI welcomes contribution from all relevant arenas: academia, industry, government, and non-profit organizations. Along with 25 other topics in AI & HCI, this year we especially encourage submissions on explainable intelligent user interfaces for IUI 2019. ** Dates ** Oct 1, 2018: Abstract deadline (compulsory) Oct 8, 2018: Papers deadline Dec 7, 2018: Notification Dec 21, 2018: Camera ready due Mar 17, 2019: Conference starts ** Why you should submit to ACM IUI ** At ACM IUI, we focus on the interaction between machine intelligence and human intelligence. While other conferences focus on one side or the other, we address the complex interaction between the two. We welcome research that explores how to make the interaction between computers and people smarter, which may leverage solutions from data mining, knowledge representation, novel interaction paradigms, and emerging technologies. We strongly encourage submissions that simultaneously discuss research from both HCI and AI. We also welcome works that focus more on one side or the other. The conference brings together people from academia, industry, government and non-profit organizations and gives its participants the opportunity to present and see cutting-edge IUI work in a focused and interactive setting. It is large enough to be diverse and lively, but small enough to allow for extensive interaction among attendees and easy attendance to the events that the conference offers, ranging from oral paper presentations, poster sessions, workshops, panels and doctoral consortium for graduate students. IUI topics of interest include, but are not limited to: - Affective and aesthetic interfaces - Big data and analytics - Collaborative interfaces - Education and learning-related technologies - Evaluations of intelligent user interfaces - Explainable intelligent user interfaces - Explainable artificial intelligence - Interactive visual analytics and interpretation for deep learning - Health and intelligent health technologies - Information retrieval and search - Intelligent assistants for complex tasks - Intelligent wearable and mobile interfaces - Intelligent ubiquitous user interfaces - Intelligent visualization tools - Interactive machine learning - Knowledge-based approaches to user interface design and generation - Modeling and prediction of user behavior - Multi-modal interfaces (speech, gestures, eye gaze, face, physiological information etc.) - Natural language and speech processing - Persuasive and assistive technologies in IUI - Planning and plan recognition for IUI - Proactive and agent-based user interaction - Recommender systems - Smart environments and tangible computing - Social media analysis - User Modelling for Intelligent Interfaces - User-Adaptive interaction and personalization ** Submission - Full and Short Papers ** We invite original paper submissions that describe novel user interfaces, applications, interactive and intelligent technologies, empirical studies, or design techniques. We do not require evaluations with users, but we do expect papers to include an appropriate evaluation for their stated contributions. Accepted papers will appear in the ACM Digital Library and citation indices. A selected set of accepted top quality full papers will be invited to submit their extended versions for publication in an ACM Transactions on Interactive Intelligent Systems (TiiS, http://tiis.acm.org) special issue titled "Highlights of IUI 2019". ** Submission Guidelines ** - Full paper (anonymized 10 pages, references do not count toward the page limit) should make substantial, novel, and relevant contribution to the field. - Short paper (anonymized 4 pages, references do not count toward the page limit) is a much more focused and succinct contribution to the field. Short papers are not expected to include a discussion of related work that is as broad and complete as that of Full papers. - Anonymization: ACM IUI uses a double-blind review process. All submissions must be appropriately anonymized according to the following guidelines: -- Author's names and affiliations are not visible anywhere in the paper. -- Acknowledgements should be anonymized or removed during the review process. -- Self-citations should be included where necessary, but must use the third person. For example, "... as shown in our previous user study [2] ... " is not allowed, whereas "... as shown in Smith et al. [2] " is acceptable (because in this case the citation [2] will NOT be perceived as self-citation). - Failure to follow these guidelines may result in submissions being rejected without review. - Authors should also be aware of the SIGCHI Policy for Submission and Review at SIGCHI Conferences, see: https://sigchi.org/about/sigchi-policies/conference-policies/submission-and-review/ - Submissions should follow the standard SigCHI format. Use either the Microsoft Word template (https://github.com/sigchi/Document-Formats/blob/master/Word/SIGCHIProceedingsFormat.docx) or the LaTeX template ( https://github.com/sigchi/Document-Formats/tree/master/LaTeX). Accepted full papers will be invited for oral presentation. Accepted short papers will be invited either as oral or poster presentation. ** AUTHORS TAKE NOTE ** The official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to two weeks prior to the first day of your conference. The official publication date affects the deadline for any patent filings related to published work. (For those rare conferences whose proceedings are published in the ACM Digital Library after the conference is over, the official publication date remains the first day of the conference.) ** Chairs - program-iui2019 at acm.org ** Oliver Brdiczka, Adobe, USA Ga?lle Calvary, Grenoble Institute of Technology, France Polo Chau, Georgia Tech, USA From george at cs.ucy.ac.cy Thu Sep 20 13:30:47 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Thu, 20 Sep 2018 20:30:47 +0300 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): First Call for Papers Message-ID: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> *** FIRST CALL FOR PAPERS *** 27th ACM International Conference on User Modeling, Adaptation and Personalization (ACM UMAP 2019) Golden Bay Beach Hotel 5*, Larnaca, Cyprus, June 9-12, 2019 https://www.um.org/umap2019/ Abstracts due: January 25, 2019 (mandatory) Papers due: February 1, 2019 BACKGROUND AND SCOPE ACM UMAP, "User Modeling, Adaptation and Personalization", is the premier international conference for researchers and practitioners working on systems that adapt to individual users, to groups of users, and that collect, represent, and model user information. ACM UMAP is sponsored by ACM SIGCHI and SIGWEB. The proceedings are published by ACM and will be part of the ACM Digital Library. ACM UMAP covers a wide variety of research areas where personalization and adaptation may be applied. This include (but is in no way limited to) a number of domains in which researchers are engendering significant innovations based on advances in user modeling and adaptation, recommender systems, adaptive educational systems, intelligent user interfaces, e-commerce, advertising, digital humanities, social networks, personalized health, entertainment, and many more. This year the conference hosts three new tracks, one on privacy and fairness, one on personalized music access, and one on personalized health. CONFERENCE TRACKS For details, see the conference website ( https://www.um.org/umap2019/ ). ? Track 1 - Personalized Recommender Systems ? Track 2 - Adaptive Hypermedia and the Semantic Web ? Track 3 - Intelligent User Interfaces ? Track 4 - Personalized Social Web ? Track 5 - Technology-Enhanced Adaptive Learning ? Track 6 - Privacy and Fairness ? Track 7 - Personalized Music Access ? Track 8 - Personalized Health SUBMISSION AND REVIEW PROCESS Papers have to be submitted through EasyChair: https://easychair.org/conferences/?conf=acmumap2019 Long (8 pages + references) and Short (4 pages + references) papers in ACM style, peer reviewed, original, and principled research papers addressing both the theory and practice of UMAP and papers showcasing innovative use of UMAP and exploring the benefits and challenges of applying UMAP technology in real-life applications and contexts are welcome. Long papers should present original reports of substantive new research techniques, findings, and applications of UMAP. They should place the work within the field and clearly indicate innovative aspects. Research procedures and technical methods should be presented in sufficient detail to ensure scrutiny and reproducibility. Results should be clearly communicated and implications of the contributions/findings for UMAP and beyond should be explicitly discussed. Short papers should present original and highly promising research or applications. Merit will be assessed in terms of originality and importance rather than maturity, extensive technical validation, and user studies. Papers must be formatted using the ACM SIG Standard (SIGCONF) proceedings template: https://www.acm.org/publications/proceedings-template . All accepted papers will be published by ACM and will be available via the ACM Digital Library. At least one author of each accepted paper must register for the conference and present the paper there. IMPORTANT DATES ? Abstracts: January 25, 2019 (mandatory) ? Full paper: February 1, 2019 ? Notification: March 11, 2019 ? Camera-ready: April 3, 2019 Note: The submission time is 11:59pm AoE time (Anywhere on Earth). GENERAL CHAIRS ? George A. Papadopoulos, University of Cyprus, Cyprus ? George Samaras, University of Cyprus, Cyprus ? Stephan Weibelzahl, PFH Private University of Applied Sciences, G?ttingen, Germany RELATED EVENTS Separate calls will be later sent for Workshops and Tutorials, Doctoral Consortium, Posters, Late Breaking Results and Theory, Opinion and Reflection works, as they have different deadlines and submission requirements. -------------- next part -------------- An HTML attachment was scrubbed... URL: From tomas.hromadka at gmail.com Thu Sep 20 19:06:26 2018 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Fri, 21 Sep 2018 01:06:26 +0200 Subject: Connectionists: COSYNE 2019: Meeting announcement and Call for workshop proposals Message-ID: <1cd1199f-44dd-989f-eb78-ea52041b7b0f@gmail.com> ==================================================== Computational and Systems Neuroscience 2019 (Cosyne) MAIN MEETING 28 February - 03 March 2019 Lisbon, Portugal WORKSHOPS 04 March - 05 March 2019 Cascais, Portugal 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 is 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 see below or 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: 09 October 2018 Abstract submission deadline: 15 November 2018 Workshop pre-proposal deadline: 30 September 2018 Workshop proposal deadline: 31 October 2018 COSYNE SPEAKERS Bruno Averbeck (NIMH) Gwyneth Card (Janelia) Kathleen Cullen (John Hopkins) Kenji Doya (OIST) Ken Harris (UCL) Sonja Hofer (Sainsbury Wellcome Centre) Yann LeCun (NYU) Edvard Moser (NTNU) Yiota Poirazi (IMBB-FORTH) Maneesh Sahani (Gatsby-UCL) Eric Shea-Brown (U Washington) Sara Solla (Northwestern) Karel Svoboda (Janelia) Ilana Witten (Princeton) 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: Linda Wilbrecht (Berkeley) and Brent Doiron (U Pittsburgh) Program Chairs: Eugenia Chiappe (Champalimaud) and Christian Machens (Champalimaud) Workshop Chairs: Catherine Hartley (NYU) and Ralf Haefner (U Rochester) Undergraduate Travel Chairs: Angela Langdon (Princeton) and Robert Wilson (U Arizona) Publicity Chair: Il Memming Park (Stony Brook) Development Chair: Michael Long (NYU) EXECUTIVE COMMITTEE Stephanie Palmer (U Chicago) Zachary Mainen (Champalimaud) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) CONTACT meeting [at] cosyne.org ----------------------------------------------------------------------- CALL FOR WORKSHOP PROPOSALS ----------------------------------------------------------------------- PRE-PROPOSAL DEADLINE: 30 September 2018 FULL PROPOSAL DEADLINE: 31 October 2018 PRE-PROPOSALS In an effort to coordinate submissions, the organizers are encouraged to submit a pre-proposal by *30 September 2018.* Pre-proposals will be shared among submitters. Pre-proposals are not mandatory, but are strongly encouraged. The organizers may submit the full proposal by its deadline. A series of workshops will be held after the main Cosyne meeting. The goal is to provide an informal forum for the discussion of important research questions and challenges. Controversial issues, open problems, comparisons of competing approaches, and alternative viewpoints are encouraged. The overarching goal of all workshops should be the integration of empirical and theoretical approaches, in an environment that fosters collegial discussion and debate. Preference will be given to proposals that differ substantially in content, scope, and/or approach from workshops of recent years (examples available at Cosyne.org -> Workshops). Relevant topics include, but are not limited to: sensory processing; motor planning and control; functional neural circuits; motivation, reward and decision making; learning and memory; adaptation and plasticity; neural coding; neural circuitry and network models; and methods in computational or systems neuroscience. In order to foster discussion within Workshops and reduce overlap between workshops, organizers should inform invited speakers that a single person should not speak in more than one of the Workshops taking place on the same day. WORKSHOP DETAILS - There will be 4-8 workshops/day, running in parallel. - Each workshop is expected to draw between 15 and 80 people. - The workshops will be split into morning (8.00-11.00 AM) and afternoon (4.30-7.30 PM) sessions. - Workshops will be held at Cascais, a coastal village ~34 km west of Lisbon. Buses from the main conference will be provided. SUBMISSION INSTRUCTIONS Submission instructions for workshop (pre)-proposals are available at Cosyne.org -> Workshops. PRE-PROPOSALS should include: - Name(s) and email address(es) of the organizers (no more than 2 organizers per session, please). The first author on the list becomes the contact author for the proposal. - A title. - A brief description of 1) what the workshop will address and accomplish, 2) why the topic is of interest, 3) who is the targeted group of participants. - Names, affiliations, and expected topics of talks of potential invitees, with indication of confirmed speakers. Preference will be given to workshops with the most confirmed speakers. - A brief summary of relevant prior experiences and publications of the organizers (about half a page total). - Proposed workshop length (1 or 2 days). Most workshops will be limited to a single day. If you think your workshop needs two days, please explain why. FULL PROPOSALS should include the list of confirmed speakers in addition to components required for a pre-proposal. Workshop organizer responsibilities include coordinating workshop participation and content, scheduling all speakers and submitting a final schedule for the workshop program, and moderating the discussion. Organizers can be speakers but need not speak depending on scheduling constraints. SUGGESTIONS Experience has shown that the best discussions during a workshop are those that arise spontaneously. A good way to foster these is to have short talks and long question periods (e.g. 30+15 minutes), and have plenty of breaks. We recommend fewer than 10 talks. When preparing pre-proposals and full proposals, the organizers are encouraged to: - address timeliness of workshop in the proposal: what new insights have been generated (new papers, data, techniques, whatever) over the past few years that make now the right time for discussing them and for presenting them to the wider community? - directly describe how speakers address the central topic, e.g. which are the big question(s), which speakers represent different viewpoints on the same question, which experimentalist addresses the theories addressed by which theoretician (and vice versa); - address controversies and bring together speakers from different ?camps? in the same field, or from different fields that---according to the organizers---should talk more to each other for whatever reason; WORKSHOP COSTS Detailed registration costs, etc, will be available at www.cosyne.org. Please note: Cosyne does NOT provide travel funding for workshop speakers. All workshop speakers are expected to pay for workshop registration fees. Participants are encouraged to register early, in order to qualify for discounted registration rates. One complementary (free) organizer registration is provided per workshop. For workshops with 2 organizers, the free registration can be given to one of the organizers or split evenly between them. COSYNE 2019 WORKSHOP CHAIRS Catherine Hartley (NYU) and Ralf Haefner (University of Rochester) QUESTIONS email: workshops [at] cosyne.org 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 christos.dimitrakakis at gmail.com Thu Sep 20 16:26:41 2018 From: christos.dimitrakakis at gmail.com (Christos Dimitrakakis) Date: Thu, 20 Sep 2018 22:26:41 +0200 Subject: Connectionists: PhD position in exploration in reinforcement learning and generative networks Message-ID: We are looking for a motivated PhD student to work on a challenging research project in adversarial neural networks and reinforcement learning. The main focus of the research will be on developing new generative deep learning models, such as generative adversarial networks (GAN) and variational autoencoders (VAE). We aim to develop novel approaches that are capable of producing in in a way that appropriately reflects underlying uncertainty. In reinforcement learning, generative models that incorporate uncertainty can enable efficient exploration of unknown environments without strong prior assumptions. Deadline: 15 Oct 2018 For more information: https://t.co/MoSCPcYse0 From max.garagnani at gmail.com Fri Sep 21 12:05:35 2018 From: max.garagnani at gmail.com (Max Garagnani) Date: Fri, 21 Sep 2018 17:05:35 +0100 Subject: Connectionists: MSc in Computational Cognitive Neuroscience -- now accepting 2019-20 applications Message-ID: <6F2230C2-2342-4901-87FD-271076F7B7FF@gmail.com> Please feel free to forward to any interested party. ///////////////////////////////////////////////////////////////////// The Departments of Computing and Psychology at Goldsmiths, University of London (UK) are pleased to announce the launch of a new MSc programme in Computational Cognitive Neuroscience (http://www.gold.ac.uk/pg/msc-computational-cognitive-neuroscience/) ///////////////////////////////////////////////////////////////////// * COURSE OUTLINE * ????????? This is a one-year Master degree programme, consisting of taught courses plus research project and dissertation. It is designed for students with a good degree in the biological / life sciences (psychology, neuroscience, biology, medicine, etc.) or physical sciences (computer science, mathematics, physics, engineering). The core contents include (i) fundamentals of cognitive neuroscience (cortical and subcortical mechanisms and structures underlying cognition and behaviour, plus experimental and neuroimaging techniques), and (ii) concepts and methods of computational modelling of biological neurons, simple neuronal circuits, and higher brain functions. Unlike many other computational neuroscience programmes, which focus predominantly on modelling ?low-level? aspects of brain function, one of the distinctive features of this course is that it includes the study of biologically-constrained models of ?higher? cognitive processes. * HOW TO APPLY * ????????? The program is now accepting students? applications for the 2019-20 intake. To fill in an application, simply click on the link below and follow the instructions: https://info.gold.ac.uk/OnlineServices/applications/appModuleList.aspx?id=128000142398953 We look forward to receiving your application! With very best wishes, Dr. Maria Herrojo-Ruiz (M.Herrojo-Ruiz at gold.ac.uk) Dr. Max Garagnani (M.Garagnani at gold.ac.uk) ----------------------------------------------------------------------------------------------- *********************************************************** -------------- next part -------------- An HTML attachment was scrubbed... URL: From has168 at eng.ucsd.edu Fri Sep 21 00:59:51 2018 From: has168 at eng.ucsd.edu (Hao Su) Date: Thu, 20 Sep 2018 21:59:51 -0700 Subject: Connectionists: Postdoctoral fellow in medical image analysis (UCSD) Message-ID: Postdoctoral position in Hamilton Glaucoma Center/Shiley Eye Institute/Computer Science SU Labs at UCSD in experiments on deep learning and Eye Diseases Diagnosis and Management. A postdoc position at the intersection of Deep Learning and Eye Diseases Diagnosis and Management is available working jointly with the labs of Professor Hao Su and Dr. Robert N. Weinreb at University of California, San Diego (UCSD). The team's goal is to develop advanced deep learning algorithms for screening and diagnosis of blindness eye diseases. The research project would also exploit theoretical and technical problems in artificial intelligence aroused from its application in Medicine. This is an opportunity to work on a challenging scientific problem in a highly interdisciplinary and vibrant environment. The postdoc will be affiliated with the Shiley Eye Institute and will get the opportunity to work with a team of researchers from various disciplines ranging from Computer Science/AI, Ophthalmology as well as clinicians from UCSD. Requirements: PhD in a related discipline (Computer Science/AI or Biomedical Engineering) with a strong experimental research record. Experience in deep learning algorithms developing and/or theoretical problem solving in the field of Artificial Intelligence. The labs are committed to the professional development of the members, making this position a valuable preparation for those interested in academic, industrial or entrepreneurial careers. The position has no mandatory teaching or administrative duties. The ideal start date is Nov or Dec 2018. The position is initially for 12 months with the possibility of renewal. Compensation will be commensurate with relevant experience. UCSD has competitive benefits (including comprehensive medical insurance) and is an equal opportunity employer. Candidates should send a CV, a statement of research experience and interests, expected date of availability, and the contact information for three references to haosu at ucsd.edu with the subject line "AI Postdoc". Application review will proceed until the position is filled. -- Hao Su Assistant Professor Department of Computer Science and Engineering Jacobs School of Engineering University of California, San Diego -------------- next part -------------- An HTML attachment was scrubbed... URL: From thomas_serre at brown.edu Thu Sep 20 20:33:18 2018 From: thomas_serre at brown.edu (Serre, Thomas) Date: Thu, 20 Sep 2018 20:33:18 -0400 Subject: Connectionists: Deep learning | RA position available at Brown U. Message-ID: The computational vision research group, headed by Dr. Thomas Serre at Brown University, has an opening for a research assistant and/or a postdoctoral fellow to work in the area of computer vision and deep learning. The applicant will have the opportunity to develop state-of-the-art machine vision algorithms and join various multi-disciplinary projects ranging from connectomics and evolutionary biology to behavioral and developmental science. Candidates are expected to have a strong background in modern computer vision and machine learning methods and a solid experience with modern deep learning libraries (tensorflow). An interest in biology and applications of computer vision to the biological sciences would also be a plus but is not a requirement for the position. The start date is negotiable though an early start is strongly preferred. Salary is commensurate with experience and is competitive. Research group: Information about Dr. Serre and his research group can be found at http://serre-lab.clps.brown.edu. Through Brown?s Center for Computation and Visualization (https://www.ccv.brown.edu), our group has access to a state-of-the-art computing facility which includes over 300K GPU cores and over 500 Teraflops of GPU computing power. Application: Please send your applications by email to thomas_serre at correct_university_name.edu where ?correct_university_name? should be replaced by ?brown?. Please include a brief statement of interests and a curriculum vita (no letters of reference required at this stage). There is no deadline for the application but applicants are encouraged to apply as soon as possible as the position will be filled as soon as a suitable applicant is found. -- Thomas Serre Carney Institute for Brain Science, Brown University Associate Professor, Dept of Cognitive Linguistic & Psychological Sciences Faculty Director, Center for Computation and Visualization T: +1(401) 484-0750 | Skype: thomas.serre | Gchat: thomas.serre at brown.edu Web: *http://serre-lab.clps.brown.edu * -------------- next part -------------- An HTML attachment was scrubbed... URL: From sergio.escalera.guerrero at gmail.com Mon Sep 24 03:14:55 2018 From: sergio.escalera.guerrero at gmail.com (Sergio Escalera) Date: Mon, 24 Sep 2018 09:14:55 +0200 Subject: Connectionists: Call for participation: NIPS 2018 competitions Message-ID: Call for participation: NIPS 2018 competitions, Several NIPS competitions are already running in different hot topics of NIPS. Best top ranked participants will be granted with several prizes, including the opportunity to register to NIPS 2018 workshops. Participants will be also invited to contribute with a book chapter to the NIPS 2018 Cup Springer book within the Series Challenges in Machine Learning: https://www.springer.com/series/15602 Details: https://nips.cc/Conferences/2018/CompetitionTrack Sergio Escalera and Ralf Herbrich NIPS 2018 Competition chairs -- *Dr. Sergio Escalera Guerrero*Head of Human Pose Recovery and Behavior Analysis Lab Project Manager at the Computer Vision Center Director of ChaLearn Challenges in Machine Learning Associate professor at University of Barcelona / Universitat Oberta de Catalunya / Aalborg Univ. / Dalhousie University Phone:+34934020853 Email: sergio.escalera.guerrero at gmail.com / Webpage: http://www.sergioescalera.com/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From caspar.schwiedrzik at googlemail.com Mon Sep 24 05:35:51 2018 From: caspar.schwiedrzik at googlemail.com (Caspar M. Schwiedrzik) Date: Mon, 24 Sep 2018 11:35:51 +0200 Subject: Connectionists: =?utf-8?q?PhD_in_visual_perceptual_learning_at_th?= =?utf-8?q?e_Neural_Circuits_and_Cognition_lab_=40_ENI_=26_German_P?= =?utf-8?q?rimate_Center_G=C3=B6ttingen?= Message-ID: The European Neuroscience Institute in G?ttingen (ENI-G) Germany, a partnership between the University Medical Center G?ttingen and the Max-Planck-Society, is seeking a *Ph.D. student * About us: The Neural Circuits and Cognition lab of Caspar Schwiedrzik at the European Neuroscience Institute (ENI-G) and the German Primate Center (DPZ) in G?ttingen, Germany is looking for an outstanding PhD student interested in studying the neural basis of perceptual learning in vision. The project investigates neural mechanisms of learning and perception at the level of circuits and single cells, utilizing functional magnetic resonance imaging (fMRI) in combination with electrophysiology and behavioral testing in humans and non-human primates. It is funded by an ERC Starting Grant (Acronym VarPL; ?Specificity or generalization? Neural mechanisms for perceptual learning with variability?). The PhD student?s project will focus on developing new perceptual learning paradigms and investigating the neural basis of perceptual learning in humans using fMRI. In addition, the PhD student will cooperate with other lab members on parallel electrophysiological and fMRI experiments as well as comparative research exploring the same questions in non-human primates. The lab seeks to understand the cortical basis and computational principles of perception and experience-dependent plasticity in the macaque and human brain (see http://www.eni-g.de/groups/neural-circuits-and-cognition). To this end, we use a multimodal approach including fMRI-guided electrophysiological recordings in non-human primates and fMRI and ECoG in humans. The PhD student will play a key role in our research efforts in this area. The lab is located at the ENI (http://www.eni-g.de) and the DPZ ( http://www.dpz.eu), which are interdisciplinary research centers with international faculty and students pursuing cutting-edge research in neuroscience. The PhD student will have access to a new imaging center with a dedicated 3T research scanner, electrophysiology, and behavioral setups. ENI-G is engaged in experimental molecular and cellular research on the central and peripheral nervous systems as well as cognitive and systems neurosciences research. ENI is part of the University Medical Center G?ttingen and associated with the Max Planck Society. The University Medical Center G?ttingen is a tertiary care center. Its 7,400 employees work in over 65 departments and facilities to provide top-quality patient care, excellent research and modern teaching facilities. G?ttingen provides a vibrant and stimulating neuroscience community with a strong background in computational as well as experimental neurosciences. The PhD student will have the opportunity to join one of the fourteen programs of the G?ttingen Graduate School for Neurosciences, Biophysics, and Molecular Biosciences (http://www.ggnb.uni-goettingen.de). Your profile: The position will be available starting in November 2018 with an initial appointment for 3 years and a salary according to 50% TVL-13. Candidates should have a degree (master, diploma or equivalent) in a relevant field (e.g., neuroscience, psychology, biology), and ideally prior experience in fMRI, strong quantitative, programming, and experimental skills, and share a passion for understanding the neural basis of visual perception and its plasticity. Interested candidates should send their curriculum vitae, a description of their scientific interest and the names and contact information of up to two references who are able to comment on your academic background and who agreed to be contacted to c.schwiedrzik at eni-g.de, preferably before October 10th, 2018, but later expressions of interest will be considered until the position is filled. A good command of English is a requirement, but fluency in German is not essential. Please apply by 10.10.2018 to: Universit?tsmedizin G?ttingen European Neuroscience Institute G?ttingen Neural Circuits and Cognition Lab Dr. Caspar Schwiedrzik Grisebachstr. 5 37077 G?ttingen Germany Tel.: +49-(0)551-39-61371 E-Mail: c.schwiedrzik at eni-g.de -------------- next part -------------- An HTML attachment was scrubbed... URL: From jbaimon at sandia.gov Mon Sep 24 11:03:05 2018 From: jbaimon at sandia.gov (Aimone, James Bradley) Date: Mon, 24 Sep 2018 15:03:05 +0000 Subject: Connectionists: Neuro-Inspired Computational Elements (NICE) 2019 Abstract Submission Open! Message-ID: Dear Colleagues: The call for abstracts for NICE 2019 is open for submissions at https://easychair.org/cfp/NICE2019 As with past NICE workshops, we are seeking submissions describing advances at the intersection of theoretical neuroscience, neural computing hardware and algorithms, and applications of this brain-inspired computing technology. Preference will be given to unpublished results that bridge our community. For agendas and videos of talks from past meetings, please see http://niceworkshop.org Submissions are 2 page extended abstracts, which will be reviewed to select full and short talks, as well as posters. New for NICE this year we are looking at potential options for proceedings papers, to be invited from the top submissions this year. Abstracts are due on November 15th. Registration will open in a few weeks. ---------------- NICE 2019 will be taking place during March 26-29, 2019 in Albany CNSE Campus in Albany, NY Important dates: Abstract call: September 15, 2018 Abstract submission open: September 22, 2018 Abstracts due: November 15, 2018 Selection announcement: January 15, 2019 ----------------- Hope to see you in Albany! Brad Aimone NICE Program Chair -------------------------- James Bradley Aimone, Ph.D. Principal Member of Technical Staff Data-driven and Neural Computing Department Center for Computing Research Sandia National Laboratories Phone: (505) 284-3147 Fax: (505) 844-4728 http://neuroscience.sandia.gov -------------- next part -------------- An HTML attachment was scrubbed... URL: From thang.buivn at gmail.com Mon Sep 24 18:56:08 2018 From: thang.buivn at gmail.com (Thang Bui) Date: Tue, 25 Sep 2018 08:56:08 +1000 Subject: Connectionists: Registration is open and 2nd CFP: 1st Symposium on Advances in Approximate Bayesian Inference (AABI 2018) Message-ID: We invite researchers in machine learning and statistics to participate in the: 1st Symposium on Advances in Approximate Bayesian Inference Sunday, December 2, 2018 Le 1000 Conference Center 1000 Rue de la Gaucheti?re Ouest Montr?al, QC H3B 0A2, Canada www.approximateinference.org Submission deadline: *19 October 2018* *1. Registration* Registration is now open: https://www.eventbrite.ca/e/1st-symposium-on-advances-in-approximate-bayesian-inference-aabi-2018-tickets-50291872344 Registration is free but will be limited. More slots may become available as we free up the reserved slots for authors of the accepted papers. If you are unable to register, feel free to sign up on the waiting list. We will contact you if more slots become available. *2. Call for Participation* We invite researchers to submit their recent work on the development, analysis, or application of approximate Bayesian inference. A submission should take the form of an extended abstract of 2-4 pages in PDF format using the PMLR one-column style [ http://approximateinference.org/pmlr/aabi_template.zip ]. For questions and troubleshooting, visit CTAN [ https://ctan.org/tex-archive/macros/latex/contrib/jmlr ]. Author names do not need to be anonymized and references may extend as far as needed beyond the 4 page upper limit. If authors' research has previously appeared in a journal, workshop, or conference (including the NIPS 2018 conference), their symposium submission should extend that previous work. Submissions may include a supplement/appendix, but reviewers are not responsible for reading any supplementary material. All submissions will be reviewed by at least three reviewers from the field. Accepted submissions will be accepted for presentation only. The authors of selected submissions will be invited to publish their paper in a PMLR volume. We aim to keep a general inclusive nature of the symposium for presentations. However, we will only invite the top-rated accepted papers to be published through PMLR. Papers should be submitted by 19 October through easychair [ https://easychair.org/conferences/?conf=aabi2018 ]. Final versions of the symposium submissions are due by 1 December and will be posted on the symposium website. If you have any questions, please contact us at aabisymposium2018 at gmail.com. *3. Symposium Overview* Probabilistic modeling is a useful tool to analyze and understand real-world data. Central to the success of Bayesian modeling is posterior inference, for which approximate inference algorithms are typically needed in most problems of interest. The two pillars of approximate Bayesian inference are variational and Monte Carlo methods. In the recent years, there have been numerous advances in both methods, which have enabled Bayesian inference in increasingly challenging scenarios involving complex probabilistic models and large datasets. In this symposium, besides recent advances in approximate inference, we will discuss the impact of Bayesian inference, connecting approximate inference methods with other fields. In particular, we encourage submissions that relate Bayesian inference to the fields of reinforcement learning, causal inference, decision processes, Bayesiancompression, or differential privacy, among others. We also encourage submissions that contribute to connecting different approximate inference methods, such as variational inference and Monte Carlo. This symposium can be seen as a continuation of previous workshops at NIPS: + NIPS 2017 Workshop: Advances in Approximate Bayesian Inference + NIPS 2016 Workshop: Advances in Approximate Bayesian Inference + NIPS 2015 Workshop: Advances in Approximate Bayesian Inference + NIPS 2014 Workshop: Advances in Variational Inference *4. Key Dates* Paper submission: *19 October 2018 (11:55pm GMT)* Acceptance notification: 13 November 2018 Final paper submission: 1 December 2018 Symposium organizers: Cheng Zhang (Microsoft Research) Dawen Liang (Netflix) Francisco Ruiz (University of Cambridge / Columbia University) Thang Bui (University of Sydney) Advisory committee: Christian Robert (Universit? Paris Dauphine / University of Warwick) David Blei (Columbia University) Dustin Tran (Google Brain / Columbia University) James McInerney (Spotify) Stephan Mandt (Disney Research) -------------- next part -------------- An HTML attachment was scrubbed... URL: From luigi.malago at gmail.com Mon Sep 24 13:45:51 2018 From: luigi.malago at gmail.com (=?UTF-8?Q?Luigi_Malag=C3=B2?=) Date: Mon, 24 Sep 2018 20:45:51 +0300 Subject: Connectionists: Postdoc position in Geometric Methods for Machine Learning and Deep Learning at RIST Message-ID: =========================================================== *Subject*: Postdoc position in Machine Learning (1 year, renewable up to 2 years) *Institution*: RIST - Romanian Institute of Science and Technology, Cluj-Napoca *Keywords*: Geometry of Latent Spaces, Optimization over Manifolds, Information Geometry, Natural Gradient, Riemannian Geometry *Application deadline*: 10 October 2018 (applicants are encouraged to apply earlier) *Salary*: around 2200 euro net *Official announcement*: http://rist.ro/en/details/news/postdoc-positions-in-deep-learning-and-machine-learning.html =========================================================== Dear colleagues, the Romanian Institute of Science and Technology (RIST) has an opening for a postdoc position, in the context of the DeepRiemann project ?Riemannian Optimization Methods for Deep Learning?, funded by European structural funds through the Competitiveness Operational Program (POC 2014-2020). The appointments will be for 1 year, with possible extensions up to 2 years. The DeepRiemann project aims at the design and analysis of novel training algorithms for Neural Networks in Deep Learning, by applying notions of Riemannian optimization and differential geometry. The task of the training a Neural Network is studied by employing tools from Optimization over Manifolds and Information Geometry, by casting the learning process to an optimization problem defined over a statistical manifold, i.e., a set of probability distributions. The project is highly interdisciplinary, with competences spanning from Machine Learning to Optimization, Deep Learning, Statistics, and Differential Geometry. The objectives of the project are multiple and include both theoretical and applied research, together with industrial activities oriented to transfer knowledge, from the institute to a startup or spin-off of the research group. The positions will be part of the new Machine Learning and Optimization group https://rist.ro/en/teams.html, which performs research at the intersection of Machine Learning, Stochastic Optimization, Deep Learning, and Optimization over Manifolds, using geometric methods based on Information Geometry. The group is one of two newly-formed groups in Machine Learning at RIST. The official job announcement can be seen here: http://rist.ro/en/details/news/postdoc-positions-in-deep-learning-and-machine-learning.html Informal inquiries can be sent to Dr. Luigi Malag? , principal investigator of the DeepRiemann project. Application deadline: 10 October 2018 (applicants are encouraged to apply earlier) best regards, Luigi Malag? -------------- next part -------------- An HTML attachment was scrubbed... URL: From ted.carnevale at yale.edu Mon Sep 24 16:49:55 2018 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 24 Sep 2018 16:49:55 -0400 Subject: Connectionists: Workshop: High Performance Computing in Neuroscience Message-ID: <04dab6fd-3ac6-7b0a-260f-a10b643c2faf@yale.edu> Does your research involve computationally intensive tasks such as large scale modeling or data analysis? Come to the workshop on High Performance Computing Resources for Parallel Simulations and Data Analysis: NSG and HPAC to share your experience with others who are dealing with similar challenges, and learn about resources that are currently available and/or being developed that may help accelerate your own research. This workshop will be held on Saturday, Nov. 3 from 8:30 AM to 12:30 PM at a location in downtown San Diego. Space is limited, and the registration deadline is Friday, Oct. 12, so you should act early. For the on-line registration form see https://neuron.yale.edu/neuron/static/courses/nsg2018/nsg2018.html The workshop will include a combination of short presentations and discussions. Confirmed speakers and topics include: "The Neuroscience Gateway" Amit Majumdar, Subhashini Sivagnanam, Kenneth Yoshimoto, Ted Carnevale "Research Activities at the Human Brain Project's High Performance Analytics and Computing Platform" Alexander Peyser "Human Neocortical Neurosolver: A New Modeling Platform for Cellular and Circuit Level Interpretation of EEG/MEG" Samuel A Neymotin, Dylan S Daniels, Noam Peled, Robert A McDougal, Ted Carnevale, Christopher I Moore, Michael L Hines, Matti Hamalainen, Stephanie R Jones "Towards a Complete Description of the Hippocampal Circuitry Underlying Sharp Wave-Mediated Memory Replay" Ivan Soltesz "Neuroanatomical models beyond the spatial resolution of MRI require HPC: The Big Brain and fiber tracts" Karl Zilles, Nicola Palomero-Gallagher and Katrin Amunts "The Virtual Brain: personalized large-scale brain network modeling and its applications" Viktor Jirsa From michel.verleysen at uclouvain.be Tue Sep 25 06:33:54 2018 From: michel.verleysen at uclouvain.be (Michel Verleysen) Date: Tue, 25 Sep 2018 10:33:54 +0000 Subject: Connectionists: ESANN 2019 call for papers Message-ID: ESANN 2019 - 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges, Belgium, 24-25-26 April 2019 http://www.esann.org/ Call for papers The call for papers is available at http://www.esann.org/. Deadline for submissions: November 19, 2018. 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: - Streaming data analysis, concept drift and analysis of dynamic data sets - Embeddings and Representation Learning for Structured Data - Parallel and Distributed Machine Learning: Theory and Applications - Societal Issues in Machine Learning: When Learning from Data is Not Enough - Reliable Machine Learning - Statistical physics of learning and inference - 60 Years of Weightless Neural Systems ESANN 2019 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 2019 and to see you in Bruges next year! [http://www.uclouvain.be/cps/ucl/doc/ac-arec/images/logo-signature.png] Michel Verleysen Professor ICTEAM institute Place du Levant, 3 box L5.03.02 B-1348-Louvain-la-Neuve michel.verleysen at uclouvain.be T?l. +32 10 47 25 51 - Fax +32 10 47 25 98 perso.uclouvain.be/michel.verleysen [cid:BA0CEBA4-4F7E-4ACE-8F18-A922077AB127 at ast.ucl.ac.be] Michel Verleysen Professor Louvain School of Engineering (EPL) ICTEAM institute Place du Levant, 3 box L5.03.02 B-1348-Louvain-la-Neuve michel.verleysen at uclouvain.be T?l. +32 10 47 25 51 - Fax +32 10 47 25 98 perso.uclouvain.be/michel.verleysen -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 3010 bytes Desc: image001.png URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image002.jpg Type: image/jpeg Size: 24337 bytes Desc: image002.jpg URL: From kripa.ghosh at gmail.com Tue Sep 25 12:31:09 2018 From: kripa.ghosh at gmail.com (Kripa Ghosh) Date: Tue, 25 Sep 2018 22:01:09 +0530 Subject: Connectionists: [CFP] CIKM 2018 Workshop on Legal Data Analytics and Mining (LeDAM 2018) Message-ID: [apologies for cross-posting ] CALL FOR PARTICIPATION Workshop on Legal Data Analytics and Mining (LeDAM 2018) In conjunction with ACM International Conference on Information and Knowledge Management (CIKM) 2018 Turin, Italy | 22nd October 2018 Website : https://sites.google.com/site/legaldam2018/ Legal data mining is the subarea of data mining applied to legal texts, such as legislation, case law, patents, and scholarly works. Legal data mining systems are key to providing easier access to law for both common persons and legal professionals. This area is becoming increasingly important, because of the rapidly growing volume of legal cases and documents available in digital formats. The broad goals of the LeDAM workshop are: -- to promote research in legal data analytics by fostering collaboration between the legal data mining practitioners and the data mining research community at large, -- to improve awareness among the legal community about the state of the art models, techniques and algorithms developed by the data mining community that can potentially benefit the problems, and -- to identify new research opportunities in data mining that arise from legal applications. ============= INVITED TALKS ============= Speaker: Giovanni Sartor, Professor of Legal Informatics and Legal Theory, European University Institute, Italy Title: Using Machine Learning to Support Law Enforcement to the Benefit of Consumers and Data Subject: the CLAUDETTE Project Abstract: The project CLAUDETTE aims to support the detection of potentially unfair and unlawful clause, both in consumer contacts and in privacy policies, through automated tools, based on computational linguistic and artificial intelligence. The purpose is to enable consumer protection bodies and data protection authorities to engage more proactively and effectively in monitoring compliance and in enforcing the law. With regard to both contract terms and privacy policy we have collected a corpus of contract terms, identified different kinds of unlawful and unfair terms through legal analysis, and annotated the documents accordingly. Then we have applied and tested different computational approaches, including various machine learning algorithms, to detect such terms. The better performing algorithms have been implemented in an application available to the public through the project's website. The system is complemented by a crawler, that detects changes in the contract and policies already submitted to the system. ***** Speaker: Luigi Di Caro, Assistant Professor, Department of Computer Science, University of Turin, Italy Title: Natural Language Processing and Ontology Learning in the Legal Domain Abstract: Legal ontologies aim to provide a structured representation of legal concepts and their interconnections. These ontologies are then exploited to support tasks such as information extraction and question answering in the legal domain. Given the increasing importance of the Web of Data in public administration and in companies, being able to provide machine-readable legal information is becoming a valuable and desired contribution. However, concepts and relations within existing ontologies usually represent limited subjective and application-oriented views of specific sub-domains of interest. The talk will discuss recent research on natural language technologies and text mining approaches towards the creation, the reuse and the enrichment of legal ontologies. ***** Speaker: Jack G. Conrad, Lead Research Scientist, Center for AI and Cognitive Computing, Thomson Reuters, USA Title: 30 Years of AI and Law: Legal Data Analytics in the Long View -- Looking Back, Looking Forward Abstract: This talk will begin by examining the roots of Artificial Intelligence and Law -- including applications involving NLP, data mining, machine learning, and more broadly, data analytics -- noting that it has been around for much longer than the recent buzz would suggest. We will explore the field of AI and Law in terms of its development and expansion starting in the 1980s and study how seminal research was conducted and reported on in conference proceedings such as ICAIL and publications such as the AI and Law journal. After having established the foundations of today's field of AI and Law, we will look to the future and sketch some of the practical application scenarios that the capabilities from the field promise to deliver. These include next-generation tools for legal professionals that can augment their skill sets by providing analytical abilities to help in the crafting of legal strategies. We will illustrate such instruments through the visualization of expected outcomes, while varying key parameters such as trial length, expected costs, and likely award or settlement figures. Lastly, we will investigate the prospective role that prediction tools can play in AI and Law application spaces, while looking still further into the future. ==================== PAPER PRESENTATIONS ==================== Structural Analysis of Contract Renewals Frieda Josi and Christian Wartena (University of Applied Sciences and Arts Hanover, Germany) Concept Hierarchy Extraction from Legal Literature Sabine Wehnert, David Broneske, Stefan Langer and Gunter Saake (Otto von Guericke University and Legal Horizon AG, Germany) Use of Pseudo Relevance Feedback for Patent Clustering with Fuzzy C-means Noushin Fadaei and Thomas Mandl (Hildesheim University, Germany) Argumentation-driven information extraction for online crime reports Marijn Schraagen, Bas Testerink, Daphne Odekerken and Floris Bex (Utrecht University, The Netherlands, and Dutch National Police) Deep Ensemble Learning for Legal Query Understanding Arunprasath Shankar and Venkata Nagaraju Buddarapu (LexisNexis, USA) ================= Organizing Committee ================= Arindam Pal, TCS Research and Innovation, India ( http://www.cse.iitd.ernet.in/~arindamp/) Arnab Bhattacharya, Indian Institute of Technology Kanpur, India ( https://www.cse.iitk.ac.in/users/arnabb/) Indrajit Bhattacharya, TCS Research and Innovation, India ( https://sites.google.com/site/indrajitb/) Kripabandhu Ghosh, Indian Institute of Technology Kanpur, India ( https://www.cse.iitk.ac.in/users/kripa/) Lipika Dey, TCS Research and Innovation, India ( http://sites.tcs.com/blogs/research-and-innovation/author/dr-lipika-dey) Marie-Francine Moens, KU Leuven, Belgium ( https://people.cs.kuleuven.be/~sien.moens/) Saptarshi Ghosh, Indian Institute of Technology Kharagpur, India ( http://cse.iitkgp.ac.in/~sghosh/) For details, see https://sites.google.com/site/legaldam2018/ Kind Regards, *Kripabandhu Ghosh * Co-organizer LeDAM 2018 Workshop CIKM 2018 -------------- next part -------------- An HTML attachment was scrubbed... URL: From msn2018 at mail.neu.edu.cn Wed Sep 26 02:47:47 2018 From: msn2018 at mail.neu.edu.cn (MSN2018) Date: Wed, 26 Sep 2018 14:47:47 +0800 (GMT+08:00) Subject: Connectionists: CFP: Mobile Ad-hoc and Sensor Networks 2018 Message-ID: <255d4e4b.1250a.16614a23923.Coremail.msn2018@mail.neu.edu.cn> Apologies for any cross posting 14th Int. Conference on Mobile Ad-hoc and Sensor Networks Shenyang, China Dec. 6- 8, 2018 http://conf.neu.edu.cn/msn2018 You are cordially invited to submit your contribution until September 15, 2018 September 30, 2018. Final manuscripts should be prepared according to IEEE Computer Society Proceedings Format (double column, 10pt font) and submitted via the EasyChair system in PDF file format. The manuscript should be no longer than 6 pages. Up to two additional pages are permitted if the authors are willing to pay an over-length charge at the time of publication (manuscripts should not exceed 8 pages in total). Final manuscripts should not be previously published in or be under consideration for publication in another conference or journal. To submit your contribution visits the submission page (https://easychair.org/conferences/?conf=msn2018). ? Papers will be included in the conference proceedings edited by IEEE ? Extended versions will be invited for publication in special issues of international journals: o IEEE Transactions on Industrial Informatics edited by IEEE o IET Networks edited by IET o IEEE Wireless Communications edited by IEEE o Sensors edited by MDPI Topics include, but are not limited to: o Ad Hoc Networks o Vehicular Networks o Intelligent Sensor Networks o Urban Computing o Internet of Things o Edge and Fog Computing/Networking o 5G networks o Cognitive Radio Networks o Mobile Social Networks o Mobile Crowdsensing and Computing o Smart Networks o Knowledge Centric Networks o Delay Tolerant and Opportunistic Networking o Network Security and Privacy o Artificial Intelligence for Networking and Communications o Novel Applications and Architecture Steering Committee Co-Chairs Xiaohua Jia, City University of Hong Kong Jiannong Cao, Hong Kong Polytechnic University General Co-Chairs Xingwei Wang, Northeastern University, China Vincenzo Piuri, University of Milan, Italy TPC Co-Chairs Ruiyun Yu, Northeastern University, China Hongyi Wu, Old Dominion University, USA Dieter Hogrefe, University of Goettingen, Germany Publication Chair Guangtao Xue, Shanghai Jiao Tong University, China Xu Yuan, University of Louisiana at Lafayette, USA Yuanguo Bi, Northeastern University, China Yuan Liu, Northeastern University, China Publicity Chair Guangjie Han, Dalian University of Technology, China Cong Wang, Old Dominion University, USA Jie Jia, Northeastern University, China Jie Li, Northeastern University, China Yang Liu, Beijing University of Posts and Telecommunications, China Financial Chair Lianbo Ma, Northeastern University, China Local arrangement Chair Zhenhua Tan, Northeastern University, China Web Chair Yu Wang, Northeastern University, China -------------- next part -------------- An HTML attachment was scrubbed... URL: From j.v.stone at sheffield.ac.uk Thu Sep 27 13:23:12 2018 From: j.v.stone at sheffield.ac.uk (James V Stone) Date: Thu, 27 Sep 2018 18:23:12 +0100 Subject: Connectionists: New ebook: Neural Information Theory Message-ID: <1a038d55-0ec5-d93e-6509-2780cc8f84b7@sheffield.ac.uk> This book (published June 2018) is now available in Kindle and pdf formats: Principles of Neural Information Theory: Computational Neuroscience and Metabolic Efficiency by James V Stone. Reviews, synopsis, and table of contents can be found here: http://sebtelpress.com "To understand life, one has to understand not just the flow of energy, but also the flow of information." William Bialek, 2012. regards, Dr James V Stone Honorary Reader, Sheffield University, UK. Web: sebtelpress.com Twitter: @jgvfwstone From barros at informatik.uni-hamburg.de Wed Sep 26 10:18:00 2018 From: barros at informatik.uni-hamburg.de (Pablo Barros) Date: Wed, 26 Sep 2018 16:18:00 +0200 Subject: Connectionists: The OMG-Empathy Prediction Challenge Message-ID: <09c912b5-e030-f234-55fc-55a5eda82786@informatik.uni-hamburg.de> CALL FOR PARTICIPATION The One-Minute Gradual-Empathy Prediction (OMG-Empathy) Competition held in partnership with the IEEE International Conference on Automatic Face and Gesture Recognition 2019 in Lille, France. https://www2.informatik.uni-hamburg.de/wtm/omgchallenges/omg_empathy.html I. Aim and Scope The ability to perceive, understand and respond to social interactions in a human-like manner is one of the most desired capabilities in artificial agents, particularly social robots. These skills are highly complex and require a focus on several different aspects of research, including affective understanding. An agent which is able to recognize, understand and, most importantly, adapt to different human affective behaviors can increase its own social capabilities by being able to interact and communicate in a natural way. Emotional expression perception and categorization are extremely popular in the affective computing community. However, the inclusion of emotions in the decision-making process of an agent is not considered in most of the research in this field. To treat emotion expressions as the final goal, although necessary, reduces the usability of such solutions in more complex scenarios. To create a general affective model to be used as a modulator for learning different cognitive tasks, such as modeling intrinsic motivation, creativity, dialog processing, grounded learning, and human-level communication, only emotion perception cannot be the pivotal focus. The integration of perception with intrinsic concepts of emotional understanding, such as a dynamic and evolving mood and affective memory, is required to model the necessary complexity of an interaction and realize adaptability in an agent's social behavior. Such models are most necessary for the development of real-world social systems, which would communicate and interact with humans in a natural way on a day-to-day basis. This could become the next goal for research on Human-Robot Interaction (HRI) and could be an essential part of the next generation of social robots. For this challenge, we designed, collected and annotated a novel corpus based on human-human interaction. This novel corpus builds on top of the experience we gathered while organizing the OMG-Emotion Recognition Challenge, making use of state-of-the-art frameworks for data collection and annotation. The One-Minute Gradual Empathy datasets (OMG-Empathy) contain multi-modal recordings of different individuals discussing predefined topics. One of them, the actor, shares a story about themselves while the other, the listener, reacts to it emotionally. We annotated each interaction based on the listener's own assessment of how they felt while the interaction was taking place. We encourage the participants to propose state-of-the-art solutions not only based on deep, recurrent and self-organizing neural networks but also traditional methods for feature representation and data processing. We also enforce that the use of contextual information, as well as personalized solutions for empathy assessment, will be extremely important for the development of competitive solutions. II. Competition Tracks We let available for the challenge a pre-defined set of training, validation and testing samples. We separate our samples based on each story: 4 stories for training, 1 for validation and 3 for testing. Each story sample is composed of 10 videos with interactions, one for each listener. Although using the same training, validation and testing data split, we propose two tracks which will measure different aspects of the self-assessed empathy: The Personalized Empathy track, where each team must predict the empathy of a specific person. We will evaluate the ability of proposed models to learn the empathic behavior of each of the subjects over a newly perceived story. We encourage the teams to develop models which take into consideration the individual behavior of each subject in the training data. The Generalized Empathy track, where the teams must predict the general behavior of all the participants over each story. We will measure the performance of the proposed models to learn a general empathic measure for each of the stories individually. We encourage the proposed models to take into consideration the aggregated behavior of all the participants for each story and to generalize this behavior in a newly perceived story. The training and validation samples will be given to the participants at the beginning of the challenge together with all the associated labels. The test set will be given to the participants without the associated labels. The team`s predictions on the test set will be used to calculate the final metrics of the challenge. III. How to Participate To participate to the challenge, please send us an email to barros @ informatik.uni-hamburg.de with the title "OMG-Empathy Team Registration". This e-mail must contain the following information: Team Name Team Members Affiliation Participating tracks We split the corpus into three subsets: training, validation and testing. The participants will receive the training and validation sets, together with the associated annotations once they subscribe to the challenge. The subscription will be done via e-mail. Each participant team must consist of 1 to 5 participants and must agree to use the data only for scientific purposes. Each team can choose to take part in one or both the tracks. After the training period is over, the testing set will be released without the associated annotations. Each team must submit, via e-mail, their final predictions as a .csv file for each video on the test set. Together with the final submission, each team must send a short 2-4 pages paper describing their solution published on Arxiv and the link for a github page to their solution. If a team fails to submit any of these items, their submission will be invalidated. Each team can submit 3 complete submissions for each track. IV. Important Dates 25th of September 2018 - Opening of the Challenge - Team registrations begin 1st of October 2018 - Training/validation data and annotation available 1st of December 2018 - Test data release 3rd of December 2018 - Final submission (Results and code) 5th of December 2018 - Final submission (Paper) 7th of December 2018 - Announcement of the winners V. Organization Pablo Barros, University of Hamburg, Germany Nikhil Churamani, University of Cambridge, United Kingdom Angelica Lim, Simon Fraser University, Canada Stefan Wermter, Hamburg University, Germany -- Dr.rer.nat. Pablo Barros Postdoctoral Research Associate - Crossmodal Learning Project (CML) Knowledge Technology Department of Informatics University of Hamburg Vogt-Koelln-Str. 30 22527 Hamburg, Germany Phone: +49 40 42883 2535 Fax: +49 40 42883 2515 barros at informatik.uni-hamburg.de https://www.inf.uni-hamburg.de/en/inst/ab/wtm/people/barros.html https://www.inf.uni-hamburg.de/en/inst/ab/wtm/ From royf at berkeley.edu Thu Sep 27 02:03:33 2018 From: royf at berkeley.edu (Roy Fox) Date: Wed, 26 Sep 2018 23:03:33 -0700 Subject: Connectionists: =?utf-8?q?NIPS_2018_Workshop_=E2=80=94_Infer2Cont?= =?utf-8?q?rol_=E2=80=94_Call_for_Papers?= Message-ID: We invite all researchers to submit their manuscripts for review. **************************************************************************************************** > Infer to Control: Probabilistic Reinforcement Learning and Structured Control > NIPS 2018 Workshop > Saturday, December 8 > Montr?al, Canada > Website: https://sites.google.com/view/infer2control-nips2018 > Please address questions to: infer2control.nips2018 at gmail.com **************************************************************************************************** Reinforcement learning and imitation learning are effective paradigms for learning controllers of dynamical systems from experience. These fields have been empowered by recent success in deep learning of differentiable parametric models, allowing end-to-end training of highly nonlinear controllers that encompass perception, memory, prediction, and decision making. The aptitude of these models to represent latent dynamics, high-level goals, and long-term outcomes is unfortunately curbed by the poor sample complexity of many current algorithms for learning these models from experience. Probabilistic reinforcement learning and inference of control structure are emerging as promising approaches for avoiding prohibitive amounts of controller?system interactions. These methods leverage informative priors on useful behavior, as well as controller structure, such as hierarchy and modularity, as useful inductive biases that reduce the effective size of policy search space and shape the optimization landscape. Intrinsic and self-supervised signals can further guide the training process of distinct internal components?such as perceptual embeddings, predictive models, exploration policies, and inter-agent communication?to break down the hard holistic problem of control into more efficiently learnable parts. Effective inference methods are crucial for probabilistic approaches to reinforcement learning and structured control. Approximate control and model-free reinforcement learning exploit latent system structure and priors on policy structure, that are not directly evident in the controller?system interactions, and must be inferred by the learning algorithm. The growing interest of the reinforcement learning and optimal control community in the application of inference methods is synchronized well with the development by the probabilistic learning community of powerful inference techniques, such as probabilistic programming, variational inference, Gaussian processes, and nonparametric regression. This workshop is a venue for the inference and reinforcement learning communities to come together in discussing recent advances, developing insights, and future potential in inference methods and their application to probabilistic reinforcement learning and structured control. The goal of this workshop is to catalyze tighter collaboration within and between the communities, that will be leveraged in upcoming years to rise to the challenges of real-world control problems. #### IMPORTANT DATES: #### - Submission deadline: Friday, October 5, 2018 (Anywhere on Earth) - Author notification: Monday, October 22, 2018 - Final version deadline: Friday, November 30, 2018 - Workshop: Saturday, December 8, 2018 #### SUBMISSION DETAILS: #### - Research papers are solicited on inference for reinforcement learning and control, its theory and applications, and related fields. - Contributed papers may include novel research, preliminary results, or surveys of recent results. - Papers are limited to 4 pages, excluding references, in the NIPS style: https://nips.cc/Conferences/2018/PaperInformation/StyleFiles. - Submissions must be anonymized for double-blind review. - All accepted papers will be presented as spotlights and posters, and made publicly available as a non-archival report, allowing future submissions to archival conferences or journals. - Authors of top accepted papers will be invited to give short contributed talks. - Submission link: https://cmt3.research.microsoft.com/INFER2CONTROL2018 - Please check the workshop website for the latest updates: https://sites.google.com/view/infer2control-nips2018 #### ORGANIZERS: #### Leslie Kaelbling Martin Riedmiller Marc Toussaint Igor Mordatch Roy Fox Tuomas Haarnoja -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Thu Sep 27 08:41:31 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Thu, 27 Sep 2018 15:41:31 +0300 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Student Grants In-Reply-To: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> Message-ID: <2A0147B0-4FE7-4DC2-84A0-0ADB7066F473@cs.ucy.ac.cy> *** SIGCHI Student Travel Grant (SSTG) Program *** 27th ACM International Conference on User Modeling, Adaptation and Personalization (ACM UMAP 2019) Golden Bay Beach Hotel 5*, Larnaca, Cyprus, June 9-12, 2019 https://www.um.org/umap2019/ We are pleased to announce that the SIGCHI Student Travel Grant (SSTG) program is offering support opportunities for students to attend UMAP 2019. This grant is for students who lack other support opportunities and whose intention is to present their work at the conference, not just plan to attend the conference. The goal is to pre-approve students for grants before the conference submission deadline, so if a student gets a submission accepted, the student can count on having a grant awarded for travel to the conference. More information about this program and the application process: https://sigchi.org/conferences/student-travel-grants/student-travel-grant/ Relevant deadline for UMAP 2019: November 1, 2018 (application will open in October) Notification of pre-approval: November 15, 2018 Information on additional funding options for students will soon be available on the UMAP 2019 web site. -------------- next part -------------- An HTML attachment was scrubbed... URL: From dwang at cse.ohio-state.edu Thu Sep 27 11:24:18 2018 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Thu, 27 Sep 2018 11:24:18 -0400 Subject: Connectionists: NEURAL NETWORKS, Oct. 2018 Message-ID: Neural Networks - Volume 106, October 2018 http://www.journals.elsevier.com/neural-networks Shaping the collision selectivity in a looming sensitive neuron model with parallel ON and OFF pathways and spike frequency adaptation Qinbing Fu, Cheng Hu, Jigen Peng, Shigang Yue Social babbling: The emergence of symbolic gestures and words Laura Cohen, Aude Billard A self-organizing short-term dynamical memory network Callie Federer, Joel Zylberberg Brain electroencephalographic segregation as a biomarker of learning Francesca Miraglia, Fabrizio Vecchio, Paolo Maria Rossini Distributed zero-sum differential game for multi-agent systems in strict-feedback form with input saturation and output constraint Jingliang Sun, Chunsheng Liu Banzhaf random forests: Cooperative game theory based random forests with consistency Jianyuan Sun, Guoqiang Zhong, Kaizhu Huang, Junyu Dong Learning to activate logic rules for textual reasoning Yiqun Yao, Jiaming Xu, Jing Shi, Bo Xu Improved multi-view privileged support vector machine Jingjing Tang, Yingjie Tian, Xiaohui Liu, Dewei Li, ... Gang Kou Spatial context-aware user mention behavior modeling for mentionee recommendation Kai Wang, Weiyi Meng, Jiang Bian, Shijun Li, Sha Yang Training sparse least squares support vector machines by the QR decomposition Xiao-Lei Xia Quantum weighted long short-term memory neural network and its application in state degradation trend prediction of rotating machinery Feng Li, Wang Xiang, Jiaxu Wang, Xueming Zhou, Baoping Tang A systematic study of the class imbalance problem in convolutional neural networks Mateusz Buda, Atsuto Maki, Maciej A. Mazurowski Graph structured autoencoder Angshul Majumdar Incremental sparse Bayesian ordinal regression Chang Li, Maarten de Rijke New conditions for global stability of neutral-type delayed Cohen-Grossberg neural networks Neyir Ozcan Effect of inhibitory spike-timing-dependent plasticity on fast sparsely synchronized rhythms in a small-world neuronal network Sang-Yoon Kim, Woochang Lim Passivity and stability analysis of neural networks with time-varying delays via extended free-weighting matrices integral inequality M.J. Park, O.M. Kwon, J.H. Ryu An Arcak-type state estimation design for time-delayed static neural networks with leakage term based on unified criteria R. Manivannan, S. Panda, Kil To Chong, Jinde Cao Memristive nanowires exhibit small-world connectivity Ross D. Pantone, Jack D. Kendall, Juan C. Nino A new mechanical approach to handle generalized Hopfield neural networks Adriano Barra, Matteo Beccaria, Alberto Fachechi Evaluation of the computational capabilities of a memristive random network (MN3) under the context of reservoir computing Laura E. Suarez, Jack D. Kendall, Juan C. Nino Synchronization criteria for inertial memristor-based neural networks with linear coupling Ning Li, Wei Xing Zheng Pinning impulsive synchronization for stochastic reaction???diffusion dynamical networks with delay Huabin Chen, Peng Shi, Cheng-Chew Lim An end to end Deep Neural Network for iris segmentation in unconstrained scenarios Shabab Bazrafkan, Shejin Thavalengal, Peter Corcoran Joint moment-matching autoencoders Mohammad Ahangar Kiasari, Dennis Singh Moirangthem, Minho Lee From n.strisciuglio at rug.nl Thu Sep 27 18:26:56 2018 From: n.strisciuglio at rug.nl (Nicola Strisciuglio) Date: Fri, 28 Sep 2018 00:26:56 +0200 Subject: Connectionists: CFP Applications of Intelligent Systems 2019 - 7-12 January 2019, Las Palmas de Gran Canaria, Spain Message-ID: <2c11241a-21a9-e27f-e86e-a94e5b034f0e@rug.nl> The 2nd International Conference on Applications of Intelligent Systems, *APPIS 2019* will be held on *7-12 January 2019* in *Las Palmas de Gran Canaria*, Spain. APPIS 2019 is organized by the University of Groningen and the University of Las Palmas de Gran Canaria, and includes a *Winter School on Machine Learning (WISMAL 2019)*. APPIS 2019 welcomes (but is not limited to) contributions related to the following topics: ??? Images, videos and time-series analysis ??? Machine learning and representation learning ??? Statistical and structural pattern recognition ??? Data visualization and dimensionality reduction ??? Robotics ??? Intelligent systems in health and medicine ??? Cyber computing and security ??? Bio-informatics ??? Data mining ??? Cognitive discovery ??? Algorithms for embedded and real-time systems ??? Semantic technologies ??? Intelligent buildings ??? Intelligent sensors and sensor networks ??? Augmented reality ??? Adaptive systems ??? Fuzzy systems ??? Human-machine interaction ??? Natural language processing ??? Situation awareness systems ??? Recommender systems ============================================================= Conference proceedings will be published by *ACM International Conference Proceedings Series.* The registration fee includes conference materials, tutorials, conference dinner, welcome reception, another social event (a guided tour of old town Las Palmas or a visit to the only coffee plantage in the EU) and daily coffee breaks. The prices are: ??? Early registration: *250 Euro* ??? Late registration: *325 Euro* The costs for each additional paper are *100 Euro. *=============================================================| *Winter School on Machine Learning - WISMAL 2019* APPIS includes a short winter school consists of several tutorials that present different techniques of Machine Learning. Please find more information at the WISMAL 2019 page . The participation in the winter school is free of charge for registered participants in APPIS 2019. The number of participants in the winter school is limited to 100 and early registration is encouraged. ============================================================= Paper submission ? *Oct 26, 2018* Paper acceptance notification ? *Dec 1, 2018* Early registration ? *Dec 8, 2018* Camera ready ? *Dec 15, 2018* Conference ? *7-9 Jan 2019* Winter school on Machine learning ? *10-12 Jan 2019 *Please find more information on the conference website .* *the conference co-chairs /Nicolai Petkov// //Nicola Strisciuglio// //Carlos Travieso-Gonzalez// / -------------- next part -------------- An HTML attachment was scrubbed... URL: From erishabh at gmail.com Thu Sep 27 07:56:15 2018 From: erishabh at gmail.com (Rishabh Mehrotra) Date: Thu, 27 Sep 2018 12:56:15 +0100 Subject: Connectionists: CFP: Special Issue on Learning from User Interactions - Information Retrieval Journal Message-ID: Information Retrieval Journal Special Issue on* Learning from User Interactions * - Call For Papers*: *https://goo.gl/2nX12V *Important Dates:* - Initial submission due: January 15, 2019 - Initial reviewer feedback: March 15, 2019 - Revised submission due: May 15, 2019 - Final reviews and notification: June 15, 2019 When users interact with online services (e.g. search engines, recommender systems, conversational agents), they leave behind traces of interaction patterns. The ability to record and interpret user interaction signals and understand user behavior gives online systems a vast treasure trove of insights for improvement and experimentation. More generally, the ability to learn from user interactions promises pathways for solving a number of problems and improving user engagement, incorporating user feedback and gauging user satisfaction. The goal of the special issue is to research systems which better support user needs and tasks, understand user interaction processes, intelligent and adaptive interfaces, among others. *Topics of Interest* Specific topics of potential interest include: - User Interaction Processes & Context : ? User Journey Optimization ? Evolution of search process ? Stages of user interactions ? User journey through the system ? Leveraging contextual signals ? Learning for user interaction optimization: algorithms, frameworks & system designs - Intelligent interface designs: ? Adaptive personal digital assistants ? Tailored decision support ? Adaptive collaboration support - User Needs & Tasks Understanding: ? User intent analysis/prediction ? Task identification ? Task aware suggestions & recommendations - User Modeling & Personalization: ? Short and Long-term User Modelling ? Personalization & Diversification ? Coherence - Metrics and Evaluation : ? Metrics based on user interactions ? User engagement metrics design ? Evaluation mechanisms; user satisfaction prediction ? Controlled laboratory study ? Online metrics Test collection - Applications: ? Conversational search, personal search, chatbots, digital assistants ? Contextual Advertising ? E-commerce recommendations ? Intelligent interfaces ? Case studies of real world implementations Special Issue Guest Editors Rishabh Mehrotra , Spotify Research, London, UK Ahmed Hassan Awadallah , Microsoft Research, USA Emine Yilmaz , University College London & the Alan Turing Institute, UK Paper Submission Papers submitted to this special issue for possible publication must be original and must not be under consideration for publication in any other journal or conference. Previously published or accepted conference papers must contain at least 30% new material to be considered for the special issue. All papers are to be submitted by referring to http://www.springer.com/10791 (submit online). At the beginning of the submission process in Editorial Manager, under ?Article Type?, please select the appropriate special issue. All manuscripts must be prepared according to the journal publication guidelines which can also be found on the website provided above. Papers will be evaluated following the journal?s standard review process. For inquiries on the above please contact Rishabh Mehrotra ( rishabhm at spotify.com) -- Rishabh. Web: www.rishabhmehrotra.com Twitter: https://twitter.com/erishabh -------------- next part -------------- An HTML attachment was scrubbed... URL: From us2ts2019 at outlook.com Thu Sep 27 02:12:12 2018 From: us2ts2019 at outlook.com (us2ts 2019) Date: Thu, 27 Sep 2018 06:12:12 +0000 Subject: Connectionists: Call for Sessions Proposal - U.S. Semantic Technologies Symposium Series (us2ts 2019) In-Reply-To: References: , , , , , , , , , Message-ID: Apologies for cross-posting. ============================================================ U.S. Semantic Technologies Symposium Series US2TS Call for Sessions Proposal http://us2ts.org/2019/ https://easychair.org/cfp/us2ts2019 ============================================================ Semantic Web is an inherently multi-disciplinary field. With an ever-growing dependence on the Web and the continuously increasing importance of large-scale data sharing, integration, and reuse, natural science researchers, geoscience, biology, library science, health care, the humanities, just to name a few, have also taken an increasing interest in the Semantic Web. The U.S. Semantic Technologies Symposium (US2TS) series provide a forum to ease the division between computer science, natural science, and academia/government/industry. We solicit anyone with an interest in the Semantic Web to propose a session for US2TS 2019. A session is any relevant activity that can fit into a 90 minutes slot (you can also propose a session that takes more than one slot). Examples of sessions are: . a panel discussion . a series of presentations on a topic . breakout-style discussions on a proposed topic . a tutorial . etc. As the main goal of the Symposium is to foster synergies and collaborations from different fields, we recommend that: 1. At least 2-3 people, preferably from different institutions, propose the session. This is not a strict requirement, mostly a recommendation (if you have a good case for a different setting we will definitely take your proposal into account) 2. All the session leaders are asked to confirm and commit to participate at the time of submission. 3. If your proposal already names speakers or panelists, you must state whether their participation is already confirmed. We encourage session proposals about cross-discipline topics which are of concern for participants from existing sub-communities Submission Guidelines -------------------------------------- Please prepare a (max) 2 page submission indicating: . Name of the session . Topic: please indicate which cross-discipline topics the session will tackle. Here you can also specify if there is any particular vertical of interest (e.g. legal, life science, medical, publisher/scholarly data, cultural heritage, library, museum, oil/gas, engineering, airplane, e-commerce, etc) . Type of session: Panel | Presentations | Break-out discussion | Tutorial | Other (please specify) . Short description of the session . The 2/3 person team (names & affiliations) that will lead the session . Speakers(when applicable). It is strictly required to specify the speakers if you are proposing a panel, in which case they must be already confirmed. . Expected participation (give a prediction of who would be interested in attending your session) . Submit your proposal on easychair: https://easychair.org/conferences/?conf=us2ts. Symposium outcome -------------------------------------- After the Symposium we will invite all session chairs to co-edit a summary of the event, which will be formally published. Important Dates -------------------------------------- . Deadline for submissions: October 31st 2018 . Notifications: November 16th 2018 . Confirmed outline of the sessions: December 10th 2018 . Final program for the sessions: January 14th 2019 . Symposium dates: March 11-13, 2019 Contact -------------------------------------- All questions about submissions should be emailed to contact-us2ts2019 at googlegroups.com [cid:413eaedd-d180-449b-b3dd-1921d094f5d3] U.S. Semantic Technologies Symposium Series March 11-13, 2019 at Duke University in Durham, NC http://us2ts.org/2019/ -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Outlook-nj1bn0w3.png Type: image/png Size: 3694 bytes Desc: Outlook-nj1bn0w3.png URL: From boubchir at ai.univ-paris8.fr Wed Sep 26 10:18:45 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Wed, 26 Sep 2018 16:18:45 +0200 Subject: Connectionists: Deadline Approaching! CFP: The 1st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) Message-ID: <686892f9-6acf-74e1-bee7-0baf41645c65@ai.univ-paris8.fr> ******************************************************************** Apologies if you receive multiple copies of this CfP. ******************************************************************** _________________________________ *The 1st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) * Madrid, Spain, December 3-6, 2018 in conjunction with the IEEE International Conference on Bioinformatics and Biomedicine http://orienta.ugr.es/bibm2018/ _________________________________ Overview EEG signal processing involves the analysis and treatment of the electrical activity of the brain measured with Electroencephalography, or EEG, in order to provide useful information on which decisions can be made. The recent advances in signal processing and machine learning for EEG data processing have brought an impressive progress to solve several practical and challenging problems in many areas such as healthcare, biomedicine, biomedical engineering, BCI and biometrics. The aim of this workshop is to present and discuss the recent advances in machine learning for EEG signal analysis and processing. We are inviting original research work, as well as significant work-in-progress, covering novel theories, innovative methods, and meaningful applications that can potentially lead to significant advances in EEG data analytics. This workshop is an opportunity to bring together academic and industrial scientists to discuss the recent advances. The topics of interest include but not limited to: ? EEG signal processing and analysis ? Time-frequency EEG signal analysis ? Signal processing for EEG Data ? EEG feature extraction and selection ? Machine learning for EEG signal processing ? EEG classification and clustering ? EEG abnormalities detection (e.g. Epileptic seizure, Alzheimer's disease, etc.) ? Machine learning in EEG Big Data ? Deep Learning for EEG Big Data ? Neural Rehabilitation Engineering ? Brain-Computer Interface ? Neurofeedback ? Biometrics with EEG data ? Related applications Program Chair: ? Assoc. Prof., Larbi Boubchir (LIASD - University of Paris 8, France) Program Committee: ? Prof. Boubaker Daachi (LIASD - University of Paris 8, France) ? Prof. Mohamad Sawan (Polytechnique Montr?al, Canada) ? Prof. Geraldine Boylan (University College Cork, Ireland) ? Prof. Lei Ding (University of Oklahoma, USA) Important Dates: ? Sept. 30, 2018 (11:59 pm CST): Due date for full workshop papers submission ? Oct. 27, 2018: Notification of paper acceptance to authors ? Nov. 15, 2018: Camera-ready of accepted papers ? Dec. 3-6, 2018: Workshops Paper Submission: ? Please submit a full-length paper (up to 8 page IEEE 2-column format) or short paper (3-6 pages) through the online submission system. You can download the format instruction here: http://www.ieee.org/conferences_events/conferences/publishing/templates.html ? Electronic submissions in PDF format are required. ? Online Submission: https://wi-lab.com/cyberchair/2018/bibm18/ Publication: All accepted papers will be published in the BIBM proceedings and IEEE Xplore Digital Library. Journal Special Issue: Selected high-quality papers will be invited for publication in a special issue in highly respected journal. Contact: Please email workshop chair: Larbi Boubchir (larbi.boubchir[at]ai.univ-paris8.fr) Please find the call for papers and more information at the workshop webpage: http://www.ai.univ-paris8.fr/~boubchir/Workshop/MLESP2018/home.htm -- _____________________________________________________ Larbi Boubchir, PhD, SMIEEE Associate Professor LIASD - University of Paris 8 2 rue de la Libert?, 93526 Saint-Denis, France Tel. (+33) 1 49 40 67 95 Email. larbi.boubchir at ai.univ-paris8.fr http://www.ai.univ-paris8.fr/~boubchir/ _____________________________________________________ -------------- next part -------------- An HTML attachment was scrubbed... URL: From dayan at gatsby.ucl.ac.uk Fri Sep 28 16:16:13 2018 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Fri, 28 Sep 2018 21:16:13 +0100 Subject: Connectionists: Course: Computational Psychiatry: From Theory to Practice! In-Reply-To: <20180112054451.GI30751@gatsby.ucl.ac.uk> References: <20180112054451.GI30751@gatsby.ucl.ac.uk> Message-ID: <20180928201613.GA15807@gatsby.ucl.ac.uk> Dear Colleagues, We are delighted to invite you to attend Computational Psychiatry: from theory to practice! This 2-day event will be held in San Diego, CA (USA) on November 2 & 3, 2018 (just before Neuroscience 2018). Registration includes: Theory lectures Interactive workshops Poster sessions Informal networking opportunities Keynote lecture by Dr. Terrence Sejnowski (Salk Institute for Biological Studies, University of California at San Diego) Additional presenters include: Danielle Bassett, Vanessa Brown, Pearl Chiu, Jonathan Cohen, Anne Collins, Michele Ferrante, Michael Frank, Xiaosi Gu, Stephanie Jones, Stephen LaConte, Jonathan Lisinski, Rosalyn Moran, Samuel Neymotin, & Martin Paulus. Visit computationalpsychiatry.org for more information and to register. We hope to see you there and would appreciate your spreading the word to others who may be interested in attending. Best wishes, Xiaosi Gu Peter Dayan Read Montague events at computationalpsychiatry.org Follow us on Twitter & Facebook From luca.oneto at unige.it Sat Sep 29 11:25:04 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Sat, 29 Sep 2018 17:25:04 +0200 Subject: Connectionists: ESANN 2019 SS - Societal Issues in Machine Learning: When Learning from Data is Not Enough Message-ID: [Apologies if you receive multiple copies of this CFP] Call for papers: special session on "Societal Issues in Machine Learning: When Learning from Data is Not Enough" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019). 24-26 April 2019, Bruges, Belgium - http://www.esann.org DESCRIPTION: It has been argued that Artificial Intelligence (AI) is experiencing a fast process of commodification. This characterization is on the interest of big IT companies, but it correctly reflects the current industrialization of AI. This phenomenon means that AI systems and products are reaching the society at large and, therefore, that societal issues related to the use of AI and Machine Learning (ML) cannot be ignored any longer. Designing ML models from this human-centered perspective means incorporating human-relevant requirements such as safety, fairness, privacy, and interpretability, but also considering broad societal issues such as ethics and legislation. These are essential aspects to foster the acceptance of ML-based technologies, as well as to be able to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. This special session aims to put forward the state-of-the-art on these increasingly relevant topics among ML theoretician and practitioners. For this purpose, we welcome both solid contributions and preliminary relevant results showing the potential, the limitations and the challenges of new ideas, refinements, or contaminations between the different fields of research, ML, and related approaches in facing real-world problems involving societal issues. We welcome works on ML theory, applications to topics listed below as well as other topics of social relevance. Studies stemming from major research initiatives and projects focusing on the session topics are particularly welcome. TOPICS OF INTEREST: - Fairness as an element in the development of ML techniques; - Ethical issues in the application of ML and related techniques in areas of social impact; - Privacy as a challenge in ML application to problems in the social domain; - Interpretability and explainability of ML and related approaches; - Safety and Security of ML and related methods in safety critical contexts; - Legislative challenges to the use of ML and related methods; - The challenge of complex data for ML and related methods; - Transparency and open data. SUBMISSION: Prospective authors must submit their paper through the ESANN portal following the instructions provided in https://www.elen.ucl.ac.be/esann/index.php?pg=submission Each paper will undergo a peer reviewing process for its acceptance. Authors should send as soon as possible an e-mail with the tentative title of their contribution to the special session organisers. IMPORTANT DATES: Submission of papers: 19 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Davide Bacciu, University of Pisa (Italy) Battista Biggio, University of Cagliari (Italy) Jos? D. Mart?n, Universitat de Val?ncia (Spain) Luca Oneto, University of Genoa (Italy) Alfredo Vellido, Universitat Polit?cnica de Catalunya (Spain) Paulo J. G. Lisboa, Liverpool John Moores University (UK) ----------------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: Luca.Oneto at unige.it SmartLab Laboratory e-mail: Luca.Oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145 Genoa ITALY Phone: +39-010-3532192 www.smartlab.ws ----------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From luca.oneto at unige.it Sat Sep 29 11:25:38 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Sat, 29 Sep 2018 17:25:38 +0200 Subject: Connectionists: [INNS-BDDL 2019] - Call for Papers Message-ID: [Apologies if you receive multiple copies of this CFP] ########################################################### CALL FOR PAPERS INNS BIG DATA AND DEEP LEARNING 2019 April 16 - 18, SESTRI LEVANTE, GENOA, ITALY, 1618 Website: https://innsbddl2019.org/ ######################Description########################## The 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) conference will be held in Sestri Levante, Italy, April 16 ? 18, 2019. The conference is organized by the International Neural Network Society, with the aim of representing an international meeting for researchers and other professionals in Big Data, Deep Learning and related areas. It will feature invited plenary talks by world renowned speakers in the area, in addition to regular and special technical sessions with oral and poster presentations. Moreover, workshops and tutorials will also be featured. ######################Invited Speakers##################### * Paolo Ferragina, University of Pisa, Italy * Guang-Bin Huang, Nanyang Technological University, Singapore ########################################################### ######################Tutorials############################ * Davide Bacciu (University of Pisa), Deep Learning for Graphs * Silvia Chiappa (DeepMind), Luca Oneto (University of Genoa), Fairness in Machine Learning * Claudio Gallicchio (University of Pisa), Simone Scardapane (Sapienza University of Rome), Deep Randomized Neural Networks * V?ra K?rkov? (Czech Academy of Sciences), Complexity of Shallow and Deep Networks * Danilo P. Mandic, Ilia Kisil, and Giuseppe G. Calvi (Imperial College London), Tensor Decompositions and Applications. Blessing of Dimensionality * German I. Parisi and Stefan Wermter (University of Hamburg), Continual Lifelong Learning with Neural Networks ########################################################### #######################IMPORTANT DATES##################### * Deadline of full paper submission: October 31, 2018 * Notification of paper acceptance: December 31, 2018 * Camera-ready submission: January 31, 2019 * Early registration deadline: January 15, 2019 * Registration deadline: January 31, 2019 * Conference date: April 16 - 18, 2019 ########################################################### ##########################SCOPE############################ We solicit both solid contributions or preliminary results which show the potentiality and the limitations of new ideas, refinements, or contaminations in any aspect of Big Data and Deep Learning. Both theoretical and practical results are welcome. Example topics of interest includes but is not limited to the following: Big Data Science and Foundations * Novel Theoretical Models for Big Data * New Computational Models for Big Data * Data and Information Quality for Big Data Big Data Mining * Social Web Mining * Data Acquisition, Integration, Cleaning, and Best Practices * Visualization Analytics for Big Data * Computational Modeling and Data Integration * Large-scale Recommendation Systems and Social Media Systems * Cloud/Grid/StreamData Mining * Big Velocity Data * Link and Graph Mining * Semantic-based Data Mining and Data Preprocessing * Mobility and Big Data * Multimedia and Multistructured Data-Big Variety Data Modern Practical Deep Networks * Deep Feedforward Networks * Regularization for Deep Learning * Optimization for Training Deep Models * Convolutional Networks * Sequence Modeling: Recurrent and Recursive Nets * Practical Methodology Deep Learning Research * Linear Factor Models * Autoencoders * Representation Learning * Structured Probabilistic Models for Deep Learning * Monte Carlo Methods * Confronting the Partition Function * Approximate Inference * Deep Generative Models ####################PROCEEDINGS & SPECIAL ISSUE############ Works submitted as a regular paper will be published in a serie indexed by Scopus. Submitted papers will be reviewed by some PC members based on technical quality, relevance, originality, significance and clarity. At least one author of an accepted submission should register to present their work at the conference. Selected papers presented at INNS BDDL 2019 will be included in special issues of top journals in the field (prospected journals: Big Data Research, Transaction on Neural Networks and Learning System, Neurocomputing, etc). ########################################################### ----------------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: Luca.Oneto at unige.it SmartLab Laboratory e-mail: Luca.Oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145 Genoa ITALY Phone: +39-010-3532192 www.smartlab.ws ----------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From joern.diedrichsen at googlemail.com Sat Sep 29 11:16:43 2018 From: joern.diedrichsen at googlemail.com (=?utf-8?Q?J=C3=B6rn_Diedrichsen?=) Date: Sat, 29 Sep 2018 11:16:43 -0400 Subject: Connectionists: Tenure-track faculty position in Computational Neuroscience Message-ID: <8B74ABE3-5BB9-4A84-85D3-FFC006267A94@googlemail.com> Supported by BrainsCAN, a $66M grant from the Canadian government (www.uwo.ca/brainscan ), Western University is expanding it?s strength in Neuroscience with a new tenure-track faculty position (Assistant or Associate Professor) in Computational Neuroscience. Successful candidates will join the Brain and Mind Institute (www.uwo.ca/bmi ), one of the leading centres in cognitive Neuroscience in Canada, with a full range of ultrahigh field, research-dedicated MRI scanners (3T, 7T, 9.4T) and state-of-the-art laboratories for cognitive, behavioural, and neurophysiological testing in humans, non-human primates and rodents. The academic appointment of the candidate will be, depending on the candidate?s background, in the Department for Applied Mathematics, Statistics, or Computer Science. The deadline for the position in Computational Neuroscience is November 1st: https://brainscan.uwo.ca/work_with_us/vacancies/index.html J?rn Diedrichsen Western Research Chair Brain Mind Institute Department of Computer Science Department of Statistics Email: jdiedric at uwo.ca Tel: 1-519-661-2111 x86994 -------------- next part -------------- An HTML attachment was scrubbed... URL: From "maneesh+connectionists>" at gatsby.ucl.ac.uk Sat Sep 29 08:47:47 2018 From: "maneesh+connectionists>" at gatsby.ucl.ac.uk (Maneesh Sahani) Date: Sat, 29 Sep 2018 13:47:47 +0100 Subject: Connectionists: Opening for a Head Research Engineer at the Gatsby Unit, UCL Message-ID: The Gatsby Computational Neuroscience Unit at UCL invites applications for a new position of Head Research Engineer, to establish and lead a team working at the interface of machine learning and neuroscience. The Gatsby Unit is a world-leading centre for theoretical neuroscience and machine learning research, running international PhD and postdoctoral training programmes. Members of the unit have been involved in many of the key breakthroughs in machine learning, statistics and neural data analysis over the past two decades. We plan to extend our mission by establishing a new group to translate and adapt novel machine learning and neural data analytic algorithms and technologies developed in the course of our research into robust, scalable, open and usable software applications and platforms that can be used by both our collaborators and a wider audience. The Head Research Engineer will lead and develop this team. The team will take the lead in interactions with collaborators in academia and industry, to understand particular data sets or applications and to engage and assist with the research and development needed to adapt algorithms to address these cases. A key responsibility will be to facilitate practical interaction between the theoretical and algorithmic work of the Gatsby Unit and the experimental systems neuroscience carried out in our sister institute, the Sainsbury-Wellcome Centre for Neural Circuits and Behaviour. A link to UCL's online application site, with further information about the position, is available from http://www.gatsby.ucl.ac.uk/vacancies/ Informal enquiries may be directed to me. -- Maneesh Sahani, Ph.D. Professor of Theoretical Neuroscience and Machine Learning, Director, Gatsby Computational Neuroscience Unit UCL, 25 Howland Street, London W1T 4JG From fmschleif at googlemail.com Sun Sep 30 08:32:46 2018 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Sun, 30 Sep 2018 14:32:46 +0200 Subject: Connectionists: CFP (reminder): ESANN 2019 special session - Streaming data analysis, concept drift and analysis of dynamic data sets Message-ID: -- Apologies in advance for multiple postings -- Call for Papers Special Session on 'Streaming data analysis, concept drift and analysis of dynamic data sets ' 24-26 April 2019, Bruges, Belgium https://www.elen.ucl.ac.be/esann/index.php?pg=specsess#streaming AIMS AND SCOPE Today many real life data are given in the form of streaming data. Prominent examples can be found in the context of IoT, in form of twitter feeds, click stream data, trading data and many other. Learning from this huge, heterogeneous and growing amount of data requires flexible learning models that can adapt over time and are capable to deal with potentially non-i.i.d., non-stationary input data. Additionally the underlying algorithms aim on processing of high-velocity and multi-channel data and have also to deal with a variety of phenomena like concept drift and novelty detection. This special session welcomes novel research about learning from data streams addressing common problem in the field of streaming data analysis. Computational intelligence methods have the potential to be used for efficient data streams processing but novel methods and mathematical and algorithmic approaches are needed. TOPICS We encourage submission of papers on novel methods for streaming data processing and streaming data analysis by means of computational intelligence and machine learning approaches, including but not limited to: - data analysis and pattern recognition approaches for streaming data - preprocessing approaches for streaming data - learning of heterogeneous data streams - adaptive data pre-processing and knowledge discovery - methods employing ex- and implicit data knowledge for non-stationary data - representation and modeling of multi-channel streaming data - approximation techniques for streaming data - online and incremental learning (dimensionality reduction, classification, clustering and regression, outlier detection) with a particular design for streaming data - data drift and shift handling, transfer learning - graph stream algorithms - security and privacy preservation on streaming data - active learning for data streams - application of deep learning with streaming data - particular interesting applications for streaming data analysis e.g. in IoT, recommender systems, social networks, sensor networks, web mining, text processing medicine ... IMPORTANT DATES Paper submission deadline : 19 November 2018 Notification of acceptance : 31 January 2019 Deadline for final papers : 20 February 2019 The ESANN 2019 conference : 24-26 April 2019 SPECIAL SESSION ORGANIZERS: Albert Bifet LTCI, T?l?com ParisTech - Universit? Paris-Saclay Paris, FRANCE Barbara Hammer, University of Bielefeld, Germany Frank-Michael Schleif, University of Appl. Sc. Wuerzburg-Schweinfurt, Germany and University of Birmingham, Birmingham, UK -- ------------------------------------------------------- Prof. Dr. rer. nat. habil. Frank-Michael Schleif School of Computer Science University of Applied Sciences W?rzburg-Schweinfurt Sanderheinrichsleitenweg 20 Raum I-3.35 Tel.: +49(0) 931 351 18127 97074 W?rzburg Honorable Research Fellow The University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom - email: frank-michael.schleif at fhws.de http://promos-science.blogspot.de/ https://www.techfak.uni-bielefeld.de/~fschleif/ ------------------------------------------------------- From boubchir at ai.univ-paris8.fr Sat Sep 29 16:03:55 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Sat, 29 Sep 2018 22:03:55 +0200 Subject: Connectionists: IEEE MLESP 2018 Deadline Extended Message-ID: <0273ddd0-ddc0-aef9-6c03-8ac71e9314b4@ai.univ-paris8.fr> ************************************************************************** Due to a number of requests, we have decided to apply an extension deadline for papers submission up to *October 7*, 2018 (11:59 pm CST). Apologies for the wide distribution of this message. This is the first (and final!) announcement for MLESP2018 (https://bit.ly/2xNnPmp). ************************************************************************** _________________________________ *The 1st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) * Madrid, Spain, December 3-6, 2018 in conjunction with the IEEE International Conference on Bioinformatics and Biomedicine http://orienta.ugr.es/bibm2018/ _________________________________ Overview EEG signal processing involves the analysis and treatment of the electrical activity of the brain measured with Electroencephalography, or EEG, in order to provide useful information on which decisions can be made. The recent advances in signal processing and machine learning for EEG data processing have brought an impressive progress to solve several practical and challenging problems in many areas such as healthcare, biomedicine, biomedical engineering, BCI and biometrics. The aim of this workshop is to present and discuss the recent advances in machine learning for EEG signal analysis and processing. We are inviting original research work, as well as significant work-in-progress, covering novel theories, innovative methods, and meaningful applications that can potentially lead to significant advances in EEG data analytics. This workshop is an opportunity to bring together academic and industrial scientists to discuss the recent advances. The topics of interest include but not limited to: ? EEG signal processing and analysis ? Time-frequency EEG signal analysis ? Signal processing for EEG Data ? EEG feature extraction and selection ? Machine learning for EEG signal processing ? EEG classification and clustering ? EEG abnormalities detection (e.g. Epileptic seizure, Alzheimer's disease, etc.) ? Machine learning in EEG Big Data ? Deep Learning for EEG Big Data ? Neural Rehabilitation Engineering ? Brain-Computer Interface ? Neurofeedback ? Biometrics with EEG data ? Related applications Program Chair: ? Assoc. Prof., Larbi Boubchir (LIASD - University of Paris 8, France) Program Committee: ? Prof. Boubaker Daachi (LIASD - University of Paris 8, France) ? Prof. Mohamad Sawan (Polytechnique Montr?al, Canada) ? Prof. Geraldine Boylan (University College Cork, Ireland) ? Prof. Lei Ding (University of Oklahoma, USA) Important Dates: ? Sept. 30, 2018 Oct. 7, 2018 (11:59 pm CST): Due date for full workshop papers submission ? Oct. 27, 2018: Notification of paper acceptance to authors ? Nov. 15, 2018: Camera-ready of accepted papers ? Dec. 3-6, 2018: Workshops Paper Submission: ? Please submit a full-length paper (up to 8 page IEEE 2-column format) or short paper (3-6 pages) through the online submission system. You can download the format instruction here: http://www.ieee.org/conferences_events/conferences/publishing/templates.html ? Electronic submissions in PDF format are required. ? Online Submission: https://wi-lab.com/cyberchair/2018/bibm18/ Publication: All accepted papers will be published in the BIBM proceedings and IEEE Xplore Digital Library. Journal Special Issue: Selected high-quality papers will be invited for publication in a special issue in highly respected journal. Contact: Please email workshop chair: Larbi Boubchir (larbi.boubchir[at]ai.univ-paris8.fr) Please find the call for papers and more information at the workshop webpage: http://www.ai.univ-paris8.fr/~boubchir/Workshop/MLESP2018/home.htm -- _____________________________________________________ Larbi Boubchir, PhD, SMIEEE Associate Professor LIASD - University of Paris 8 2 rue de la Libert?, 93526 Saint-Denis, France Tel. (+33) 1 49 40 67 95 Email. larbi.boubchir at ai.univ-paris8.fr http://www.ai.univ-paris8.fr/~boubchir/ _____________________________________________________ -------------- next part -------------- An HTML attachment was scrubbed... URL: From thomas_serre at brown.edu Sun Sep 30 21:01:14 2018 From: thomas_serre at brown.edu (Serre, Thomas) Date: Sun, 30 Sep 2018 21:01:14 -0400 Subject: Connectionists: =?utf-8?q?Paul_J=2E_Salem_Postdoctoral_Scholars_i?= =?utf-8?q?n_Computational_Brain_Science_=E2=80=93_Carney_Institute?= =?utf-8?q?_for_Brain_Sciences=2C_Brown_=28Providence=2C_RI=29?= Message-ID: The Frank and Serre labs at Brown University are seeking applicants for the Paul J. Salem Postdoctoral Scholarships in Brain Science. The postdoctoral fellow will lead an exciting new project at the interface between machine learning and neuroscience at the intersection between vision, memory and reinforcement learning. Relevant projects in the two groups can be seen in the following example works: - Drew Linsley, Junkyung Kim, Vijay Veerabadran, Thomas Serre. (2018) Learning long-range spatial dependencies with horizontal gated recurrent units. Neural Information Processing Systems. 2018 https://arxiv.org/abs/1805.08315v1 - J.K Kim, M. Ricci & T. Serre. Learning same-different relations strains feedforward neural networks. Interface Focus (special issue on ?Understanding images in biological and computer vision?), 8(4), 2018 - Drew Linsley, Dan Scheibler, Sven Eberhardt, Thomas Serre. (2018) Global-and-local attention networks for visual recognition. 2018 https://arxiv.org/abs/1805.08819v1 - Franklin, N.T. & Frank, M.J. (2018). Compositional clustering in task structure learning. *PLOS Computational Biology, 14(4): e1006116*. http://ski.clps.brown.edu/papers/FranklinFrank_Compositional18.pdf - Nassar, M.R., Helmers, J. & Frank, M.J. (2018). Chunking as a rational strategy for lossy data compression in visual working memory. *Psychological Review*. http://ski.clps.brown.edu/papers/NassarHelmersFrank_chunking.pdf Candidates are expected to have a solid background in one or more of the following domains: modern machine learning and deep learning, computational models of neural dynamics underlying perceptual or cognitive processes and signal processing. In addition, to conducting primary research with neural networks, candidates will be involved in the mentoring of students and will participate in workshops and challenges at the interface between machine learning and neuroscience (see e.g., http://compneuro.clps.brown.edu/datathon_2017/ and http://compneuro.clps.brown.edu/2018-modeling-competition/). The initial appointment is for 12 months, renewable for another year, and potentially longer depending on funding. The start date is negotiable though an early start is strongly preferred. Salary is commensurate with experience and is competitive. We encourage Salem Scholars to seek external funding during their appointment, as a critical component in their professional development. *Requirements:* Candidates must have received their PhDs within 3 years of the application deadline and will work under the supervision of Drs Frank and Serre who are affiliated with the Carney Initiative for Computation in Brain and Mind. They must have a strong background in computational neuroscience and machine learning, with a track record of relevant publications at top venues (such as NIPS, ICML, PLOS Computational Biology, etc). Excellent programming skills are required (e.g., C/C++/Matlab/Python/R). *Application:* Please send your applications by email to michael_frank at brown.edu thomas_serre at brown.edu. Please include a brief statement of interests, a curriculum vita, a list of publications and the name of 2-3 reference writers (no letter needed at this stage). There is no deadline for the application but applicants are encouraged to apply as soon as possible as the position will be filled as soon as a suitable applicant is found. *The Carney Initiative for Computation in Brain and Mind (CICBM;* http://compneuro.clps.brown.edu ), which began Fall 2013 as a component of BIBS, is an energetic and enthusiastic effort that fosters synergistic collaborations across departments. Groups affiliated with the initiative work on two core levels of computation. The first level focuses on theoretical neuroscience, including computational perception, control over action and learning, and fundamental questions in neuronal networks (synaptic plasticity, circuits, networks, oscillations). The second level focuses on applications and neurotechnology, including brain-machine interfaces, advanced neural data analysis, computer vision, computational psychiatry, and robotics. CICBM has 16 core computational faculty (http://compneuro.clps.brown.edu/people/) spanning six departments, and many more faculty who incorporate computation for theory development, analysis, or both. Computational neuroscience tools at Brown have been applied in projects including brain-machine control of robotic arms in paralyzed humans; models of visual systems in biological organisms and their innovative application for classifying animal behavioral patterns; predicting and quantifying effects of genetics, disease, medications, and brain stimulation on motor and cognitive function; identification of the source of neural rhythms and their roles in sensorimotor function; development of fundamental theories of brain plasticity, and learning; state-of-the-art models of machine learning and reinforcement learning in computer science. The Carney Institute for Brain Science at Brown University advances multidisciplinary research, technology development, and training in the brain sciences and works to establish Brown University as an internationally recognized leader in brain research. The institute was just endowed with a new $100 million gift. CIBS unites more than 100 faculty from a diverse group of departments at Brown, spanning basic and clinical departments, and physical and biological sciences. CIBS provides a mechanism to advance interdisciplinary research efforts among this broad group. CIBS provides essential support to obtain and administer multi-investigator grants for research, infrastructure, and training. The Institute actively seeks new training funds to support interdisciplinary education that transcends that available in individual academic departments. -- Thomas Serre Carney Institute for Brain Science, Brown University Associate Professor, Dept of Cognitive Linguistic & Psychological Sciences Faculty Director, Center for Computation and Visualization T: +1(401) 484-0750 | Skype: thomas.serre | Gchat: thomas.serre at brown.edu Web: *http://serre-lab.clps.brown.edu * -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Sun Sep 30 14:56:04 2018 From: terry at salk.edu (Terry Sejnowski) Date: Sun, 30 Sep 2018 11:56:04 -0700 Subject: Connectionists: NEURAL COMPUTATION - October 1, 2018 In-Reply-To: Message-ID: Neural Computation - Volume 30, Number 10 - October 1, 2018 Available online for download now: http://www.mitpressjournals.org/toc/neco/30/10 ----- Article Learning Data Manifolds with a Cutting Plane Method *Free* SueYeon Chung, Uri Cohen, Haim Sompolinsky, and Daniel D. Lee Recognition Dynamics in the Brain under the Free Energy Principle Chang Sub Kim Letters Computing with Spikes: The Advantage of Fine-Grained Timing Stephen J. Verzi, Fredrick Rothganger, Ojas D. Parekh, Tu-Thach Quach, Nadine E. Miner, Craig M. Vineyard, Conrad D. James, and James B. Aimone Hexagonal Grid Fields Optimally Encode Transitions in Spatiotemporal Sequences Nicolai Waniek CosMIC: A Consistent Metric for Spike Inference from Calcium Imaging Stephanie Reynolds, Therese Abrahamsson, Per Jesper Sjostrom, Simon R. Schultz, and Pier Luigi Dragotti Autoregressive Point Processes as Latent State-Space Models: A Moment-Closure Approach to Fluctuations and Autocorrelations Michael Rule and Guido Sanguinetti Multiclass Classification and Feature Selection Based on Least Squares Regression with Large Margin Haifeng Zhao, Siqi Wang, and Zheng Wang Adaptive Learning Algorithm Convergence in Passive and Reactive Environments Richard M. Golden Improving Stock Closing Price Prediction Using Recurrent Neural Network and Technical Indicators Tingwei Gao and Yueting Chai ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp MIT Press Journals, One Rogers Street, Cambridge, MA 02142-1209 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-cs at mit.edu ------------