From luca.oneto at unige.it Sat Dec 1 02:37:29 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Sat, 1 Dec 2018 08:37:29 +0100 Subject: Connectionists: [INNS-BDDL 2019] - Submission Final Deadline 7th of December Message-ID: [Apologies if you receive multiple copies of this CFP] Due to many requests the submission deadline has been postponed to the 7th of December. THIS WILL BE THE LAST POSTPONEMENT. ########################################################### CALL FOR PAPERS INNS BIG DATA AND DEEP LEARNING 2019 April 16-18 SESTRI LEVANTE, GENOA, ITALY 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##################### * Hava Siegelmann, DARPA, USA * Paolo Ferragina, University of Pisa, Italy * Guang-Bin Huang, Nanyang Technological University, Singapore ########################################################### ######################Tutorials############################ * Alessio Micheli (University of Pisa), 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: December 7, 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 george at cs.ucy.ac.cy Sat Dec 1 06:42:20 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Sat, 1 Dec 2018 13:42:20 +0200 Subject: Connectionists: 46th International Conference on Current Trends in Theory and Practice of Computer Science (SOFSEM 2020): Call for Track Proposals In-Reply-To: <6978C684-25CD-4FF6-BD9A-4AA340EF7189@cs.ucy.ac.cy> References: <31C24FFB-0CFA-4FDA-A707-4F88A4937121@cs.ucy.ac.cy> <6978C684-25CD-4FF6-BD9A-4AA340EF7189@cs.ucy.ac.cy> Message-ID: *** Call for Track Proposals *** 46th International Conference on Current Trends in Theory and Practice of Computer Science (SOFSEM 2020) Atlantica Miramare 4* Beach Hotel, Limassol, Cyprus January 20-24, 2020 http://cyprusconferences.org/sofsem2020/ *** Submission Deadline: February 11, 2019 *** (Proceedings to be published by Springer) SOFSEM (SOFtware SEMinar) is an annual international winter conference devoted to the theory and practice of computer science. SOFSEM presents the latest results and developments in academic and industrial research in leading areas of Computer Science. The first SOFSEM was organized in 1974, and it was traditionally located in the Czech and Slovak Republics, before it starting moving to other European locations. In 2017 it was organised in Ireland, in 2018 in Austria and in 2019 in Slovakia. The 46th edition will be organised in the sunny Mediterranean island of Cyprus. SOFSEM consists of Invited Talks by prominent researchers, Contributed Talks selected from the submitted papers, and the Student Research Forum. The program is organized in plenary talks and parallel tracks devoted to original research in contemporary areas of Computer Science. SOFSEM has a long-standing tradition of facilitating discussions and collegial interactions and is well-known for its familiar and inspiring atmosphere and as a meeting place for active and leading computer scientists. SOFSEM is a track based conference. It features the traditional track on Foundations of Computer Science and a number of other tracks that over the years have evolved to cover and address contemporary important areas of Computer Science, such as Artificial Intelligence, Cryptography, Security, and Verification, Data Science, Knowledge Engineering, Social Computing and Human Factors, Software and Web Engineering, etc. The proceedings of SOFSEM are published in the prestigious ARCoSS (Advanced Research in Computing and Software Science) subseries of Springer's Lecture Notes in Computer Science (LNCS) series. For SOFSEM 2020, the Steering Committee is inviting proposals for organising tracks. The tracks can be of theoretical or practical nature or a combination of both. Tracks from industry are particularly welcome. The proposal should not exceed 3 pages and should include the following items: a) Title, aim and scope of the proposed track, as well as the list of topics that the proposed track will address. b) Rationale for having this track in SOFSEM, including any other similar events that the proposed track complements or differs from. c) Names, affiliations and short CVs for the chairs of the proposed track, demonstrating past relevant experience in organising such tracks or events. d) Tentative list of names of the Program Committee for the proposed track. e) A short dissemination plan for the CFP mentioning the forums where the latter will be posted. The proposals will be reviewed by the Steering Committee and the General Chairs, based on the above mentioned criteria. A proposal may be accepted as is, requested to modify its title and/or topics covered, merged with another proposed track or rejected. Upon acceptance, the track chairs will be notified of their exact duties in managing the affairs of their track. The Steering Committee reserves the right to cancel a track at any moment in time, if these responsibilities are not dealt with satisfactorily by the track chairs. Proposals should be submitted by February 11th, 2019 to the SOFSEM 2020 General Chairs, Yannis Manolopoulos (yannis.manolopoulos AT ouc.ac.cy) and George A. Papadopoulos (george AT cs.ucy.ac.cy). IMPORTANT DATES * Submission of track proposals: February 11, 2019 * Notification of proposals acceptance or rejection: February 25, 2019 * Submission of abstracts: July 29, 2019 * Submission of full papers: August 5, 2019 * Notification of acceptance for submitted papers: September 30, 2019 * Camera-Ready submission of accepted papers: October 28, 2019 * Early and author registration deadline: November 25, 2019 * Conference dates: January 20-24, 2020 ORGANISATION General Chairs Yannis Manolopoulos, Open University of Cyprus, CY George A, Papadopoulos, University of Cyprus, CY Steering Committee Barbara Catania, University of Genova, IT Miroslaw Kutylowski, Wroclaw Uni. of Technology, PL Tiziana Margaria-Steffen, University of Limerick, IE Branislav Rovan, Comenius University, Bratislava, SK Petr Saloun, Technical University of Ostrava, CZ Julius Stuller, Academy of Sciences, Prague, CZ, chair Jan van Leeuwen, Utrecht University, Utrecht, NL -------------- next part -------------- An HTML attachment was scrubbed... URL: From mail at jan-peters.net Sun Dec 2 05:21:27 2018 From: mail at jan-peters.net (Jan Peters) Date: Sun, 02 Dec 2018 11:21:27 +0100 Subject: Connectionists: Call for Applications Message-ID: <15301928-D9B3-4033-9930-658C7761FC67@jan-peters.net> Robotics & Machine Learning Positions =============================== The Intelligent Autonomous Systems Labs (IAS) at the Technical University of Darmstadt (TU Darmstadt) is seeking for several *highly qualified postdoctoral researchers.* (exceptionally talented Ph.D. students will also be considered) with strong interest in one or more of the following research topics: * Robot Learning (especially Robot Reinforcement Learning, Imitation, and Model Learning) * Robot Grasping and Manipulation * Robot Control, Learning for Control * Robot Table Tennis Please relate clearly to these topic in your Research Statement. Note that we currently can only consider PhD students with real robot experience (for post-docs, we are more open-minded). Outstanding students and researchers from the areas of robotics and robotics-related areas including machine learning, control engineering or computer vision are welcome to apply. The candidates are expected to conduct independent research and at the same time contribute to ongoing projects in the areas listed above. Successful candidates can furthermore be given the opportunity to work with undergraduate, M.Sc. and Ph.D. students. Due to our strong ties to the Max Planck Institute for Intelligent Systems, many companies (ABB, Bosch Centre for AI, Honda Research Institute, Intel, NVIDEA NVAIL, Porsche Motor Sports, VW AI Lab, etc) there will be ample opportunities of collaboration with these institutes. ABOUT THE APPLICANT Ph.D. position applicants need to have a Master's degree in a relevant field (e.g., Robotics, Computer Science, Engineering, Statistics & Optimization, Math and Physics) and have exhibited their ability to perform research in either robotics or machine learning. A successful Post-doc applicant should have a strong robotics and/or machine learning background with a track record of top-tier research publications, including relevant conferences (e.g., RSS, ICRA, IROS or ICML, IJCAI, AAAI, NIPS, AISTATS) and journals (e.g., AURO, TRo, IJRR or JMLR, MLJ, Neural Computation) . A Ph.D. in Computer Science, Electrical or Mechanical Engineering (or another field clearly related to robotics and/or machine learning) as well as strong organizational and coordination skills are a must. Expertise in working with real robot systems is a big plus for all applicants. THE POSITIONS The positions are started with a 24 months contract and may be extendable up to 48 months. Payment will be according to the German TVL E-13 or E-14 payment scheme, depending on the candidates experience and qualifications. HOW TO APPLY? All complete applications submitted through our online application system found at http://www.ias.tu-darmstadt.de/Jobs/Application will be considered. There is no fixed deadline: the positions will be filled as soon as possible. Ph.D. applicants should provide at least a research statement, a PDF with their CV, degrees, and grade-sheets, and two references who are willing to write a recommendation letter. PostDoc applicants require three references and, in addition, should provide their top three publications. Please ensure to include a link to your research web-site as well as your date of availability. ABOUT IAS The Intelligent Autonomous Systems Lab (IAS) aims at endowing robots with the ability to learn new tasks and adapt their behavior to their environment. To accomplish this goal, IAS focuses on the intersection between Machine Learning, Robotics and Biomimetic Systems. Resulting research topics range from algorithm development in machine learning over robot grasping/manipulation and robot table tennis to biomimetic motor control/learning and brain-robot interfaces. Members of CLAS and IAS have been highly successful, as exhibited by recent awards, which include a Daimler Benz Fellowship, several Best Cognitive Robotics Paper Awards, the Georges Giralt Best 2013 Robotics PhD Thesis Award, an IEEE RAS Early Career Award, etc. The lab collaborates with numerous universities in Germany, Europe, the USA and Japan. IAS is partner in several European projects with many top institutes in ML and Robotics.. Our lab member have been *EXCEPTIONALLY* successful. All our former postdocs have been offered faculty positions and five of our 14 graduated PhD students have taken on faculty jobs. The IAS lab is located in the Robert Piloty Building in the beautiful Herrngarten park. It is less than fifty meters from a beer garden frequently used for lab meetings and after successful paper submissions. ABOUT TU DARMSTADT The TU Darmstadt is one of the top technical universities in Germany, and is well known for its research and teaching. It was one of the first universities in the world to introduce programs in electrical engineering. our chemical elements were discovered at Darmstadt, most prominently, the element darmstadtium, and it is Germany's first fully autonomous university. More information can be found on: http://en.wikipedia.org/wiki/Darmstadt_University_of_Technology ABOUT DARMSTADT Darmstadt is well known high-tech center with important activities in space craft operations (e.g., through the European Space Operations Centre, the European Organization for Exploitation of Meteorological Satellites), chemistry, pharmacy, information technology, biotechnology, telecommunications and mechatronics, and consistently ranked among the top high-tech regions in Germany. Darmstadt's important centers for arts, music and theatre allow for versatile cultural activities, while the proximity of the Odenwald forest and the Rhine valley allows for many outdoor sports. The 33,547 students of Darmstadt's three universities constitute a major part of Darmstadt's 140,000 inhabitants. Darmstadt's immigrant population is among the most diverse in Germany, such that the knowledge of German language is rarely ever needed (and many IAS members do not speak *any* German). Darmstadt is located close to the center of Europe. With just 17 Minutes driving distance to the Frankfurt airport (closer than Frankfurt itself), it is one of best connected cities in Europe. Most major European cities can be reached within less than 2.5h from Darmstadt. From n.strisciuglio at rug.nl Sun Dec 2 11:54:19 2018 From: n.strisciuglio at rug.nl (Nicola Strisciuglio) Date: Sun, 2 Dec 2018 17:54:19 +0100 Subject: Connectionists: Call for contests at CAIP 2019 in Salerno, Italy (2-5 September 2019) Message-ID: ** *18th International Conference on Computer Analysis of Images and Patterns* 2-5 SEPTEMBER, SALERNO ITALY Call for contests The CAIP2019 Organizers invite proposals for contests to be held within the framework of the CAIP Conference. The aim of the contests is to stimulate and share advances in the development of algorithms and methods for computer vision and pattern recognition with objective evaluation on common datasets. The contest organizer is responsible for providing good quality data and defining objective evaluation criteria that are applied to the results of submitted solutions. Proposals should contain the following information: 1. Contest title and abstract. 2. General description of the problem. 3. Description of the dataset to be used. 4. Description of the specific contest tasks. 5. Evaluation metrics or tool to be used for evaluation. 6. Plans for contest web site. 7. Contact information for the organizer(s). 8. Brief CVs of the organizer(s). The following rules will apply to the accepted contests: * All contests must run well in advance of the conference. * Datasets used in the contests should be made available after the end of the contests. * Evaluation methodologies and metrics must be clearly described and easy to apply. * Contests should have sufficient number of participants to be able to draw meaningfulconclusions. * Contest organizers should present the contest organization and results at a special session of CAIP2019. * Reports (full papers) on each contest will be reviewed and, if accepted (the contest run according to plan and is appropriately described), will be published in the CAIP2019 conference proceedings. *Submission* Proposals should be submitted by electronic mail to the CAIP Organizing Committee (caip2019 at unisa.it ) *Important dates* Contest proposal submission deadline: *December 3, 2018* Contest acceptance notification deadline: *December 17, 2018* Contest reports due: *April 30, 2018* If you have any query, please contact the CAIP2019 Organizing Committee. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: geocbmgpmlihpoll.png Type: image/png Size: 54007 bytes Desc: not available URL: From shu-chen.li at tu-dresden.de Sun Dec 2 14:12:33 2018 From: shu-chen.li at tu-dresden.de (Shu-Chen Li) Date: Sun, 2 Dec 2018 19:12:33 +0000 Subject: Connectionists: Two Postdoc (or PhD) Fellow Positions in Multi-Sensory Perception and Perception in Virtual Reality Message-ID: <213503C5-27E6-4C0F-955A-47CCFC97EEBC@contoso.com> The Chair of Lifespan Developmental Neuroscience at TU Dresden, Germany (https://tu-dresden.de/mn/psychologie/ipep/epsy?set_language=en) is searching for two new researchers (Postdoc and/or PhD fellows) through the newly funded Excellence Cluster ?Tactile Internet with Human-in-the-Loop? (https://www.ceti.one/). subject to personal qualification employees are remunerated according to salary group E13 TV-L. The positions are for a fixed term for 3 years and can start as soon as possible in 2019. CeTI-position_Li_1 ? Research associate / Postdoc for human multisensory perception Topic: Psychophysical and neural mechanisms of goal-directed multisensory perception (Research room TP1) Tasks: One of CeTI?s research aims is to understand key psychophysical parameters and neural mechanisms of human multisensory perception and decision making that are sensitive to brain development, brain aging or individual differences in expertise. These parameters are crucial for designing sensors/actuators and closed-loop human-machine interactive models that are sensitive to the user?s age and other user characteristics. This position will be located in TP1, where we will conduct multisensory perception (e.g., audio-tactile, visual-tactile, audio-visual-tactile) and decision making experiments with human participants of different ages, covering early childhood to old age, while assessing functional brain correlates of multisensory perception using electroencephalography (EEG) or near-infrared spectroscopy (NIRS). Requirements: We are looking for a candidate with a PhD degree in cognitive neuroscience, psychology or related fields who has expertise in psychophysical research of sensory and perceptual processes and cognitive neuroscience methods. Interests and prior experiences in computational modelling or human-technology interactions would be a plus. CeTI-position_Li_2 ? Research associate / PhD / Postdoc for augmented perception and action Topic: Age & individual differences in perception and action in augmented and virtual reality (Research rooms TP1 and K3) Tasks: One of CeTI?s research aims is to augment human perception and action with new real-time sensor/actuator technologies. As the new technologies are targeted at a wide population, we need to investigate age and other user characteristics that may influence perception and action in augmented and virtual reality. This position is located in TP1 and K3, where we will contact multisensory behavioural and neurocognitive experiments with human participants in augmented/virtual reality and in situations involving tele-operation. Requirements: We are looking for a candidate with a master?s or PhD degree in human factor engineering, psychology or related fields who has expertise in human-machine systems, augmented /virtual reality and tele-operation. Interests and prior experiences in eye tracking and motion capture technologies as well as EEG analysis would be a plus. How To Apply: [http://www.dresden-concept.de/fileadmin/user_upload/seitenbilder/download/DDC-Logos/DDC-09.png] Please submit your comprehensive application including the usual documentation by January 4th, 2019 (stamped arrival date of the university central mail service applies) with the reference ?CeTI-position_Li_1 or CeTI-position_Li_2? (as given above) in the subject header preferably via the TU Dresden SecureMail Portal https://securemail.tu-dresden.de or S/MIME encrypted by sending it as a pdf document to positions at ceti.tu-dresden.de and shu-chen.li at tu-dresden.de or by mail to: TU Dresden, Sprecher des Exzellenzclusters CeTI, Herrn Prof. Frank H. P. Fitzek, Helmholtzstr. 10, 01069 Dresden, Germany. Please submit copies only as your application documents will not be returned. Expenses incurred in attending interviews cannot be reimbursed. We look forward to your applications! -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 8534 bytes Desc: image001.png URL: From richard.jiang at northumbria.ac.uk Sun Dec 2 20:41:12 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Mon, 3 Dec 2018 01:41:12 +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: as soon as possible Notification of initial editorial decisions: 2-3 days after abstract submission 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 ? Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia Email: chli at csu.edu.au ? Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark Email: weme at dtu.dk ? 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 sbminna at gmail.com Mon Dec 3 03:14:01 2018 From: sbminna at gmail.com (Inna S) Date: Mon, 3 Dec 2018 10:14:01 +0200 Subject: Connectionists: posting a position in computational neuroscience Message-ID: I'd appreciate posting a following position in computational neuroscience at the Gonda Multidisciplinary Brain Research Center at Bar-Ilan University, thank you and best regards, Inna Sukhotinsky, PhD *Faculty Positions at the Gonda Brain Research Center, Bar-Ilan University* The Gonda Multidisciplinary Brain Research Center at Bar-Ilan University anticipates new tenure track positions (rank commensurate with qualifications and experience), starting in the academic years 2019-2020. We are looking for excellent early-stage scientists who aspire to establish innovative and interdisciplinary research programs in neuroscience. One position is open for a candidate particularly with a computational focus, including theoretical neuroscience and modelling. The second position is open for neuroscience research broadly defined, including systems and cognitive neuroscience, molecular neurobiology, and biological psychiatry. All applicants will be evaluated for merit. The appointments are subject to budgetary approval. The Gonda Multidisciplinary Brain Research Center at Bar-Ilan University brings together researchers from a variety of fields essential for understanding the brain, including life sciences, neurophysiology, psychology, linguistics, computer science, mathematics and physics. Research at the Center addresses the brain at all levels - from behavior and cognitive processing through neural circuits, all the way to molecular mechanisms, in health and in disease. Candidates are expected to have a doctorate and post-doctoral training in relevant fields, and to show an excellent track-record for their stage of career. Interested candidates should submit a letter of application, CV and a research statement. For more information, inquiries and applications, please contact Dr. Inna Sukhotinsky (Inna.Sukhotinsky at biu.ac.il). BIU is an equal opportunity employer and all qualified applicants will receive consideration for employment. Application deadline 31/12/2018 -------------- next part -------------- An HTML attachment was scrubbed... URL: From nnavarin at math.unipd.it Mon Dec 3 05:35:35 2018 From: nnavarin at math.unipd.it (=?utf-8?Q?Nicol=C3=B2_Navarin?=) Date: Mon, 3 Dec 2018 11:35:35 +0100 Subject: Connectionists: CFP Special Session on Learning Representations for Structured Data (LR4SD) @ IJCNN 2019 Message-ID: <15534_1543834239_wB3AoaGP017836_B2BFC20E-5F68-4C52-BFA6-D6F47F3BC036@math.unipd.it> ** Apologies for cross-posting** CFP: Special Session on "Learning Representations for Structured Data" 2019 International Joint Conference on Neural Networks (IJCNN) July 14-19 2019, Budapest, Hungary https://sites.google.com/view/lr4sd-ijcnn19 Important Dates: Paper submission: 15 December 2018 Notification of acceptance: 30 January 2019 Aims and Scope: Structured data, e.g. sequences, trees and graphs, are a natural representation for compound information made of atomic information pieces (i.e. the nodes and their labels) and their intertwined relationships, represented by the edges (and their labels). Sequences are simple structures representing linear dependencies such as in genomics and proteomics, or with time series data. Trees, on the other hand, allow to model hierarchical contexts and relationships, such as with natural language sentences, crystallographic structures, images. Graphs are the most general and complex form of structured data allowing to represent networks of interacting elements, e.g. in social graphs or metabolomics, as well as data where topological variations influence the feature of interest, e.g. molecular compounds. Being able to process data in these rich structured forms provides a fundamental advantage when it comes to identifying data patterns suitable for predictive and/or explorative analyses. This has motivated a recent increasing interest of the machine learning community into the development of learning models for structured information. On the other hand, recent improvements in the predictive performances shown by machine learning methods is due to their ability, in contrast to traditional approaches, to learn a ?good? representation for the task under consideration. Deep Learning techniques are nowadays widespread, since they allow to perform such representation learning in an end-to-end fashion. Nonetheless, representations learning is becoming of great importance in other areas, such in kernel-based and probabilistic models. It has also been shown that, when the data available for the task at hand is limited, it is still beneficial to resort to representations learned in an unsupervised fashion, or on different, but related, tasks. This session focuses on learning representation for structured data such as sequences, trees, graphs, and relational data. Topics that are of interest to this session include, but are not limited to: - Probabilistic models for structured data - Structured output generation (probabilistic models, variational autoencoders, adversarial training, ?) - Deep learning and representation learning for structures - Learning with network data - Recurrent, recursive and contextual models - Reservoir computing and randomized neural networks for structures - Kernels for structured data - Relational deep learning - Learning implicit representations - Applications of adaptive structured data processing: e.g. Natural Language Processing, machine vision (e.g. point clouds as graphs), materials science, chemoinformatics, computational biology, social networks. Submission: - For paper guidelines please visit https://www.ijcnn.org/paper-submission-guidelines - For submissions please select the single topic "S11. Learning Representations for Structured Data" from the "S. SPECIAL SESSIONS" category as the main research topic on https://ieee-cis.org/conferences/ijcnn2019/upload.php Organisers: - Davide Bacciu, University of Pisa - Thomas G?rtner, University of Nottingham - Nicol? Navarin, University of Padova - Alessandro Sperduti, University of Padova For any enquire, please write to: bacciu [at] di.unipi.it or nnavarin [at] math.unipd.it ? Nicol? Navarin, PhD Assistant Professor University of Padova - Department of Mathematics via Trieste 63, 35121 Padova - Italy -------------- next part -------------- An HTML attachment was scrubbed... URL: From iswc.conf at gmail.com Mon Dec 3 05:54:05 2018 From: iswc.conf at gmail.com (International Semantic Web Conference) Date: Mon, 3 Dec 2018 11:54:05 +0100 Subject: Connectionists: [CfP] ISWC 2019 - Joint CfP: 18th International Semantic Web Conference (ISWC 2019) Message-ID: ***Joint CfP: 18th International Semantic Web Conference (ISWC 2019)*** ?knowledge graphs, linked data, linked schemas and AI on the Web? Auckland, New Zealand, 26-30 October, 2019 The International Semantic Web Conference (ISWC) is the premier venue for presenting fundamental research, innovative technology, and applications concerning semantics, data, and the Web. It is the most important international venue to discuss and present latest advances and applications of the semantic Web, knowledge graphs, linked data, ontologies and artificial intelligence (AI) on the Web. Follow us: Twitter: @iswc_conf , #iswc_conf ( https://twitter.com/iswc_conf ) LinkedIn: https://www.linkedin.com/groups/13612370 Facebook: https://www.facebook.com/ISWConf/ Become part of ISWC 2019 by submitting to the following tracks & activities or just attend them! (All deadlines are midnight Hawaii time.) 1. Call for Workshops: https://iswc2019.semanticweb.org/call-for-workshop-proposals/ Call for Tutorials: https://iswc2019.semanticweb.org/call-for-tutorial-proposals/ Deadline: January 18, 2019 2. Call for Semantic Web Challenge Proposals: https://iswc2019.semanticweb.org/call-for-challenge/ Deadline: January 18, 2019 3. Call for Papers: Research Track: https://iswc2019.semanticweb.org/call-for-research-track-papers/ Call for Papers: Resources Track: https://iswc2019.semanticweb.org/call-for-resources-track-papers/ Call for Papers: In-Use Track: https://iswc2019.semanticweb.org/call-for-in-use-track-papers/ Abstract deadline: April 3, 2019 4. Call for Papers: Doctoral Consortium: https://iswc2019.semanticweb.org/call-for-doctoral-consortium-papers/ Deadline: April 17, 2019 5. Call for Papers: Journal Track: https://iswc2019.semanticweb.org/call-for-journal-track/ Deadline: May 29, 2019 6. Call for Papers: Poster and Demos: https://iswc2019.semanticweb.org/call-for-posters-demos/ Deadline: June 28, 2019 7. Call for Papers: Industry Track: https://iswc2019.semanticweb.org/call-for-industry/ Deadline: June 28, 2019 8. Call for Papers: Outrageous Ideas Track: https://iswc2019.semanticweb.org/call-for-outrageous-papers/ Deadline: June 28, 2019 9. Call for Presentations: Minute Madness: TBA Deadline: October 27, 2019 The ISWC 2019 Organising Team ( https://iswc2019.semanticweb.org/organizing-committee/ ) -------------- next part -------------- An HTML attachment was scrubbed... URL: From nnavarin at math.unipd.it Mon Dec 3 05:37:18 2018 From: nnavarin at math.unipd.it (=?utf-8?Q?Nicol=C3=B2_Navarin?=) Date: Mon, 3 Dec 2018 11:37:18 +0100 Subject: Connectionists: CFP Special Session on Deep learning for brain data (DL4BRAIN) @ IJCNN 2019 Message-ID: ** Apologies for cross-posting** CFP: Special Session on "Deep learning for brain data" 2019 International Joint Conference on Neural Networks (IJCNN) July 14-19 2019, Budapest, Hungary https://sites.google.com/view/dl4brain Important Dates: Paper submission: 15 December 2018 Notification of acceptance: 30 January 2019 Aims and Scope: Structural and Functional techniques to investigate brain, such as MRI, CT scan, fMRI, EEG, PET, are nowadays widely used both for basic research (for instance on cognition) or for clinical purposes (for instance diagnosis of brain based disorders). In the past two decades, scientists have tried to use these techniques to study brain functioning, to investigate human cognition, to assist the diagnosis of brain-based disorders, and to try to predict the prognosis of patients. Unfortunately, the attempts to find a technique that achieve results with the potential to be translated to daily practice have not succeeded due to the presence of complex, distributed and subtle individual differences that are difficult to detect using standard statistical techniques. Very recently, this research field witnessed an exponential increased interest in the application of Machine Learning (ML) methods, and in particular of Deep Learning (DL), to brain data to support researchers in the study of cognition and to support clinicians in the diagnosis and prognosis of brain-based disorders. To date, applications of ML/DL techniques to brain data is still an under-investigated field of research. The aim of this special session is twofold: first, it provides a point of contact between scientists and researchers from the machine learning and medical communities (medicine, neuroscience, psychology, psychophysiology, etc.), encouraging a multidisciplinary view on open problems. Second, it provides a forum to present original ideas, theories and novel applications of ML/DL to brain data, and to find solutions to open issues. Topics that are of interest to this session include, but are not limited to: - Presentation of new structural and functional brain data databases; - Computer vision applied to MRI, fMRI, DTI, PET; - Time series analysis applied to EEG; - New advancement in Deep Learning algorithms for brain data; - Application of Deep Learning to brain data to study cognition (e.g., attention, language, memory, decision making, problem solving, spatial abilities); - Application of Deep Learning to brain data for clinical diagnosis and prognosis of psychiatric and neurologic disorders; - Application of Deep Learning to brain data for identification of risk factors of neurologic and psychiatric disorders; - Application of Deep Learning to evaluate the impact of inter-scanner variability on the results; - Multicentric studies on brain MRI data; - Integrating functional and structural information to enhance clinical diagnosis and prognosis; - Integrating functional and structural information to enhance the understanding of cognitive processes; Submission: - For paper guidelines please visit https://www.ijcnn.org/paper-submission-guidelines - For submissions please select the single topic "S10. Deep learning for brain data" from the "S. SPECIAL SESSIONS" category as the main research topic on https://ieee-cis.org/conferences/ijcnn2019/upload.php Organisers: - Nicol? Navarin, University of Padova, Italy - Cristina Scarpazza, University of Padova, Italy - Merylin Monaro, University of Padova, Italy For any enquire, please write to: nnavarin [at] math.unipd.it, cristina.scarpazza [at] unipd.it or merylin.monaro [at] unipd.it ? Nicol? Navarin, PhD Assistant Professor University of Padova - Department of Mathematics via Trieste 63, 35121 Padova - Italy -------------- next part -------------- An HTML attachment was scrubbed... URL: From Pavis at iit.it Mon Dec 3 11:56:48 2018 From: Pavis at iit.it (Pavis) Date: Mon, 3 Dec 2018 16:56:48 +0000 Subject: Connectionists: =?cp1258?q?PostDoc_on_Computer_Vision_on_Cultural?= =?cp1258?q?_Heritage_Technologies_=28CCHT=40Ca=CCFoscari=29_BC_75117?= In-Reply-To: References: Message-ID: PostDoc on Computer Vision on Cultural Heritage Technologies (CCHT at Ca?Foscari) - [ Postdoc ] BC 75117 Workplace: Venezia, CCHT, Italy The IIT center at Ca' Foscari University in Venice - Center for Cultural Heritage Technology at Ca?Foscari (CCHT at Ca?Foscari) has the mission to research and promote new technologies and to extend existing techniques for preservation and analysis of the invaluable Cultural Heritage assets managed by cities, galleries, libraries, archives and museums across different fields of art. CCHT at Ca?Foscari is currently seeking to appoint a Computer Vision Postdoc. The selected candidate will join an interdisciplinary team of researchers, contributing to the development of next-generation 3D digitization and machine learning approaches applied to the Cultural Heritage (CH) and Digital Humanities (DH) domain. Required qualifications: - A Ph.D. in computer science (with specialization in either computer vision or machine learning) or related field; - Proficiency with programming languages, in particular, Python, C/C++ and MATLAB; - Experience in the 3D computer vision field e.g. 3D reconstruction from RGBD data, photometric stereo, structure from motion, BRDF estimation, structured light systems. - Publications in major Computer Vision and/or Computer Graphics conferences/journals (e.g. CVPR, ICCV, ECCV, SIGGRAPH, Eurographics, ToG, TPAMI, IJCV, IVC, CVIU). - Good communication skills and ability to cooperate; - Proficient in English language (written and oral). Desirable skills: - Knowledge of OpenCV, PCL and Open3D libraries; - Practical experience on Deep Learning algorithms and relevant platforms for geometric learning (e.g. TensorFlow, PyTorch, Theano, Caffe); - Experience in Cultural Heritage 2D-3D digitization and analysis. The successful candidate will be offered a salary commensurate to experience and skills. The call will remain open until the position is filled but the first deadline for evaluation of candidates will be January 6, 2019. Please send your application to ccht at iit.it quoting ?CCHT Computer Vision Postdoc ? BC 75117? in the e-mail subject. Your application shall contain i) a detailed CV, ii) a one-page research statement and iii) contact information of two referees. Fondazione Istituto Italiano di Tecnologia (http://www.iit.it) is a non-profit institution created with the objective of promoting technological development and higher education in science and technology. Research at IIT is carried out in highly innovative scientific fields with state-of-the-art technology. Istituto Italiano di Tecnologia is an equal opportunity employer that actively seeks diversity in the workforce. Please note that the data that you provide will be used exclusively for the purpose of professional profiles? evaluation and selection and in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, based in Genoa, Via Morego 30, acting as Data Controller, in compliance with the rules on protection of personal data, including those related to data security. Please also note that, pursuant to articles 15 et. seq. of European Regulation no. 679/2016 (General Data Protection Regulation), you may exercise your rights at any time by contacting the Data Protection Officer (phone +39 010 71781 - email: dpo at iit.it) -------------- next part -------------- An HTML attachment was scrubbed... URL: From andreas.weiler at data-service-alliance.ch Mon Dec 3 10:45:17 2018 From: andreas.weiler at data-service-alliance.ch (Andreas Weiler) Date: Mon, 3 Dec 2018 16:45:17 +0100 Subject: Connectionists: CfP 6th Swiss Conference on Data Science (IEEE technically co-sponsored) Message-ID: -------- Call for Papers / Participation The 6th Swiss Conference on Data Science (IEEE technically co-sponsored) -------- 6th Swiss Conference on Data Science 2019 (SDS2019) 14 June 2019, Kursaal, Bern, Switzerland (https://sds2019.ch/) * Introduction * We are happy to announce the 6th Swiss Conference on Data Science (SDS2019) in continuation of what has successfully started with the past events. SDS2019 brings together opinion-leaders, practitioners, decision-makers and researchers with interest in Data Science. The goal is to foster the exchange of ideas for innovative products and services especially for the Swiss market and to sustain the community of Data Scientists. SDS2019 will have talks in 2 distinct streams of academic and business contributions. The accepted academic paper proceedings will be published in IEEE Xplore digital library. For businesses, talks having business impact and data-driven innovation concepts are invited and will be presented. Get access to trends, innovations, and technologies that you can directly use for the development of your products, solutions, and applications based on data, and use the breaks for networking and discussion with peers. * Awards * - Best Paper Award: The program committee will carefully evaluate the submitted papers according to their originality, contributions to the field, quality of presentation, and soundness of the science and will then select a paper for the best paper award that receives a cash price of CHF 1,500. - Best Presentation Award: The best presentation will be elected through an online voting system that is available for the participants during the conference. Keynote speakers will not be eligible for the best presentation price, which is a cash price of CHF 1,??500. - Best Reproducibility Award: This award recognizes the best papers in terms of reproducibility. The criteria include flexibility, coverage, and code replication as well as data availability of the research work. The recipient of this award receives a cash prize of CHF 1,??500. * Academic Track * We invite submissions of original research papers related to all aspects of data science, especially best practice and use-case oriented research work with technical depth and practical applicability. We also highly welcome innovative demos, show-cases, and awesome data products. ** Topics of interest include (but are not limited to) ** - artificial intelligence and autonomous machines - big data mining and analytics - data mining applications in healthcare, finance, and industry - data ethics and society - data integration, governance, and sharing - data intelligence and security - machine learning - natural language processing and analysis - predictive modelling and analytics - spatial data analysis - techniques and tools for data science - user interfaces and data visualization ** Submission ** - Full Paper: present high-quality research contributions, including experiment, analysis, or system papers, as well as descriptions of industrial and application results. Each submission can have up to 6 pages incl. references. - Short Paper: present late-breaking results, work in progress, follow-up extensions, application case studies, or evaluations of existing methods. Each submission can have up to 2 pages incl. references. - Roundtable Discussion: intimate, moderated group discussions of current topics important to the field of data science. The objective is to trade ideas and thoughts with other engaged individuals with similar interests and questions. Submissions can have up to 1 page and needs to contain an abstract, a description of the questions or pointers to the controversy of the topic, and a short biography. The duration of each session is 30 minutes, including topic introduction (~5 mins) of the topic leader. All submissions must be original works that have not been published previously in any conference proceedings, magazine, journal, or edited book. Concurrent submissions are strictly forbidden. If it is determined that a manuscript is simultaneously under the consideration by another publication venue, the manuscript will be rejected. Submission of papers implies intention to register and present the related content at the conference. The academic program committee will carefully review the submissions. Excellent content and presentation as demonstrated in the submission are mandatory for acceptance. Accepted submissions will be presented in English by the authors at the conference. Proceedings papers presented at the conference will be submitted for inclusion in the IEEE Xplore digital library. All submissions must be formatted by following the following the IEEE 8.5??? x 11??? two-column format. ** Steering Committee ** - Markus Christen, University of Zuerich - Melanie Geiger, Zuerich University of Applied Sciences - Christoph Heitz, Zuerich University of Applied Sciences - Thilo Stadelmann, Zuerich University of Applied Sciences - Andreas Weiler, Zuerich University of Applied Sciences ** Program Committee ** - Kubilay Atasu, IBM Research - Joeran Beel, Trinity College Dublin - Michael Brodie, Massachusetts Institute of Technology - Mark Cieliebak, Zuerich University of Applied Sciences - Fabio Crestani, University of Lugano - Andre Csillaghy, University of Applied Sciences and Arts North West Switzerland - Philippe Cudre-Mauroux, University of Fribourg - Giovanna Di Marzo Serugendo, University of Geneva - Oliver Duerr, Konstanz University of Applied Sciences - Andreas Fischer, University of Applied Sciences Western Switzerland - Samuel Fricker, University of Applied Sciences and Arts North West - Switzerland - Bernd Freisleben, University of Marburg - Pascale Frossard, Ecole Polytechnique Fed?ral de Lausanne - Reinhard Furrer, University of Zuerich - Michael Grossniklaus, University of Konstanz - Niels Hagenbuch, Swiss Statistical Society - Anne Herrmann, University of Applied Sciences and Arts North West Switzerland - Stefan Keller, University of Applied Sciences Rapperswil - Hans Kestler, University of Ulm - Diego Kuonen, University of Geneva - Michele Loi, University of Zuerich - Elena Mugellini, University of Applied Sciences Western Switzerland - Henning Mueller, University of Applied Sciences Western Switzerland - Marcello Pelillo, University of Venice - Andres Perez-Uribe, University of Applied Sciences Western Switzerland - Jacques Savoy, University of Neuchatel - Tobias Schreck, University of Graz - Rene Schumann, University of Applied Sciences Western Switzerland - Philipp Schuetz, Luzern University of Applied Sciences - Fabio Sigrist, Luzern University of Applied Sciences - Josef Spillner, Zuerich University of Applied Sciences - Ingo Steinwart, University of Stuttgart - Kurt Stockinger, Zuerich University of Applied Sciences - Matthias Stuermer, University of Bern - Jens Teubner, Technical University Dortmund - Marco Zaffalon, University of Lugano ** Important Dates: ** 1st February 2019 - Paper submission deadline 15th March 2019 - Author notification 1st May 2019 - Camera ready papers deadline * Business Track * We invite submissions of talks related to all aspects of data science, especially best practice and use-case oriented work with technical depth and practical applicability. ** Topics of interest include (but are not limited to): ** - business analytics - data-driven business models - data engineering and architecture - data ethics and society - machine learning - natural language processing - organization, collaboration, culture - streaming and IoT - user interfaces and data visualization ** Submission ** - Business Talk: presentation covering technological aspects, deployment and use of solutions in Data Science. Submissions should be in pdf format and have a maximum length of 2 pages and contain all of the following elements: a title; an extended abstract of no more than 200 words and explaining the business impact / innovation; a description of the target audience; an outline of the intended talk; a short author biography - Roundtable Discussion: intimate, moderated group discussions of current topics important to the field of data science. The objective is to trade ideas and thoughts with other engaged individuals with similar interests and questions. Submissions can have up to 1 page and needs to contain an abstract, a description of the questions or pointers to the controversy of the topic, and a short biography. The duration of each session is 30 minutes, including topic introduction (~5 mins) of the topic leader. The Business Program Committee will carefully review the submissions. Excellent content demonstrating data-driven value creation, business impact and innovation in the submission are mandatory for acceptance. Accepted submissions will be presented in English by the authors at the conference. ** Steering Committee ** - Hans Peter Graenicher, D ONE Solutions - Gundula Heinatz Buerki, Swiss Alliance for Data-Intensive Services ** Program Committee ** - Michael Baeriswyl, Swisscom - Rainer Baumann, SwissRe - Marcel Blattner, Tamedia - Matthias Braendle, Mobiliar - Rodolphe Dewarrat, IMSD - Thomas Duebendorfer, Swiss ICT Investor Club - Alex Hall, Google - Peter Kolbe, SBB - Asif Rana, Hexagon - Marco Roehrle, Ergo - Tanvi Singh, Credit Suisse - Christian Spindler, PwC - Stamatis Stefanakos, D ONE Solutions - Philipp Vetter, Biovotion ** Important Dates: ** 1st February 2019 - Talk submission deadline 5th April 2019 - Speaker notification From Pavis at iit.it Mon Dec 3 12:10:19 2018 From: Pavis at iit.it (Pavis) Date: Mon, 3 Dec 2018 17:10:19 +0000 Subject: Connectionists: PostDoc on Visual Understanding for Cultural Heritage Technologies (CCHT@Ca'Foscari) - [ Postdoc ] BC 75119 In-Reply-To: <8e5c69e67ada4653b3aa72d7c3496426@iit.it> References: <8e5c69e67ada4653b3aa72d7c3496426@iit.it> Message-ID: PostDoc on Visual Understanding for Cultural Heritage Technologies (CCHT at Ca'Foscari) - [ Postdoc ] BC 75119 Workplace: Venezia, IIT, Italy The IIT center at Ca' Foscari University of Venice - Center for Cultural Heritage Technology at Ca'Foscari (CCHT at Ca'Foscari) has the mission to research and promote new technologies and to extend existing techniques for preservation and analysis of the invaluable Cultural Heritage assets managed by cities, galleries, libraries, archives and museums across different fields of art. CCHT at Ca'Foscari is currently seeking to appoint a Visual Understanding Postdoc. The selected candidate will join an interdisciplinary team of researchers, contributing to the development of next-generation 3D digitization and machine learning approaches applied to the Cultural Heritage (CH) and Digital Humanities (DH) domain. Required qualifications: - A Ph.D. in computer science (with specialization in either computer vision, information retrieval or machine learning) or related fields; - Proficiency with programming languages, in particular Python, C/C++ and MATLAB; - Experience of visual recognition or understanding in 2D & 3D, e.g. attribute recognition, object recognition, relationship detection and their multi-view equivalence; - Practical experience on Deep Learning algorithms and relevant platforms for geometric learning (e.g. TensorFlow, PyTorch, Theano, Caffe); - Publication in major Computer Vision and/or Computer Graphics conferences/journals (e.g. CVPR, ICCV, ECCV, SIGGRAPH, Eurographics, ToG, TPAMI, IJCV, IVC, CVIU); - Good communication skills and ability to cooperate; - Proficient in English language (written and oral). Desirable skills: - Knowledge of OpenCV, PCL and Open3D libraries; - Experience of graph structure applications e.g. matching, retrieval or inference; - Knowledge of SPARQL / CIDOC; - Experience on Cultural Heritage knowledge data. The successful candidate will be offered a salary commensurate to experience and skills. The call will remain open until the position is filled but a first deadline for evaluation of candidates will be January 6, 2019. Please send your application to ccht at iit.it quoting "CCHT Visual Understanding Postdoc - BC 75119" in the e-mail subject. Your application shall contain i) a detailed CV, ii) a one-page research statement and iii) contact information of two referees. Fondazione Istituto Italiano di Tecnologia (http://www.iit.it) is a non-profit institution created with the objective of promoting technological development and higher education in science and technology. Research at IIT is carried out in highly innovative scientific fields with state-of-the-art technology. Istituto Italiano di Tecnologia is an equal opportunity employer that actively seeks diversity in the workforce. Please note that the data that you provide will be used exclusively for the purpose of professional profiles' evaluation and selection, and in order to meet the requirements of Istituto Italiano di Tecnologia. Your data will be processed by Istituto Italiano di Tecnologia, based in Genoa, Via Morego 30, acting as Data Controller, in compliance with the rules on protection of personal data, including those related to data security. Please also note that, pursuant to articles 15 et. seq. of European Regulation no. 679/2016 (General Data Protection Regulation), you may exercise your rights at any time by contacting the Data Protection Officer (phone +39 010 71781 - email: dpo at iit.it) -------------- next part -------------- An HTML attachment was scrubbed... URL: From fukumizu at ism.ac.jp Mon Dec 3 22:48:31 2018 From: fukumizu at ism.ac.jp (Kenji Fukumizu) Date: Tue, 4 Dec 2018 12:48:31 +0900 Subject: Connectionists: Two postdoc positions available at Institute of Statistical Mathematics (Tokyo) Message-ID: <9c87e6b6-81c2-fa1b-9dfa-90104926ec43@ism.ac.jp> Dear Connectionists, The Research Center for Statistical Machine Learning at the Institute of Statistical Mathematics (in Tokyo) is looking for two postdoctoral researchers, who are expected to work in some projects on machine learning and statistics, collaborating with other project members. (1) One of the positions is funded by the Institute of Statistical Mathematics, and a researcher is expected to work with Prof. Kenji Fukumizu and other colleagues on machine learning projects. Research topics include kernel methods, deep learning, Bayesian inference, and combinations of these approaches, but are not limited to them. The contract is fiscal-year based with competitive salary, and can be extended up to four years if both sides agree. (2) The other is funded by JST CREST Project, "Topological data analysis for new descriptors on soft matters", and focusing on machine learning and statistical topics related to topological data analysis (TDA).A researcher is expected work in collaborations with some of other project members, who are working in aspects of TDA including mathematics, probability, statistics, and applications. The contract is fiscal-year based with competitive salary, and the position is up to the end of March 2021. For more details, see https://www.ism.ac.jp/jobs/index_e.html or contact Kenji Fukumizu (fukumizu at ism.ac.jp ) If you are around NeurIPS 2018, we can also meet directly. Best regards, Kenji Fukumizu //--------------------- Kenji Fukumizu The Institute of Statistical Mathematics Professor, Department of Mathematical Analysis and Statistical Inference Director, Research Center for Statistical Machine Learning 10-3 Midori-cho, Tachikawa, Tokyo 190-8562 Japan email:fukumizu at ism.ac.jp URL:http://www.ism.ac.jp/~fukumizu/ ------------------------// From julien.vitay at informatik.tu-chemnitz.de Mon Dec 3 16:18:14 2018 From: julien.vitay at informatik.tu-chemnitz.de (Julien Vitay) Date: Mon, 3 Dec 2018 22:18:14 +0100 Subject: Connectionists: Faculty position in Neurorobotics at Chemnitz University of Technology (Germany) Message-ID: The Department of Computer Science at Chemnitz University of Technology (Germany) invites applications for a faculty position in Neurorobotics (W2-Professor with W3 Tenure-Track-Option). Please note that the position is initially limited to a duration of six years and requires a positive tenure review beginning 4 years after starting the position to be continued for an indefinite period as a W3 position. Further, the position includes teaching obligations. Courses can be given in English. Applicants are encouraged to submit their application by January 31, 2019. The complete job advertisement (in German) can be found here: https://www.tu-chemnitz.de/verwaltung/personal/stellen/W2-Neurorobotik.php Informal inquiries can be addressed to: Prof. Dr. Fred Hamker, Chair of the Search Committee (fred.hamker at informatik.tu-chemnitz.de). Best regards Julien Vitay -- Professur f?r K?nstliche Intelligenz Fakult?t f?r Informatik Technische Universit?t Chemnitz, 09107 Chemnitz (+49) 371 531-39468 julien.vitay at informatik.tu-chemnitz.de http://www.tu-chemnitz.de/~vitay/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From xfern at eecs.oregonstate.edu Tue Dec 4 01:47:54 2018 From: xfern at eecs.oregonstate.edu (Xiaoli Fern) Date: Mon, 3 Dec 2018 22:47:54 -0800 Subject: Connectionists: Faculty position in AI, ML and related areas at Oregon State University Message-ID: <006c01d48b9d$495d13b0$dc173b10$@eecs.oregonstate.edu> The School EECS at Oregon State University is hiring in AI, machine learning and other related areas. Appointments are anticipated at the Assistant Professor rank, but candidates with exceptional qualifications may be considered for appointment at the rank of Associate or Full Professor. We are a highly collaborative school with strong research in many areas, and are on a rapid growth path. The university is located in Corvallis, at the heart of Oregon's Willamette Valley and close to Portland's Silicon Forest with numerous collaboration opportunities. Many faculty members of the School of EECS are active participants of the recently established Collaborative Robotics and Intelligent Systems Institute (CoRIS). The school hosts an innovative distance education post-baccalaureate degree program in computer science which is highly rated. Corvallis has been ranked # 1 on a list of "Best Places for Work-Life Balance" and is within easy reach of the Cascade Mountains and the Oregon Coast. The full consideration date is December 15, 2018. Please see the following link for more information regarding these positions. http://eecs.oregonstate.edu/prospective-faculty/current-job-openings Best, Xiaoli Fern Associate Professor School of EECS, Oregon State University -------------- next part -------------- An HTML attachment was scrubbed... URL: From stefano.rovetta at unige.it Tue Dec 4 06:48:04 2018 From: stefano.rovetta at unige.it (Stefano Rovetta) Date: Tue, 4 Dec 2018 12:48:04 +0100 Subject: Connectionists: CFP: Evolving and adaptive fuzzy models for data streams @EUSFLAT2019 In-Reply-To: References: Message-ID: *** CALL FOR PAPERS *** Evolving and adaptive fuzzy models for data streams https://sites.google.com/view/fuzzystreams Special session at EUSFLAT2019, September 9-13, 2019 - Prague http://eusflat2019.cz/ Scope Nowadays a wide range of real-world scenarios yield data streams, i.e. collections of data being generated continuously either over time or over space. E-commerce and banking transactions, weather forecasting recordings and sensor data, customer reports and network traffic records are common examples of data streams produced every day. Accordingly there is an urgent need of methods capable to handle and analyze streams of data that are usually vast in volume (or possibly infinite), high-dimensional and changing dynamically. Analysis of data streams requires models that are specifically designed to adapt continuously and automatically to smooth evolutions (drifts) and abrupt changes (shifts) in the data distribution. Evolving intelligent systems (EIS) is an emerging field that focuses on adaptive evolving models in soft computing. The main objective of this special session is to discuss the potential of fuzzy techniques to develop EIS for prediction and classification tasks in challenging scenarios involving data streams. Topics The special session is intended to collect novel ideas and share different experiences in the field of evolving fuzzy models for data streams. Submission of papers covering theoretical and application aspects of evolving fuzzy models are encouraged. Possible topics include (but are not limited to): - Learning in non-stationary environments - Online/incremental fuzzy clustering - Fuzzy techniques for data stream mining - Evolving Fuzzy Systems - Evolving Rule-Based Classifiers - Evolving Neuro-Fuzzy Systems - Adaptive Evolving Fuzzy Systems - Online Genetic and Evolutionary Algorithms - Adaptive Pattern Recognition - Incremental and Evolving Fuzzy ML Classifiers - Big Data analysis through Fuzzy techniques Important dates Paper submission deadline: February 1, 2019 Notification of acceptance: April 1, 2019 Please submit your manuscript according to the general instructions for authors for EUSFLAT 2019, http://eusflat2019.cz/submission.html Submissions to EUSFLAT2019 can be either for a full papers, to be included in the proceedings (indexed book), or for a 1-page abstract, which will appear in the book of abstracts (with ISBN). Accordingly, in the first submission step please choose either of the two tracks "Full papers in proceedings" or "Book of Abstracts". Then in the second step choose the special session "Evolving and adaptive fuzzy models for data streams". Organizers Giovanna Castellano, giovanna.castellano at uniba.it Dept. of Computer Science - University of Bari Aldo Moro, Italy Stefano Rovetta, stefano.rovetta at unige.it Dept. of Informatics, Bioengineering, Robotics and Systems Engineering University of Genova, Italy Zied Mnasri, zied.mnasri at enit.utm.tn University of Tunis El Manar, Tunisia From m.lengyel at eng.cam.ac.uk Tue Dec 4 12:01:29 2018 From: m.lengyel at eng.cam.ac.uk (=?utf-8?B?TcOhdMOpIExlbmd5ZWw=?=) Date: Tue, 4 Dec 2018 18:01:29 +0100 Subject: Connectionists: faculty positions at the Central European University Message-ID: Note that the search below includes machine learning even if it is not specified explicitly in the advert. https://hro.ceu.edu/vacancies/faculty-positions-2 *** The Department of Network and Data Science [http://networkdatascience.ceu.edu] at the Central European University (CEU) [https://www.ceu.edu/] invites applications for two full-time faculty positions (one at the associate and one at the assistant professor level) in the area of network science and data science. The Department of Network and Data Science was established as an interdisciplinary unit, integrating natural science and social science approaches. CEU is a graduate research-intensive university specializing in the social sciences, humanities, law, public policy and management. It is accredited in the United States and Hungary. CEU?s mission is to promote academic excellence, state-of-the-art research, research-based teaching and learning and civic engagement, in order to contribute to the development of open societies in Central and Eastern Europe, the former Soviet Union, and other emerging democracies throughout the world. CEU offers both Master?s and doctoral programs, and enrolls more than 1,400 students from over 100 countries. The teaching staff consists of more than 180 resident faculty, from over 50 countries, and a large number of prominent visiting scholars from around the world. The language of instruction is English. CEU is an equal opportunity employer. We expect applications from network scientists, data scientists, or social scientists with an excellent publication record. We especially encourage researchers with experience in: social networks and organizations, urban mobility and spatial networks, digital inequalities, data visualization, economic complexity. The candidates should have strong motivation to conduct interdisciplinary research and be interested in participating in projects with several departments at CEU. Capability of high-quality teaching is assumed. Candidates should have a PhD in either network science, data science, social science, physics, or equivalent by the start date (August 1) as well as an excellent record of publications in international peer-reviewed journals. We offer a competitive salary that is commensurate with experience as well as a dynamic and international academic environment. Teaching load is comparable to that of research universities. The normal teaching load at CEU is 12 taught credits (where one credit equals 50 minutes of classroom contact over a 12-week academic term) per academic year, plus thesis supervision. Applicants need to submit: ? A comprehensive C.V., ? Names of three referees (candidates should ask two referees to send recommendations directly to the CEU) ? List of publications, ? A sample publication, ? And a short statement of research and teaching. Review of applications will begin January 14, 2019 and will continue until the positions are filled. Start date: Aug 1, 2019 Questions of an academic nature may be addressed to Janos Kertesz (cc), Director of the Department of Network and Data Science (kerteszj at ceu.edu) Please send your complete application package to: advert098 at ceu.edu - including job code in subject line: 2018/098 The privacy of your personal information is very important to us. We collect, use, and store your personal information in accordance with the requirements of the General Data Protection Regulation. To learn more about how we manage your personal data during the recruitment process, please see our Privacy Notice at https://hro.ceu.edu/KEE_privacy_notice. -- Mate Lengyel Professor of Computational Neuroscience Computational and Biological Learning Lab Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ, UK tel: +44 (0)1223 748 532, fax: +44 (0)1223 332 662 Senior Research Fellow Department of Cognitive Science Central European University Oktober 6 street 7, Budapest H-1051, Hungary tel: +36 1 887 5142 , fax: +36 1 887 5010 From amir.aly at em.ci.ritsumei.ac.jp Tue Dec 4 12:27:49 2018 From: amir.aly at em.ci.ritsumei.ac.jp (Amir Aly) Date: Wed, 5 Dec 2018 02:27:49 +0900 Subject: Connectionists: SoAIR 2019: IEEE-RAS Spring School on "Social and Artificial Intelligence for User-Friendly Robots" in Japan Message-ID: CALL FOR APPLICATIONS **Apologies for cross posting ** We are pleased to call for applications for the IEEE-RAS spring school on: "*Social and Artificial Intelligence for User-Friendly Robots*" * Which will be held from 17-24 March, 2019 in Shonan Village, Japan *after the *Human-Robot Interaction (HRI)* conference that will be held in the near South Korea. *Webpage: **https://inic8.bitbucket.io/SoAIR19/* *I. Aim and Scope *Autonomous and intelligent systems are progressively moving into spaces, which have previously been predominantly shaped by human agency. Unlike in the past where machines obediently served their human operators, machines now increasingly act without the intervention of a human. Artificial intelligence is meeting new challenges in the world, though human-like intelligence may still be a distant goal. Robots in factories are coming out of their cages. Autonomous cars are being tested on streets with regular human-driven cars. The private household is changing with the appearance of not only robotic vacuum cleaners, but also with the first-generation of social robots and smart devices. The challenges that face both the robotics and artificial intelligence communities are how the necessary intelligence for such new environments can be created as well as how to make artificial agents capable of not only solving tasks at hand but also considering social environments around them during interaction with human users so as to behave appropriately. Within the school, we plan to address the tension created by the balance between task-specific artificial intelligence and the demands of sociability required to function effectively in human-centered environments. ** *Who should apply?* We invite *Masters and PhD students* as well as *post-doctoral candidates and researchers from industry* with relevant research background to apply for this spring school. ** *This spring school is a Technical Education Program (TEP) endorsed and supported by IEEE-RAS*. ** *The school aims at bridging the gap between social and cognitive Human-Robot Interaction (HRI), Artificial Intelligence (AI), and Autonomous Vehicles (AV) through high level talks, tutorials, and hands-on workshops (the program will be announced soon).* *II. Keynote Speakers: * 1. * Jun Tani *? Okinawa Institute of Science and Technology (OIST), Japan 2. *Daniele Magazzeni *? King's College London, UK 3. * Yukie Nagai *? National Institute of Information and Communications Technology (NICT), Japan 4. * Tetsuya Ogata* ? Waseda University, Japan 5. *Mohamed Chetouani *? University of Pierre and Marie Curie (UPMC), France 6. *Silvia Rossi* ? University of Naples, Italy 7. *Agnieszka Wykowska *? Italian Institute of Technology (IIT), Italy 8. *Tetsunari Inamura *? National Institute of Informatics (NII), Japan 9. *Amit Kumar Pandey *? SoftBank (Aldebaran) Robotics, France 10. *Mehul Bhatt* ? Orebro University, Sweden (Tutorial) 11. *Mohsen Kaboli ?* Bavarian Motor Works (BMW), Germany (Tutorial) 12. *Francesco Maurelli *? Jacobs University, Germany (Preparing Marie Curie funding proposal) 13. *Atsuko Nakatsuka* ? Japan Society for the Promotion of Science (JSPS), Japan (Preparing JSPS funding proposal) *III. Submission * The applications must include the following files (combined into one file). No other documents would be necessary (More information is available on the school's webpage). 1. *Curriculum vitae*: A CV detailing relevant aspects of the candidate's academic career that demonstrates her/his relevance to the school theme. Please consider including the list of publications. 2. *Research abstract*: A 200-word research abstract that the candidate intends to present during the school. 3. *Letter of recommendation*: A brief letter from the academic advisor or the employer of the candidate supporting her/his application. Please also indicate if partial support would be required to attend the school. *Application submission*: Please use the following EasyChair web link:* Application Submission .* *IV. Important Dates * 1. Application submission: *20-December, 2018 * 2. Notification of acceptance: *28-December, 2018 * 3. Spring School: *17-24 March, 2019* *V. Organizers * 1. *Amir Aly *? Ritsumeikan University ? Japan 2. *Franziska Kirstein *? Blue Ocean Robotics, Denmark 3. * Shashank Pathak *? Visteon Corporation, Germany --------------------- *Amir Aly, Ph.D.* Senior Researcher Emergent Systems Laboratory College of Information Science and Engineering Ritsumeikan University 1-1-1 Noji Higashi, Kusatsu, Shiga 525-8577 Japan -------------- next part -------------- An HTML attachment was scrubbed... URL: From papaleon at sch.gr Tue Dec 4 17:50:50 2018 From: papaleon at sch.gr (Papaleonidas Antonis) Date: Wed, 5 Dec 2018 00:50:50 +0200 Subject: Connectionists: AIAI2019 - EANN2019 @ Crete, Greece - 2nd Call for Papers In-Reply-To: References: Message-ID: <00B2C294CB794BB691F64B69EB98B3B2@main> AIAI2019 - EANN2019 @ Crete, Greece - 2nd Call for PapersAIAI 2019 - EANN 2019, 24 - 26 May 2019 @ Crete, Greece 2nd CALL FOR PAPERS for 20th EANN - 15th AIAI 2019 @ Crete, Greece Dear colleagues We would like to invite you to submit your work at the 20th International Conference on Engineering Applications of Neural Networks (EANN2019) - 15th International Conference on Artificial Intelligence Applications and Innovations (AIAI2019) joint Conferences. EANN2019 / AIAI2019 are Technically sponsored by INNS / IFIP WG12.5 Websites: eann2019.eu - aiai2019.eu IMPORTANT DATES: . Paper Submission Deadline: 9th of February 2019 . Notification of Acceptance: 3rd of March 2019 . Conference: 24 - 26 of May 2019 SPECIAL ISSUES - PROCEEDINGS: Selected papers from the main event and workshops will be published in special issues of scientific Journals . Special Issue of the Neural computing and Applications SPRINGER journal Impact Factor 4.2 . Special Issue of the Evolving Systems Journal (SPRINGER) PROCEEDINGS will be published by SRINGER LNBIP Series for EANN2019 and in SPRINGER IFIP AICT for AIAI2019 VENUE: island of CRETE Greece, 5 stars ALDEMAR KNOSSOS ROYAL BEACH RESORT https://www.aldemar-resorts.gr/hotel/knossos-royal/ SPECIAL PRICES are arranged for conference participants WORKSHOPS: . 8th Mining Humanistic Data Workshop . 4th 5G-PINE (5G ? Putting Intelligence to the Network Edge) TUTORIALS: . "Deep learning in Medicine and Bioinformatics: state of art and potentialities, visions" Tutorial (2 hours) by Professor Pietro Lio, University of Cambridge, UK . "Automated Machine Learning for Bioinformatics and Computational Biology", Tutorial (3 hours) by Ioannis Tsamardinos, Vincenzo Lagani KEYNOTE SPEAKERS: . Professor Panagiotis Papapetrou, Dept. of Computer and Systems Sciences, Stockholm University . Dr. Evangelos Eleftheriou, IBM Fellow, Cloud & Computing Infrastructure, Zurich Research Laboratory, Zurich, Switzerland . Professor Plamen Angelov, University of Lancaster, UK Conference topics, CFPs and submissions details can be found at: . http://www.aiai2019.eu/cfp/ . http://www.eann2019.eu/cfp/ -------------------------------------------------------------------------------- Dr Papaleonidas Antonios Publication Chair of AIAI2019 & EANN 2019 Civil Engineering Department Democritus University of Thrace papaleon at sch.gr -------------- next part -------------- An HTML attachment was scrubbed... URL: From n.strisciuglio at rug.nl Wed Dec 5 05:25:44 2018 From: n.strisciuglio at rug.nl (Nicola Strisciuglio) Date: Wed, 5 Dec 2018 11:25:44 +0100 Subject: Connectionists: Call for Contests at CAIP 2019 (Salerno, Italy) - Extended deadline December 10th Message-ID: <174a41a9-130a-4bb6-7224-a03c2f59ffa7@rug.nl> /Apologies for cross-postings./ ** *18th International Conference on Computer Analysis of Images and Patterns* 2-5 SEPTEMBER, SALERNO ITALY Call for contests The CAIP2019 Organizers invite proposals for contests to be held within the framework of the CAIP Conference. The aim of the contests is to stimulate and share advances in the development of algorithms and methods for computer vision and pattern recognition with objective evaluation on common datasets. The contest organizer is responsible for providing good quality data and defining objective evaluation criteria that are applied to the results of submitted solutions. Proposals should contain the following information: 1. Contest title and abstract. 2. General description of the problem. 3. Description of the dataset to be used. 4. Description of the specific contest tasks. 5. Evaluation metrics or tool to be used for evaluation. 6. Plans for contest web site. 7. Contact information for the organizer(s). 8. Brief CVs of the organizer(s). The following rules will apply to the accepted contests: * All contests must run well in advance of the conference. * Datasets used in the contests should be made available after the end of the contests. * Evaluation methodologies and metrics must be clearly described and easy to apply. * Contests should have sufficient number of participants to be able to draw meaningfulconclusions. * Contest organizers should present the contest organization and results at a special session of CAIP2019. * Reports (full papers) on each contest will be reviewed and, if accepted (the contest run according to plan and is appropriately described), will be published in the CAIP2019 conference proceedings. *Submission* Proposals should be submitted by electronic mail to the CAIP Organizing Committee (caip2019 at unisa.it ) *Important dates* Contest proposal submission*extended deadlin**e*:*_December 10, 2018_* Contest acceptance notification deadline: *December 17, 2018* Contest reports due: *April 30, 2018* Please find more information on the CAIP website http://caip2019.unisa.it. If you have any query, please contact the CAIP2019 Organizing Committee. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: geocbmgpmlihpoll.png Type: image/png Size: 54007 bytes Desc: not available URL: From jpezaris at gmail.com Wed Dec 5 12:16:54 2018 From: jpezaris at gmail.com (John Pezaris) Date: Wed, 5 Dec 2018 12:16:54 -0500 Subject: Connectionists: Postdoctoral Fellowship in Systems Neuroscience for Visual Prosthesis Development (2nd position) Message-ID: POSTDOCTORAL FELLOWSHIP IN SYSTEMS NEUROSCIENCE Visual Prosthesis Development The Visual Prosthesis Laboratory led by John Pezaris in the Department of Neurosurgery at Massachusetts General Hospital / Harvard Medical School in Boston, Massachusetts is seeking applications for a second NIH-funded postdoctoral fellowship to study the perceptual characteristics of phosphenes electrically evoked from the lateral geniculate nucleus (LGN), and investigate the detailed response field characteristics of LGN cells. Experimental techniques include multi-channel recordings from LGN, and coordinated stimulation through the same electrodes. The position includes interacting extensively with other lab members, the PI, and the neighboring laboratories who do similar work. Please visit sight2blind.org to obtain more information on current interests and recent research papers. The ideal candidate will have experience in training non-human primates, electrical or biomedical engineering, extracellular electrophysiology, and MATLAB programming, and will be comfortable building experimental and computational tools to high standards. Salary will be commensurate with experience according to the current NIH scale, and conforming to MGH requirements. Please send CV, a 1-paragraph statement of research interests, and up to three articles, manuscripts, or dissertations (all as PDFs) to pezaris.john at mgh.harvard.edu. -- John Pezaris, Ph.D. jpezaris at gmail.com From wermter at informatik.uni-hamburg.de Thu Dec 6 05:53:14 2018 From: wermter at informatik.uni-hamburg.de (Wermter, Stefan) Date: Thu, 6 Dec 2018 11:53:14 +0100 Subject: Connectionists: [jobs] Research Associate Intelligent Adaptive Systems (e.g neural networks, nlp or robotics) Message-ID: The Knowledge Technology Research Institute at the University of Hamburg invites applications for a Research Associate (Postdoc or postdoc-level/ final year PhD candidate) in accordance with Section 28 subsection 2 of the Hamburg Higher Education Act (Hamburgisches Hochschul- gesetz, HmbHG). The position commences on 1 Feb 2019 or as soon as possible and is for three years plus a three year extension option subject to the availability of resources. Responsibilities: Duties include teaching and research in the knowledge technology institute. Research associates can also pursue independent research and further academic qualifications as well as acquire teaching experience. These duties are intended to promote academic achieve- ment. Therefore, at least one-third of set working hours will be made available for the associate's own academic work. Specific Duties: The successful candidate will manage the international Master Programme in Computer Science (Intelligent Adaptive Systems) as well as contribute to teaching (4hrs/teaching week). Furthermore, the candidate is expected to conduct research in the area of Knowledge Technology and Intelligent Systems. Requirements: A university degree in a relevant subject plus doctorate prefered. Academic degree preferably in computer science qualifying the post holder to carry out the above-mentioned responsibilities. In particular, an MSc or PhD in Artificial Intelligence or Computer Science is essential. This post is open to Postdocs or experienced PhD candidates. Your demonstrated research interests should be in the areas of Knowledge Technology and Intelligent Systems (e.g. Neural Networks, Robotics, Natural Language Processing, Vision, or Knowledge Representation etc). You should have published in a field relevant to this post. We are also looking for very good communication skills and teamwork; a very good command of both German and English is a requirement. Experience with teaching or organisation of MSc programmes is considered an advantage. The job is remunerated at the salary level TV-L 13. The position is full-time and comprises 39 hours per week. The fixed-term nature of this contract is based upon Section 2 of the Academic Fixed-Term Labor Contract Act (Wissenschaftszeitver- tragsgesetz, WissZeitVG). The initial fixed term is three years. The contract provides for a maximum extension of another three years de- pending on the associate's achievements during the first stage. The University aims to increase the number of women in research and teaching and explicitly encourages women to apply. Equally qualified female applicants will receive preference in accordance with the Hamburg Equality Act (Hamburgisches Gleichstellungsgesetz, HmbGleiG). Severely disabled applicants will receive preference over equally qualified non-disabled applicants. For further information, please contact Prof. Dr. Stefan Wermter, Head of Knowledge Technology Institute or consult our website at https://www.informatik.uni-hamburg.de/wtm/ https://www.inf.uni-hamburg.de/en/inst/ab/wtm/about/job/files/open-position-postdoc.pdf Applications should include an application letter, full curriculum vitae, pdf of best international publications, copies of degree certificates, evidence for required German and English language. The application deadline is 19 Dec 2018. Please email applications in a single pdf file to: Ms Katja Koesters, katja.koesters at informatik.uni-hamburg.de *********************************************** Professor Dr. Stefan Wermter Director of Knowledge Technology Department of Informatics University of Hamburg Vogt Koelln Str. 30 22527 Hamburg, Germany Email: wermter AT informatik.uni-hamburg.de http://www.informatik.uni-hamburg.de/~wermter/ http://www.informatik.uni-hamburg.de/WTM/ *********************************************** From laurenz.wiskott at rub.de Thu Dec 6 05:50:51 2018 From: laurenz.wiskott at rub.de (Laurenz Wiskott) Date: Thu, 6 Dec 2018 11:50:51 +0100 Subject: Connectionists: up to 1.25 million Euros for young AI/ML researchers returning to Germany Message-ID: <20181206105051.frlemkxobxkrvtkd@garlic> Dear AI/ML Postdocs and Young Faculty, we would like to draw your attention to the program by the North Rhine-Westphalian (NRW) Ministry of Culture and Science for young scientist to return to NRW, Germany. In short, if you * work in the field of artificial intelligence and/or machine learning, * are successfully doing research outside of Germany, * received a Dr or PhD two to six years ago, * lived in Germany before going abroad, then you are entitled to apply for a grant for a junior research group of up to 1.25 million Euros in total for five years. German citizenship is not required. See https://www.mkw.nrw/forschung/foerderung/wissenschaftlichen-nachwuchs-foerdern/rueckkehrprogramm/ for further details (in German). If you want to apply and feel your research interests fit into the profile of the Institute for Neural Computation [https://www.ini.rub.de] at the Ruhr-University Bochum, please feel free to approach us to host your prospective junior research group. Our research interests include but are not limited to embodied cognition, navigation, memory, reinforcement learning, agents in computer games, and self-organization of visual representations, see https://www.ini.rub.de/research/groups/ Laurenz Wiskott. From dominik.endres at uni-marburg.de Thu Dec 6 11:19:38 2018 From: dominik.endres at uni-marburg.de (Dominik Endres) Date: Thu, 06 Dec 2018 17:19:38 +0100 Subject: Connectionists: =?utf-8?q?=5BDeadline-Extension=5D_24th_Internati?= =?utf-8?q?onal_Conference_on_Conceptual_Structures_=28ICCS?= =?utf-8?b?4oCZMTkp?= Message-ID: <2142931.jK0mFO0plt@pc04174> [Apologies for multiple postings.] =================================== 2nd Call for Papers: 24th International Conference on Conceptual Structures (ICCS 2019) ?Graphs in Human and Machine Cognition? July 1st - July 4th, 2019, Marburg, Germany. Website: https://iccs-conference.org Twitter: @iccs_confs Facebook: https://www.facebook.com/conceptualstructures/ =================================== ========== About ICCS: ========== The International Conferences on Conceptual Structures (ICCS) focus on the formal analysis and representation of conceptual knowledge, at the crossroads of artificial intelligence, human cognition, computational linguistics, and related areas of computer science and cognitive science. The ICCS conferences evolved from a series of seven annual workshops on conceptual graphs, starting with an informal gathering hosted by John F. Sowa in 1986. Recently, graph-based knowledge representation and reasoning (KRR) paradigms are getting more and more attention. With the rise of quasi-autonomous AI, graph-based representations provide a vehicle for making machine cognition explicit to its human users. Conversely, graphical and graph-based models can provide a rigorous way of expressing intuitive notions in computable frameworks. The aim of the ICCS 2019 conference is to build upon its long standing expertise in graph-based KRR and focus on providing modelling, formal and application results of graph-based systems. The conference welcomes contributions from a modelling, application and theoretical viewpoint: - Modelling results will investigate concrete real world needs for graph-based representation, for example (but not limited to) how human cognition can be mapped onto and facilitated by graphical representations, how certain use cases are of interest to the graph community, how using graphs can bring added (business) value, what kind of graph representation is needed for a given case, etc. - Papers reporting on application experience will be expected to demonstrate the benefits of the graph-based proposed solutions in the context of the use case studied. Where appropriate, the graph-based solutions are compared to other possible solutions. - Technical results will include fundamental graph theory based results for novel structures for representation, extensions of existing structures for added expressivity, conciseness, optimisation algorithms for reasoning, reasoning explanation, etc. General Chair: Dominik Endres, Philipps-University Marburg, Germany Program Chairs: Mehwish Alam, ST-Lab, ISTC, CNR, Rome, Italy Diana Sotropa, Babes-Bolyai University of Cluj-Napoca, Romania ============================= The main research topics are: ============================= - Graph-based models and tools for human reasoning, - Existential and Conceptual Graphs - Formal Concept Analysis - Philosophical, neural, and didactic investigations of conceptual, graphical representations - Knowledge architecture and management, - Human and machine reasoning under inconsistency, - Human and machine knowledge representation and uncertainty, - Contextual logic, - Constraint satisfaction, - Decision making and Argumentation, - Ontologies, - Semantic Web, Web of Data, Web 2.0, - Social network analysis, - Conceptual knowledge acquisition, - Data and Text mining, - Conceptual structures in natural language processing and linguistics - Metaphoric, cultural or semiotic considerations, - Resource allocation and agreement technologies. ====== Dates ====== - Abstract submission deadline: -November 30, 2018- December 15, 2018 - Full paper submission deadline: -December 7, 2018- December 23, 2018 - Poster submission deadline: -December 21, 2018- January 6, 2019(Posters do not require advanced abstract submission) - Paper Reviews Sent to Authors: January 18, 2019 - Rebuttals Due: January 25, 2019 - Notification to authors: February 1, 2019 - Camera-ready papers due: February 22, 2019 ======================== Submission Information ======================== We invite scientific papers of up to fourteen pages, short contributions up to eight pages and extended poster abstracts of up to three pages. Papers and posters must be formatted according to Springer?s LNCS style guidelines and not exceed the page limit. The submission is to be done via EasyChair: https:// easychair.org/conferences/?conf=iccs19[1] . -------------- next part -------------- An HTML attachment was scrubbed... URL: From jiankliu at gmail.com Thu Dec 6 11:49:56 2018 From: jiankliu at gmail.com (Jian Liu) Date: Thu, 6 Dec 2018 16:49:56 +0000 Subject: Connectionists: 3 Faculty Positions in Psychology at the University of Leicester Message-ID: LECTURER IN PSYCHOLOGY https://jobs.le.ac.uk/vacancies/621/lecturer-in-psychology.html Vacancy ID:621 Location:Leicester Department:Neuroscience, Psychology and Behaviour Vacancy terms:Full-time permanent Salary details:Grade 8 ?39,609 to ?48,677 per annum Hours per week:37.5 Advert closes midnight on:02 Jan 2019 About the role We are looking for an excellent researcher to develop and enhance the reputation of the Department of Neuroscience, Psychology and Behaviour. This post provides the opportunity for those with excellent academic potential to contribute to high quality research and teaching within the Department. You will be expected to contribute to raising levels of research activity, research income, teaching excellence and the overall visibility of the Department. You will undertake high quality individual and collaborative research in line with the Department?s aim of producing world-leading research with meaningful impact. You will contribute to undergraduate teaching primarily in the School of Psychology and be involved in postgraduate training at MSc and PhD level. About you The successful applicant will be an experienced researcher, as demonstrated by publications in leading peer-reviewed journals. You will be undertaking high quality teaching in cognate areas and across the discipline of psychology. You will have an international research profile that will integrate, complement and strengthen our existing NPB Department expertise. We are particularly interested in recruiting researchers in developmental psychology, behaviour (e.g. learning and memory) or artificial intelligence/human-machine interaction. Additional information Leicester is a leading University committed to international excellence, world-changing research and high quality, inspirational teaching. We are strongly committed to inclusivity, promoting equality and celebrating diversity among our staff and students. Our strength is built on the talent of our scholars, drawn to us by a mutual passion for discovery. We seek to embed an adventurous and entrepreneurial spirit into our research culture, and to create an environment in which both disciplinary excellence and interdisciplinarity thrive. In return for your hard work, we offer a working environment that is committed to inclusivity, through promoting equality and valuing diversity. We offer a competitive salary package with excellent pension scheme, a generous annual leave allowance and an online portal that offers a range of lifestyle benefits and discounts. Located close to Leicester city centre, our award winning campus benefits from a wide range of cafes, a fully equipped sports centre and nursery facilities. Further information regarding our extensive range of staff benefits is available here. Informal enquiries are welcome and should be made to: Professor Ian Forsythe, Head of the Department of Neuroscience, Psychology and Behaviour, on idf at leicester.ac.uk Professor John Maltby, Professor of Differential Psychology, on jm148 at leicester.ac.uk Professor Kevin Paterson, Professor of Experimental Psychology, on kbp3 at leicester.ac.uk Dr Jose Prados, Head of the School of Psychology, on jpg19 at leicester.ac.uk -------------- next part -------------- An HTML attachment was scrubbed... URL: From jiankliu at gmail.com Thu Dec 6 12:07:01 2018 From: jiankliu at gmail.com (Jian Liu) Date: Thu, 6 Dec 2018 17:07:01 +0000 Subject: Connectionists: PhD Studentships in Neuroscience/Psychology at the University of Leicester Message-ID: PhD Studentships in Neuroscience/Psychology at the University of Leicester, UK. Centre for Systems Neuroscience www.le.ac.uk/csn Department of Neuroscience, Psychology and Behaviour https://le.ac.uk/npb A number of PhD studentships are available in a wide range of research topics. Please find the details of all the projects below. Please contact the PIs on the list: https://www.findaphd.com/phds/phd-research-projects/department-of-neuroscience-psychology-and-behaviour/?c2wgh031 Jian K. Liu, Ph.D. Mathematics Centre for Systems Neuroscience Department of Neuroscience, Psychology and Behaviour University of Leicester, Leicester, UK Phone: +44 (0)116 373-6860 Webpage: https://sites.google.com/site/jiankliu -------------- next part -------------- An HTML attachment was scrubbed... URL: From smart at neuralcorrelate.com Thu Dec 6 11:55:00 2018 From: smart at neuralcorrelate.com (Susana Martinez-Conde) Date: Thu, 6 Dec 2018 11:55:00 -0500 Subject: Connectionists: save the dates for the 20th ECEM meeting in Spain: August 18th-22nd, 2019 In-Reply-To: <004e01d48d83$fdad6b20$f9084160$@neuralcorrelate.com> References: <004e01d48d83$fdad6b20$f9084160$@neuralcorrelate.com> Message-ID: <00b101d48d84$7021a680$5064f380$@neuralcorrelate.com> ECEM 2019 Conference Information The 20th European Conference on Eye Movements, ECEM 2019, will take place from Sunday, August 18th, to Thursday, August 22nd, in Alicante, Spain. Over its more than three-decade long history, ECEM has grown to become the largest scientific meeting on eye movement research worldwide. The conference brings together a vibrant community of researchers working towards a better understanding of eye movements, and their use in the study of a wide range of topics in neuroscience, cognitive science and various applied fields. Our goal is to promote communication and cooperation between participants from diverse areas, such as neurophysiology, psychology, medical sciences, linguistics, computer science, human factors and many others. An important feature of ECEM is the presentation of state of the art equipment and software by manufacturers of eye movement recording systems. The conference website will soon be active at www.ecem2019.com. In the meantime, please save the dates: August 18th through August 22nd, 2019. Conference Venue and Accommodation Alicante, with more than 320,000 inhabitants, is a traditional maritime city located on the Mediterranean Sea. The old part of the city encompasses Postiguet Beach, two marinas and a large commercial port. The city embraces an imposing 166-meter rocky hill right next to the sea, Monte Benacantil, crowned by The Castillo de Santa B?rbara (Santa Barbara Castle). This is one of the largest castles on the Mediterranean, and the conference dinner will take place within its premises, with breathtaking views over the city and the Mediterranean. The slopes of Monte Benacantil surround the old city of Alicante (El Barrio) like a shield. El Barrio is well known for its vibrant nightlife. The local organizing team has secured a large block of hotel rooms at special discounted rates for the conference. Specific hotel information will be made available on the website in March 2019. Lodging in the area is reasonably priced, but accommodation can become limited in the high summer season. We advise early hotel reservation. Publication of Abstracts Accepted abstracts will be published as a special issue in the Journal of Eye Movement Research (Editor: Rudolf Groner, Bern). See ECEM 2017?s abstracts at: https://bop.unibe.ch/JEMR/issue/view/779 On Behalf of the Local Organization Committee Please feel free to share this information with your colleagues. We look forward to welcoming you to Alicante! Luis Martinez-Otero (chair), Albert Compte, and Susana Martinez-Conde -------------------------------------- Susana Martinez-Conde, PhD Author, Champions of Illusion and Sleights of Mind Professor of Ophthalmology, Neurology, and Physiology & Pharmacology State University of New York (SUNY) Downstate Medical Center 450 Clarkson Ave, Brooklyn NY 11203, USA Email: smart at neuralcorrelate.com Phone: +1 718-270-4520 http://smc.neuralcorrelate.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From daniel.urda at uca.es Fri Dec 7 02:35:54 2018 From: daniel.urda at uca.es (=?utf-8?Q?Daniel_Urda_Mu=C3=B1oz?=) Date: Fri, 7 Dec 2018 07:35:54 +0000 Subject: Connectionists: Five industrial PhD positions at University of Cadiz (Spain) Message-ID: <87B20C78-0F78-4D1A-BE36-1D0FA438F040@uca.es> Dear All, The University of Cadiz (Spain) offers five industrial PhD positions covering different topics such as Machine Learning, Computer Vision, Cybersecurity and Internet of Things: 5 Industrial PhD positions at UCA Datalab The University of C?diz and UCA Datalab offer 5 PhD contracts for mathematicians, physicists and engineers to participate in technological projects in partnership with two large companies in the aeronautical and naval sector: Airbus D&S and Navantia. The proposed lines of research cover topics in the fields of data science, machine learning, computer vision, internet of things and cybersecurity, and their description can be found in http://datalab.uca.es/opportunities Candidates must either hold an Msc degree or expect to achieve it in the current academic year 2018/19. Applications must be submitted through the University official procedure, so we encourage interested participants to send us their CV and motivation letter, and we will guide them through the application process. UCA Datalab is a recently created research group with a multidisciplinary focus and emphasis on solving applied technological problems in the industrial sector. We offer a stimulating environment, professional career development and competitive salary for a 4-year PhD contract. C?diz is a beautiful city in the south of Spain with an impressive cultural heritage, pleasant atmosphere and excellent quality of life. Deadline: December 26th, 2018. 5 contratos predoctorales en el UCA Datalab La Universidad de C?diz y el UCA Datalab ofrecen 5 contratos predoctorales para la realizaci?n de tesis industriales en colaboraci?n con empresas del sector aeron?utico y naval: Airbus D&S y Navantia. Las l?neas de investigaci?n propuestas abarcan temas en ciencia de datos, machine learning, visi?n artificial, internet de las cosas y ciberseguridad. La descripci?n de estas l?neas se puede encontrar en http://datalab.uca.es/opportunities Los candidatos deben poseer un m?ster en disciplinas t?cnicas (f?sica, matem?ticas, ingenier?a inform?tica, telecomunicaciones, etc.) o bien estar cursando un m?ster durante el presente curso acad?mico 2018/19. Las solicitudes se deben presentar a trav?s del procedimiento oficial de la Universidad. Se recomienda a los candidatos interesados que se pongan en contacto lo antes posible con nosotros, enviando su CV y carta de motivaci?n, para recibir asistencia en el proceso de solicitud. El UCA Datalab es un grupo de investigaci?n con un enfoque tecnol?gico multidisciplinar, recientemente creado en la Universidad de C?diz para dinamizar proyectos de transferencia con el sector industrial. Los candidatos se incorporar?n a un entorno estimulante, con posibilidades de desarrollo acad?mico y profesional y se formar?n en uno de los perfiles m?s demandados por la sociedad. Los contratos son de 3 a?os (prorrogables a 4) y cuentan con un salario competitivo. Fecha l?mite: 26 de Diciembre, 2018. Daniel Urda Mu?oz PI - ASECTI (Big Data & Machine Learning) Departamento de Ingenier?a Inform?tica, Escuela Superior de Ingenier?a. Universidad de C?diz (Spain) Avenida de la Universidad de C?diz, n? 10, CP 11519, Puerto Real (C?diz). Tel: +34 956483246 ResearcherID: B-2040-2017 ORCID: 0000-0003-2662-798X Google Scholar: https://scholar.google.es/citations?user=fNblEd8AAAAJ&hl=es ResearchGate: https://www.researchgate.net/profile/Daniel_Urda daniel.urda at uca.es -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: cartel_PhD_ucadatalab.pdf Type: application/pdf Size: 623337 bytes Desc: not available URL: -------------- next part -------------- An HTML attachment was scrubbed... URL: From james.rankin at gmail.com Fri Dec 7 05:32:18 2018 From: james.rankin at gmail.com (James Rankin) Date: Fri, 7 Dec 2018 10:32:18 +0000 Subject: Connectionists: PhD in Computational and Mathematical Neuroscience (EPSRC funded, 3.5 yrs, Sept 2019 start) Message-ID: *PhD in Computational and Mathematical Neuroscience (EPSRC funded, 3.5 yrs, Sept 2019 start)* General information & apply (funding is primarily targeted at UK students): http://www.exeter.ac.uk/studying/funding/award/index.php?id=3386 Project description: http://www.exeter.ac.uk/codebox/phdprojects/Rankin-EPSRC-DTP-Project.pdf *Closing date 7th Jan 2019* This interdisciplinary project will develop computational and mathematical models of the auditory system to understand how complex stimuli like speech are encoded by spiking neurons in the midbrain. The auditory midbrain is a key hub in the auditory processing pathway, functioning as an important junction that relays and shapes neural signals as they ascend towards auditory cortex. Knowledge of the way in which complex sounds, e.g. speech, are encoded in the midbrain is crucial for understanding how dysfunction in the earlier auditory processing pathway (cochlea, auditory nerve, cochlear nucleus) leads to different types of hearing loss (a problem affecting 1 in 6 people in the UK). Working with neural recordings from the auditory midbrain in gerbils, a commonly-used animal for the study of low-frequency hearing, this project will develop mathematical and computational models of the auditory processing pathway. The aim is to understand the different roles of the patterns of inputs to midbrain neurons and their intrinsic response properties (e.g. their spiking rate) in shaping their responses to complex sounds. The project will use a dynamical systems approach to model the intrinsic properties of individual neurons in the midbrain in a biologically plausible way (working with, e.g. adaptive exponential integrate-and-fire neurons or the Hodgkin-Huxley equations). Inputs to these neurons will be based on established cochlear models and the biological details of the auditory nerve and cochlear nucleus. The resulting model will produce firing patterns directly comparable with neural recordings provided by the experimental supervisor. This data will be used to train and parameter fit the model using e.g. Bayesian optimisation or genetic algorithms. The resultant model will have explanatory power for the extent to which midbrain responses are shaped by its inputs from cochlear nucleus. Further, it will make predictions, testable in new experiments, of how midbrain responses will be affected by different dysfunctions of the early auditory system relating to hearing loss. The successful candidate will receive training dynamical systems theory and in the development and analysis of individual neuron and neural network models. An interdisciplinary approach, incorporating known biological details of the auditory processing pathway, will require the candidate to learn the relevant biology and neuroscience along with mathematical and computational techniques. The project will involve working closely with experimental neuroscientists and experimental data. This project provides a unique opportunity to receive training in mathematical modelling in close collaboration with experimentalists using cutting-edge methods recording spikes simultaneously from hundreds of neurons. Experience working on such interdisciplinary projects is highly sought after. Candidates with quantitative backgrounds (mathematics, physics, engineering) and from neuroscience programmes are encouraged to apply. Programming experience, knowledge of dynamical systems theory and experience in biological modelling are a plus. For further information, please contact me at the email address above. *For further information, please contact Dr James Rankin, email j.a.rankin at exeter.ac.uk * http://emps.exeter.ac.uk/mathematics/staff/jar226 -------------- next part -------------- An HTML attachment was scrubbed... URL: From sepand.haghighi at yahoo.com Fri Dec 7 07:24:55 2018 From: sepand.haghighi at yahoo.com (Sepand Haghighi) Date: Fri, 7 Dec 2018 12:24:55 +0000 (UTC) Subject: Connectionists: PyCM : New machine learning library for confusion matrix statistical analysis References: <1382550230.359974.1544185495446.ref@mail.yahoo.com> Message-ID: <1382550230.359974.1544185495446@mail.yahoo.com> Dear All,? Here I want to introduce an open source Python library which named PyCM. PyCM is a machine learning library providing statistical analysis of confusion matrix through a large variety of parameters such as AUC, Confusion Entropy, information theory related parameters, and etc. This developing library can be used in order to evaluate the performance of different machine learning algorithms by offering different evaluation parameters on their resulted confusion matrix. PyCM is a multi-class confusion matrix library written in Python that supports both input data vectors and direct matrix, and a proper tool for post-classification model evaluation that supports most classes and overall statistics parameters. PyCM is the swiss-army knife of confusion matrices, targeted mainly at data scientists that need a broad array of metrics for predictive models and an accurate evaluation of large variety of classifiers. Do not hesitate to contact us about this library and help us to develop it by your valuable suggestions.You can find us on https://github.com/sepandhaghighi/pycm -------------- next part -------------- An HTML attachment was scrubbed... URL: From irina.illina at loria.fr Fri Dec 7 08:53:58 2018 From: irina.illina at loria.fr (Irina Illina) Date: Fri, 7 Dec 2018 14:53:58 +0100 (CET) Subject: Connectionists: Research engineer or post-doc position in Natural Language Processing (LORIA, France) In-Reply-To: <1405387991.21186394.1542703967147.JavaMail.zimbra@loria.fr> References: <563224855.15324328.1541364984538.JavaMail.zimbra@loria.fr> <1405387991.21186394.1542703967147.JavaMail.zimbra@loria.fr> Message-ID: <240864110.7699132.1544190838899.JavaMail.zimbra@loria.fr> Research engineer or post-doc position in Natural Language Processing: Introduction of semantic information in a speech recognition system Supervisors: Irina Illina, MdC, Dominique Fohr, CR CNRS Team: Multispeech, LORIA-INRIA (https://team.inria.fr/multispeech/) Contact: illina at loria.fr, dominique.fohr at loria.fr Duration: 12-15 months Deadline to apply : December 20th, 2019 Required skills: Strong background in mathematics, machine learning (DNN), statistics, natural language processing and computer program skills (Perl, Python). Following profiles are welcome, either: ? Strong background in signal processing or ? Strong experience with natural language processing Excellent English writing and speaking skills are required in any case. Candidates should email a detailed CV with diploma LORIA is the French acronym for the ?Lorraine Research Laboratory in Computer Science and its Applications? and is a research unit (UMR 7503), common to [ http://www.cnrs.fr/index.php | CNRS ] , the [ http://vers.univ-lorraine.fr/ | University of Lorraine ] and [ http://www.inria.fr/en/ | INRIA ] . This unit was officially created in 1997. Loria?s missions mainly deal with fundamental and applied research in computer sciences. MULTISPEECH is a joint research team between the Universit? of Lorraine, Inria, and CNRS. Its research focuses on speech processing, with particular emphasis to multisource (source separation, robust speech recognition), multilingual (computer assisted language learning), and multimodal aspects (audiovisual synthesis). Context and objectives Under noisy conditions, audio acquisition is one of the toughest challenges to have a successful automatic speech recognition (ASR). Much of the success relies on the ability to attenuate ambient noise in the signal and to take it into account in the acoustic model used by the ASR. Our DNN (Deep Neural Network) denoising system and our approach to exploiting uncertainties have shown their combined effectiveness against noisy speech. The ASR stage will be supplemented by a semantic analysis. Predictive representations using continuous vectors have been shown to capture the semantic characteristics of words and their context, and to overcome representations based on counting words. Semantic analysis will be performed by combining predictive representations using continuous vectors and uncertainty on denoising. This combination will be done by the rescoring component. All our models will be based on the powerful technologies of DNN. The performances of the various modules will be evaluated on artificially noisy speech signals and on real noisy data. At the end, a demonstrator, integrating all the modules, will be set up. Main activities ? study and implementation of a noisy speech enhancement module and a propagation of uncertainty module; ? design a semantic analysis module; ? design a module taking into account the semantic and uncertainty information. References [Nathwani et al ., 2018] Nathwani, K., Vincent, E., and Illina, I. DNN uncertainty propagation using GMM-derived uncertainty features for noise robust ASR, IEEE Signal Processing Letters , 2018. [Nathwani et al ., 2017] Nathwani, K., Vincent, E., and Illina, I. Consistent DNN uncertainty training and decoding for robust ASR, in Proc. IEEE Automatic Speech Recognition and Understanding Workshop , 2017. [Nugraha et al., 2016] Nugraha, A., Liutkus, A., Vincent E. Multichannel audio source separation with deep neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2016. [Sheikh, 2016] Sheikh, I. Exploitation du contexte s?mantique pour am?liorer la reconnaissance des noms propres dans les documents audio diachroniques?, These de doctorat en Informatique, Universit? de Lorraine, 2016. [Sheikh et al., 2016] Sheikh, I. Illina, I. Fohr, D. Linares, G. Learning word importance with the neural bag-of-words model, in Proc. ACL Representation Learning for NLP (Repl4NLP) Workshop, Aug 2016. [Mikolov et al., 2013a] Mikolov, T. Chen, K., Corrado, G., and Dean, J. Efficient estimation of word representations in vector space, CoRR , vol. abs/1301.3781, 2013. -- Associate Professor Lorraine University LORIA-INRIA office C147 Building C 615 rue du Jardin Botanique 54600 Villers-les-Nancy Cedex Tel:+ 33 3 54 95 84 90 -------------- next part -------------- An HTML attachment was scrubbed... URL: From Sharon.Crook at asu.edu Fri Dec 7 13:58:53 2018 From: Sharon.Crook at asu.edu (Sharon Crook) Date: Fri, 7 Dec 2018 18:58:53 +0000 Subject: Connectionists: Call for Proposals: Local Organizers for CNS*2020 In-Reply-To: References: , , , , Message-ID: We look forward to seeing all of you next summer at the 2019 Computational Neuroscience meeting in Barcelona! However, it is already time to begin planning for CNS*2020. OCNS requests proposals from candidate local organizers to hold CNS*2020 at a location outside of Europe, preferably in North or South America. Groups or individuals interested in organizing the 2020 meeting should submit a proposal following the extensive on-line instructions and using the on-line templates at: https://www.cnsorg.org/cns-2020-local-organizer. Proposals should be submitted by email to the OCNS President at president at cnsorg.org no later than February 1, 2019.The OCNS Board Members will consider the proposals, contact local organizers for more information if necessary, and select a location in a timely agreement between OCNS and the potential local organizers. As usual, the selected location will be officially announced at the CNS Meeting in July. An earlier email to the OCNS President declaring the intent to submit a proposal would be appreciated, but is not required. Thank you! Your Organization for Computational Neuroscience Team From george at cs.ucy.ac.cy Sat Dec 8 09:02:39 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Sat, 8 Dec 2018 16:02:39 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Last Call for Workshop Proposals In-Reply-To: <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> Message-ID: <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> *** LAST CALL FOR WORKSHOP PROPOSALS *** 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/ Proposals due: December 14, 2018 ACM UMAP 2019, the premier international conference for researchers and practitioners working on systems that adapt to individual users or to groups of users, and which collect, represent, and model user information, is pleased to invite proposals for workshops to be held in conjunction with the conference. The workshops provide a venue to discuss and explore emerging areas of User Modelling and Adaptive Hypermedia research with a group of like-minded researchers and practitioners from industry and academia. In this edition, our goal is to have a balanced workshop program comprising different workshop formats and combining emerging and established research topics. Different full-day and half-day workshop schemas are possible, such as: ? Working group meetings around a specific problem or topic; participants may be asked to submit a white paper or position statement. ? Mini-conferences on specialized topics, having their own paper submission and review processes. ? Mini-competitions or challenges around selected topics with individual or team participation. ? Interactive discussion meetings focusing on subtopics of the UMAP general research topics. PROPOSAL FORMAT Workshop proposals should be submitted in PDF format to both workshop chairs, not exceeding 5 pages and organized as follows: ? Workshop title and acronym. ? Workshop chair(s), including affiliation, email address, homepage, and experiences in organizing such events. ? Abstract (up to 300 words) and topics of interest. ? Motivation on why the workshop is of particular interest at this time. ? Workshop format, discussing the mix of events such as paper presentations, invited talks, panels, and general discussions. ? Intended audience and expected number of participants. ? List of (potential) members of the program committee (at least 50% have to be confirmed at the time of the proposal). ? Requested duration (half day or full day). ? When available, past editions of the workshop, including URLs, a brief statement on the development of the workshop series, e.g., in terms of topics, number of paper submissions and participants, post-workshop publications over the years and acceptance statistics. INSTRUCTIONS We encourage both researchers and industry practitioners to submit workshop proposals. Researchers interested in submitting a workshop proposal are invited to contact us in advance, so we can help to design successful proposals. In particular, for workshop proposals with novel interactive formats, we are happy to assist in further developing and implementing the ideas. We strongly suggest to have organizers from different institutions, bringing different perspectives to the workshop topic. We welcome workshops with a creative structure that may attract various types of contributions and may ensure rich interactions. The organizers of accepted workshops will prepare a workshop web site containing the call for papers and detailed information about the workshop organization and timeline. They will be responsible for their own publicity and reviewing processes. There will be a conference adjunct proceedings published by ACM where all the workshop papers will be published. Hence, the workshop organizers will need to adhere to the adjunct proceedings publication timeline. IMPORTANT DATES ? Proposal submission: December 14, 2018 ? Notification of proposal acceptance: January 9, 2019 ? Send the workshop description & website URL : January 23, 2019 ? (Suggested) 1st call for papers: January 28, 2019 ? (Suggested) 2nd call for papers: February 20, 2019 ? (Suggested) paper submission: March 13, 2019 ? (Suggested) notification to authors: March 26, 2019 ? Workshop summary camera-ready: April 3, 2019 ? Workshop papers camera-ready: April 3, 2019 ? Adjunct proceedings camera ready: April 15, 2019 WORKSHOP CHAIRS ? Milos Kravc?k, German Research Center for Artificial Intelligence (DFKI), Germany (milos.kravcik AT dfki.de) ? Iv?n Cantador, Universidad Aut?noma de Madrid, Spain (ivan.cantador AT uam.es) -------------- next part -------------- An HTML attachment was scrubbed... URL: From stdm at zhaw.ch Sat Dec 8 07:18:09 2018 From: stdm at zhaw.ch (Stadelmann Thilo (stdm)) Date: Sat, 8 Dec 2018 12:18:09 +0000 Subject: Connectionists: 20 minutes to participate in survey on the social impact of Artificial Intelligence Message-ID: Dear Expert With this e-mail we would like to invite you to participate in an international survey on the social impact of Artificial Intelligence. The survey takes about 20 minutes. You are contributing to a study commissioned by TA-Swiss that is executed by the Digital Society Initiative of the University of Zurich, the Technology and Society Department of Empa and the Institute for Technology Assessment of the Austrian Academy of Sciences. You are also welcome to send the survey link to other interested experts from your field. Please click on the link below to participate in the study and receive further information: TA-Swiss Umfrage / Survey / Questionnaire Alternatively, you can also enter the following URL in your browser https://ufspezurich.eu.qualtrics.com/jfe/form/SV_brNE0IjpGVWIDgp We thank you for your support The research team -------------- next part -------------- An HTML attachment was scrubbed... URL: From axel.soto at cs.uns.edu.ar Sun Dec 9 00:43:16 2018 From: axel.soto at cs.uns.edu.ar (Axel Soto) Date: Sun, 09 Dec 2018 02:43:16 -0300 Subject: Connectionists: Last CFP: ACM IUI Workshop on Exploratory Search and Interactive Data Analytics (ESIDA) Message-ID: Workshop on Exploratory Search and Interactive Data Analytics (ESIDA) Los Angeles, USA, March 20, 2019 Hosted by ACM IUI 2019, March 17-20, 201 https://sites.google.com/view/esida2019 Important dates Submission deadline: December 17, 2018 (midnight Hawaii time) Acceptance notification: January 23, 2019 Final manuscript due: February 6, 2019 Workshop Topic and Description In recent years, retrieval techniques operating on text or semantic annotations, have become the industry standard for retrieval from large data collections, such as documents, images, videos, music, medical data. This approach works well with sufficient high-quality meta-data or tagging. However, with the explosive growth of big data collections, it has become apparent that tagging new data quickly and efficiently is not always possible. Secondly, even if instantaneous high-quality data tagging were possible, there would still be many instances, where search by keyword query is problematic. For example, in the case of image retrieval it might be easier for a user to define their query if they are looking for an image of a cat, but how would they specify that the cat should be of a particular shade of ginger with sad looking eyes? A solution to these problems is active engagement of the user in the information retrieval loop, thus enabling the user to not only explore a given dataset more easily but also gradually direct their search to a more specific area of the search space. The aim of this workshop is to explore new methods and interface/system design for interactive data analytics and management in various domains, including specialised text collections (e.g. legal, medical, scientific), multimedia, and bioinformatics, as well as for various tasks, such as semantic information retrieval, conceptual organization and clustering of data collections for sense-making, semantic expert profiling, and document/multimedia recommender systems. The primary audience of the workshop is researchers and practitioners in the area of interactive and personalized system design as well as interactive machine learning both from academia and industry. IUI, with its focus on the intersection of HCI and AI, is a perfect venue where researchers from system/interface design community and the machine learning community can meet. Workshop Target Areas The workshop aims to solicit submissions in all areas of interactive data analytics and exploratory search including: - design, testing and assessment of interactive systems for data analytics - interactive data visualization for exploratory and investigative analysis - interactive classification and clustering of data - user-assisted curation and validation of the analysis process, and generation of data visualizations - user engagement in the semantic analysis process via suitable annotation and correction tools - study of the trade-off between accuracy of the results and user effort - personalization and user modeling related to interactive system design Submissions aimed at solving practical problems in specific application domains are especially welcome, including: - digital libraries - legal document management - personalized online learning systems - news media - biomedical data - multimedia collections - specialized image and video collections, e.g. medical images. We encourage submissions of work in progress, concept papers, case studies, and generally material that will stimulate discussion, generate useful feedback to the authors, encourage research collaborations and vigorous exchange of ideas on promising research directions, in one of the following formats: - full papers (up to 8 pages in the ACM SIGCHI format), which will be presented either as contributed talks or posters - extended abstracts (up to 4 pages in the ACM SIGCHI format), which will be presented as posters with a possibility to be accompanied by a demo. Submission information Submissions to the workshop will be through EasyChair, https://easychair.org/conferences/?conf=esida19 Workshop date March 20, 2019 Workshop location Marriott Marina Del Rey, Los Angeles, CA, USA - https://iui.acm.org/2019/venue_transportation.html Keynote Speaker John O'Donovan: University of California, Santa Barbara, USA Organizers Dorota Glowacka, School of Informatics, University of Edinburgh, dorota.glowacka at ed.ac.uk Evangelos Milios, Faculty of Computer Science, Dalhousie University, eem at cs.dal.ca Axel J. Soto, School of Computer Science, University of Manchester, axel.soto at manchester.ac.uk Fernando V. Paulovich, Faculty of Computer Science, Dalhousie University, paulovich at dal.ca Denis Parra, Department of Computer Science, Pontificia Universidad Cat?lica de Chile, dparra at ing.puc.cl Osnat (Ossi) Mokryn, Department of Information and Knowledge Management, University of Haifa (Israel), omokryn at univ.haifa.ac.il From george at cs.ucy.ac.cy Sun Dec 9 07:01:52 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Sun, 9 Dec 2018 14:01:52 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): First Call for Demos and Late Breaking Results In-Reply-To: <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> Message-ID: <05EDB924-A9A7-4E3B-8E36-05EAE5D4242A@cs.ucy.ac.cy> *** FIRST CALL FOR DEMOS AND LATE BREAKING RESULTS *** 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/ Submissions due: March 16, 2019 ACM UMAP - User Modelling, 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 2019 invites Demonstrations and Late-Breaking Results (LBR) papers of innovative UMAP-based systems (including research prototypes). You are encouraged to submit your Demo or LBR by March 16th 2019. DEMONSTRATIONS Demonstrations will showcase research prototypes and commercially available products in a dedicated session. Demo submissions must be based on an implemented and tested system that pursues one or more innovative ideas in the interest areas of the conference. Demonstrations are an excellent and exciting way to showcase implementations and to get valuable feedback from the community. Each demo submission must make clear which aspects of the system will be demonstrated, and how. To better identify the value of demos, we also encourage authors to submit a pointer to a screencast (max. 5 minutes on Vimeo or YouTube) or to any external material related to the demo (e.g., shared code on GitHub). Descriptions of demonstrations should have a length of max. 2 pages in the ACM SIG proceedings template. On an extra page (not to be published), submissions should include a specification of the technical requirements for demonstrating the system at UMAP 2019. LATE-BREAKING RESULTS Late-Breaking Results (LBR) are research-in-progress that must contain original and unpublished accounts of innovative research ideas, preliminary results, industry showcases, and system prototypes, addressing both the theory and practice of User Modeling, Adaptation and Personalization. In addition, papers introducing recently started research projects or summarizing project results are welcome as well. We encourage researchers and practitioners to submit a late-breaking work as it provides a unique opportunity for sharing valuable ideas, eliciting useful feedback on early-stage work, and fostering discussions and collaborations among colleagues. Late-Breaking Results papers have a length of 4 to 6 pages in the ACM SIG proceedings template and will be presented to the conference as posters. SUBMISSION AND REVIEW PROCESS Submissions (demos and late-breaking results) must adhere to the ACM SIG Standard (SIGCONF) proceedings template. A template can be found at: https://www.acm.org/publications/proceedings-template . Submit your papers in PDF format via EasyChair for ACM UMAP 2019 Demos and Late-Breaking Results at: https://easychair.org/conferences/?conf=umap2019_demo-lbr . The review process will be single blinded, i.e. authors' names should be included in the papers. Submissions will be reviewed by at least two independent reviewers. They will be assessed based on their originality and novelty, potential contribution to the research field, potential impact in particular use cases, and the usefulness of presented experiences, as well as their overall readability. Papers that exceed the page limits (2 pages for demos and 6 pages for LBR) or do not adhere to the formatting guidelines will be returned without review. IMPORTANT DATES ? Submission of demos and LBR papers: March 16th, 2019 ? Notification of acceptance: April 5th, 2019 ? Camera-ready versions of accepted papers: April 15th, 2019 The submissions times are 11:59 pm Anywhere on Earth PUBLICATION AND PRESENTATION Accepted Demo and Late Breaking Results papers will be published in the ACM UMAP 2019 Adjunct Proceedings in the ACM Digital Library. All categories will be presented at the poster reception of the conference, in the form of a poster and/or a software demonstration following poster format. This form of presentation will provide presenters with an opportunity to obtain direct feedback about their work from a wide audience during the conference. At least one author of each accepted paper must register for the conference and present the paper there. LATE-BREAKING RESULTS AND DEMO CHAIRS ? Styliani Kleanthous, University of Cyprus, Cyprus & RISE LIMITED, Cyprus (Contact: stellak at ucy.ac.cy) ? Maria Bielikova, Slovak University of Technology Bratislava, Slovakia ? Ben Steichen, California State Polytechnic University, Pomona, USA -------------- next part -------------- An HTML attachment was scrubbed... URL: From ohad.kammar at gmail.com Sun Dec 9 17:56:17 2018 From: ohad.kammar at gmail.com (Ohad Kammar) Date: Sun, 9 Dec 2018 22:56:17 +0000 Subject: Connectionists: LAFI 2019: Languages for Inference --- Call-for-Participation Message-ID: tl;dr: * Programme is out * Early registration deadline is Monday 10 Dec (AoE). LAFI 2019: Languages for Inference (formerly PPS) ================================================ Tuesday, 15 January 2019, Cascais/Lisbon, Portugal A workshop affiliated with POPL 2019 https://popl19.sigplan.org/track/lafi-2019 Important dates (anywhere on earth) ------------------------------------------------- Early Registration Deadline Mon 10 Dec 2018 Workshop Tue 15 Jan 2019 (day before POPL) ------------------------------------------------- Registration: https://popl19.sigplan.org/attending/Registration Invited Speaker: Matthijs V?k?r (Columbia University) Invited talk: Connecting probabilistic programming theory to applications in Stan Full programme: https://popl19.sigplan.org/track/lafi-2019#program Context ======= Inference concerns re-calibrating program parameters based on observed data, and has gained wide traction in machine learning and data science. Inference can be driven by probabilistic analysis and simulation, and through back-propagation and differentiation. Languages for inference offer built-in support for expressing probabilistic models and inference methods as programs, to ease reasoning, use, and reuse. The recent rise of practical implementations as well as research activity in inference-based programming has renewed the need for semantics to help us share insights and innovations. This workshop aims to bring programming-language and machine-learning researchers together to advance all aspects of languages for inference. Topics include but are not limited to: + design of programming languages for inference and/or differentiable programming; + inference algorithms for probabilistic programming languages, including ones that incorporate automatic differentiation; + automatic differentiation algorithms for differentiable programming languages; + probabilistic generative modelling and inference; + variational and differential modelling and inference; + semantics (axiomatic, operational, denotational, games, etc) and types for inference and/or differentiable programming; + efficient and correct implementation; + and last but not least, applications of inference and/or differentiable programming. This year we are explicitly expanding the focus of the workshop from statistical probabilistic programming to encompass differentiable programming for statistical machine learning. We expect this workshop to be informal, and our goal is to foster collaboration and establish common ground. Thus, the proceedings will not be a formal or archival publication. Nevertheless, as a concrete basis for fruitful discussions, we call for extended abstracts describing specific and ideally ongoing work on probabilistic programming languages, semantics, and systems. In line with the SIGPLAN Republication Policy: http://www.sigplan.org/Resources/Policies/Republication/ inclusion of extended abstracts in the programme is not intended to preclude later formal publication. Programme committee: At?l?m G?ne? Baydin University of Oxford Department of Engineering Bart van Merri?nboer University of Montreal Christine Tasson University Paris Diderot David Duvenaud University of Toronto Jeffrey Siskind (co-chair) School of Electrical and Computer Engineering, Purdue University Matthew Johnson Google Brain Ohad Kammar (co-chair) University of Oxford Department of Computer Science Praveen Narayanan Indiana University Ryan Culpepper Czech Technical University Sophia Gold Tezos Steven Holtzen University of California Los Angeles Tom Rainforth University of Oxford Department of Statistics -------------- next part -------------- An HTML attachment was scrubbed... URL: From smartstart at fz-juelich.de Mon Dec 10 04:38:22 2018 From: smartstart at fz-juelich.de (SMARTStart) Date: Mon, 10 Dec 2018 10:38:22 +0100 Subject: Connectionists: SMARTSTART Program accepts the next round of applications Message-ID: Dear colleagues, please be invited to share the information on the training program SMARTSTART Computational Neuroscience with your students: **** On January 1, 2019, the SMARTSTART Program accepts the next round of applications. The program offers students and prospective doctoral students the opportunity to complement their previous studies with concepts, theories and techniques of computational neuroscience. Target groups are: 1. students who are enrolled in a relevant Master's program in Germany during the funding period Sep 19 - Sep 20 (SMARTSTART 1) and 2. students who have successfully completed a relevant Master's program at the start of their funding period without having started a doctoral project (SMARTSTART 2). Applications can be submitted from January 1 until February 28, 2019 at the application platform on https://www.smartstart-compneuro.de/ SMARTSTART is the Joint Training Program in Computational Neuroscience of the Bernstein Network; the program is funded by the Volkswagen Foundation. The program was launched in 2016 with the support of the Volkswagen Foundation. Since then, more than 60 students have successfully completed the program. Many of them are currently continuing their research projects as doctoral projects. **** Kind regards, Janina Radny - SMARTSTART coordinator -- Smart Start - Joint Training Program in Computational Neuroscience Bernstein Network Computational Neuroscience Smart Start Coordination Office at the Bernstein Coordination Site (BCOS) Branch Office of the Forschungszentrum J?lich at the University of Freiburg postal address: Hansastr. 9A | 79104 Freiburg, Germany phone: (+49) 0761 203 9593 mail: smartstart at fz-juelich.de web: www.smartstart-compneuro.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 ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From Vibhav.Gogate at utdallas.edu Tue Dec 11 03:56:37 2018 From: Vibhav.Gogate at utdallas.edu (Gogate, Vibhav) Date: Tue, 11 Dec 2018 08:56:37 +0000 Subject: Connectionists: Call for Papers: Distributed Machine Learning Track at ICDCS 2019 Message-ID: Apologies for multiple postings. ********** The 39th IEEE International Conference on Distributed Computing Systems (ICDCS 2019) will be held during July 7th to July 10th, 2019 in Dallas, Texas, USA. The conference provides a platform for researchers, scientists and engineers in various domains, in fields such as academics, industry and government, to present their current findings in the emerging areas of distributed computing. See: https://theory.utdallas.edu/ICDCS2019/ As a part of this conference, we have a special track on distributed machine learning systems. Please consider submitting your original, unpublished research to this track. Important Dates Abstract Registration: January 5th, 2019 Submission Due: January 12th, 2019 Author Notification: March 28th, 2019 Camera-ready paper deadline: April 3rd, 2019 Paper Submission All submissions should follow the IEEE 8.5 inch x 11 inch Two-Column Format. Each submission can have up to 10 pages without references. Papers Submission Link:https://easychair.org/conferences/?conf=icdcs2019 Best Regards, Vibhav Gogate Distributed Machine Learning Track Chair at ICDCS 2019. ********* -------------- next part -------------- An HTML attachment was scrubbed... URL: From mary.heinrich at uni-luebeck.de Tue Dec 11 05:49:59 2018 From: mary.heinrich at uni-luebeck.de (Mary Katherine Heinrich) Date: Tue, 11 Dec 2018 10:49:59 +0000 Subject: Connectionists: CfP SOCO 2019 - 3rd Int. Workshop on Self-Organised Construction, IEEE FAS* In-Reply-To: <9339CD7B344B0E448B3062317062228C2EAE250B@DAG02.uni-luebeck.de> References: <9339CD7B344B0E448B3062317062228C2EAE24C0@DAG02.uni-luebeck.de>, <9339CD7B344B0E448B3062317062228C2EAE250B@DAG02.uni-luebeck.de> Message-ID: <9339CD7B344B0E448B3062317062228C2EAE2528@DAG02.uni-luebeck.de> Are you working on construction or self-assembly, for example, with robots, cyber-physical systems, agents, or social insects? The SOCO workshop focuses on self-organizing strategies to build architecture and structures. Apologies for any cross-postings. 3rd International Workshop on Self-Organised Construction (SOCO) (Int. Workshops on Foundations and Applications of Self-* Systems of the SASO and ICAC conferences, FAS*) Umea, Sweden, June 17, 2019 http://www.selforganisedconstruction.org http://saso2019.cs.umu.se/workshops-and-tutorials/ - Important Deadlines - ? Submission deadline: March 3, 2019 ? Acceptance notification: April 1, 2019 - Summary - SOCO is on self-organised construction and we want to cumulate, present, discuss, and advance new research results from theory and practice as well as novel scientific concepts and methodologies. Originally inspired by nest construction in social insects, the general concept relies on a large number of agents that coordinate their construction efforts by prompting and reacting to local stimuli. Recently, with the wake of robotic swarms and novel material processing approaches, including for instance 3D printing techniques and innovative deployment of carbon fibres, self-organising construction is quickly gaining tremendous transformative significance in the context of various design and construction processes. These include also the construction, extension, and renovation of architectural buildings, engineering design, industrial assembly, and landscape architecture. Our focus is on the design and management of self-organising construction from a computational perspective. - Special Interests - ? Self-organising biologically inspired construction models ? Analysis and design of coordinating construction algorithms ? Agent-based simulations of building usage ? Self-organising robot groups and swarms for construction ? Computational metrics for evaluating complex structures (e.g., complexity, energy efficiency, structural integrity of buildings) ? Parameterisation, evaluation, optimisation of artefact utilisation and purpose ? Decentralised supply chains of construction materials ? Internet of Things (IoT) technologies for self-organised construction and maintenance ? 3D printing technologies for self-organised construction ? Applications in architectural design, building engineering, landscaping, industrial design, engineering and manufacture and swarm robotics ? Interfaces for human inspection and control of self-organising construction systems ? Modelling and simulation techniques, tools and platforms for self-organising construction - Submissions - Submitted papers of up to six pages will be evaluated in a single-blind reviewing process by the workshop committee members. Accepted papers will be submitted for publication to the FAS* workshop proceedings through IEEE. All papers need to follow the IEEE DL format of the SASO conference and follow the IEEE Computer Society Press proceedings style guide. Please submit your paper through EasyChair: https://easychair.org/conferences/?conf=soco20190 We are looking for contributions that present novel theoretical or experimental results, novel design patterns, mechanisms, system architectures, frameworks or tools, or practical approaches and experiences in building or deploying real-world systems and applications. We ask the authors to ensure that their submissions comply with the high standards in ingenuity and quality as expected by the SASO conference in general. The workshop on Self-organising Construction (SOCO) is one of the International Workshops on Foundations and Applications of Self-* Systems (FAS*) held in the context of the IEEE International Conferences on Self-Adaptive and Self-Organising systems (SASO) and on Cloud and Autonomic Computing (ICAC). - Organisors - ? Sebastian von Mammen, University of Wuerzburg ? Heiko Hamann, University of Luebeck ? Mary Katherine Heinrich, University of Luebeck - Programme Committee (confirmed as of 11.12.18) - * Phil Ayres * Peter Bentley * Marco Dorigo * Ren? Doursat * Ilaria Mazzoleni * Achim Menges * Nils Napp * Kirstin Petersen * Hiroki Sayama * Kasper Stoy * Joshua Taron * Justin Werfel * Ales Zamuda We are looking forward to your submissions! Sebastian, Heiko and Mary Katherine -------------- next part -------------- An HTML attachment was scrubbed... URL: From barros at informatik.uni-hamburg.de Tue Dec 11 05:32:57 2018 From: barros at informatik.uni-hamburg.de (Pablo Barros) Date: Tue, 11 Dec 2018 11:32:57 +0100 Subject: Connectionists: CFP: TAC | Special Issue on Automated Perception of Human Affect from Longitudinal Behavioral Data Message-ID: 2nd CALL FOR PAPERS IEEE Transactions on Affective Computing Special Issue on Automated Perception of Human Affect from Longitudinal Behavioral Data Website: https://www2.informatik.uni-hamburg.de/wtm/omgchallenges/tacSpecialIssue2018.html I. Aim and Scope Research trends within artificial intelligence and cognitive sciences are still heavily based on computational models that attempt to imitate human perception in various behavior categorization tasks. However, most of the research in the field focuses on instantaneous categorization and interpretation of human affect, such as the inference of six basic emotions from face images, and/or affective dimensions (valence-arousal), stress and engagement from multi-modal (e.g., video, audio, and autonomic physiology) data. This diverges from the developmental aspect of emotional behavior perception and learning, where human behavior and expressions of affect evolve and change over time. Moreover, these changes are present not only in the temporal domain but also within different populations and more importantly, within each individual. This calls for a new perspective when designing computational models for analysis and interpretation of human affective behaviors: the computational models that can timely and efficiently adapt to different contexts and individuals over time, and also incorporate existing neurophysiological and psychological findings (prior knowledge). Thus, the long-term goal is to create life-long personalized learning and inference systems for analysis and perception of human affective behaviors. Such systems would benefit from long-term contextual information (including demographic and social aspects) as well as individual characteristics. This, in turn, would allow building intelligent agents (such as mobile and robot technologies) capable of adapting their behavior in a continuous and on-line manner to the target contexts and individuals. This special issue aims at contributions from computational neuroscience and psychology, artificial intelligence, machine learning, and affective computing, challenging and expanding current research on interpretation and estimation of human affective behavior from longitudinal behavioral data, i.e., single or multiple modalities captured over extended periods of time allowing efficient profiling of target behaviors and their inference in terms of affect and other socio-cognitive dimensions. We invite contributions focusing on both the theoretical and modeling perspective, as well as applications ranging from human-human, human-computer and human-robot interactions. II. Potential Topics Given computational models, the capability to perceive and understand emotion behavior is an important and popular research topic. That is why recent special issues on the IEEE Journal on Transactions on Affective Computing covered topics from emotion behavior analysis ?in-the-wild? to personality analysis. However, most of the research published by these specific calls treat emotion behavior as an instantaneous event, relating mostly to emotion recognition, and thus neglect the development of complex emotion behavior models. Our special issue will foster the development of the field by focusing excellent research on emotion models for long-term behavior analysis. The topics of interest for this special issue include, but are not limited to: - New theories and findings on continuous emotion recognition - Multi- and Cross-modal emotion perception and interpretation - Lifelong affect analysis, perception, and interpretation - Novel neural network models for affective processing - New neuroscientific and psychological findings on continuous emotion representation - Embodied artificial agents for empathy and emotion appraisal - Machine learning for affect-driven interventions - Socially intelligent human-robot interaction - Personalized systems for human affect recognition III. Submission Prospective authors are invited to submit their manuscripts electronically, adhering to the IEEE Transactions on Affective Computing guidelines ( https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5165369). Please submit your papers through the online system ( https://mc.manuscriptcentral.com/taffc-cs) and be sure to select the special issue: Special Issue/Section on Automated Perception of Human Affect from Longitudinal Behavioral Data. IV. IMPORTANT DATES: Submissions Deadline: 15th of January 2019 Deadline for reviews and response to authors: 06th of April 2019 Camera-ready deadline: 05th of August 2019 V. Guest Editors Pablo Barros, University of Hamburg, Germany Stefan Wermter, University of Hamburg, Germany Ognjen (Oggi) Rudovic, Massachusetts Institute of Technology, United States of America Hatice Gunes, University of Cambridge, United Kingdom -- Dr. 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.dehttp://www.pablobarros.nethttps://www.inf.uni-hamburg.de/en/inst/ab/wtm/people/barros.htmlhttps://www.inf.uni-hamburg.de/en/inst/ab/wtm/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From stefan.kiebel at tu-dresden.de Tue Dec 11 07:53:26 2018 From: stefan.kiebel at tu-dresden.de (Stefan Kiebel) Date: Tue, 11 Dec 2018 12:53:26 +0000 Subject: Connectionists: Postdoc position in computational neuroscience Message-ID: <1ac33f5ad7f94325ac3bc0b31cb63fef@MSX-L103.msx.ad.zih.tu-dresden.de> Dear all, there is a postdoc position available at the TU Dresden/Germany, see also attached pdf. With best wishes, Stefan -- The Chair of Neuroimaging at TU Dresden, Germany is offering a postdoc position. The position is funded by the Excellence Cluster "Tactile Internet with Human-in-the-Loop" (CeTI), https://www.ceti.one/. The position is available for three years initially but can be extended. CeTI-position_Kiebel_1 - Research associate / Postdoc for computational neuroscience Topic: Computational modelling of sequences of goal-directed actions and multisensory integration Tasks: This position will develop computational models how humans integrate multisensory sensory input while performing sequences of goal-directed actions. We will be using Bayesian inference techniques in combination with nonlinear dynamic systems to model the perception of observed human movements and the inference of intent. This position is embedded in the newly funded research excellence cluster 'Tactile Internet with Human-in-the-Loop (CeTI)' and will work alongside cognitive neuroscientists, roboticists, psychologists, engineers and computer scientists. In collaboration with experimenters, the candidate will use the developed models to experimentally test predictions about how humans use multisensory information during goal-reaching. Requirements: We are looking for a candidate with a PhD degree in computational neuroscience, physics, maths, robotics, computer science, or related fields, ideally with expertise in computational models of human behaviour. Additional expertise in Bayesian inference, EEG, eye tracking analysis, or multisensory integration is a plus. The excellence cluster CeTI and TU Dresden provide an outstanding scientific infrastructure and ideal environment for interdisciplinary collaboration. For computational work, the group has access to the TU Dresden high-performance computing clusters. Experiments by collaborators will be performed at the Neuroimaging Centre Dresden (http://www.nic-tud.de). All computing and experimental facilities are supported by experienced physics and IT staff. For questions about this position please contact Prof. Stefan Kiebel (stefan.kiebel at tu-dresden.de). How To Apply: [http://www.dresden-concept.de/fileadmin/user_upload/seitenbilder/download/DDC-Logos/DDC-09.png] Please submit your comprehensive application including the usual documentation (CV, cover letter including a brief summary of research interests, and two references), by January 4th, 2019 (stamped arrival date of the university central mail service applies) with the reference "CeTI-position_Kiebel_1" in the subject header preferably via the TU Dresden SecureMail Portal https://securemail.tu-dresden.de or S/MIME encrypted by sending it as a pdf document to positions at ceti.tu-dresden.de and stefan.kiebel at tu-dresden.de or by mail to: TU Dresden, Sprecher des Exzellenzclusters CeTI, Herrn Prof. Frank H. P. Fitzek, Helmholtzstr. 10, 01069 Dresden, Germany. Please submit copies only as your application documents will not be returned. We look forward to your applications! The CeTI Team -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 8534 bytes Desc: image001.png URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image002.png Type: image/png Size: 8240 bytes Desc: image002.png URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: CeTI_kiebel_postdoc.pdf Type: application/pdf Size: 75209 bytes Desc: CeTI_kiebel_postdoc.pdf URL: From martaruizcostajussa at gmail.com Tue Dec 11 07:53:06 2018 From: martaruizcostajussa at gmail.com (Marta Ruiz) Date: Tue, 11 Dec 2018 13:53:06 +0100 Subject: Connectionists: 2on CfP: Special Issue of Computational Linguistics: Multilingual and Interlingual Semantic Representations for Natural Language Processing In-Reply-To: References: Message-ID: *CfP: Special Issue of Computational Linguistics: * *Multilingual and Interlingual Semantic Representations forNatural Language Processing* Special Issue of Computational Linguistics: Multilingual and Interlingual Semantic Representations for Natural Language Processing Guest Editors: Marta R. Costa-juss?, Cristina Espa?a-Bonet, Pascale Fung, Noah A. Smith * Submission deadline: March 1, 2019 * --------------------------------------------------------------------------------------------------- Call for Papers --------------- Semantic representations at different levels ? word, sentence, paragraph ? are central to many solutions to Natural Language Processing (NLP) tasks. Text annotation, information retrieval, sentiment analysis, text summarisation, question answering, and machine translation solutions have achieved significant improvements using semantic representations of words. The number of tasks has also grown with the popularisation of unsupervised word embeddings, a fast and efficient way of estimating continuous representations of words. Now, representations derived from deep learning methods are giving a new boost to the field. But in an increasingly globalised world, multilingual and cross-language applications are needed. Extensions to monolingual representations of words such as multilingual Brown clusters, multilingual or interlingual word embeddings, multilingual topic models, and cross-lingual semantic parsers have been successfully applied, though performance lags behind their monolingual counterparts. On the other hand, multilinguality should be able to overcome one of the main limitations of standard representations: multiple senses of a word are conflated into a single vector. In addition, representations of sentences and paragraphs are arising through the encoder-decoder approach (in the fields of natural language inference, machine translation, and text summarization, among others) and the extension to multilingual inputs is equally or even more interesting for NLP applications. Abstract semantic representations attract interest both in academia and industry, as shown by the wide and varied publications from universities and companies on this topic. Achieving improvements in this direction will change the conception of translation (from pairwise to interlingua), enable greater sharing among different NLP applications, and overcome low-resource limitations through zero-shot learning, among other advantages. This research direction will not only increase the performance of current architectures in cross-language settings, but will also lead to novel language-independent architectures and tasks for NLP. Topics ------ This call aims to motivate research on multilingual and interlingual representations that, in the context of any NLP task, go beyond projections from one language into another one and that target crosslinguality. The special topic proposed aims to put together a compact and openly accessible volume, which presents high quality research works that cover an overview of this multidisciplinary field as well as most recent advances. Topics include, but are not limited to: ? Multilingual and crosslingual embeddings for words, sentences, paragraphs, or documents ? Interlingual representations for disambiguation (e.g., embeddings of interlingual word senses, concepts, etc.) ? Disambiguated representations through multilinguality ? Intrinsic evaluation of multilingual or crosslingual representations ? Extrinsic evaluation on NLP tasks We strongly encourage submissions that include experimental findings on languages and dialects less commonly studied in natural language processing at present. Submission Date --------------- Submission of full articles: March 1st 2019 Submission Instructions ----------------------- Papers should be submitted according to the Computational Linguistics style: *http://cljournal.org/ * As in regular submissions to the journal, paper submissions should be made through the CL electronic submission system: *http://cljournal.org/submissions.html *. In Step 1 of the submission process, please select 'Special Issue: Multilingual and Interlingual Semantic Representations' under the 'Journal Section' heading. Please note that papers submitted to a special issue undergo the same reviewing process as regular papers. Guest Editors ------------- *Marta R. Costa-juss?* Universitat Polit?cnica de Catalunya, Barcelona, Spain marta.ruiz AT upc.edu *Cristina Espa?a i Bonet* DFKI and Saarland University, Saarbr?cken, Germany cristinae AT dfki.de *Pascale Fung* Hong Kong University of Science and Technology pascale AT ee.ust.hk *Noah A. Smith* University of Washington and Allen Institute for Artificial Intelligence nasmith AT cs.washington.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Tue Dec 11 08:46:59 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Tue, 11 Dec 2018 15:46:59 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): First Call for Theory, Opinion and Reflection Papers In-Reply-To: <05EDB924-A9A7-4E3B-8E36-05EAE5D4242A@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> <05EDB924-A9A7-4E3B-8E36-05EAE5D4242A@cs.ucy.ac.cy> Message-ID: <6FC69A4B-F456-4336-A7CC-2AAE2723CB67@cs.ucy.ac.cy> *** FIRST CALL FOR THEORY, OPINION AND REFLECTION 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/ Submissions due: March 16, 2019 ACM UMAP - User Modelling, 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. Theory, Opinion and Reflection (TOR) are position papers that critically look at ongoing and emerging research topics, reflections on persistent or fleeting trends in the field and blue sky future ideas for UMAP research. They offer an opportunity for discussing thought-provoking work relevant to the UMAP community, albeit they are not yet ready to be published as a full length research papers at a refereed conference. They should be of sufficient quality and relevance to the UMAP community and demonstrate the ability to spur discussion and debate on the future course of the UMAP research. The presentations will be in the form of a 10 minute pitch in a plenary conference session, just before a break. The presenters will present the topic and raise relevant questions to stimulate discussion during the breaks. Submissions should have a maximum length of 4 pages in the ACM SIG proceedings template. SUBMISSION AND REVIEW PROCESS Submissions must adhere to the ACM SIG Standard (SIGCONF) proceedings template. A template can be found at: https://www.acm.org/publications/proceedings-template. Submit your papers in PDF format via EasyChair for UMAP 2019 TOR at: https://easychair.org/conferences/?conf=umap2019tor. The review process will be single blinded, i.e. authors' names should be included in the papers. Submissions will be reviewed by at least two independent reviewers. They will be assessed based on their originality and novelty, potential to stimulate discussion on important research questions, potential contribution to UMAP research and practice, potential impact in particular use cases, as well as their overall readability. Papers that exceed the page limits (4 pages for TOR) or do not adhere to the formatting guidelines will be returned without review. IMPORTANT DATES ? Submission of TOR papers: March 16th, 2019 ? Notification of acceptance: April 5th, 2019 ? Camera-ready versions of accepted papers: April 15th, 2019 Note: The submissions times are 11:59 pm Anywhere on Earth. PUBLICATION AND PRESENTATION Accepted Theory, Opinion and Reflection papers will be published in the ACM UMAP 2019 Adjunct Proceedings in the ACM Digital Library. All categories will be presented at the poster reception of the conference, in the form of a poster and/or a software demonstration following poster format. This form of presentation will provide presenters with an opportunity to obtain direct feedback about their work from a wide audience during the conference. At least one author of each accepted paper must register for the conference and present the paper there. THEORY, OPINION AND REFLECTION PAPERS CHAIRS ? Jan-Geert Houben, Delft University, The Netherlands (g.j.p.m.houben AT tudelft.nl) ? Bamshad Mobasher, DePaul University, USA (mobasher AT cs.depaul.edu) -------------- next part -------------- An HTML attachment was scrubbed... URL: From rothkopf at fias.uni-frankfurt.de Tue Dec 11 15:14:50 2018 From: rothkopf at fias.uni-frankfurt.de (Constantin Rothkopf) Date: Tue, 11 Dec 2018 21:14:50 +0100 Subject: Connectionists: PhD position - Inverse Reinforcement Learning Message-ID: The Centre for Cognitive Science at Technische Universit?t Darmstadt, Germany invites applications for a Ph.D. Position in Inverse Reinforcement Learning initially limited to a period of three years. Research area The Ph.D. student is expected to work in the domain of inverse reinforcement learning with the particular focus of elucidating human decision making and collective human decision making in the wild, i.e., under real world noisy conditions. The research project is a joint venture between the Bioinspired Communication Lab and the Psychology of Information Processing Lab, both members of the Centre of Cognitive Science at TU Darmstadt. Accordingly, the student will be advised by Prof. Heinz Koeppl, Department of Electrical Engineering and Prof. Constantin Rothkopf, Department of Psychology. Work will involve methodological research in machine learning, design of dedicated human behavioral experiments, and the analysis and further processing of gathered data. What we offer We offer a unique interdisciplinary environment to perform cutting-edge research at one of Germany?s leading universities in the domain of computer science and engineering. The student will be embedded in the ongoing research activities within the Centre for Cognitive Science and will hence have the opportunity to interact with many other cognitive science researchers. The conducted research is expected to culminate in a Ph.D. degree. We offer comprehensive support for dissemination of results through leading scientific journals and through participation in leading international conferences and workshops. Your profile Candidates should have a M.Sc. degree in one of the following fields: computer science, physics, mathematics, engineering, or cognitive science. Candidates are required to have a sincere interest in interdisciplinary research at the crossroad of psychology and computer science. Application Technische Universit?t Darmstadt is striving to increase the proportion of women in its staff and therefore particularly invites women to apply. Applicants with a degree of disability of at least 50% or equivalent are preferred in the case of equal aptitude. Part-time employment is generally possible. We look forward to receiving your application, consisting of a cover letter in which you rationalize your interest in the indicated research area, curriculum vitae, copies of certificates and contact details of at least two academic references. Your application package should be sent as a single PDF file to application at bcs.tu-darmstadt.de From samarasinghe at ini.rub.de Wed Dec 12 02:10:46 2018 From: samarasinghe at ini.rub.de (samarasinghe at ini.rub.de) Date: Wed, 12 Dec 2018 08:10:46 +0100 Subject: Connectionists: International Student Fellowship at the PhD level in Computational Neuroscience Message-ID: Prof. Sen Cheng, Institute for Neural Computation at the *Ruhr University Bochum* in Germany, invites applicants for an International Student Fellowship to be awarded through the international research training group ?Integration and Representation of Sensory Processes? (SFB 874). The fellowship has a duration of 4 months, after which it could be extended to a 3 year PhD position if a good fit with the group is observed. The work will focus on studying the interaction between neocortex and hippocampus using spiking neural network models. The position is part of the project "Theory of the interplay between sensory cortices and hippocampus in memory formation and retrieval", which is funded by the German Research Foundation as part of the collaborative research center SFB 874. The appointment will be initially from 01.03.2019-30.06.2019. Candidates should have an excellent university degree in neuroscience, physics, mathematics, engineering or a related field and be eligible to enroll in a relevant PhD program at the Ruhr University. Competence in mathematical modeling and excellent programming skillsare mandatory. Familiarity with computational neuroscience or computational cognitive modeling would be a further asset. Only candidates who have not previously lived in Germany will be considered. For further information regarding the IRTG fellowship please visit https://www.ruhr-uni-bochum.de/sfb874/integrated_research_training_group/fellowship/fellowship.html The Ruhr University Bochum is home to a vibrant research community in neuroscience and cognitive science. The Institute for Neural Computation is an independent research unit and combines different areas of expertise ranging from experimental and theoretical neuroscience to machine learning and robotics. For further information see www.rub.de/cns . To apply please send a statement of your motivation and research interests, academic transcripts, and a complete CV to samarasinghe at ini.rub.de in a single PDF file. Please, also request from at least two academic referees that they send letters of reference directly to the same email address. The deadline for applications is 15.01.2019. The Ruhr University Bochum is committed to equal opportunity. We strongly encourage applications from qualified women and persons with disabilities. -- Vinita Samarasinghe M.Sc., M.A. Science Manager Arbeitsgruppe Computational Neuroscience Institut f?r Neuroinformatik Ruhr-Universit?t Bochum, NB 3/26 Universit?tstr. 150 D-44801 Bochum Tel: +49 (0)234 32 27316 Email: samarasinghe at ini.rub.de Hours: Mon. - Fri. 8-11 -------------- next part -------------- An HTML attachment was scrubbed... URL: From pavan.ramdya at epfl.ch Wed Dec 12 04:44:06 2018 From: pavan.ramdya at epfl.ch (Pavan Ramdya) Date: Wed, 12 Dec 2018 09:44:06 +0000 Subject: Connectionists: [JOBS] Postdoc & PhD positions in neural network modeling of insect limb control - EPFL, Lausanne Switzerland In-Reply-To: References: <2f9165cc3a724616aa201f9ee0674225@epfl.ch>, Message-ID: <06ee6390e585464387c14dd00c3f51f5@epfl.ch> 1.?Postdoc position in neural network modeling of insect limb control ? The Neuroengineering Laboratory (NeLy, https://ramdya-lab.epfl.ch/) in collaboration with the Biorobotics laboratory (Biorob, http://biorob.epfl.ch/) at EPFL (Lausanne, Switzerland) has one open Postdoctoral position in the bioinspired motor control and robotics. The goal of the project is to design neural networks that can control a Drosophila melanogaster neuromechanical simulation for limbed behaviors including grooming and walking. This work will be in collaboration with individuals performing recordings of actual neural activity and behaviors in real flies. Our vision is to apply what we learn from the real fly to develop more effective robotic limb control algorithms and simultaneously to use our fly simulation and neural network models to generate predictions that can be tested in the real fly. The position is fully funded for 2 years (possibly up to 5 years). EPFL is one of the leading Institutes of Technology in Europe and offers extremely competitive salaries and research infrastructure. Requirements: Candidates should have a Ph.D. and a strong publication record in computational neuroscience, robotics, or a related field. An ideal candidate would have prior experience in: - neural network simulations - programming of limb controllers and/or strong basic programming in Python and/or C - Good communication and management skills are a plus. Fluency in oral and written English is required.? How to apply for the position: Postdoctoral applications should consist of a motivation letter (explaining why you are interested in the project, and why you feel qualified for it), a full CV, two or three relevant publications, and the email addresses of two referees. PDF files are preferred. The files should be sent to pavan.ramdya at epfl.ch. Deadline and starting date: The starting date is April 1, 2018 (but flexible).? Applications are requested for January 20 2018, and will then be processed as they arrive until the position is closed. Contact: Information concerning the type of research carried out by the groups can be found at http://biorob.epfl.ch/ and https://ramdya-lab.epfl.ch/. ?You should send your application and any inquiry by email to: Prof. Pavan Ramdya, pavan.ramdya at epfl.ch ============================================================= 2. PhD student position in neural network modeling of insect limb control ? The Neuroengineering Laboratory (NeLy, https://ramdya-lab.epfl.ch/) in collaboration with the Biorobotics laboratory (Biorob, http://biorob.epfl.ch/) at EPFL (Lausanne, Switzerland) has one open Doctoral position in the bioinspired motor control and robotics. The goal of the project is to design neural networks that can control a Drosophila melanogaster neuromechanical simulation for limbed behaviors including grooming and walking. This work will be in collaboration with individuals performing recordings of actual neural activity and behaviors in real flies. Our vision is to apply what we learn from the real fly to develop more effective robotic limb control algorithms and simultaneously to use our fly simulation and neural network models to generate predictions that can be tested in the real fly. The position is fully funded for 2 years (possibly up to 5 years). EPFL is one of the leading Institutes of Technology in Europe and offers extremely competitive salaries and research infrastructure. Requirements: Candidates need to have a Master degree in a field related to computational neuroscience and/or biomechanics, e.g. in physics, computer science, mechanical engineering or bioengineering. The ideal candidate for this position should have a strong math background (e.g. in dynamical systems), good programming skills, and interest/expertise in modeling neural circuits and biomechanical systems, and in locomotion. How to apply for the position:Step 1: The position is only open to applicants who have been accepted by the EPFL doctoral school (see http://phd.epfl.ch/). The first step is therefore to fill the applications for one of the relevant EPFL doctoral programs in robotics (http://phd.epfl.ch/EDPR), or neuroscience (http://phd.epfl.ch/neuroscience). Step 2: In parallel to step 1, or once accepted by one of the doctoral programs (please specify which doctoral program and the date of acceptance), the application to the position should be sent by email to Prof. Pavan Ramdya and consist of a motivation letter (explaining why you are interested in the project, and why you feel qualified for it) and a copy of the doctoral program application. Informal inquiries about the relevance of an application can be sent to pavan.ramdya at epfl.ch (e.g. before or while submitting an application to the doctoral school), but responses can be slow because of a heavy schedule and a filled mail box.? Deadline and starting date:Applications will be considered starting from Feb 15 2019, and then continuously until the position is filled. The starting date is September 2019. Note that the doctoral programs have different deadlines, e.g. January 15 2019 for robotics (EDRS), and May 1st 2019 for neuroscience (EDNE). Contact: Information concerning the type of research carried out by the groups can be found at http://biorob.epfl.ch/ and https://ramdya-lab.epfl.ch/.? You should send your application and any inquiry by email to: Prof. Pavan Ramdya, pavan.ramdya at epfl.ch *********************************************************************************** Prof. Pavan Ramdya ?? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?? Pavan.Ramdya at epfl.ch Swiss Federal Institute of Technology (EPFL) AAB 105, Station 19 ? ? ? ? ? ? ? ? ? ? ? ????????????? Telephone: +41 21 693 6960 CH-1015 Lausanne, Switzerland ? ? ? ? ? ? ? ?? Assistant:?? +41 21 693 0756 Director, Neuroengineering Laboratory???????? https://ramdya-lab.epfl.ch From albagarciaseco at gmail.com Wed Dec 12 06:29:33 2018 From: albagarciaseco at gmail.com (=?UTF-8?B?QWxiYSBHYXJjw61h?=) Date: Wed, 12 Dec 2018 11:29:33 +0000 Subject: Connectionists: Call For Participation: 1st Edition of ImageCLEF Coral Annotation Challenge (@ CLEF 2019) Message-ID: *The 1st Edition of the ImageCLEF Coral Annotation Challenge 2019* Website: https://www.imageclef.org/2019/coral *Motivation* The increasing use of structure-from-motion photogrammetry for modelling large-scale environments from action cameras attached to drones has driven the next-generation of visualisation techniques that can be used in augmented and virtual reality headsets. It has also created a need to have such models labelled, with objects such as people, buildings, vehicles, terrain, etc. all essential for machine learning techniques to automatically identify as areas of interest and to label them appropriately. However, the complexity of the images makes impossible for human annotators to assess the contents of images on a large scale. Advances in automatically annotating images for complexity and benthic composition have been promising, and we are interested in automatically identify areas of interest and to label them appropriately for monitoring coral reefs. Coral reefs are in danger of being lost within the next 30 years, and with them the ecosystems they support. This catastrophe will not only see the extinction of many marine species, but also create a humanitarian crisis on a global scale for the billions of humans who rely on reef services. By monitoring the changes and composition of coral reefs we can help prioritise conservation efforts. *Data* The data for this task originates from a growing, large-scale collection of images taken from coral reefs around the world as part of a coral reef monitoring project with the Marine Technology Research Unit at the University of Essex (currently containing over 2TB of image data of benthic reef structure). * Challenge description* Participants will be require to annotate and localise coral reef images by labelling the images with types of benthic substrate together. Each image is provided with possible class types. *Preliminary Schedule* - *19.11.2018*: Registration opens for all ImageCLEF tasks (until *26.04.2019*) - *15.01.2019*: training release starts - *18.03.2019*: Test data release starts - *01.05.2019*: Deadline for submitting the participants runs - *13.05.2019*: Release of the processed results by the task organizers - *24.05.2019*: Deadline for submission of working notes papers by the participants - *07.06.2019*: Notification of acceptance of the working notes papers - *28.06.2019*: Camera-ready working notes papers - *09-12.09.2019*: CLEF 2019 , Lugano, Switzerland *Participant Registration* Please refer to the general ImageCLEF registration instructions *Organizing Committee* - Jon Chamberlain ,University of Essex, UK - Adrian Clark ,University of Essex, UK - Alba Garc?a Seco de Herrera ,University of Essex, UK For more details and updates, please visit the task website at: https://www.imageclef.org/2019/coral And join our mailing list: https://groups.google.com/d/forum/imageclefcoral Dr Alba Garc?a Seco de Herrera PhD Lecturer Department of Computer Science and Electronic Engineering (CSEE) University of Essex T +44 (0) 1206 872907 E alba.garcia at essex.ac.uk ? *https://www.essex.ac.uk/ * WE ARE ESSEX -------------- next part -------------- An HTML attachment was scrubbed... URL: From pgrover at andrew.cmu.edu Wed Dec 12 16:05:32 2018 From: pgrover at andrew.cmu.edu (Pulkit Grover) Date: Wed, 12 Dec 2018 16:05:32 -0500 Subject: Connectionists: Postdoctoral Position in the Epilepsy, Cognition, and Development Laboratory (ECDL) In-Reply-To: References: Message-ID: Please see an exciting opportunity for a machine-learning postdoc position in an impactful and influential lab in University of Pittsburgh. Posting on behalf of Dr. Taylor Abel from Pitt pediatrics neurosurgery. Best, Pulkit ---------- Forwarded message --------- From: Taylor Abel Date: Wed, Dec 12, 2018 at 3:35 PM Subject: Re: lists on which to post To: Pulkit Grover *Postdoctoral Position in the Epilepsy, Cognition, and Development Laboratory (ECDL) * We are seeking a full-time postdoctoral researcher to work on a project that seeks to understand the neurophysiologic mechanisms underlying visual recognition and how these mechanisms emerge in human development. A background in machine learning analysis is ideal. A background in electrophysiology and behavioral methods is desirable. The project will involve collection and analysis of human brain recordings in epilepsy surgery patients, so candidates would ideally be comfortable working in a clinical environment. The ideal start date is Feb 2019, but application review will continue until the positions are filled. The position is initially for at least 12 months with the possibility of renewal. Compensation will be competitive, and commensurate with relevant experience. University of Pittsburgh has competitive benefits (including comprehensive medical insurance) and is an equal opportunity employer. The ECDL is based at the Children?s Hospital of Pittsburgh. There is close collaboration with Marlene Behrmann, Avniel Ghuman, and Pulkit Grover through the Center for the Neural Basis of Cognition. Please send your CV to and provide 3 email addresses for reference to Dr. Taylor Abel abeltj at upmc.edu. On Wed, Dec 12, 2018 at 10:15 AM Pulkit Grover wrote: > connectionists at cs.cmu.edu, > comp-neuro at neuroinformatics.be > > Both might require subscription. Both have wide access to computational > neuroscience researchers (the first one has subscribers outside of > PIttsburgh as well). > > Also, conferences sometimes have postdoc ad possibilities for payment. > That worked out very well for us at SfN. Perhaps ACNS or AES or other > epilepsy conferences have these? Or ML conferences, such as > NIPS/ICML/AISTATS? > > Cheers! > -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Postdoctoral Position in ECDL.docx Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document Size: 80000 bytes Desc: not available URL: From irina.illina at loria.fr Thu Dec 13 03:27:58 2018 From: irina.illina at loria.fr (Irina Illina) Date: Thu, 13 Dec 2018 09:27:58 +0100 (CET) Subject: Connectionists: Research engineer or post-doc position in Natural Language Processing (LORIA, France) In-Reply-To: <563224855.15324328.1541364984538.JavaMail.zimbra@loria.fr> References: <563224855.15324328.1541364984538.JavaMail.zimbra@loria.fr> Message-ID: <1591960117.9505381.1544689678607.JavaMail.zimbra@loria.fr> Research engineer or post-doc position in Natural Language Processing: Introduction of semantic information in a speech recognition system Supervisors: Irina Illina, MdC, Dominique Fohr, CR CNRS Team: Multispeech, LORIA-INRIA (https://team.inria.fr/multispeech/) Contact: illina at loria.fr, dominique.fohr at loria.fr Duration: 12-18 months Deadline to apply : January 10th, 2019 Required skills: Strong background in mathematics, machine learning (DNN), statistics, natural language processing and computer program skills (Perl, Python). Following profiles are welcome, either: ? Strong background in signal processing or ? Strong experience with natural language processing Excellent English writing and speaking skills are required in any case. Candidates should email a detailed CV with diploma LORIA is the French acronym for the ?Lorraine Research Laboratory in Computer Science and its Applications? and is a research unit (UMR 7503), common to [ http://www.cnrs.fr/index.php | CNRS ] , the [ http://vers.univ-lorraine.fr/ | University of Lorraine ] and [ http://www.inria.fr/en/ | INRIA ] . This unit was officially created in 1997. Loria?s missions mainly deal with fundamental and applied research in computer sciences. MULTISPEECH is a joint research team between the Universit? of Lorraine, Inria, and CNRS. Its research focuses on speech processing, with particular emphasis to multisource (source separation, robust speech recognition), multilingual (computer assisted language learning), and multimodal aspects (audiovisual synthesis). Context and objectives Under noisy conditions, audio acquisition is one of the toughest challenges to have a successful automatic speech recognition (ASR). Much of the success relies on the ability to attenuate ambient noise in the signal and to take it into account in the acoustic model used by the ASR. Our DNN (Deep Neural Network) denoising system and our approach to exploiting uncertainties have shown their combined effectiveness against noisy speech. The ASR stage will be supplemented by a semantic analysis. Predictive representations using continuous vectors have been shown to capture the semantic characteristics of words and their context, and to overcome representations based on counting words. Semantic analysis will be performed by combining predictive representations using continuous vectors and uncertainty on denoising. This combination will be done by the rescoring component. All our models will be based on the powerful technologies of DNN. The performances of the various modules will be evaluated on artificially noisy speech signals and on real noisy data. At the end, a demonstrator, integrating all the modules, will be set up. Main activities ? study and implementation of a noisy speech enhancement module and a propagation of uncertainty module; ? design a semantic analysis module; ? design a module taking into account the semantic and uncertainty information. References [Nathwani et al ., 2018] Nathwani, K., Vincent, E., and Illina, I. DNN uncertainty propagation using GMM-derived uncertainty features for noise robust ASR, IEEE Signal Processing Letters , 2018. [Nathwani et al ., 2017] Nathwani, K., Vincent, E., and Illina, I. Consistent DNN uncertainty training and decoding for robust ASR, in Proc. IEEE Automatic Speech Recognition and Understanding Workshop , 2017. [Nugraha et al., 2016] Nugraha, A., Liutkus, A., Vincent E. Multichannel audio source separation with deep neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2016. [Sheikh, 2016] Sheikh, I. Exploitation du contexte s?mantique pour am?liorer la reconnaissance des noms propres dans les documents audio diachroniques?, These de doctorat en Informatique, Universit? de Lorraine, 2016. [Sheikh et al., 2016] Sheikh, I. Illina, I. Fohr, D. Linares, G. Learning word importance with the neural bag-of-words model, in Proc. ACL Representation Learning for NLP (Repl4NLP) Workshop, Aug 2016. [Mikolov et al., 2013a] Mikolov, T. Chen, K., Corrado, G., and Dean, J. Efficient estimation of word representations in vector space, CoRR , vol. abs/1301.3781, 2013. -- Associate Professor Lorraine University LORIA-INRIA office C147 Building C 615 rue du Jardin Botanique 54600 Villers-les-Nancy Cedex Tel:+ 33 3 54 95 84 90 -------------- next part -------------- An HTML attachment was scrubbed... URL: From Mark.Humphries at nottingham.ac.uk Thu Dec 13 07:37:01 2018 From: Mark.Humphries at nottingham.ac.uk (Mark Humphries) Date: Thu, 13 Dec 2018 12:37:01 +0000 Subject: Connectionists: "The Spike": the key stories about neuroscience, from neuroscientists In-Reply-To: References: Message-ID: If you're interested in keeping up with the cutting edge of neuroscience, you might like to know about The Spike: https://medium.com/the-spike [https://cdn-images-1.medium.com/max/1200/1*H6cV11b9xeYl-Q8ybx7Rmg.png] The Spike ? Medium medium.com The science of the brain, from the scientists of the brain. The Spike's mission is to convey the triumphs, tragedies and challenges of systems and computational neuroscience to a broad audience; while keeping you, the reader, entertained along the way. Founded in 2016, we publish stories from a diverse array of writers. Our >400 unique visitors each day reflect a diverse readership from across AI, machine learning, psychology, psychiatry, neurology, clinical neurosciences, and beyond. And, of course, the public! Popular recent stories include: "Why you should (or shouldn't) get a PhD in Neuroscience" by Ashley Juavinett: https://medium.com/the-spike/why-you-should-or-shouldnt-get-a-phd-in-neuroscience-cdb4daf6a248 [https://cdn-images-1.medium.com/max/1200/1*X-GdSTSuz569RsB95GxGbA.jpeg] Why you should (or shouldn?t) get a PhD in Neuroscience medium.com A few good reasons why you should get a neuroscience PhD You?ll open doors to different careers, and higher (paying) positions. There are certain jobs that require a PhD. "Brains as Analog Computers" by Corey Maley: https://medium.com/the-spike/brains-as-analog-computers-fa297021f935 [https://cdn-images-1.medium.com/max/1200/1*J3tX8SxApeRHo7HwNBv19A.png] Brains as Analog Computers ? The Spike ? Medium medium.com Algorithms. One idea, explored in a previous blog post in this very forum, is that the brain is a computer because what it does can be described in terms of algorithms.Unfortunately, this view has ... "A not entirely serious future history of neuroscience" by me: https://medium.com/the-spike/a-not-entirely-serious-future-history-of-neuroscience-e5d92b85d470 [https://cdn-images-1.medium.com/max/1200/1*jvbMd-eEkRfqmzkN6wMkwQ.jpeg] A not entirely serious future history of neuroscience - Medium medium.com Author?s note: resting for a moment in a dark corner of the Society for Neuroscience conference?s poster hall, on the quiet solitude of the Wednesday afternoon in the History of Neuroscience ... How to keep up to date with The Spike: Bookmark the homepage Follow us on Medium Follow us on Twitter @markdhumphries Happy reading, Prof Mark Humphries This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please contact the sender and delete the email and attachment. Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham. Email communications with the University of Nottingham may be monitored where permitted by law. -------------- next part -------------- An HTML attachment was scrubbed... URL: From J.Verhoef at donders.ru.nl Fri Dec 14 07:57:30 2018 From: J.Verhoef at donders.ru.nl (Verhoef, J.P. (Julia)) Date: Fri, 14 Dec 2018 12:57:30 +0000 Subject: Connectionists: Language in Interaction: Research Data Manager for Research Consortium 'Language in Interaction' (0.8 FTE) In-Reply-To: <0581358689e9425faeae4d338faf9be5@EXPRD05.hosting.ru.nl> References: <0581358689e9425faeae4d338faf9be5@EXPRD05.hosting.ru.nl> Message-ID: <2557884cb6bb4fc88ae5809d90676da8@EXPRD05.hosting.ru.nl> We would like to draw your attention to the following opening within the Language in Interaction consortium. Please feel free to forward this information to anyone who might be interested. Research Data Manager for Research Consortium 'Language in Interaction' (0.8 FTE) Dutch Research Consortium 'Language in Interaction' Maximum salary: ? 4,166 gross/month Vacancy number: 30.14.18 Application deadline: 6 January 2019 [Logo NWO] [Logo Language in Interaction] Responsibilities The Dutch research consortium Language in Interaction (LiI) invites applications for a Research Data Manager position. You will be responsible for the further development, elaboration and implementation of FAIR data management for all research data created within our consortium. You will facilitate and streamline lean and efficient research data management (RDM) at our different partner institutes through fostering discussion, sharing knowledge and accumulating best practices. Extensive consultation and close collaboration with data stewards at our different partner institutions will be required. You will serve as a first point of contact for RDM for all LiI partner institutions as well as our individual researchers, providing information, templates, guidelines and regulations. You will monitor compliance with the agreed LiI RDM plan for all research projects funded by LiI. In collaboration with existing support teams, you will be expected to operate as product owner by taking responsibility for the implementation of a database through which all data produced in our consortium is made available under the principles of FAIR data management. This requires translation of the functional aspects into technical implementation using opportunities offered by the existing infrastructure. You will become a member of the Management Team of our consortium, under the supervision of Prof. Peter Hagoort. This position provides the opportunity to become a member of an interdisciplinary consortium conducting world-class research. Work environment The Language in Interaction (LiI) research consortium is sponsored by a Gravitation grant from the Netherlands Organisation for Scientific Research (NWO). LiI brings together many excellent researchers from eight different research institutions in the Netherlands in a research programme on the foundations of language. Teams of researchers collaborate to collectively address five key questions in our research field, producing an enormous variety of data types, all of which require different approaches to fulfil the criteria for FAIR data management. Until now, each partner institution has developed its own protocols for FAIR data management. The consortium offers a unique opportunity to standardise data management on a transcending scale. You will be appointed at the Donders Institute, Centre for Cognitive Neuroimaging (Radboud University, Nijmegen). All our partner institutions offer an international setting. English is the lingua franca. What we expect from you ? you have a scientific background (preferably in a domain related to the research performed by our consortium); ? you have affinity with scientific research; ? you have an excellent sense of organisational and managerial relations; ? you have good communication skills; ? you are able to translate functional requirements into technical implementations; ? you have general programming skills; ? you are acquainted (or willing to familiarise yourself) with all aspects that influence FAIR data management (technical aspects, but also ethics, legislation, etc.); ? you are enterprising and result-oriented; ? you have strong oral and written English proficiency. What we have to offer ? employment: 0.8 FTE; ? a maximum gross monthly salary of ? 4,166 based on a 38-hour working week (salary scale 10); ? in addition to the salary: an 8% holiday allowance and an 8.3% end-of-year bonus; ? you will be appointed for the remaining time frame of our consortium, until June 30, 2023; ? University job profile: Project Leader Level 1; ? you will be able to make use of our Dual Career Service where our Dual Career Officer will assist with family related support, such as child care, and help your partner prepare for the local labour market and with finding an occupation. Are you interested in our excellent employment conditions? Other Information The intended start date is as soon as possible. The institute involved is an equal opportunity employer, committed to building a culturally diverse intellectual community, and as such encourages applications from women and minorities. Would you like to know more? Further information on: The Language in Interaction research consortium For more information about this vacancy, please contact: MSc. Sander Berends, programme manager Language in Interaction Telephone: +31 24 3619838 E-mail: s.berends at donders.ru.nl Prof. dr. Peter Hagoort, principal investigator Telephone: +31 24 3610648, +31 24 3521301 E-mail: p.hagoort at donders.ru.nl Are you interested? You should upload your application (attn. of Prof. dr. P. Hagoort) exclusively using the button 'Apply' below. Your application should include (and be limited to) the following attachment(s): ? a cover letter ? your curriculum vitae, including the names of at least two persons who can provide references [Apply] No commercial propositions please. Kind regards, Julia Verhoef Secretary - Language in Interaction Consortium Radboud University | Donders Centre for Cognitive Neuroimaging (DCCN) Room 0.026 Kapittelweg 29, 6525 EN Nijmegen, The Netherlands P.O. Box 9101, 6500 HB, Nijmegen, The Netherlands |T: +31 (0)24 3666272 E: J.Verhoef at donders.ru.nll|Office hours: 9-14 hr on Mon - Fri -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.jpg Type: image/jpeg Size: 2461 bytes Desc: image001.jpg URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image002.jpg Type: image/jpeg Size: 40202 bytes Desc: image002.jpg URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image003.jpg Type: image/jpeg Size: 3660 bytes Desc: image003.jpg URL: From annalisa.riccardi at strath.ac.uk Fri Dec 14 08:55:20 2018 From: annalisa.riccardi at strath.ac.uk (Annalisa Riccardi) Date: Fri, 14 Dec 2018 13:55:20 +0000 Subject: Connectionists: Special Session on Computational Intelligence for Aerospace @ CEC 2019 Message-ID: <5F981B7DF1B7214DB40BAA37423DD2B636DE9B7B@EX2010-MBX1.ds.strath.ac.uk> (we apologize for possible multiple copies of this message ) Dear Colleague, this is a gentle reminder that the deadline for the submission of the paper to the Special Session on Computational Intelligence in Aerospace Sciences & Engineering within the framework of the IEEE Congress on Evolutionary Computation (10-13 June, 2019, Wellington, New Zealand) is fast approaching. http://cec2019.org/ http://cec2019.org/programs/special_sessions.html#cec-53 *Important Dates Paper Submission: 7 January 2019 Decision Notification: 7 March 2019 Final submission: 31 March 2019 Note: all deadlines are 11:59pm US pacific time *Submission Guidelines Manuscripts should be prepared according to the standard format of regular papers specified in IEEE CEC2019. Paper submission is online through the CEC2019 submission website http://www.cec2019.org/papers.html#submission. Papers submitted for these session will be peer-reviewed with the same criteria used for other contributed papers. All accepted papers in the special sessions will be included in the published conference proceedings. Best regards, Special Session Organisers Prof Massimiliano Vasile Aerospace Centre of Excellence University of Strathclyde, UK Dr Annalisa Riccardi, Aerospace Centre of Excellence University of Strathclyde, UK Prof Peter Koro?ec Jo?ef Stefan Institute Ljubljana, Slovenia From gershman at fas.harvard.edu Fri Dec 14 08:59:19 2018 From: gershman at fas.harvard.edu (Gershman, Samuel Joseph) Date: Fri, 14 Dec 2018 13:59:19 +0000 Subject: Connectionists: RLDM call for workshops Message-ID: The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2019) will be held in Montr?al, Canada, from July 7-10, 2019. Workshops are a new addition to the RLDM program, and will be held on the last afternoon of the meeting, Wednesday July 10, from 1pm to 5pm. We invite researchers interested in chairing one of these workshops to submit workshop proposals. The goal of the workshops is to encourage interdisciplinary discussion and provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are encouraged as workshop topics. We also invite both standard and innovative/non-standard formats, such as invited oral presentations, panel discussions, data modeling challenges, hackathons, debates, and workshops aimed at improving communication between researchers from different fields rather than presenting novel research. Workshop organizers have several responsibilities, including coordinating workshop participation and content as well as providing the program for the workshop in a timely manner. Due to the short length of the workshops, we discourage poster sessions. Submission Instructions To submit a workshop proposal, please e-mail your submission to Sam Gershman (gershman at fas.harvard.edu) by 23:59 UTC on Friday, March 1st, 2019. Notifications will be provided by March 15, 2019. Proposals should clearly specify the following: * Workshop title and acronym if available * A brief description of the workshop focus, emphasizing why this workshop would appeal to the diverse RLDM audience * A short description of the format of planned activities (talks, panels, invited speakers, activities, etc.) * A list of which invited speakers have confirmed their willingness to participate * A list of organizers with email addresses, web page URLs RLDM will not be able to provide travel funding for workshop speakers. In other venues, some workshops have sought and received funding from external sources to bring in outside speakers and RLDM is open to that model. -------------- next part -------------- An HTML attachment was scrubbed... URL: From luigi.malago at gmail.com Fri Dec 14 10:26:34 2018 From: luigi.malago at gmail.com (=?UTF-8?Q?Luigi_Malag=C3=B2?=) Date: Fri, 14 Dec 2018 17:26:34 +0200 Subject: Connectionists: Postdoc position in Geometric Methods for Machine Learning and Deep Learning at RIST In-Reply-To: References: 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 January 2018 (applicants are encouraged to apply earlier) *Salary*: around 2200 euro net *Official announcement*: *https://rist.ro/postdoc-position-in-deep-learning-and-machine-learning/ * =========================================================== 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: *https://rist.ro/postdoc-position-in-deep-learning-and-machine-learning/ * Informal inquiries can be sent to Dr. Luigi Malag? , principal investigator of the DeepRiemann project. Application deadline: 10 January 2018 (applicants are encouraged to apply earlier) best regards, Luigi Malag? -------------- next part -------------- An HTML attachment was scrubbed... URL: From dimitri.ognibene at gmail.com Fri Dec 14 11:02:17 2018 From: dimitri.ognibene at gmail.com (Dimitri Ognibene) Date: Fri, 14 Dec 2018 16:02:17 +0000 Subject: Connectionists: Open Post Doc Position on Bayesian Computational Modelling for multimodal social interaction Message-ID: <234264F4-E286-4553-844D-13CEED3CB880@gmail.com> [Apologies for cross-posting] Dear Colleagues, I would be grateful if you could help me spreading the word about this position in the Essex Brain-Computer Interface and Neural Engineering (BCI-NE) Laboratory that I recently joined. Thank you very much, Dimitri We are looking for a Post Doctoral Research Associate to collaborate at the development of Bayesian (DCM and Active Inference) computational models of multimodal social interaction taking into account the role of human chemosignals perception. This will involve also the development of robust algorithms for signal processing, statistical inference and extraction of information from EEG and other physiological signals, as well as the design and implementation of software for the execution of experiments with adaptive VR stimulation. Application closing date 02/01/2019 Application Links https://www.jobs.ac.uk/job/BOO174/senior-research-officer https://vacancies.essex.ac.uk/tlive_webrecruitment/wrd/run/ETREC107GF.open?VACANCY_ID=271640IULU&WVID=9918109NEm&LANG=USA Job reference REQ02121 Job Details The School of Computer Science and Electronic Engineering, the Department of Psychology, and the Essex Brain-Computer Interfaces and Neural Engineering Lab are pleased to announce this postdoctoral position in the Horizon 2020 project "POTION: Promoting social interaction through emotional body odours?. The project will last five years and start in January 2019 and includes partners from the Universities of Pisa (Italy), Padova (Italy), and Essex (UK), the Universitat Politecnica De Valencia (Spain), the Katholieke Universiteit Leuven (Belgium), and the Karolinska Institutet (Sweden), and three companies ISPA CRL (Portougal), SRA Instruments (France) and Feel-Ing s.r.l. (Italy). POTION proposes a novel technological paradigm to delve deeper into understanding meaningful social interaction, combining new knowledge about the chemical composition of human social chemosignals together with a novel olfactory-based technology designed to drive social behaviour. Duties of the Role The Essex team's work on the project focuses on the development of Bayesian (DCM and Active Inference) computational models of multimodal social interaction. This models will be applied to evaluate socially relevant variables, such as trust, presence and inclusion as well as to generate optimal stimuli in artificially mediated social interactions. In particular, the models will cover the role of human chemosignal perception in social interactions. The models will be identified and tested using neurophysiological data (e.g. EEG), peripheral physiological activation (i.e., ECG, RESP, EDA) and behavioural changes (i.e., f-EMG) collected using VR scenarios of increasing complexity. The successful applicant will research and develop Bayesian (DCM and Active Inference) computational models of multimodal social interaction with an emphasis on the role of human chemosignals. They will also develop robust algorithms for signal processing, statistical inference and extraction of information from EEG and other physiological signals, design and implement software for the execution of experiments with VR stimulation, and contribute to the reporting and dissemination of the project. Skills and qualifications required Applicants are expected to hold a PhD (or be close to completion) in Computational Neuroscience, Brain-computer Interfaces, Neural Engineering, Psychology, Machine Learning, Statistics, Physics, Mathematics, Computer Science or a closely related discipline, or equivalent professional experience or practice. The ideal candidate will have significant experience in computational modelling of social interaction, signal processing, statistical modelling of neural signals and processes, brain-computer interfaces, and virtual reality interfaces. Applicants are also expected to have a strong publication record (relative to their career stage) as first author, ideally including publications in 1st quartile journals in relevant areas. We strongly encourage women to apply as they are currently under-represented in the School of Computer Science and Electronic Engineering. At the University of Essex internationalism is central to who we are and what we do. We are committed to being a cosmopolitan, internationally-oriented university that is welcoming to staff and students from all countries and a university where you can find the world in one place. Who we are University of Essex has just been awarded the prestigious title of "University of the Year" by the Times Higher Education for "transforming the lives of a growing student body? and " putting both staff and students first" The School of Computer Science and Electronic Engineering (CSEE) at the University of Essex has an outstanding reputation for teaching and high-quality research in artificial intelligence, biomedical engineering, brain-computer interfaces, computer games, evolutionary computation, human language technology, robotics, networks and optoelectronics. Particularly relevant to this application is our research in artificial intelligence and in life and medical sciences applications, which was judged as world-leading in the recent Research Excellence Framework, the system for assessing the quality of research in UK higher education institutions. An important centre spanning both areas is the Essex Brain-Computer Interface and Neural Engineering (BCI-NE) Laboratory. The BCI lab was founded in 2004 by Dr Citi among others, and is one of the largest and best equipped in Europe. For over a decade, it has produced highly visible internationally leading research, with international collaborators at MIT, Berkley, the European Space Agency, and many others. Our members have led high-profile externally funded projects in the area of Assisted Living Technologies. Since 2007 our research has featured prominently in the UK?s Department of Health?s annual report on research and development work relating to assistive technology, e.g. see the 2012 report, which was presented to parliament. The successful applicant will work in collaboration with the Department of Psychology at the University of Essex. This department was ranked 13th out of more than 100 in the UK in the most recent Research Excellence Framework (REF 2014 ), with 90% of our research rated as world-leading or internationally excellent. Academic staff in the department have wide-ranging and world-leading expertise in vision, cognition, cognitive neuroscience, health and social psychology. Students and staff make use of facilities in the Centre for Brain Science, a purpose-built facility dedicated to research and with considerable resources for understanding brain and behaviour. The research facilities are located on our Colchester Campus, which is set within 200 acres of beautiful parkland , located two miles from the historic town centre of Colchester ? England's oldest recorded town. Our Colchester Campus is also easily reached from London and Stansted Airport in under one hour. Home to over 13,000 students from more than 130 countries, our Colchester Campus is the largest of our three sites, making us one of the most internationally diverse campuses on the planet - we like to think of ourselves as the world in one place. Colchester has a relatively low cost of living, while being well connected to London, the coast, and areas of natural beauty in East Anglia. Please see the link below for a full job description and person specification which outlines the full duties, skills, qualifications and experience needed for this role plus more information relating to the post. We recommend you read this information carefully before making an application. Applications should be made on-line, but if you would like advice or help in making an application, or need information in a different format, please telephone the Resourcing Team (+44 1206 876559 ). Feel free to contact us (Dr Citi, (CSEE) lciti at essex.ac.uk (PI), Dr Ognibene (CSEE) dimitri.ognibene at essex.ac.uk , Dr Foulsham (PSYCH) foulsham at essex.ac.uk) for an informal discussion about this post. Job reference REQ02121 Application closing date02/01/2019 Application Links https://www.jobs.ac.uk/job/BOO174/senior-research-officer https://vacancies.essex.ac.uk/tlive_webrecruitment/wrd/run/ETREC107GF.open?VACANCY_ID=271640IULU&WVID=9918109NEm&LANG=USA -- Dimitri Ognibene, PhD Lecturer in Computer Science and Artificial Intelligence Department of Computer Science and Electronic Engineering, University of Essex, UK http://sites.google.com/site/dimitriognibenehomepage/ Skype: dimitri.ognibene -------------- next part -------------- An HTML attachment was scrubbed... URL: From c.decampos at uu.nl Sat Dec 15 04:48:42 2018 From: c.decampos at uu.nl (Polpo de Campos, C. (Cassio)) Date: Sat, 15 Dec 2018 09:48:42 +0000 Subject: Connectionists: ISIPTA 2019: There is more to uncertainty than probabilities Message-ID: What if we told you that ?There?s more to uncertainty than probabilities.? Would you agree? Would you object? Are you intrigued? Regardless of the answer, you have a place at, and are invited to submit a paper to, ISIPTA 2019, the 20-year anniversary edition of the world?s main forum on imprecise probabilities. Already convinced? Then come to Ghent, Belgium, 3-6 July 2019, and take a look at the following website for any and all details you might require: http://isipta2019.ugent.be. Not convinced yet? Then perhaps the following features can convince you: Topic: ISIPTA 2019 is devoted to robustness and imprecision in uncertainty modelling, inference and decision making, focusing in particular on uncertainty frameworks that extend or replace the probabilistic one. Concept: Each accepted contribution is presented and discussed, in two separate sessions. Presentations are short and plenary. Detailed explanations and discussions are face-to-face, with the aid of a poster, a whiteboard, pen and paper, or whichever medium you prefer. Atmosphere: ISIPTA conferences are characterised by a friendly and cooperative style, a strong emphasis on in-depth discussion and a true openness to new ideas. We hope that you too will both enjoy and contribute to this unique atmosphere. Venue: Ghent has been called ?Belgium?s best kept secret? by the Lonely Planet travel guide and a ?medieval masterpiece? by The Guardian. The conference itself takes place in an old Augustinian monastery, situated in its historic city centre. Types of contributions: We accept long papers, short papers and poster abstracts. Papers are published in a volume of PMLR (formerly known as JMLR WCP), unless explicitly preferred otherwise by their authors. We look forward to receiving your contribution and/or to seeing you in Ghent! Sincerely, The ISIPTA 2019 Steering Committee and PC board F. Cozman (University of Sao Paulo, Brazil) J. De Bock (Ghent University, Belgium) G. de Cooman (Ghent University, Belgium) C. de Campos (Utrecht University, The Netherlands) E. Quaeghebeur (Delft University of Technology, The Netherlands) T. Seidenfeld (Carnegie Mellon University, USA) G. Wheeler (Frankfurt School of Finance and Management, Germany) From george at cs.ucy.ac.cy Sat Dec 15 06:36:16 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Sat, 15 Dec 2018 13:36:16 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Second Call for Tutorial Proposals In-Reply-To: <6FC69A4B-F456-4336-A7CC-2AAE2723CB67@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> <05EDB924-A9A7-4E3B-8E36-05EAE5D4242A@cs.ucy.ac.cy> <6FC69A4B-F456-4336-A7CC-2AAE2723CB67@cs.ucy.ac.cy> Message-ID: *** SECOND CALL FOR TUTORIAL PROPOSALS *** 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/ Proposals due: February 11, 2019 ACM UMAP 2019, the premier international conference for researchers and practitioners working on systems that adapt to individual users or to groups of users, and which collect, represent, and model user information, is pleased to invite proposals for tutorials to be given in conjunction with the conference. Tutorials are intensive instructional sessions aimed to provide a comprehensive introduction to established or emerging research topics of interest for the UMAP community. Topics of interest include, but are not limited to: ? new user modeling technologies, methods, techniques, and trends (e.g. exploiting data mining and big data analytics for user modeling, evaluation methodologies, data visualization, etc.); ? user modeling and personalization techniques for specific domains (e.g., health sciences, e-government, e-commerce, cultural heritage, education, internet of things, mobile, music, information retrieval, etc.); ? application of user modeling and personalization techniques for information retrieval and recommender systems; ? eliciting and learning user preferences by taking into account users? emotional state, physical state, personality, trust, cognitive factors. An ideal tutorial should be broad enough to provide a basic introduction to the chosen area, but it should also cover the most important topics in depth. Tutorial presenters can have one page in the adjunct proceedings. PROPOSAL FORMAT AND SUBMISSION Tutorial proposals should be submitted in PDF format to both tutorial chairs, not exceeding 5 pages and containing the following information: 1. Title and abstract of the tutorial for inclusion on the ACM UMAP 2019 website (200 words maximum). 2. Tutorial description: ? learning objectives of the tutorial and relevance to ACM UMAP 2019; ? targeted audience (introductory, intermediate, advanced) and prerequisite knowledge or skills; ? a brief outline of the tutorial structure; ? practical sessions. 3. Tutorial length: full (6 hours) or half day (3 hours). 4. Other venues to which the tutorial or part thereof has been or will be presented, in addition to explaining how the current tutorial differs from the other editions. 5. Name, email address, affiliation and brief professional biography of the tutorial instructor(s), indicating previous training and speaking experience. IMPORTANT DATES ? Tutorial proposals: February 11, 2019 ? Notification of acceptance: February 26, 2019 ? Tutorial summary camera-ready: April 3, 2019 ? Adjunct proceedings camera ready: April 15, 2019 ? Tutorial day: June 9, 2019 EVALUATION CRITERIA All proposals will be reviewed by the tutorial chairs. The features that will be evaluated are: 1. ability of the tutorial to contribute to strengthening the foundations of UMAP research; 2. clarity of the tutorial, which should emerge from its description; 3. good organization, as appearing from the outline; 4. background/experience of tutorial instructor(s) in teaching the target topics. TUTORIAL CHAIRS ? Milos Kravc?k, German Research Center for Artificial Intelligence (DFKI), Germany (milos.kravcik AT dfki.de) ? Iv?n Cantador, Universidad Aut?noma de Madrid, Spain (ivan.cantador AT uam.es) -------------- next part -------------- An HTML attachment was scrubbed... URL: From marc.dymetman at naverlabs.com Sat Dec 15 14:15:13 2018 From: marc.dymetman at naverlabs.com (Marc Dymetman) Date: Sat, 15 Dec 2018 20:15:13 +0100 Subject: Connectionists: Internship on Prior Knowledge for Training Neural Seq2Seq Models, NAVER Labs Europe (Grenoble, France) Message-ID: Are you a currently enrolled student with a strong interest in Deep Learning for Sequential models, at the Master or PhD level? NAVER Labs Europe (NLE) is opening an exciting internship on Prior Knowledge for Training Neural Seq2Seq Models. NLE is the largest AI research center in France, located in Grenoble. For more information and application procedure, please visit the link: http://www.europe.naverlabs.com/NAVER-LABS-Europe/Internships/Prior-Knowledge-for-Training-Neural-Seq2Seq-Models ------------------------------? Prior Knowledge for Training Neural Seq2Seq Models NAVER LABS Europe (NLE) is opening a research internship with the goal of advancing the use of prior knowledge for training neural seq2seq models. When training data is scarce, as is often the case in practice, standard end-to-end training of sequential models tends to produce mediocre results; however, it is often the case that the developer of such models is aware of structural biases and global characteristics of candidates that could be exploited to better generalize from the available direct observations. We are looking for a motivated intern to join an ongoing research project addressing this general problem, both in theory and in practice. The experiments will be conducted both on synthetic data, for permitting a fine-grained and flexible exploration of different parameters of the problem, as well as on natural data (e.g. NLG, MT), for validating the usefulness of the techniques. The successful candidate should be enrolled in a graduate program, at the Master or (preferably) PhD level, with a focus on Deep Learning (knowledge of NLP and RL a plus). Strong mathematical and programming skills as well as familiarity with one of the major current deep learning toolkits (PyTorch preferred but not compulsory) are a requirement. Publication of results in major conferences/journals will be strongly encouraged. Start Date Early 2019 Duration 5-6 months Application instructions To apply, please send a mail and CV to Marc Dymetman (marc.dymetman at naverlabs.com) and Jean-Marc Andreoli (jean-marc.andreoli at naverlabs.com). -------------- next part -------------- An HTML attachment was scrubbed... URL: From jorgecbalmeida at gmail.com Sat Dec 15 18:16:57 2018 From: jorgecbalmeida at gmail.com (Jorge Almeida) Date: Sat, 15 Dec 2018 23:16:57 +0000 Subject: Connectionists: Cognitive Neuroscience Research positions in Coimbra Portugal. Message-ID: The Proaction Laboratory (Jorge Almeida's lab; proactionlab.fpce.uc.pt) at the University Coimbra Portugal is looking for Researchers at different levels of their career from newly phd graduates, to assistant, associate or full level researchers to be part of the lab in a joint application to a Portuguese Science Foundation (FCT) call. The applicants should have an interest on cognitive neuroscience, vision science and object recognition. The applicants should also have expertise in one or some of the techniques used in the lab - e.g., population Receptive Fields/phase lag analysis; Representational Similarity Analysis, MVPA, deep learning and other computational neuroscience approaches. Good programming skills, great communication and mentoring skills, and a great command of english are a plus. The positions are as independent researchers in the Proaction Lab, are for 6 years, and the salary is the same as the Portuguese payroll for University Professors (net values for junior, assistant, associate positions, for instance are approximately 1500, 1900 and 2100 euros per month in a 14 month salary per year; these are competitive salaries for the cost of living in Portugal and especially in Coimbra). The Proaction Lab is currently very well funded as we have a set of on-going funded projects including a Starting Grant ERC to Jorge Almeida (starting in February) and several FCT projects. We have access to a 3T MRI scanner with a 64-channel coil (with EEG inside the scanner), to tDCS, and to a fully set psychophysics lab. We have EEG and eyetracking on site. Finally, the University of Coimbra is a 700 year old University and has been selected as a UNESCO world Heritage site. Coimbra is one of the most lively university cities in the world, and it is a beautiful city with easy access to the beach and mountain. The deadline for this pre-application is January 10, but you should apply as soon as you can - the sooner the better so that we can prepare the application. If interested send an email to jorgecbalmeida at gmail.com, with a CV, and motivation/scientific proposal letter. If there is a fit, we will jointly apply to these positions. -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Sun Dec 16 08:42:25 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Sun, 16 Dec 2018 15:42:25 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Second Call for Doctoral Consortium Submissions In-Reply-To: <6FC69A4B-F456-4336-A7CC-2AAE2723CB67@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> <05EDB924-A9A7-4E3B-8E36-05EAE5D4242A@cs.ucy.ac.cy> <6FC69A4B-F456-4336-A7CC-2AAE2723CB67@cs.ucy.ac.cy> Message-ID: <3D0926CD-0237-493E-BBD1-914DD649F38F@cs.ucy.ac.cy> *** SECOND CALL FOR DOCTORAL CONSORTIUM SUBMISSIONS *** 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/ Submissions due: March 1, 2019 ACM UMAP 2019, the premier international conference for researchers and practitioners working on systems that adapt to individual users or to groups of users, and which collect, represent, and model user information, will, as in previous issues of the conference series, include a Doctoral Consortium (DC) Session, which provides an opportunity for doctoral students to explore and develop their research interests under the guidance of distinguished researchers from the field. Doctoral students are invited to apply to present their research to experienced scholars who will provide constructive feedback and advice. The Doctoral Consortium is implemented as a student mentoring program that introduces students to senior researchers from the relevant fields. Students are expected to document in a brief submission their doctoral research (see below described submission information for further details), which will be evaluated by the consortium committee. Good quality applications will be selected for presentation at a Doctoral Consortium Session as part of the conference. Promising, but less well- developed applications will be selected for presentation at a poster session. Each student with an accepted submission will be assigned a mentor who will provide feedback on the student's work and will discuss the doctoral research with the student and the audience at the consortium. How to Submit to the Doctoral Consortium To apply for the ACM UMAP 2019 Doctoral Consortium, students are asked to submit a paper presenting their doctoral research that describes: ? The problem being addressed. ? Motivation outlining the relevance of the problem and referring to related work. ? The main contributions that the PhD project aims to achieve. ? The progress made to date (including a clear description of the proposed approach, methodology and preliminary results) as well as the plan for further research. ? Topics include (but are not limited to) the ACM UMAP 2019 key areas. Each DC submission is encouraged to consider the following: identification of related (state of the art) work, indication of the potential innovation, application or advancement of the state-of-the-art that the work intends to achieve. In addition, as appropriate for the PhD project, the submissions can consider: indication of data to be used for experimentation, indication of implementation approach, indication of evaluation criteria and experimental design. Each submission should contain a cover page including the paper title, name of the PhD candidate, the name of his/her supervisor(s) and University, a paragraph describing the stage they are in the PhD programme, together with a brief description of their background. This will enable the committee to adapt its assistance to each student. Papers should be submitted via the EasyChair Doctoral Consortium submission system: https://easychair.org/conferences/?conf=acmumap2019dc Submissions should be pdf documents consisting of 1 cover page and the paper (up to 4 pages long), formatted using the ACM SIG proceedings template. ACM UMAP Proceedings The accepted ACM UMAP 2019 Doctoral Consortium papers will be included in the Conference Proceedings, which will be published by ACM and that will be available via the ACM Digital Library. The main author (doctoral student) must register for the conference for the paper to be included in the proceedings. Financial Support ACM UMAP has a history of supporting students to attend. Further details will be announced on the website soon. Important Dates ? Paper submission: March 1st, 2019 ? Notification to authors: March 22nd, 2019 ? Camera ready submission: April 3rd, 2019 ? ACM UMAP 2019 DC Session: June 11th and 12th, 2019 Note: The submissions times are 11:59pm AoE time (Anywhere on Earth). Doctoral Consortium Chairs ? Laurens Rook, TU Delft, The Netherlands (l.rook AT tudelft.nl) ? Markus Zanker, Free University of Bozen-Bolzano, Italy (mzanker AT unibz.it) -------------- next part -------------- An HTML attachment was scrubbed... URL: From aurel at ee.columbia.edu Sun Dec 16 13:18:28 2018 From: aurel at ee.columbia.edu (Aurel A. Lazar) Date: Sun, 16 Dec 2018 13:18:28 -0500 Subject: Connectionists: Columbia Workshop on Brain Circuits, Memory and Computation 2019 In-Reply-To: <637598E5-CCA7-43A1-B32C-A09700E2E302@ee.columbia.edu> References: <637598E5-CCA7-43A1-B32C-A09700E2E302@ee.columbia.edu> Message-ID: <3D2287D0-11BD-40BD-9EFD-AF84D8A3594F@ee.columbia.edu> Columbia Workshop on Brain Circuits, Memory and Computation 2019 BCMC 2019 March 21-22, 2019 Center for Neural Engineering and Computation Columbia University, New York, NY, USA Overview The goal of the workshop is to bring together researchers interested in developing executable models of neural computation/processing of the brain of model organisms. Of interest are models of computation that consist of elementary units of processing using brain circuits and memory elements. Elementary units of computation/processing include population encoding/decoding circuits with biophysically-grounded neuron models, non-linear dendritic processors for motion detection/direction selectivity, spike processing and pattern recognition neural circuits, movement control and decision-making circuits, etc. Memory units include models of spatio-temporal memory circuits, circuit models for memory access and storage, etc. A major aim of the workshop is to explore the integration of various sensory and control circuits in higher brain centers. A Fruit Fly Brain Hackathon is being conducted in conjunction with the workshop. Workshop participants are welcome to attend the hackathon. Organizer and Program Chair Aurel A. Lazar , Columbia University Registration Registration is free but all participants have to register . Thank you! Lodging and Directions to Venue Please follow this link for lodging details and directions to the hotel and venue. Sponsorship The 2019 Columbia Workshop on Brain Circuits, Memory and Computation is supported by the Department of Electrical Engineering , Columbia University Center for Computing Systems for Data-Driven Science , Data Science Institute, Columbia University School of Engineering and Applied Science , Columbia University Invited Speakers Anton Arkhipov , Allen Institute of Brain Science. Richard Benton , Center for Integrative Genomics, University of Lausanne. Benjamin L. de Bivort , Department of Organismic and Evolutionary Biology, Harvard University. Kristin Branson , Janelia Research Campus, Ashburn, VA. Gwyneth Card , Janelia Research Campus, Ashburn, VA. Kevin M. Franks , Department of Neurobiology, Duke University. Paul A. Garrity , Department of Biology, Brandeis University. Stephen F. Goodwin , Department of Physiology, Anatomy and Genetics, University of Oxford. Tim Jarsky , Allen Institute of Brain Science. Karla Kaun , Department of Neuroscience, Brown University. Gero A. Miesenboeck , Centre for Neural Circuits and Behaviour, University of Oxford. Venkatesh N. Murthy , Department of Molecular and Cellular Biology, Harvard University. Stephan Saalfeld , Janelia Research Campus, Ashburn, VA. Louis Scheffer , Janelia Research Campus, Ashburn, VA. Srinivas C. Turaga , Janelia Research Campus, Ashburn, VA. Further information about BCMC 2019 can be found here . Aurel http://www.bionet.ee.columbia.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From perfo897 at gmail.com Mon Dec 17 13:41:38 2018 From: perfo897 at gmail.com (=?utf-8?Q?Per-Erik_Forss=C3=A9n?=) Date: Mon, 17 Dec 2018 19:41:38 +0100 Subject: Connectionists: SCIA 2019 2nd Call for Papers Message-ID: Scandinavian Conference on Image Analysis, SCIA 2019 http://ssba.org.se/scia2019/ SCIA is a biennial conference that dates back to 1980. SCIA 2019 will be held in June 11-13 in Norrk?ping on the Link?ping University campus. The conference will feature three international invited speakers, and is co-located with the Swedish Symposium on Deep Learning (SSDL) which takes place June 10-11. The submission system is now open, and is accessible from the conference website: http://ssba.org.se/scia2019/ SCIA covers a broad range of image analysis and pattern recognition, including the following topics: 3D vision Color and multispectral image analysis Computational imaging and graphics Faces and gestures Feature extraction and segmentation Biometrics Document analysis Matching, registration and alignment Medical and biomedical image analysis Motion analysis and tracking Object and scene recognition Machine learning and pattern recognition Remote sensing image analysis Robot vision Video and multimedia analysis IR image processing Deep convolutional neural networks Signal processing and applications We welcome you to Norrk?ping next year. Conference chair: Jonas Unger, Link?ping University. Program chairs: Michael Felsberg, Link?ping University Per-Erik Forss?n, Link?ping University Ida-Maria Sintorn, Uppsala University. -------------- next part -------------- An HTML attachment was scrubbed... URL: From iswc.conf at gmail.com Mon Dec 17 09:28:57 2018 From: iswc.conf at gmail.com (International Semantic Web Conference) Date: Mon, 17 Dec 2018 15:28:57 +0100 Subject: Connectionists: [CfP] ISWC 2019 - Call for Tutorials, Workshops and Challenges Message-ID: 18th International Semantic Web Conference (ISWC 2019) ?knowledge graphs, linked data, linked schemas and AI on the Web? Auckland, New Zealand, 26-30 October, 2019 https://iswc2019.semanticweb.org/ The International Semantic Web Conference (ISWC) is the premier venue for presenting fundamental research, innovative technology, and applications concerning semantics, data, and the Web. It is the most important international venue to discuss and present latest advances and applications of the semantic Web, knowledge graphs, linked data, ontologies and artificial intelligence (AI) on the Web. ISWC attracts a large number of high quality submissions every year and participants from both industry and academia. ISWC brings together researchers from different areas, such as artificial intelligence, databases, natural language processing, information systems, human computer interaction, information retrieval, web science, etc., who investigate, develop and use novel methods and technologies for accessing, interpreting and using information on the Web in a more effective way. Follow us: Twitter: @iswc_conf , #iswc_conf ( https://twitter.com/iswc_conf ) LinkedIn: https://www.linkedin.com/groups/13612370 Facebook: https://www.facebook.com/ISWConf/ Become part of ISWC 2019 by submitting to the following tracks & activities or just attend them! (All deadlines are midnight Hawaii time.) In this announcement: 1. Call for Workshops 2. Call for Tutorials 3. Call for Semantic Web Challenges 1. Call for Workshops ******************************************* Besides the main technical program, ISWC will host several workshops on topics related to the general theme of the conference. The role of the workshops is to provide a setting for focused, intensive scientific exchange among researchers and practitioners interested in a specific topic. As such, workshops are the primary venues for the exploration of emerging ideas as well as for the discussion of novel aspects of established research topics. We invite you to submit a proposal for workshops on a research topic of interest to ISWC attendees. Further info: https://iswc2019.semanticweb.org/call-for-workshop-proposals/ == Important Dates == Proposals deadline: January 18, 2019 Notification: February 15, 2019 == Program Chairs == Contact: iswc2019-workshop-tutorial at inria.fr H. Sofia Pinto, INESC-ID, Instituto Superior T?cnico, Universidade de Lisboa, Lisboa, Portugal Hideaki Takeda, National Institute of Informatics, Tokyo, Japan 2. Call for Tutorials ******************************************* In addition to the regular research and workshop program, ISWC 2019 will feature a tutorial program addressing the diverse interests of its audience: Semantic Web practitioners that wish to learn about new technologies, novices to the Semantic Web interested in introductory tutorials to key Semantic Web / Linked Data topics, government and industry representatives focusing on the applicability of Semantic Web / Linked Data technologies in practical settings. We hereby invite you to submit a tutorial proposal on a research topic relevant to the ISWC 2019 audience. Further info: https://iswc2019.semanticweb.org/call-for-tutorial-proposals/ == Important Dates == Proposals deadline: January 18, 2019 Notification: February 15, 2019 == Program Chairs == Contact: iswc2019-workshop-tutorial at inria.fr H. Sofia Pinto, INESC-ID, Instituto Superior T?cnico, Universidade de Lisboa, Lisboa, Portugal Hideaki Takeda, National Institute of Informatics, Tokyo, Japan 3. Call for Semantic Web Challenges ******************************************* ISWC 2019 will run multiple Challenges (SWCs) with the aim to evaluate and compare software solutions for the Semantic Web in a systematic way. Each SWC will: * Define a task to be addressed, * Provide a training and a test dataset and * Define evaluation measures to compare the performance of participating systems. The organizers of each SWC will be responsible for the selection of the participants who will be invited to present their solutions at ISWC 2019. For ISWC 2019, SWC proposals are invited for any challenge involving Semantic Web tasks, including but not limited to: * Ontology alignment * Fact checking * Sentiment and Emotion analysis * Entity resolution * Link prediction * Attribute prediction and validation * Query and reasoning scalability * Energy efficiency of computation (e.g. green processing) * Stream processing Selected SWC systems will be presented at ISWC 2019 on October 30, 2019. Further info: https://iswc2019.semanticweb.org/call-for-workshop-proposals/ == Important Dates == Proposals deadline: January 18, 2019 Notification: February 15, 2019 == Program Chairs == Contact: iswc2019-challenge at inria.fr Gianluca Demartini, The University of Queensland, Brisbane, Australia Valentina Presutti, STLab-ISTC, National Research Council, Rome, Italy Axel Ngonga, Paderborn University, Paderborn, Germany See you all in Auckland! The ISWC 2019 Organising Team ( https://iswc2019.semanticweb.org/organizing-committee/ ) -------------- next part -------------- An HTML attachment was scrubbed... URL: From albagarciaseco at gmail.com Mon Dec 17 07:15:08 2018 From: albagarciaseco at gmail.com (=?UTF-8?B?QWxiYSBHYXJjw61h?=) Date: Mon, 17 Dec 2018 12:15:08 +0000 Subject: Connectionists: Call For Participation: 3rd Edition of ImageCLEF Caption Challenge (@ CLEF 2019) Message-ID: *The 3rdEdition of the ImageCLEF Caption Challenge 2019* https://www.imageclef.org/2019/medical/caption *Motivation* Interpreting and summarizing the insights gained from medical images such as radiology output is a time consuming task that involves highly trained experts and often represents a bottleneck in clinical diagnosis pipelines. Consequently, there is a considerable need for automatic methods that can approximate this mapping from visual information to condensed textual descriptions. The more image characteristics are known, the more structured are the radiology scans and hence, the more efficient are the radiologists regarding interpretation. *Data* We work on the basis of a large-scale collection of figures from open access biomedical journal articles (PubMed Central). All images in the training data are accompanied by UMLS concepts extracted from the original image caption. *Challenge description* The first step to automatic image captioning and scene understanding is identifying the presence and location of relevant concepts in a large corpus of medical images. Based on the visual image content, this subtask provides the building blocks for the scene understanding step by identifying the individual components from which captions are composed. The concepts can be further applied for context-based image and information retrieval purposes. *Preliminary Schedule* - *19.11.2018*: Registration opens for all ImageCLEF tasks (until *26.04.2019*) - *15.01.2019*: training release starts - *18.03.2019*: Test data release starts - *01.05.2019*: Deadline for submitting the participants runs - *13.05.2019*: Release of the processed results by the task organizers - *24.05.2019*: Deadline for submission of working notes papers by the participants - *07.06.2019*: Notification of acceptance of the working notes papers - *28.06.2019*: Camera-ready working notes papers - *09-12.09.2019*: CLEF 2019 , Lugano, Switzerland *Participant Registration* Please refer to the general ImageCLEF registration instructions *Organizing Committee* - Obioma Pelka , University of Applied Sciences and Arts Dortmund, Germany - Christoph M. Friedrich , University of Applied Sciences and Arts Dortmund, Germany - Alba Garc?a Seco de Herrera ,University of Essex, UK - Henning M?ller , University of Applied Sciences Western Switzerland, Sierre, Switzerland For more details and updates, please visit the task website at: https://www.imageclef.org/2019/medical/caption and join our mailing list: https://groups.google.com/d/forum/imageclefcaption Dr Alba Garc?a Seco de Herrera PhD Lecturer Department of Computer Science and Electronic Engineering (CSEE) University of Essex T +44 (0) 1206 872907 E alba.garcia at essex.ac.uk ? https://www.essex.ac.uk/ WE ARE ESSEX -------------- next part -------------- An HTML attachment was scrubbed... URL: From nnavarin at math.unipd.it Mon Dec 17 08:58:13 2018 From: nnavarin at math.unipd.it (=?utf-8?Q?Nicol=C3=B2_Navarin?=) Date: Mon, 17 Dec 2018 14:58:13 +0100 Subject: Connectionists: CFP [Deadline extended] Special Session on Learning Representations for Structured Data (LR4SD) @ IJCNN 2019 Message-ID: <42875695-5720-4E58-BE78-557E5D8B5384@math.unipd.it> ** Apologies for cross-posting** CFP [Deadline extended]: Special Session on "Learning Representations for Structured Data" 2019 International Joint Conference on Neural Networks (IJCNN) July 14-19 2019, Budapest, Hungary https://sites.google.com/view/lr4sd-ijcnn19 Important Dates: Paper submission: EXTENDED to 15 January 2019 Notification of acceptance: 28 February 2019 Aims and Scope: Structured data, e.g. sequences, trees and graphs, are a natural representation for compound information made of atomic information pieces (i.e. the nodes and their labels) and their intertwined relationships, represented by the edges (and their labels). Sequences are simple structures representing linear dependencies such as in genomics and proteomics, or with time series data. Trees, on the other hand, allow to model hierarchical contexts and relationships, such as with natural language sentences, crystallographic structures, images. Graphs are the most general and complex form of structured data allowing to represent networks of interacting elements, e.g. in social graphs or metabolomics, as well as data where topological variations influence the feature of interest, e.g. molecular compounds. Being able to process data in these rich structured forms provides a fundamental advantage when it comes to identifying data patterns suitable for predictive and/or explorative analyses. This has motivated a recent increasing interest of the machine learning community into the development of learning models for structured information. On the other hand, recent improvements in the predictive performances shown by machine learning methods is due to their ability, in contrast to traditional approaches, to learn a ?good? representation for the task under consideration. Deep Learning techniques are nowadays widespread, since they allow to perform such representation learning in an end-to-end fashion. Nonetheless, representations learning is becoming of great importance in other areas, such in kernel-based and probabilistic models. It has also been shown that, when the data available for the task at hand is limited, it is still beneficial to resort to representations learned in an unsupervised fashion, or on different, but related, tasks. This session focuses on learning representation for structured data such as sequences, trees, graphs, and relational data. Topics that are of interest to this session include, but are not limited to: - Probabilistic models for structured data - Structured output generation (probabilistic models, variational autoencoders, adversarial training, ?) - Deep learning and representation learning for structures - Learning with network data - Recurrent, recursive and contextual models - Reservoir computing and randomized neural networks for structures - Kernels for structured data - Relational deep learning - Learning implicit representations - Applications of adaptive structured data processing: e.g. Natural Language Processing, machine vision (e.g. point clouds as graphs), materials science, chemoinformatics, computational biology, social networks. Submission: - For paper guidelines please visit https://www.ijcnn.org/paper-submission-guidelines - For submissions please select the single topic "S11. Learning Representations for Structured Data" from the "S. SPECIAL SESSIONS" category as the main research topic on https://ieee-cis.org/conferences/ijcnn2019/upload.php Organisers: - Davide Bacciu, University of Pisa - Thomas G?rtner, University of Nottingham - Nicol? Navarin, University of Padova - Alessandro Sperduti, University of Padova For any enquire, please write to: bacciu [at] di.unipi.it or nnavarin [at] math.unipd.it ? Nicol? Navarin, PhD Assistant Professor University of Padova - Department of Mathematics via Trieste 63, 35121 Padova - Italy -------------- next part -------------- An HTML attachment was scrubbed... URL: From james4424 at gmail.com Mon Dec 17 23:20:01 2018 From: james4424 at gmail.com (Yansong Chua) Date: Tue, 18 Dec 2018 12:20:01 +0800 Subject: Connectionists: Fwd: Research positions in Neuromorphic computing in Singapore In-Reply-To: References: Message-ID: Multiple scientist and engineer positions are open for a neuromorphic program (on-going till 2021) in Singapore, at the Institute for Infocomm Research (I2R), A*STAR. The program is a multi-disciplinary effort, that straddles across the hardware (neuromorphic chip with RRAM, on-chip learning), middleware (emulator) and software (learning algorithms), and we aim to develop a demonstrating application system at end of the program. The program hence presents an unique research opportunity for candidates hoping to build a complete neuromorphic learning system. We are now in the second year of the program and have made good progress on all three aspects of the program. We have still a few openings for talented scientists and both software and hardware engineers who would be excited to work on any aspects of the program (hardware, middleware, software and system integration). Multiple top-ranked universities and research institutes in Singapore (NUS, NTU, IME, IHPC, I2R) are collaborating on the program. The work package I am in-charge of is primarily involved in the design of better algorithms for spiking neural networks. To this end, successful candidates will conduct research in one or more of the following areas: - Neuronal encoding: how to better encode external stimuli into spike based representations to facilitate decoding with high fidelity and also better learning performance (in terms of accuracy and power efficiency). - Supervised learning: given that spiking neural networks are asynchronous and sparse in their activities, the design of supervised learning algorithms that can fully capitalize on these properties becomes critical. - Mapping of state-of-art deep learning networks to spiking networks. Neuromorphic learning algorithms are still solving fairly simple problems compared to deep learning. For this, we would like to systematically borrow from the deep learning community networks and learning algorithms that can quickly boost the capabilities of spiking neural networks. - Unsupervised learning. STDP is well suited for unsupervised learning in spiking neural networks, and we would like to further advance STDP learning in spiking neural networks (both theory and applications). Preference will be given to candidates who can document knowledge in deep learning, spiking neural networks or signal processing (with interest in spiking neural networks). Candidates must have a PhD (for scientists) or MS/BS (for engineers) in computer science, computational neuroscience or related fields. Strong programming and quantitative skills are highly desired. Candidates should be proficient in spoken and written English. The appointment will be for 3 years, and extended for another 1 year, after review. Salaries are commensurate with internationally-competitive salaries and benefits. The start date is flexible and applications will be considered on a rolling basis until the positions are filled. Other benefits include: - Funding for international conferences and training courses - Collaboration opportunities with an excellent network of international scientists Candidates please send your curriculum vitae, a statement of research interests and three references to Dr. Yansong Chua (chuays at i2r.a-star.edu.sg ). -------------- next part -------------- An HTML attachment was scrubbed... URL: From james4424 at gmail.com Mon Dec 17 23:39:16 2018 From: james4424 at gmail.com (Yansong Chua) Date: Tue, 18 Dec 2018 12:39:16 +0800 Subject: Connectionists: =?utf-8?q?Joint_A*STAR_=28Singapore=29_and_King?= =?utf-8?q?=E2=80=99s_College_London_PhD_Studentship?= Message-ID: We would like to encourage potential PhD candidates interested to work on understanding the role of stochastic neuron models in neuromorphic computing to apply for the above PhD studentship. We are including below a non-technical introduction to the project involved. The candidate will be jointly supervised by Prof. Osvaldo Simeone, Professor of Information Engineering, King's College London and Dr. Yansong Chua, Institute for Infocomm Research, A*STAR. For further queries, we maybe reached at: Prof Simeone: osvaldo.simeone at kcl.ac.uk Dr Chua: chuays at i2r.a-star.edu.sg More application details are also available at https://www.kcl.ac.uk/research/funding-opportunities/doctoral-research-opportunities/homeeu-funding.aspx https://www.kcl.ac.uk/research/funding-opportunities/doctoral-research-opportunities/current-phd-opportunities/astar-phd-studentships.aspx For all its recent breakthroughs, modern machine learning based on deep neural networks is becoming increasingly unaffordable in terms of computing and energy resources needed to run training algorithms that achieve state-of-the-art performance. This poses possibly insurmountable challenges for the implementation of efficient learning methods on resource-limited devices such as smart sensors or wearables. A possible solution to this problem is the adoption of the new paradigm of neuromorphic computing, which relies on energy-efficient sparse spike-domain processing and communication that are inspired by the operation of the brain. Whether Spiking Neural Networks (SNNs) can overcome the limitations of conventional deep networks for the implementation of low-power machine learning is a fundamental question that is currently being investigated by major technology companies and universities. In this project, this issue will be tackled both theoretically and through hands-on experiments by leveraging the complementary expertise of the respective research teams at KCL and A*STAR. Specifically, this research will seek to understand whether conventional deterministic models for SNNs can be improved by probabilistic models, which are typically used in neuroscience to model the brain operation, in terms of accuracy, speed, and robustness. In the first two years, at KCL, the project will concentrate on deriving models and learning rules for probabilistic SNNs. In the last two years, at A*STAR, the research will shift to aspects related to implementation, with a focus on the comparison between deterministic and probabilistic SNNs and on the use of nano-scale devices for the implementation of probabilistic SNNs. -------------- next part -------------- An HTML attachment was scrubbed... URL: From nnavarin at math.unipd.it Mon Dec 17 08:57:44 2018 From: nnavarin at math.unipd.it (=?utf-8?Q?Nicol=C3=B2_Navarin?=) Date: Mon, 17 Dec 2018 14:57:44 +0100 Subject: Connectionists: CFP [Deadline extended] Special Session on Deep learning for brain data (DL4BRAIN) @ IJCNN 2019 Message-ID: ** Apologies for cross-posting** CFP [Deadline extended]: Special Session on "Deep learning for brain data" 2019 International Joint Conference on Neural Networks (IJCNN) July 14-19 2019, Budapest, Hungary https://sites.google.com/view/dl4brain Important Dates: Paper submission: EXTENDED to 15 January 2019 Notification of acceptance: 28 February 2019 Aims and Scope: Structural and Functional techniques to investigate brain, such as MRI, CT scan, fMRI, EEG, PET, are nowadays widely used both for basic research (for instance on cognition) or for clinical purposes (for instance diagnosis of brain based disorders). In the past two decades, scientists have tried to use these techniques to study brain functioning, to investigate human cognition, to assist the diagnosis of brain-based disorders, and to try to predict the prognosis of patients. Unfortunately, the attempts to find a technique that achieve results with the potential to be translated to daily practice have not succeeded due to the presence of complex, distributed and subtle individual differences that are difficult to detect using standard statistical techniques. Very recently, this research field witnessed an exponential increased interest in the application of Machine Learning (ML) methods, and in particular of Deep Learning (DL), to brain data to support researchers in the study of cognition and to support clinicians in the diagnosis and prognosis of brain-based disorders. To date, applications of ML/DL techniques to brain data is still an under-investigated field of research. The aim of this special session is twofold: first, it provides a point of contact between scientists and researchers from the machine learning and medical communities (medicine, neuroscience, psychology, psychophysiology, etc.), encouraging a multidisciplinary view on open problems. Second, it provides a forum to present original ideas, theories and novel applications of ML/DL to brain data, and to find solutions to open issues. Topics that are of interest to this session include, but are not limited to: - Presentation of new structural and functional brain data databases; - Computer vision applied to MRI, fMRI, DTI, PET; - Time series analysis applied to EEG; - New advancement in Deep Learning algorithms for brain data; - Application of Deep Learning to brain data to study cognition (e.g., attention, language, memory, decision making, problem solving, spatial abilities); - Application of Deep Learning to brain data for clinical diagnosis and prognosis of psychiatric and neurologic disorders; - Application of Deep Learning to brain data for identification of risk factors of neurologic and psychiatric disorders; - Application of Deep Learning to evaluate the impact of inter-scanner variability on the results; - Multicentric studies on brain MRI data; - Integrating functional and structural information to enhance clinical diagnosis and prognosis; - Integrating functional and structural information to enhance the understanding of cognitive processes; Submission: - For paper guidelines please visit https://www.ijcnn.org/paper-submission-guidelines - For submissions please select the single topic "S10. Deep learning for brain data" from the "S. SPECIAL SESSIONS" category as the main research topic on https://ieee-cis.org/conferences/ijcnn2019/upload.php Organisers: - Nicol? Navarin, University of Padova, Italy - Cristina Scarpazza, University of Padova, Italy - Merylin Monaro, University of Padova, Italy For any enquire, please write to: nnavarin [at] math.unipd.it , cristina.scarpazza [at] unipd.it or merylin.monaro [at] unipd.it ? Nicol? Navarin, PhD Assistant Professor University of Padova - Department of Mathematics via Trieste 63, 35121 Padova - Italy -------------- next part -------------- An HTML attachment was scrubbed... URL: From tony.pipe at brl.ac.uk Tue Dec 18 06:59:14 2018 From: tony.pipe at brl.ac.uk (Tony Pipe) Date: Tue, 18 Dec 2018 11:59:14 +0000 Subject: Connectionists: Research Support Engineer: FARSCOPE CDT In-Reply-To: References: <35ccac3d-bd2e-d705-ff42-b6e9267e685d@brl.ac.uk> <9d584535-6135-7703-106f-0eb85bd11695@brl.ac.uk> <8425dbb3-796a-e96e-155f-659462cf14b3@brl.ac.uk> <9012577d-d913-0b40-63b5-259851d593d2@brl.ac.uk> <0d4bedb8-ed61-f8e2-a5b8-22e668e2f9d7@brl.ac.uk> <9ef4410e-6f17-c652-0bc8-353d431192c3@brl.ac.uk> Message-ID: <750d82a3-8b2a-fbab-1df2-c85fedd5f14d@brl.ac.uk> Research Support Engineer: FARSCOPE CDT Full Description of post at: https://atsv7.wcn.co.uk/search_engine/jobs.cgi?SID=amNvZGU9MTc4MzEzNiZ2dF90ZW1wbGF0ZT0xNTM4Jm93bmVyPTUwNTUyNzgmb3duZXJ0eXBlPWZhaXImYnJhbmRfaWQ9MCZwb3N0aW5nX2NvZGU9NDk3 Duration of post: Fixed term until 31st July 2021 Closing Date: 16th Jan 2019 Salary: ?33,199 - ?39,609 (Currency: GBP) The Bristol Robotics Laboratory is the largest co-located establishment engaged in advanced Robotics and Autonomous Systems research and innovation. It is an exciting mix of fundamental and applied research in almost all topics relating to modern robotics, and especially those domains where robots work with us and amongst us to improve our lives. The FARSCOPE Centre for Doctoral Training is designed explicitly to deliver research outcomes in this domain and is already highly successful in doing so. Due to the existing incumbent of this post moving on to new challenges, we now wish to fill this exciting and fulfilling position with a highly motivated and well-organised individual. In brief, the role is to provide technical support in Mechanical, Electronics/Electrical and Software disciplines for Research and Development being undertaken by the FARSCOPE CDT PhD students; to support the coordination and planning of work by the technical team supporting the FARSCOPE Programme in order to complete highly advanced R&D work; to provide technical advice and training to junior members of the technical team and to FARSCOPE students; to propose Robotic and Automated System solutions for FARSCOPE R&D projects. The successful applicant will possess a degree in an Engineering or Computer Science related Subject, evidence of CPD and, ideally, a Research Degree in an Engineering or Computer Science related subject. This post is not available on a job share basis. Interviews are planned for Monday 4th February 2019. In addition to progressive pay rates, UWE Bristol offers a wide range of staff benefits including: ? a generous holiday allowance of 27 Days ? up to 12.5 bank holiday/closure days per year in addition; ? flexible working; ? excellent defined benefit pension schemes; ? option to participate in the cycle to work scheme; ? family friendly policies; ? on-site nursery at our Frenchay Campus; This post is based at our lively Frenchay campus where we have invested in the latest facilities and resources to give our students access to everything they need to succeed ? with ?300m having been spent recently on new state-of-the-art learning spaces and accommodation to enhance our offer even further. Frenchay campus is within close proximity to excellent motorway links and within walking distance of two train stations, making UWE Frenchay Campus the ideal place to work for those wishing to commute to Bristol. Please see the full job description and information for applicants for the role at: https://atsv7.wcn.co.uk/search_engine/jobs.cgi?SID=amNvZGU9MTc4MzEzNiZ2dF90ZW1wbGF0ZT0xNTM4Jm93bmVyPTUwNTUyNzgmb3duZXJ0eXBlPWZhaXImYnJhbmRfaWQ9MCZwb3N0aW5nX2NvZGU9NDk3 If you have any queries or would like an informal discussion, please contact Tony Pipe by email: Anthony.Pipe at uwe.ac.uk. UWE is committed to supporting and promoting equality and diversity to create an inclusive working environment. We believe this can be achieved through attracting, developing, and retaining a diverse range of staff from many different backgrounds who share our ambition to be a university recognised for the success and impact of our practice-oriented programmes; our strong industry networks and our inclusive global outlook. From tony.pipe at brl.ac.uk Tue Dec 18 06:57:45 2018 From: tony.pipe at brl.ac.uk (Tony Pipe) Date: Tue, 18 Dec 2018 11:57:45 +0000 Subject: Connectionists: Research Associate - Robotics for Nuclear Environments In-Reply-To: <9ef4410e-6f17-c652-0bc8-353d431192c3@brl.ac.uk> References: <35ccac3d-bd2e-d705-ff42-b6e9267e685d@brl.ac.uk> <9d584535-6135-7703-106f-0eb85bd11695@brl.ac.uk> <8425dbb3-796a-e96e-155f-659462cf14b3@brl.ac.uk> <9012577d-d913-0b40-63b5-259851d593d2@brl.ac.uk> <0d4bedb8-ed61-f8e2-a5b8-22e668e2f9d7@brl.ac.uk> <9ef4410e-6f17-c652-0bc8-353d431192c3@brl.ac.uk> Message-ID: <9deebb3a-cba3-405f-4b73-a801cb022a51@brl.ac.uk> Research Associate - Robotics for Nuclear Environments Salary band: ?29,515 - ?33,199 (Currency GBP) Dear colleagues, Link to full job description and information how to apply: https://bit.ly/2KfrjTG The Universities of Manchester, West of England and Birmingham, in collaboration with the National Nuclear Laboratory (NNL) and supported by Sellafield Ltd. are collaborating together on the 5-year Robotics for Nuclear Environments project (https://nuclearrobots.org/) to undertake fundamental research in Robotics and Autonomous Systems (RAS) which will enable step changes to be made in the capabilities of industrial robotic solutions for use in the nuclear industry. This specific post will focus on research and development of planning and control approaches for heterogeneous teams of multiple robots and/or humans, and the development of embedded online risk assessment strategies for such robots. The research divides into three work packages. Ideally, you have some experience in all three of the work package topics. However, we also strongly encourage candidates who have experience in only one of the research areas and are willing to broaden their research into the other areas to submit an application. The three work packages are as follows: ??? Heterogeneous team working. This work package (WP) will analyse existing approaches to heterogeneous robot team working, in order to develop an approach providing the best balance between autonomy and remote human supervision. ??? Human-robot team interaction. This WP will analyse the requirements of sensorimotor interfaces and embedded AI (cognition) for team working both between robots and also with human co-workers, including differing levels of human supervision. ??? On line behaviour risk assessment. This WP will aim to design, implement and test a novel system for robots to be able to assess, at run-time, the risks associated with their own actions and the robots (and humans) around them in the context on their current mission tasks. As part of this project, you will be based at the Bristol Robotics Laboratory (BRL) and work closely with other researchers at BRL, and the Universities of Manchester and Birmingham. You will be required to travel regularly to Manchester, Birmingham, and Cumbria for project meetings, and also to liaise with collaborators from industry. You will also be expected to travel overseas from time to time to attend conferences and to meet with collaborating organisations. This project will provide the successful candidate with the ideal introduction into the challenges faced in deploying robotic systems in the nuclear industry and the size and scope of problems therein. It will also provide a unique opportunity to interact with engineers from both the supply chain and end users in the UK and Japan. Due to the requirement for regular UK travel and occasional international travel - This post is not available on a job share basis. In addition to progressive pay rates, UWE Bristol offers a wide range of staff benefits including: ??? a generous holiday allowance of 27 Days ??? up to 12.5 bank holiday/closure days per year in addition; ??? flexible working; ??? excellent defined benefit pension schemes; ??? option to participate in the cycle to work scheme; ??? family friendly policies; ??? onsite nursery at our Frenchay Campus; This post is based at our lively Frenchay campus. Please follow this link to see the full job description and information for applicants for the role: https://bit.ly/2KfrjTG If you have any queries or would like an informal discussion, please write an email to Manuel Giuliani at manuel.giuliani at brl.ac.uk or Tony Pipe at Tony.Pipe at brl.ac.uk. UWE is committed to supporting and promoting equality and diversity to create an inclusive working environment. We believe this can be achieved through attracting, developing, and retaining a diverse range of staff from many different backgrounds who share our ambition to be a university recognised for the success and impact of our practice-oriented programmes; our strong industry networks and our inclusive global outlook. -- Tony Pipe Professor of Robotics and Autonomous Systems Deputy Director: Bristol Robotics Laboratory Bristol Robotics Laboratory T-Building Frenchay Campus Bristol UK BS16 1QY Tel: +44 (0)117 3286330 From tony.pipe at brl.ac.uk Tue Dec 18 07:00:39 2018 From: tony.pipe at brl.ac.uk (Tony Pipe) Date: Tue, 18 Dec 2018 12:00:39 +0000 Subject: Connectionists: Robotics Technician In-Reply-To: References: <35ccac3d-bd2e-d705-ff42-b6e9267e685d@brl.ac.uk> <9d584535-6135-7703-106f-0eb85bd11695@brl.ac.uk> <8425dbb3-796a-e96e-155f-659462cf14b3@brl.ac.uk> <9012577d-d913-0b40-63b5-259851d593d2@brl.ac.uk> <0d4bedb8-ed61-f8e2-a5b8-22e668e2f9d7@brl.ac.uk> <9ef4410e-6f17-c652-0bc8-353d431192c3@brl.ac.uk> Message-ID: <561f1621-a5bc-c380-18f2-f92dc7d97019@brl.ac.uk> Robotics Technician Full Description of post at: https://atsv7.wcn.co.uk/search_engine/jobs.cgi?SID=amNvZGU9MTc3NTU5NiZ2dF90ZW1wbGF0ZT0xNTM4Jm93bmVyPTUwNTUyNzgmb3duZXJ0eXBlPWZhaXImYnJhbmRfaWQ9MCZwb3N0aW5nX2NvZGU9NDk3 Duration of post: Permanent Closing Date: 13th Jan 2019 Salary: ?29,515 - ?33,199 (Currency: GBP) The Bristol Robotics lab seeks an experienced and enthusiastic Robotics Technician to support teaching on their rapidly growing undergraduate and postgraduate courses. The job role involves supporting taught sessions in core robotic disciplines, such as electronics, mechatronics and engineering control systems. The successful candidate will have experience in a technical role, with a background in designing/building robotic or mechatronic systems. The MSc Robotics at BRL is an exciting mix of the latest technology developments in this burgeoning and strongly inter-disciplinary area of engineering. In fact, the remit of the students? study crosses even beyond engineering into all of the life sciences (e.g. Psychology, Sociology, Biology). The programme has grown quickly to a size where dedicated engineering support is required, and hence the requirement for this role. As well as providing the engineering support for the teaching programme, a large part of your role will be to liaise with the student dissertation project supervisory teams and work with the students in assisting them on the software and hardware aspects of designing, building and testing robot artefacts for R&D Projects. In addition to these activities, there are many other ground-breaking research-oriented areas taking place in this, the largest co-located robotics laboratory in the UK, that require additional engineering support from time to time. The successful applicant will, therefore, need to have a flexible attitude towards occasionally providing engineering support for BRL-based activities, beyond the MSc programme?s support, in the software and hardware aspects of designing, building and testing advanced robot artefacts, as well as assisting in maintaining the good working status of the laboratory itself. In all of these roles, you will be working amongst and alongside a friendly and well-motivated team of co-workers who, together, support the wide-ranging requirements of this steadily expanding laboratory that conducts advanced work in all of the upcoming areas of robotics. This post is not available on a job share basis. Other benefits, in addition to salary: ? a generous holiday allowance of 27 days ? up to 12.5 bank holiday/closure days per year in addition; ? flexible working; ? excellent defined benefit pension schemes; ? option to participate in the cycle to work scheme; ? family friendly policies; ? onsite nursery at our Frenchay Campus; ? option to purchase childcare vouchers. This post is based at our lively Frenchay campus where we have invested in the latest facilities and resources to give our students access to everything they need to succeed ? with ?200m being spent on new state-of-the-art learning spaces and accommodation between now and 2020 to enhance our offer even further. If you would like an informal discussion, please contact Ian Horsfield on 0117 3286337 or email Ian2.Horsfield at uwe.ac.uk. Please see the full job description and information for applicants for the role at: https://atsv7.wcn.co.uk/search_engine/jobs.cgi?SID=amNvZGU9MTc3NTU5NiZ2dF90ZW1wbGF0ZT0xNTM4Jm93bmVyPTUwNTUyNzgmb3duZXJ0eXBlPWZhaXImYnJhbmRfaWQ9MCZwb3N0aW5nX2NvZGU9NDk3 UWE is committed to supporting and promoting equality and diversity to create an inclusive working environment. We believe this can be achieved through attracting, developing, and retaining a diverse range of staff from many different backgrounds who share our ambition to be a university recognised for the success and impact of our practice-oriented programmes; our strong industry networks and our inclusive global outlook. -- Tony Pipe Professor of Robotics and Autonomous Systems Deputy Director: Bristol Robotics Laboratory Bristol Robotics Laboratory T-Building Frenchay Campus Bristol UK BS16 1QY Tel: +44 (0)117 3286330 From sepand.haghighi at yahoo.com Tue Dec 18 09:29:29 2018 From: sepand.haghighi at yahoo.com (Sepand Haghighi) Date: Tue, 18 Dec 2018 14:29:29 +0000 (UTC) Subject: Connectionists: PyCM 1.7 released: Machine learning library for confusion matrix statistical analysis References: <1236547591.1464212.1545143369706.ref@mail.yahoo.com> Message-ID: <1236547591.1464212.1545143369706@mail.yahoo.com> Version 1.7 Changelog : - Gini Index (GI) added - Example-7 added - pycm_profile.py?added - class_name?argument added to?stat,save_stat,save_csv?and?save_html?methods - overall_param?and?class_param?arguments empty list bug fixed - matrix_params_calc,?matrix_params_from_table?and?vector_filter?functions optimized (10x faster) - overall_MCC_calc,?CEN_misclassification_calc?and?convex_combination?functions optimized (5x faster) - Document modified Github Repo :?https://github.com/sepandhaghighi/pycm Webpage?:?http://pycm.shaghighi.ir/ Document :??http://www.shaghighi.ir/pycm/doc/index.html -------------- next part -------------- An HTML attachment was scrubbed... URL: From djkrusienski at vcu.edu Tue Dec 18 10:41:26 2018 From: djkrusienski at vcu.edu (Dean Krusienski) Date: Tue, 18 Dec 2018 10:41:26 -0500 Subject: Connectionists: Graduate Research Assistantships in Neural Signal Processing Message-ID: <005601d496e8$2373fcd0$6a5bf670$@vcu.edu> Graduate Research Assistantships in Neural Signal Processing Virginia Commonwealth University, Richmond, VA The Advanced Signal Processing in Engineering and Neuroscience (ASPEN) Laboratory at Virginia Commonwealth University (VCU) is seeking qualified and ambitious graduate research assistants for funded projects on neural speech decoding and neurofeedback in virtual reality. Preference will be given to Ph.D. students with prior experience in signal processing and machine learning for neural and speech signals. Proficiency in MATLAB is expected. The research assistantships offer a competitive stipend and tuition waiver. The ASPEN Lab collaborates with the VCU Epilepsy Center, University of San Diego Epilepsy Center, and the Cognitive Systems Lab at the University of Bremen, Germany to conduct original neuroscientific studies using intracranial brain signals. The lab also maintains active collaborations with several prominent neurotechnology labs around the world. For more information on the ASPEN Lab visit: sites.google.com/vcu.edu/aspenlab/ VCU is a state-assisted, Carnegie doctoral/research institution enrolling more than 31,000 students. It has an urban campus located in Richmond, VA, with vibrant art, food, historical, and entertainment scenes. Applicants should email a cover letter, resume, academic transcripts, GRE scores, and contact information for 3 references to: Dean Krusienski, Ph.D. Professor, Biomedical Engineering Director, ASPEN Laboratory Virginia Commonwealth University djkrusienski at vcu.edu Review of applications will begin immediately and continue until the positions are filled. ________________________________ Dean J. Krusienski, Ph.D. Professor, Biomedical Engineering Virginia Commonwealth University Richmond, VA 23220 Office: 425 Biotech 8 | Lab: 470A Biotech 8 Phone: 804.827.1890 Web: sites.google.com/vcu.edu/aspenlab/ -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Graduate Assistantships - ASPEN Lab.pdf Type: application/pdf Size: 1353221 bytes Desc: not available URL: From Sharon.Crook at asu.edu Tue Dec 18 11:53:28 2018 From: Sharon.Crook at asu.edu (Sharon Crook) Date: Tue, 18 Dec 2018 16:53:28 +0000 Subject: Connectionists: CNS*2019 Barcelona: Call for Workshop Proposals and Tutorials In-Reply-To: <589101c0-b3c3-432d-92d5-e0c806b19ab9.10034382534.4128.1545070475905@memberclicks-mail.net> References: <589101c0-b3c3-432d-92d5-e0c806b19ab9.10034382534.4128.1545070475905@memberclicks-mail.net> Message-ID: Organization for Computational Neurosciences 2885 Sanford Ave SW #15359 Grandville, MI 49418 USA We request proposals for workshops and tutorials from the international community of computational neuroscientists. Proposals from all levels of faculty as well as advanced postdoctoral fellows are welcome. This is a great opportunity to organize a small meeting or introduce novel methodology through a tutorial with only a few of the headaches of organizing it. We look forward to your submissions. CALL FOR WORKSHOPS (see below and also https://www.cnsorg.org/cns-2019-call-for-workshops) Martin Zopotocky, Workshop Organizer, CNS*2019 CALL FOR TUTORIALS (see below and also https://www.cnsorg.org/cns-2019-call-for-tutorials) Hermann Cuntz, Tutorial Organizer, CNS*2019 1. WORKSHOP PROPOSAL SUBMISSION INSTRUCTIONS FOR CNS*2019, BARCELONA Workshops, in which computationally related neuroscience topics can be presented, will take place during the last two days (July 16 and July 17 2019) of the 28th Annual Computational Neuroscience Meeting (https://www.cnsorg.org/cns-2019). For each workshop, usually several speakers are invited to introduce a unifying theme, but ample time for discussion should also be planned. Please note that there is a change in the format of the meeting compared to previous years. The main meeting will conclude on July 16, with a keynote lecture and a poster session taking place in the afternoon. The morning of July 16 is reserved for workshops. A goal of this "mixed day" of the meeting is to facilitate an overlap of attendance. Participants who have registered for either the main meeting or the workshops will be allowed to attend all of the events on July 16 (workshops, keynote, poster session). The last day of the meeting, July 17, is reserved for workshops, as in the previous years (workshop registration will be required to attend). Accordingly, the possible duration of a workshop is anywhere from 0.5 days (one session lasting 3.5 hours) to 1.5 days (three half-day sessions). Half-day workshops will be preferentially scheduled for July 16. They will thus offer the opportunity to attract a wider audience still present for the main meeting. Submit workshop proposals to: workshops at cnsorg.org. The Past Meetings page (https://www.cnsorg.org/past-annual-meetings) gives access to archives of workshops held at previous CNS meetings. The proposal should be submitted as a Word or pdf file and MUST include the following sections: * WORKSHOP TITLE * ORGANIZERS (list primary organizer first; include affiliations and emails) * WORKSHOP DURATION * NUMBER OF EXPECTED SPEAKERS * BRIEF DESCRIPTION (~150 words; if possible, say why this is significant or timely) * SPEAKERS (mark expected or confirmed) Also please note the following rules which were approved by the OCNS Board on July 15, 2013: * Each individual can be the organizer or co-organizer on only one workshop. * The number of confirmed speakers is a criterion for accepting the proposal. * Overlapping proposals may be asked to be combined. If the organizers do not wish to combine the proposals, only one of the proposals may be accepted. DEADLINE: Workshops submitted before January 31, 2019 will be given priority in acceptance. Workshop proposals arriving after January 31, 2019 will be evaluated based on remaining space for additional workshops. No further workshop acceptances will be anticipated after May 15, 2019. 2. TUTORIAL PROPOSAL SUBMISSION INSTRUCTIONS FOR CNS*2019, BARCELONA Tutorials are intended as introductions into main methodologies of various fields in computational neuroscience. Tutorials are particularly tailored for early stage researchers as well as researchers entering a new field in computational neuroscience. The tutorials will be held on the first day of the meeting, July 13 2019, with a typical total attendance of approximately 100 attendees, allowing for four concurrent sessions during the day. Three different formats are available: * Introductory FULL DAY courses (incl. some reimbursement for the tutors) * Specialized HALF DAY tutorials (incl. some reimbursement for the tutors) * 30 MINUTES software showcase (no funding available) Submit tutorial proposals to: tutorials at cnsorg.org. Please compare with last year's tutorials at https://www.cnsorg.org/cns-2018-tutorials. Note that our new format, the showcases, will be combined into one continuous afternoon program. The proposal should be submitted as a Word or pdf file and MUST include the following sections: * TUTORIAL TITLE * ORGANIZERS (list primary organizer first; include affiliations and emails) * FORMAT (full day, half day, showcase) * BRIEF DESCRIPTION (max. 300 words; include links to relevant software) DEADLINE: Tutorial proposals should be submitted before January 31, 2019. Registration: Workshop registration will occur through the OCNS registration web site for CNS*2019. All workshop participants, including speakers must register. Each workshop is eligible to receive registration waivers for 2 speakers. Travel awards: A limited number of Travel Awards will be available for organizers or speakers. Priority will be given to postdocs and early career faculty. Travel Award amounts will be variable, depending on distance traveled. Please indicate which speakers you would like to be considered for this mechanism but take into account that there likely will be fewer Travel Awards than workshops. From A.K.Seth at sussex.ac.uk Tue Dec 18 11:55:40 2018 From: A.K.Seth at sussex.ac.uk (Anil Seth) Date: Tue, 18 Dec 2018 16:55:40 +0000 Subject: Connectionists: PhD studentships available at the University of Sussex Message-ID: Ph.D. Scholarships available at the University of Sussex: From sensation and perception to awareness. We are delighted to invite applications for the second round of the Leverhulme Doctoral Scholarship Programme in ?From Sensation and Perception to Awareness?, hosted across multiple Schools at the University of Sussex. Up to eight fully funded positions will be awarded (for UK/EU applicants), starting Sep 2019. The aim of the programme is to bring together doctoral researchers from different disciplines to advance our understanding of the interactions between sensing, perception, and awareness in humans, animals, and machines. Applicants can select from a range of projects or propose their own. Pre-specified projects are divided into three main themes: (i) Human-computer interaction and digital arts, (ii) human cognitive neuroscience and computational neuroscience, and (iii) sensory neuroscience. For more details and for how to apply please see https://www.findaphd.com/search/PhdDetails.aspx?CAID=3783 and https://www.sussex.ac.uk/sensation/applications. For more on the Programme please visit https://www.sussex.ac.uk/sensation/, and follow us on Twitter @SensationSussex. Email enquries to Leverhulme at sussex.ac.uk. Application deadline is 31 January 2019. The programme is co-directed by Anil Seth (Engineering and Informatics) and Jamie Ward (Psychology). ------------------------------------------- Anil K. Seth, D.Phil. University of Sussex, UK Professor of Cognitive and Computational Neuroscience Co-Director, Sackler Centre for Consciousness Science Editor-in-Chief, Neuroscience of Consciousness Senior Fellow, Canadian Institute for Advanced Research Engagement Fellow, Wellcome Trust www.anilseth.com, www.neurobanter.com @anilkseth -------------- next part -------------- An HTML attachment was scrubbed... URL: From alberto.nogales at ceiec.es Tue Dec 18 12:18:28 2018 From: alberto.nogales at ceiec.es (Alberto Nogales Moyano) Date: Tue, 18 Dec 2018 18:18:28 +0100 Subject: Connectionists: Lecturer and researcher AI, Deep Learning Message-ID: Universidad Francisco de Vitoria More info www.ceiec.es LECTURER/RESEARCHER Job description We are looking for a lecturer/researcher in Deep Learning. He will integrate into a team currently composed of researches and professors of the Polytechnic School. His research activity will include the achievement of research objectives, publication of results in journals with impact (it is expected to obtain sexennials on a regular basis) and the achievement and participation in competitive R & D + i both national and European. He is expected to participate in the transfer of results through competitive projects of university-company collaboration at national or European level. He will teach in degree or master courses in the area of Artificial Intelligence/Machine Learning and Data Mining. He may also teach other courses not directly related to these topics. We offer a fulltime, indefinite contract subject to the fulfillment of multi-annual objectives agreed between the management of the Center, the dean of the Polytechnic School and the Researcher and a trial period of 1 year. He will also supervise CEIEC interns and mentor them during their final bachelor?s project. Desired skills and experience PhD (in Computer Science but also Engineering, Physics or Maths) with experience in Cognitive Computing research or nearby areas within the AI and with accredited knowledge (thesis and / or publications with JCR> 3) in several of the following areas: - Artificial intelligence: - Machine learning - Deep Learning & Neural Networks - NLP / treatment of real texts - Image / video / text processing - Mass data processing (as a tool applicable to AI systems) - Big Data / Data Mining - Statistical analysis - Python language programming - Cognitive SW platforms / tools / environments (TensorFlow, Torch, Theano, CNTK, etc.) and other Scientific Python libraries(Scipy, Sklearn?) - Cognitive application lifecycle methodologies - Ability to communicate effectively internationally with excellent level of Spanish and English (essential). Send your CV to our contact email address. -------------- next part -------------- An HTML attachment was scrubbed... URL: From Donald.Adjeroh at mail.wvu.edu Tue Dec 18 20:08:38 2018 From: Donald.Adjeroh at mail.wvu.edu (Donald Adjeroh) Date: Wed, 19 Dec 2018 01:08:38 +0000 Subject: Connectionists: Call for Papers: SBP-BRiMS 2019 -- Social Computing, Behavior/Cultural Modeling, Prediction and Simulation Message-ID: Apologies if you receive multiple copies SBP-BRiMS 2019 2019 International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation July 9-12, 2019, Lehman Auditorium, George Washington University, Washington DC, US http://sbp-brims.org/ #sbpbrims CALL FOR PAPERS: SBP-BRiMS is an interdisciplinary computational social science conference focused on both modeling complex socio-technical systems and using computational techniques to reason about and study complex socio-technical systems. The participants in this conference take part in forming the conversation on how computation is shaping the modern world and helping us to better understand and reason about human behavior. Both papers addressing basic research and those addressing applied research are accepted. All methodological approaches are encouraged; however, the vast majority of papers use computer simulation, network analysis or machine learning as the method of choice in addressing human social and behavioral activities. At the conference, these paper presentations are complemented by data science challenge problems, demonstrations of new technologies, and a government funding panel. Submissions are solicited on research issues, methodologies, theories, and applications. Topics of interests include but are not limited to the following: Advances in Sociocultural & Behavioral Process Modeling * Group formation, interaction, and/or evolution * Collective action and governance * Information, belief, technology of disease diffusion * Public opinion representation, identification and modeling * Information diffusion * Psycho-cultural situation awareness * Intelligent agents and avatars/adversarial modeling * Models of reasoning and decision making * Performance prediction, assessment, & skill monitoring/tracking * Intelligent tutoring systems * Cognitive robotics and human-robot interaction * Human behavior issues in model federations * Validation and analysis techniques for social behavioral models Information, Systems, & Network Science * Data mining on social media platforms * Diffusion and other dynamic processes over networks * Inference of network topologies and changes over time or space * Analysis of link formations and link types * Detection of communities and other types of structures in networks * Analysis of high-dimensional networks * Analytics for social and human dynamics Military & Intelligence Applications * Group formation and evolution in the political context * Networks and political influence * Group representation and profiling * Reasoning about terrorist group behaviors and policies towards them * Cyber and attribution * Social Cyber-Security applications * Social simulation for military training * Cyber diplomacy * Computational methods to transform traditional GEOINT and open source data into spatio-temporal information describing events and activities Applications for Health and Well-being * Data science applied to health behavior * Modeling of public health and health care policy and decision making * Modeling of behavioral aspects of infectious disease spread * Modeling of behavioral aspects of prevention and treatment for chronic diseases (e.g., cancer, obesity, asthma) * Intervention design and modeling for behavioral health Example Other Applications of Interest to the Community * Economic applications of behavioral and social prediction * Model federation, integration, verification, or validation * Evolutionary computing and optimization * Education, training, professional development and workforce training in modeling and simulation CHALLENGE PROBLEMS: There will be two data science challenges, one on opioids and one on disinformation. Additional details are posted on the conference website, SBP-BRiMS.org/challenge. The deadline for submissions this year will be 17-May-2019. IMPORTANT DATES: Regular Paper Submission: 22-February-2019 Author Notification: 22-March-2019 Final Version Submission for Regular Papers: 12-April-2019 Challenge Problem Paper Submission: 17-May-2019 All accepted papers require confirmation of conference registration when uploading final versions. Each accepted paper requires a separate registration. All regular papers will be a maximum of 10 pages including all figures, tables and references. See http://sbp-brims.org/cfp for more information on formatting AWARDS: All papers are qualified for the Best Paper Award. Papers with student first authors will be considered for the Best Student Paper Award. Those receiving these awards will be invited to publish an extended version in a special issue of the journal Computational and Mathematical Organization Theory. Submission of a paper to the conference means that the authors consent to send an extended version to the special issue, should they receive one of the awards. Papers receiving the best paper awards, the best student paper award, winner of the opioid challenge, and winner of the disinformation challenge will then send an extended version of their paper for publication in the best of SBP-BRiMS 2019 special issue. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ieee.cibcb.2019 at gmail.com Wed Dec 19 07:58:59 2018 From: ieee.cibcb.2019 at gmail.com (IEEE CIBCB 2019) Date: Wed, 19 Dec 2018 13:58:59 +0100 Subject: Connectionists: IEEE CIBCB 2019 - Call for Papers Message-ID: Dear Sir or Madame, Please find attached the Call for Papers of the 16th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology (IEEE CIBCB 2019: https://cibcb2019.icas.xyz). Call for papers is also available at https://cibcb2019.icas.xyz/call-for-papers/ Best regards. Barbara Di Camillo and Giuseppe Nicosia IEEE CIBCB 2019 Program and General Chair Giacomo Baruzzo and Alessandro Zandon? IEEE CIBCB 2019 Publicity and Proceedings Chairs ----- IEEE CIBCB 2019 - Call for Papers IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology has become a major technical event in the field of Computational Intelligence and its application to problems in biology, bioinformatics, computational biology, chemical informatics, bioengineering and related fields. It provides a global forum for academic and industrial scientists to discuss and present their latest research findings from theory to applications. CIBCB 2019 (https://cibcb2019.icas.xyz/) will be held in Certosa di Pontignano (Siena), Tuscany (Italy) in July 9th-11th. Keynote speakers: - Pierre Baldi University of California, Irvine, USA (TBC) - Riccardo Bellazzi University of Pavia, Italy - Thomas Keane EMBL-EBI, Cambridge, UK Submission Guidelines Prospective authors are invited to submit papers of 2 to 4 pages (short papers) or of 5 to 8 pages (complete papers) including results, figures and references, or poster abstracts. At maximum, two additional pages are permitted with over-length page charge of US$100/page, to be paid during author registration. Papers must be in PDF and written in English. Detailed instructions and templates for preparing your manuscript can be found here: https://www.ieee.org/conferences/publishing/templates.html. The deadline for paper submission is by February 15, 2019. Each paper will be peer-reviewed. All papers must be original and not simultaneously submitted to another journal or conference. Accepted papers will be published in the conference proceedings and will be indexed in IEEE Xplore?. Submission implies the willingness of at least one of the authors to register (https://cibcb2019.icas.xyz/registration/) and present the paper at the conference. All papers should be submitted via the EasyChair online submission system. IEEE reserves the right to exclude a paper from distribution after the conference, including IEEE Xplore? Digital Library, if the paper is not presented by the author at the conference. Important Dates: - Paper submission deadline: February 15, 2019 - Final (revised) paper submission deadline: May 31, 2019 - Abstract submission deadline: May 31, 2019 Topics We particularly encourage submissions in emerging topics of high importance for Bioinformatics and Computational Biology. Topics of interest include, but are not limited to: CI in Bioinformatics: - Single cell and bulk transcriptomics - Machine learning and artificial intelligence in bioinformatics - Regulatory networks reconstruction/robustness/evolvability - MicroRNA analysis - Molecular sequence alignment and analysis - Pattern recognition/data mining/optimization methods in Bioinformatics - Visualization of large biological data sets CI in Computational Biology: - Metabolic pathway analysis - Modelling, simulation, and optimization of biological systems - Biological network - Structure prediction and folding - Epigenomics CI in Biomedical Engineering, Bioprocessing and Healthcare Informatics: - Biomedical data modelling/data mining/model parametrization - Biomarker discovery and development - Personalized medicine and treatment optimization - Big data analysis and tools for biological and medical data - Health data acquisition/analysis/mining - Healthcare information systems/knowledge representation/reasoning - Parallel/high performance computing - Medical imaging and pattern recognition - Biopharmaceutical manufacturing - Closed-loop optimization methods/platforms Additional information Participants will be accommodated in the Certosa di Pontignano, which is also the venue of the Conference, where rooms and apartments are available. Rooms will be assigned as availability permits: the most charming rooms tend to be booked fast and it is recommended that prospective participants enroll early to help ensure the best accommodation ( https://cibcb2019.icas.xyz/accommodation/). Contact Any questions regarding the submission process can be sent to conference organizers: ieee-cibcb-2019 at icas.xyz -------------- next part -------------- An HTML attachment was scrubbed... URL: From auke.ijspeert at epfl.ch Wed Dec 19 08:15:41 2018 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Wed, 19 Dec 2018 14:15:41 +0100 Subject: Connectionists: Call for abstracts, AMAM 2019, Adaptive motion in animals and machines, Aug 19-23 2019, EPFL, Lausanne, Switzerland Message-ID: <996d7de9-8d66-01dd-7f22-fd10aff6a748@epfl.ch> AMAM 2019, Adaptive Motion in Animals and Machines, Aug 19-23 2019, EPFL, Lausanne, Switzerland https://amam2019.epfl.ch/ Call for abstracts and robot demonstrations, deadline March 8th, 2019 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). Two-page abstract contributions are invited from all areas pertaining to adaptive motion in animals and machines. Accepted abstracts will be presented in poster sessions. Invited talks will be presented in oral sessions in a single track (see the exciting list of speakers below). We also encourage participants to contribute hardware demonstrations, as part of the ?Robot Zoo?@AMAM2019. See https://amam2019.epfl.ch/ for instructions. 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 Sponsors: Maxon https://www.maxonmotor.com Plenary speakers: * Gr?goire Courtine, EPFL, Switzerland * Monica Daley, Royal Veterinary College, UK * Dario Floreano, EPFL, Switzerland * Radhika Nagpal, Harvard University, USA * Lena Ting, Emory University & Georgia Institute of Technology, USA * Herman van der Kooij, University of Twente & Delft University of Technology, Netherlands Invited speakers: * Shinya Aoi, Kyoto University, Japan * David Franklin, Technische Universit?t M?nchen, Germany * John Hutchinson, Royal Veterinary College, UK * Tetsuya Iwasaki, University of California, Los Angeles, USA * Katsu Kagaya, Kyoto University, Japan * Sangbae Kim, MIT, USA * Megan Leftwich, The George Washington University, USA * David Lentink, Stanford University, USA * Charlotte Le Mouel, Max Planck Institute for Intelligent Systems, Germany * Poramate Manoonpong, University of Southern Denmark, Denmark * Kamilo Melo, EPFL, Switzerland * Katja Mombaur, Heidelberg University, Germany * Beth Mortimer, University of Oxford, UK * Ulrike M?eller, California State University, Fresno, USA * Jamie Paik, EPFL, Switzerland * Pavan Ramdya, EPFL, Switzerland * Chris Richards, Royal Veterinary College, UK * Nidhi Seethapathi, University of Pennsylvania, USA * Simon Sponberg, Georgia Institute of Technology, USA * Emily Standen, University of Ottawa, Canada * Dagmar Sternad, Northeastern University, USA * Barbara Webb, University of Edinburgh, UK * Rob Wood, Harvard University, USA * Kotaro Yasui, Tohoku University, Japan 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 Local organization committee: * Jonathan Arreguit * Alessandro Crespi * Florin Dzeladini * Peter Eckert * Sylvie Fiaux * Anne Koelewijn * Mehmet Mutlu * Laura P?ez * Amy Wu -- ----------------------------------------------------------------- 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 martaruizcostajussa at gmail.com Wed Dec 19 05:50:15 2018 From: martaruizcostajussa at gmail.com (Marta Ruiz) Date: Wed, 19 Dec 2018 11:50:15 +0100 Subject: Connectionists: 1st ACL Workshop on Gender Bias for Natural Language Processing In-Reply-To: References: Message-ID: 1st ACL Workshop on Gender Bias for Natural Language Processing http://genderbiasnlp.talp.cat 1st/2nd August, Florence Gender and other demographic biases in machine-learned models are of increasing interest to the scientific community and industry. Models of natural language are highly affected by such perceived biases, present in widely used products, can lead to poor user experiences. There is a growing body of research into fair representations of gender in NLP models. Key example approaches are to build and use fairer training and evaluation datasets (e.g. Reddy & Knight, 2016, Webster et al., 2018, Maadan et al., 2018), and to change the learning algorithms themselves (e.g. Bolukbasi et al., 2016, Chiappa et al., 2018). While these approaches show promising results, there is more to do to solve identified and future bias issues. In order to make progress as a field, we need standard tasks which quantify bias. This workshop will be the first dedicated to the issue of gender bias in NLP techniques and it includes a shared task on coreference resolution. In order to make progress as a field, this workshop will specially focus on discussing and proposing standard tasks which quantify bias. Shared Task We invite work on gender-fair modeling via our shared task, coreference resolution on GAP (Webster et al. 2018). GAP is a coreference dataset designed to highlight current challenges for the resolution of ambiguous pronouns in context. GAP is a gender-balanced dataset and evaluation is gender disaggregated. Previous work has shown state-of-the-art resolvers are biased to yield better performance on masculine pronouns due to differences in the public discourse between genders. Participation will be via Kaggle, with submissions open over a three month period in the lead up to the workshop. Topics of interest We invite submissions of technical work exploring the detection, measurement, and mediation of gender bias in NLP models and applications. Other important topics are the creation of datasets exploring demographics such as metrics to identify and assess relevant biases or focusing on fairness in NLP systems. Finally, the workshop is also open to non-technical work welcoming socialogical perspectives. Paper Submission Information Submissions will be accepted as short papers (4-6 pages) and as long papers (8-10 pages), plus additional pages for references, following the ACL 2019 guidelines. Supplementary material can be added. Blind submission is required. Shared task participants will be invited to submit short papers (4-6 pages, plus references). No need to anonymize papers in this shared task submission. Important dates Shared Task Jan 21. Baseline system released April 15-21. Test phase April 26. Results announced May 3. Submission of system description papers May 17. Description paper reviews completed May 30. Camera-ready description papers due Technical Papers April 26. Deadline for Submission May 15. Notification of acceptance May 22. Camera ready submission Keynote Speaker Pascale Fung, Hong Kong University of Science and Technology Programme Committee Cristina Espa?a-Bonet, DFKI, Germany Silvia Chiappa, DeepMind, UK Rachel Rudinger, John Hopkins University, US Saif Mohammad, National Council Canada Svetlana Kiritchenko, National Council Canada Corina Koolen, University of Amsterdam Kai-Wei Chang, University of Washington Kaiji Lu, Carnegie Mellon University, US Sameep Mehta, IBM Research India Sharid Lo?iciga, University of Gothenburg Zhengxian Gong, Soochow University Marta Recasens, Google, US Jason Baldridge, Google AI Language, US Bonnie Webber, University of Edinburgh Ben Hachey, The University of Sydney, Australia Organizers Marta R. Costa-juss?, Universitat Polit?cnica de Catalunya, Barcelona Christian Hardmeier, Uppsala University Kellie Webster, Google AI Language, New York Will Radford, Canva, Sydney Contact persons General Workshop: Marta R. Costa-juss?: marta (dot) ruiz (at) upc (dot) edu Shared Task: Kellie Webster: websterk (at) google (dot) com -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.lengyel at eng.cam.ac.uk Thu Dec 20 05:00:43 2018 From: m.lengyel at eng.cam.ac.uk (=?utf-8?B?TcOhdMOpIExlbmd5ZWw=?=) Date: Thu, 20 Dec 2018 11:00:43 +0100 Subject: Connectionists: Faculty position in AI and Neuroscience, Cambridge Message-ID: Faculty position in AI and Neuroscience Department of Engineering, University of Cambridge, UK Applications are invited for a University Lectureship (~ US Assistant Professor equivalent) at the intersection of Artificial Intelligence (AI) and Neuroscience (including Cognitive Science) in the Computational and Biological Learning Lab (cbl.eng.cam.ac.uk). CBL combines expertise in computational neuroscience and cognitive science (Mate Lengyel, Guillaume Hennequin, Rich Turner) and machine learning (Zoubin Ghahramani, Carl Rasmussen, Rich Turner, Jose Miguel Hernandez-Lobato). We particularly encourage applicants who would complement our current research activities. The successful applicant?s research should use AI-inspired computational and theoretical approaches to neuroscience (including computational cognitive science), or conversely, biological intelligence-inspired approaches to AI (with an emphasis on machine learning-based approaches), and may combine these approaches with behavioural experiments. This is a linked post offered in association with Wolfson College, and the successful applicant will be elected to an Official Fellowship of the College. Informal enquiries are welcome to: Mate Lengyel Guillaume Hennequin Richard Turner Timeline: - Closing date of applications: Friday, 1 February 2019 - Interviews: March-April 2019 - Decision expected: April 2019 Further information and details of the application process can be found at http://www.jobs.cam.ac.uk/job/19416/ The University of Cambridge values diversity and is committed to equality of opportunity. -- Mate Lengyel Professor of Computational Neuroscience Computational and Biological Learning Lab Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ, UK tel: +44 (0)1223 748 532, fax: +44 (0)1223 765 587 email: m.lengyel at eng.cam.ac.uk web: www.eng.cam.ac.uk/~m.lengyel From sahidullahmd at gmail.com Thu Dec 20 05:53:51 2018 From: sahidullahmd at gmail.com (Md Sahidullah) Date: Thu, 20 Dec 2018 11:53:51 +0100 Subject: Connectionists: ASVspoof 2019 CHALLENGE: Future horizons in spoofed/fake audio detection Message-ID: [Apologies for possible cross-posting] **=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=** *ASVspoof 2019 CHALLENGE:Future horizons in spoofed/fake audio detection**http://www.asvspoof.org/ * * =*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=* Can you distinguish computer-generated or replayed speech from authentic/bona fide speech? Are you able to design algorithms to detect spoofs/fakes automatically? Are you concerned with the security of voice-driven interfaces? Are you searching for new challenges in machine learning and signal processing? *Join ASVspoof 2019* ? the effort to develop next-generation countermeasures for the automatic detection of spoofed/fake audio. In combining the forces of leading research institutes and industry, ASVspoof 2019 encompasses two separate sub-challenges in logical and physical access control, and provides a common database of the most advanced spoofing attacks to date. The aim is to study both the limits and opportunities of spoofing countermeasures in the context of automatic speaker verification and fake audio detection. *CHALLENGE TASK* Given a short audio clip, determine whether it represents authentic/bona fide human speech, or a spoof/fake (replay, synthesized speech or converted voice). You will be provided with a large database of labelled training and development data and will develop machine learning and signal processing countermeasures to distinguish automatically between the two. Countermeasure performance will be evaluated jointly with an automatic speaker verification (ASV) system provided by the organisers. *BACKGROUND:*The ASVspoof 2019 challenge follows on from two previous ASVspoof challenges, held in 2015 and 2017. The 2015 edition focused on spoofed speech generated with text-to-speech (TTS) and voice conversion (VC) technologies. The 2017 edition focused on replay spoofing. The 2019 edition is the first to address all three forms attack and the latest, cutting-edge spoofing attack technology. *ADVANCES:* Today?s state-of-the-art, TTS and VC technologies produce speech signals that are as good as perceptually indistinguishable from bona fide speech. The LOGICAL ACCESS sub-challenge aims to determine whether the advances in TTS and VC pose a greater threat to the reliability of automatic speaker verification and spoofing countermeasure technologies. The PHYSICAL ACCESS sub-challenge builds upon the 2017 edition with a far more controlled evaluation setup which extends the focus of ASVspoof to fake audio detection in, e.g. the manipulation of voice-driven interfaces (smart speakers). *METRICS:* The 2019 edition also adopts a new metric, the tandem detection cost function (t-DCF). Adoption of the t-DCF metric aligns ASVspoof more closely to the field of ASV. The challenge nonetheless focuses on the development of standalone spoofing countermeasures; participation in ASVspoof 2019 does NOT require any expertise in ASV. The equal error rate (EER) used in previous editions remains as a secondary metric, supporting the wider implications of ASVspoof involving fake audio detection. *SCHEDULE:* Training and development data release: 19th December 2018 Evaluation data release: 15th February 2019 Deadline to submit evaluation scores: 22nd February 2019 Organisers return results to participants: 15th March 2019 INTERSPEECH paper submission deadline: 29th March 2019 *REGISTRATION:* Registration should be performed once only for each participating entity and by sending an email to registration at asvspoof.org with ?ASVspoof 2019 registration? as the subject line. The mail body should include: (i) the name of the team; (ii) the name of the contact person; (iii) their country; (iv) their status (academic/non-academic), and (v) the challenge scenario(s) for which they wish to participate (indicative only). Data download links will be communicated to registered contact persons only. *MAILING LIST:* Subscribe to general mailing list by sending e-mail with subject line ?subscribe asvspoof2019? to *sympa at asvspoof.org *. To post messages to the mailing list itself, send e-mails to *asvspoof2019 at asvspoof.org * *ORGANIZERS*:* Junichi Yamagishi, NII, Japan & Univ. of Edinburgh, UK Massimiliano Todisco, EURECOM, France Md Sahidullah, Inria, France H?ctor Delgado, EURECOM, France Xin Wang, National Institute of Informatics, Japan Nicholas Evans, EURECOM, France Tomi Kinnunen, University of Eastern Finland, Finland Kong Aik Lee, NEC, JAPAN Ville Vestman, University of Eastern Finland, Finland (*) Equal contribution *CONTRIBUTORS:* University of Edinburgh, UK; Nara Institute of Science and Technology, Japan, University of Science and Technology of China, China; iFlytek Research, China; Saarland University / DFKI GmbH, Germany; Trinity College Dublin, Ireland; NTT Communication Science Laboratories, Japan; HOYA, Japan; Google LLC (Text-to-Speech team, Google Brain team, Deepmind); University of Avignon, France; Aalto University, Finland; University of Eastern Finland, Finland; EURECOM, France. *FURTHER INFORMATION:* *info at asvspoof.org * -- Md Sahidullah website: *https://sites.google.com/site/iitkgpsahi/ * -------------- next part -------------- An HTML attachment was scrubbed... URL: From avellido at cs.upc.edu Thu Dec 20 06:44:41 2018 From: avellido at cs.upc.edu (Alfredo Vellido) Date: Thu, 20 Dec 2018 12:44:41 +0100 Subject: Connectionists: WSOM+ 2019: One month to deadline and some news Message-ID: <3438e976-3a7e-30f6-91cf-8204fe3d2777@cs.upc.edu> ************ WSOM+ 2019 ************ 13th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization Barcelona, Spain, 26-28 June 2019 https://wsom2019.cs.upc.edu NEWS Confirmed invited speakers: Paulo Lisboa (Liverpool John Moores University, U.K.) Tobias Schreck (Graz University of Technology, Austria) A?da Valls (Universitat Rovira i Virgili, Spain) Alessandro Sperduti (Universit? degli Studi di Padova, Italy) Confirmed sponsors (sponsored student registration fees and awards): LumenAI (www.lumenai.fr) Amalfi Analytics (www.amalfianalytics.com) Connecthink (connecthink.pro) New student registration fee: 375? === CFP Paper submission deadline: January 20, 2019 WSOM+ invites contributions related to the theoretical and methodological aspects of Unsupervised Learning, Self-Organizing Maps, Learning Vector Quantization, Clustering, Data Visualization and closely related topics. We also call for and encourage scientific and application-oriented papers that demonstrate the use of the aforementioned methods and models in fields of knowledge. For the full CFP and further details on dates, submission, registration, venue, committees, and the city at large, please visit https://wsom2019.cs.upc.edu The WSOM+ 2019 proceedings will be published as a book in Springer?s Advances in Intelligent Systems and Computing (AISC) series. Barcelona awaits your participation in the 13th WSOM+ conference! This is a welcoming and inclusive city, home to thriving Machine Learning and Computational Intelligence communities. Hosted by the Intelligent Data Engineering and Artificial Intelligence (IDEAI) Research Center at Universitat Polit?cnica de Catalunya (UPC BarcelonaTech), WSOM+ 2019 aims to build on a successful string of editions that started more than two decades ago with WSOM?97 in Helsinki. The conference is meant to be an international reference for research in unsupervised learning, self-organizing systems, Learning Vector Quantization and data visualization. Submit your contributions to WSOM+2019 and meet us in the Barcelona summer! ************ WSOM+ 2019 ************ Organizing Committee Alfredo Vellido, Chair (IDEAI, UPC BarcelonaTech) Karina Gibert (IDEAI, UPC BarcelonaTech) Cecilio Angulo (IDEAI, UPC BarcelonaTech) Jos? David Mart?n (Universitat de Val?ncia) Steering Committee: Teuvo Kohonen (Honorary Chairman, Finland) Marie Cottrell (France) Pablo Estevez (Chile) Timo Honkela (Finland) Jean Charles Lamirel (France) Thomas Martinetz (Germany) Erzsebet Merenyi (USA) Madalina Olteanu (France) Michel Verleysen (Belgium) Thomas Villmann (Germany) Takeshi Yamakawa (Japan) Hujun Yin (UK) From researchpositions at scienceofintelligence.de Thu Dec 20 09:24:11 2018 From: researchpositions at scienceofintelligence.de (researchpositions@scienceofintelligence.de ) Date: Thu, 20 Dec 2018 15:24:11 +0100 Subject: Connectionists: Call for applications - Science of Intelligence Berlin - Cluster of Excellence In-Reply-To: References: Message-ID: <889164$3fr5ct@ir2-relay.cms.hu-berlin.de> *Early notice* Call for applications - Science of Intelligence Berlin - Cluster of Excellence 11 PhD and 12 Postdoc positions Cross-disciplinary research in artificial intelligence, machine learning, control, robotics, computer vision, behavioral biology, cognitive science, psychology, educational science, neuroscience, and philosophy. Starting dates: Summer / Fall 2019 Duration: 3 years Salary level: TV-L 13, 100% What are the principles of intelligence, shared by all forms of intelligence, no matter whether artificial or biological, whether robot, computer program, human, or animal? And how can we apply these principles to create intelligent technology? Answering these questions - in an ethically responsible way - is the central scientific objective of the new Cluster of Excellence Science of Intelligence (www.scioi.de). Researchers from a large number of analytic and synthetic disciplines - artificial intelligence, machine learning, control, robotics, computer vision, behavioral biology, cognitive science, psychology, educational science, neuroscience, and philosophy - join forces to create a multi-disciplinary research program across universities and research institutes in Berlin. Our approach is driven by the insight, that any method, concept, and theory must demonstrate its merits by contributing to the intelligent behavior of a synthetic artifact, such as a robot or a computer program. These artifacts represent the shared ?language? across disciplines, enabling the validation, combination, transfer, and extension of research results. Thus we expect to attain cohesion among disciplines, which currently produce their own theories and empirical findings about aspects of intelligence. Interdisciplinary research projects have been defined which combine analytic and synthetic research and which address key aspects of individual, social, and collective intelligence. In addition the Science of Intelligence graduate program promotes the cross-disciplinary education of young scientists on a Master, PhD, and postdoctoral level. All PhD students associated with the cluster are expected to join the Science of Intelligence doctoral program (www.scioi.de/education/doctoral-program). The cluster welcomes applications from all disciplines that contribute to intelligence research. Applications shall be uploaded through the application portal (www.scioi.de/call-for-applications/application-process), where details of the individual research projects (www.scioi.de/call-for-applications/open-positions) are also available. Please submit your applications by 15 February 2019 in order to receive full consideration. Applicants wishing to apply for several projects need to upload separate applications for each project. From axel.soto at cs.uns.edu.ar Thu Dec 20 16:52:34 2018 From: axel.soto at cs.uns.edu.ar (Axel Soto) Date: Thu, 20 Dec 2018 18:52:34 -0300 Subject: Connectionists: Student travel support grants for ACM IUI 2019 Message-ID: Applications for student travel support grants for attending IUI 2019 are now open! See https://iui.acm.org/2019/student_grants.html for details. -- ACM IUI 2019 (https://iui.acm.org/2019/) is the 24th 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. From mgalle at gmail.com Thu Dec 20 15:55:53 2018 From: mgalle at gmail.com (=?UTF-8?Q?Matthias_Gall=C3=A9?=) Date: Thu, 20 Dec 2018 21:55:53 +0100 Subject: Connectionists: 1st CFP: Deep Learning and Formal Languages: Building Bridges (workshop @ACL) Message-ID: Hohoho... you don't know if you want to ask Santa for a wooden train or a quadcopter drone? Despair no more, you can have the best of both worlds: Deep Learning and Formal Languages: Building Bridges Deep Learning and Formal Languages: Building Bridges -- ACL 2019 Workshop Florence, Italy Website: https://sites.google.com/view/delfol-workshop-acl19 SUBMISSION DEADLINE: 26 April 2019 While deep learning and neural networks have revolutionized the field of natural language processing, changed the habits of its practitioners and opened up new research directions, many aspects of the inner workings of deep neural networks remain unknown. At the same time, we have access to many decades of accumulated knowledge on formal languages, grammar, and transductions, both weighted and unweighted and for strings as well as trees: closure properties, computational complexity of various operations, relationships between various classes of them, and many empirical and theoretical results on their learnability. The goal of this workshop is to bring researchers together who are interested in how our understanding of formal languages can contribute to the understanding and design of neural network architectures for natural language processing. For example, fundamental work on neural nets has examined whether they could learn different classes of formal languages, and reciprocally whether formal grammars or automata could closely approximate neural networks. Recently we have seen new research directions on what each formalism can bring to understand or improve the other. Topics which fall within the purview of the workshop include, but are not limited to - Learnability of formal languages with neural nets (both strong and weak learning) - Relationship between deep learning models and linguistically inspired formalisms - Connections between neural network architectures and classical computational models - Traditional formal grammars augmented through non-linearity - Hybrid models combining neural networks and finite state machines - The use of formal grammars to analyze and interpret the behavior of neural networks - Approximating neural networks with weighted automata and grammars - Including formal grammar constraints as symbolic priors in neural networks We call for three types of papers: (1) Regular workshop paper (2) Extended abstracts (3) Cross-submissions Only (1) will be included in the workshop proceedings Some recent work which falls within the scope of this call include: - Bridging CNNs, RNNs, and Weighted Finite-State Machines. Roy Schwartz, Sam Thomson,and Noah A Smith. (ACL 2018) - Rational Recurrences. Hao Peng, Roy Schwartz, Sam Thomson, Noah A. Smith. (ENMLP 2018) - Recurrent Neural Networks as Weighted Language Recognizers. Y. Chen, S. Gilroy, A. Maletti, J. May, and K. Knight. (NAACL 2018) - Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures. Abhijit Mahalunkar and John D. Kelleher. (ICANN 2018) - Explaining black boxes on sequential data using weighted automata. St?phane Ayache, R?mi Eyraud and No? Goudian. (ICGI 2018) - Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples. Gail Weiss, Yoav Goldberg, and Eran Yahav. (ICML 2018) - Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction. Siyuan Qi, Baoxiong Jia, and Song-Chun Zhu. (ICML 2018) - Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses. Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Dmitry Storcheus, Scott Yang (NIPS 2018) - Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text. Oiwi Parker Jones and Brendan Shillingford (IRASL workshop at NIPS 2018) - Verification of Recurrent Neural Networks Through Rule Extraction. Q Wang, K Zhang, X Liu, and CL Giles (arxiv.org 2018) - A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity. Q Wang, K Zhang, II Ororbia, G Alexander, X Xing, X Liu, CL Giles (arxiv.org 2018) - Grammar Variational Autoencoder. Matt J. Kusner, Brooks Paige, Jos? Miguel Hern?ndez-Lobato. (ICML 2017) - Subregular Complexity and Deep Learning. Enes Avcu, Chihiro Shibata, and Jeffrey Heinz. (LAML 2017) - Recurrent Neural Network Grammars. Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, and Noah A. Smith. (NAACL 2016). - Weighting finite-state transductions with neural context. Pushpendre Rastogi, Ryan Cotterell, and Jason Eisner (NAACL 2016) Programme Committee - Borja Balle, Amazon - Xavier Carreras, dMetrics - Shay B. Cohen, University of Edinburgh - Alex Clark, University of London - Ewan Dunbar, Universit? Paris Diderot - Marc Dymetman, Naver Labs Europe - Kyle Gorman, City University of New York - Hadrien Glaude, Amazon - John Hale, University of Georgia - Mans Hulden, University of Colorado - Franco Luque, University of C?rdoba - Chihiro Shibata, Tokyo University of Technology - Adina Williams, FAIR Organizers - Jason Eisner, Johns Hopkins University - Matthias Gall?, Naver Labs Europe - Jeffrey Heinz, Stony Brook University - Ariadna Quattoni, dMetrics - Guillaume Rabusseau, Universit? de Montr?al / Mila -------------- next part -------------- An HTML attachment was scrubbed... URL: From Mark.Humphries at nottingham.ac.uk Fri Dec 21 06:04:57 2018 From: Mark.Humphries at nottingham.ac.uk (Mark Humphries) Date: Fri, 21 Dec 2018 11:04:57 +0000 Subject: Connectionists: A review of the year in (systems) neuroscience, from The Spike Message-ID: <30FFCEB8-8ADE-4F27-B6E2-A5D397A06408@exmail.nottingham.ac.uk> Systems neuroscience is a fascinating, if daunting, subject - daunting to keep up with, even more daunting to dive into for the first time That?s why I launched The Spike in 2016, as a platform to bring the triumphs and challenges of systems neuroscience to a broad audience As a great place to start, we?ve just published our review of 2018, https://medium.com/the-spike/2018-a-mildly-muddled-review-of-the-year-in-neuroscience-de0d9f15fc30 And read the rest here: https://medium.com/the-spike Enjoy! Prof Mark Humphries @markdhumphries This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please contact the sender and delete the email and attachment. Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham. Email communications with the University of Nottingham may be monitored where permitted by law. -------------- next part -------------- An HTML attachment was scrubbed... URL: From alessandra.sciutti at gmail.com Fri Dec 21 11:58:27 2018 From: alessandra.sciutti at gmail.com (Alessandra Sciutti) Date: Fri, 21 Dec 2018 17:58:27 +0100 Subject: Connectionists: Two Post-Doc Positions at IIT working on Perception and HRI Message-ID: <00d201d4994e$6518f420$2f4adc60$@gmail.com> ******************************************************************* Two Post-Doc Positions at IIT working on Perception and HRI Italian Institute of Technology ? Genoa Deadline: 14 January 2019 Project: ERC Starting Grant ?wHiSPER? ******************************************************************* Perception is a complex process, where prior knowledge is incorporated into the current percept to help the brain cope with sensory uncertainty. This implies that two individuals could perceive differently the very same physical stimulus, e.g. the duration of an interval of time could look longer to one than to the other. Yet, humans are very good at achieving a tight coordination in space and time. The project aims at understanding how such a shared perception is achieved, by modelling how visual perception of time and space changes during interaction and enabling a robot to adapt its perception to the individual needs of the partner. These aims require a multidisciplinary team of motivated researchers, coming from different backgrounds and eager to address the challenges of understanding humans and of making better robots! If you want to be part of the team, here you find the official calls: ? Postodctoral position in "Enabling shared perception with robots" https://www.iit.it/careers/openings/opening/903-postdoctoral-position-in-ena bling-shared-perception-with-robots oriented to researchers with a background in computer science, robotics, engineering or related fields; ? Postoctoral position in ?Investigating perception during interaction with humans and robots" https://www.iit.it/careers/openings/opening/902-postdoctoral-position-in-inv estigating-perception-during-interaction-with-humans-and-robots oriented to researchers with a background in psychology, neuroscience, biomedical engineering or related fields; The successful applicants will join an interdisciplinary team based at Istituto Italiano di Tecnologia?in Erzelli, Genoa, Italy, and conduct research in the context of the ERC Starting Grant ?wHiSPER ? investigating Human Shared PErception with Robots? funded by the European Research Council with Grant Agreement n. 804388 (Principal Investigator: Alessandra Sciutti).?Research will happen in a fully equipped laboratory, supplied with a iCub humanoid robot, motion capture and eye-tracking devices, in a group with a variety of competences ranging from robotics to psychology and bioengineering. ******************************************** The deadline for applications is: 14 January 2019 ******************************************** The project will start in March 2019. Additionally positions are available at the PhD level and projects for Bachelor and Master preparation can be discussed. Please contact: alessandra.sciutti at iit.it for any further question or information and share this communication with anybody who could be interested. ---------------------------------------- Alessandra Sciutti (PhD) Istituto Italiano di Tecnologia Center for Human Technologies Via Enrico Melen 83, Building B 16152 Genova, Italy tel: +39 010? 8172 210 email: alessandra.sciutti at iit.it website: https://www.iit.it/people/alessandra-sciutti twitter: @alefreedot TEDx talk (Italian): https://www.youtube.com/watch?reload=9&v=e0eMayWU_lc From schurgerlab at gmail.com Fri Dec 21 07:42:18 2018 From: schurgerlab at gmail.com (Schurger Lab) Date: Fri, 21 Dec 2018 13:42:18 +0100 Subject: Connectionists: post-doc opportunity Message-ID: Post-doctoral positions in the cognitive neuroscience of volition Brain-behavior forecasting: Neural antecedents of self-initiated movement and the forecasting of behavior based on brain activity Starting date: Spring 2019 Duration: 18 months The French Institute of Health and Medical Research (INSERM) invites applications for a post-doctoral position in the Cognitive Neuroimaging Group, at the NeuroSpin Research Center near Paris, France, as part of the research team of Dr. Aaron Schurger. The Schurger lab focuses on understanding how decisions are made and actions initiated spontaneously, without an external sensory cue, and how time series of neural activity can be used to forecast behavior. We pursue this research using a combination of behavioral experiments, neuroimaging, computational modeling, time-series analyses, and machine learning. We are especially interested in applicants with significant experience in one or more of the following areas: -machine learning / pattern classification -modeling of time series / predicting discrete events in time series -Bayesian statistics -Kalman filters -dynamical systems theory -magnetoencephalography (MEG) Candidates with experience in other neural recording modalities (such as fMRI or ECoG) may also be considered. An interest in volition, action initiation, and/or the purposeful generation of unpredictable behavior is essential. Applicants should have a obtained a PhD in a relevant discipline prior to the starting date, and at a minimum should have strong skills in the following three areas: computer programming (MatLab or Python), statistics, signal processing Candidates with a background in engineering, computer science, physics, or applied math are encouraged to apply. Resources available at NeuroSpin include Siemens 3T and 7T MRI scanners; high-density EEG (EGI Inc.); Elekta NeuroMag 306-channel MEG (allowing for the simultaneous recording of EEG); eye tracking (available for MRI, MEG, and behavioral experiments); an in-house team of experts in signal processing and statistical learning; a dedicated staff handling subject recruitment, scheduling, and payment; various Nespresso devices; and proximity to Paris. Applicants should send a CV, letter of motivation (max 2 pages), and a list of three references via e-mail to schurgerlab at gmail.com. Review of applicants will begin immediately, and will continue until the position is filled. The NeuroSpin Research Center is located on the campus of the CEA-Saclay, near Orsay, about 18 km southwest of Paris. For more information on the NeuroSpin Research Center and the Cognitive Neuroimaging Group: http://www-centre-saclay.cea.fr/fr/Visite-guidee-de-NeuroSpin http://meg-france.in2p3.fr/_lesCentres/Neurospin_en.php http://www-dsv.cea.fr/en/institutes/institute-of-biomedical-imaging-i2bm/departments/neurospin-neurospin http://www.unicog.org/pm/pmwiki.php ----------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Fri Dec 21 08:09:04 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Fri, 21 Dec 2018 15:09:04 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Fourth Call for Papers In-Reply-To: <3D0926CD-0237-493E-BBD1-914DD649F38F@cs.ucy.ac.cy> References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> <95F40EA8-2662-46AD-B301-3385D4B8601B@cs.ucy.ac.cy> <05EDB924-A9A7-4E3B-8E36-05EAE5D4242A@cs.ucy.ac.cy> <6FC69A4B-F456-4336-A7CC-2AAE2723CB67@cs.ucy.ac.cy> <3D0926CD-0237-493E-BBD1-914DD649F38F@cs.ucy.ac.cy> Message-ID: *** FOURTH CALL FOR PAPERS *** 27th ACM International Conference on User Modeling, Adaptation and Personalization (ACM UMAP 2019) ?Making Personalization Transparent: Giving control back to the User" 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. CONFIRMED INVITED SPEAKERS ? Marios Avraamides, University of Cyprus ? Judith Masthoff, Utrecht University ? Mounia Lalmas-Roelleke, Spotify London CONFERENCE TRACKS Track 1 - Personalized Recommender Systems Chairs: Marko Tkalcic, Free University of Bozen-Bolzano, marko.tkalcic at unibz.it Alan Said, University of Sk?vde, alansaid at acm.org Personalized, computer-generated recommendations have become a pervasive feature of today?s online world. The underlying recommender systems are designed to help users and providers in a number of ways. From a user?s viewpoint, for example, these systems assist consumers in finding relevant things within large item collections. On the other hand, from a provider?s perspective, recommenders have also shown to be valuable tools to steer consumer behavior. From a technical perspective, the design of such systems requires the careful consideration of various aspects, including the choice of the user modeling approach, the underlying recommendation algorithm, and the user interface. This track aims to provide a forum for researchers and practitioners to discuss open challenges, latest solutions and novel research approaches in the field of recommender systems. Besides the above-mentioned technical aspects, works are also particularly welcome that address questions related to the user perception and the business value of recommender systems. Topics include (but are not limited to): ? Recommendation algorithms ? Recommender and personalization system evaluation ? User modeling and preference elicitation ? Users? perception of recommender systems ? Business value of recommendation systems and multi-stakeholder environments ? Explanations and trust ? Context-aware recommendation algorithms ? Recommending to groups of users ? Case studies of real-world implementations ? Novel, Psychology-informed User- and Item-modeling Track 2 - Adaptive Hypermedia And The Semantic Web Chairs: Liliana Ardissono, University of Torino, liliana.ardissono at unito.it Katrien Verbert, KU Leuven, katrien.verbert at cs.kuleuven.be Adaptive hypermedia and adaptive web explore alternatives to the traditional ?one-size-fits-all? approach in the development of web and hypermedia systems. Adaptive hypermedia and adaptive web systems build a model of the interests, preferences and knowledge of each individual user, and use this model in order to adapt the behavior of hypermedia and web systems to the needs of that user. Semantic web frequently serves as an infrastructure to enable adaptive and personalized Web systems. Semantic web technology targets the use of explicit semantics and metadata to help web systems perform the desired functionality: this implies the use of linked data from the web, the use of ontologies in models, or the use of metadata in user interfaces, as well as the use of ontologies for information integration. This track aims to provide a forum to researchers to discuss open research problems, solid solutions, latest challenges, novel applications and innovative research approaches in adaptive hypermedia and semantic web. Topics include (but are not limited to): ? Web user profiles ? Adaptive navigation support ? Personalized search ? Web content adaptation ? Analytics of web user data ? Adaptive web sites and portals ? Adaptive books and textbooks ? Social navigation and social search ? Navigation support in continuous media and virtual environments ? Usability engineering for adaptive hypermedia and web systems ? Novel methodologies for evaluating adaptive hypermedia and web systems ? Semantic Web technologies for web personalization ? Ontology-based data access and integration/exchange on the adaptive web ? Ontology engineering and ontology patterns for the adaptive web ? Ontology-based user models ? Semantic social network mining, analysis, representation, and management ? Crowdsourcing semantics; methods, dynamics, and challenges ? Semantic Web and Linked Data for adaptation Track 3 - Intelligent User Interfaces Chairs: Li Chen, Hong Kong Baptist University, lichen at comp.hkbu.edu.hk Jingtao Wang, Google, jingtaow at acm.org Intelligent User Interfaces aim to improve the interaction between computer systems and human users by means of Artificial Intelligence. The systems support and complement different types of abilities that are normally unavailable in the context of human-only cognition. Previous work has found that humans do not always make the best possible decisions when working together with computer systems. By designing and deploying improved forms of support for interactive collaboration between human decision makers and systems, we can enable decision making processes that better leverage the strengths of both collaborators. More generally this research track can be characterized by exploring how to make the interaction between computers and people smarter and more productive, which may leverage solutions from human-computer interaction, data mining, natural language processing, information visualization, and knowledge representation and reasoning. Topics include (but are not limited to): ? Adaptive personal virtual assistants (e.g., interaction with robots) ? Adapting natural interaction (e.g., natural language, speech, gesture) ? Intelligent user interfaces based on sensor data (UIs for cars, fridges, etc.) ? Multi-modal interfaces (speech, gestures, eye gaze, face, physiological info, etc.) ? Intelligent wearable and mobile interfaces ? Smart environments and tangible computing ? Transparency and control of decision support systems (e.g., semi-autonomous systems) ? Explainable intelligent user interfaces ? Affective and aesthetic interfaces ? Tailored persuasion and argumentation interfaces ? Tailored decision support (e.g., over- and under-reliance in uncertain domains) ? Adaptive information visualization ? Scalability of intelligent user interfaces to access huge datasets ? User-centric studies of interactions with intelligent user interfaces ? Novel datasets and use cases for intelligent user interfaces ? Evaluations of intelligent user interfaces Track 4 - Personalized Social Web Chairs: Ilaria Torre, University of Genova, ilaria.torre at unige.it Osnat Mokryn, omokryn at univ.haifa.ac.il The social web is continuously growing and social platforms are a fundamental part of our life. Mediated communication is becoming the primary form of communication for young people, and adults follow in increasing numbers. Online communication is increasingly enriched by the use of memes, pictures, audio and video, though language (textual and oral) remains a fundamental tool with which people interact, convey their opinions, construct and determine their social identity. Lifelogging data (e.g., health, fitness, food) is growing as well on the social web. This type of personal information source, gathered for private use through personal devices, is now often shared in online communities. These trends open new challenges for research: how to harness the power of collective intelligence and quantified self data in online social platforms to identify social identities, how to exploit continuous feedback threads, and how to improve the individual user experience on the social web. We invite original submissions addressing all aspects of personalization, user models building and personal experience in online social systems. Topics include (but are not limited to): ? Personalization of the web experience in social systems ? Adaptations based on personality, society, and culture ? Personalization algorithms and protocols inspired by human societies ? Social recommendation ? Identifying social identities in social media ? Social and crowd-generated data for adaptation ? Personalized information retrieval ? Exploiting quantified self data on the social web of things ? Data-driven approaches for personalization ? Modeling individuals, groups, and communities ? Collective intelligence and experience mining ? Pattern and behaviour discovery in social network analysis ? Opinion mining for user modeling ? Sentiment analysis ? Topic modeling for online conversations and short texts ? Privacy, perceived security, and trust in social systems ? Ethical issues involved in studying the social web ? User awareness and control ? Evaluation methodologies for the social web Track 5 - Technology-Enhanced Adaptive Learning Chairs: Jes?s G. Boticario, UNED, jgb at dia.uned.es Inge Molenaar, Radboud University, i.molenaar at pwo.ru.nl At large there is an on-going ?fusion? between humans and technological systems. The ongoing integration of devices into our daily lives furthers the integration of technology in human learning. With technology increasingly gaining more data and intelligence, a new era of technology-enhanced adaptive learning is emerging. Consequently, the interactions between learners, teachers and technology are becoming increasingly complex. Learning is a positioned as a complex human process that involves cognitive, metacognitive, motivational, affective and psychomotor aspects which interact with the learning context. Smart technological solutions are increasingly able to identify and model the learner needs on these five aspects and accordingly provide personalized support that can improve the effectiveness, efficiency and satisfaction of learning experiences. Current research in artificial intelligence combined with data science and learning analytics bring new opportunities to recognize, and effectively support individual learners? needs and orchestrate collaborate and classroom learning with intelligent learning solutions, and augment teachers in blended learning situations. The aim of this track is to foreground the systematic complexity of human learning and use systematic analytic approaches to measure, diagnose and support human learning with technologies. This covers not only formal educational settings, but also lifelong learning requirements (including workplace training) as well as the acquisition of skills informal learning settings (e.g., in daily activities, serious games, sports, healthcare, wellbeing, etc.). To address the wide spectrum of modeling issues and challenges that can be raised, contributions from various research areas are welcome. Therefore, this track invites researchers, developers, and practitioners from various disciplines to present their innovative adaptive learning solutions, share acquired experience, and discuss the main modeling challenges for technology enhanced adaptive learning. Topics include (but are not limited to): ? Domain, learner, teacher and context modeling ? Modeling cognitive, metacognitive, motivational, affective and psychomotor aspects of learning ? Diagnosis of learner needs and calibration of support and feedback Adaptive and personalized support for learning ? Dealing with ethical issues involved in detecting and modeling a wider range of information sources (e.g., information from novel sensing devices, ambient intelligent features) that may affect learning ? Management of large, open, and public datasets for educational data mining ? Agent-based learning environments and virtual pedagogical agents ? Open corpus personalized learning ? Collaborative and group learning ? Adaptive technologies to orchestrated classroom Learning ? Personalized teachers awareness and support tools ? Multimodal learning analytics to personalize learning ? UMAP aspects in specific learning solutions: educational recommender systems, intelligent tutoring systems, serious games, personal learning environments, MOOCs ? Wearable technologies and augmented reality in adaptive personalized learning ? Processing collected data for UMAP: educational data mining, learning analytics, big data, deep learning. ? Semantic web and ontologies for e-learning ? Interoperability, portability, and scalability issues ? Case studies in real-world educational settings ? New methodologies to develop user-centered highly personalized learning solutions Track 6 - Privacy And Fairness Chairs: Bart Knijnenburg, Clemson University, bartk at clemson.edu Esma Aimeur, University of Montreal, aimeur at iro.umontreal.ca Adaptive systems researchers and developers have a social responsibility to care about their users. This involves building, maintaining, evaluating, and studying adaptive systems that are fair, transparent, and protect users' privacy. We invite papers that study, in the context of UMAP, the topics of privacy (as well as innovative means to resolve privacy problems through algorithms, interfaces, or other technical or non-technical means), fairness (covering the spectrum from algorithmic fairness to social implications of adaptive systems), and transparency (as a concept of system usability as well as a means to resolve problems with privacy and fairness). Beyond this we encourage authors to submit to this track any work that ascribes to or advances the general idea of "adaptive systems that care?. Privacy topics: ? Analysis of privacy implications of user modeling ? Privacy compliance ? Algorithmic solutions to privacy ? Architectural solutions to privacy ? Interactive solutions to privacy ? Usable privacy for adaptive systems ? User perceptions of privacy in UMAP applications ? Studies of users? privacy-related behaviors in UMAP applications ? Descriptions or evaluations of privacy-settings user interfaces ? Privacy prediction / personalization ? User-tailored approaches to privacy ? Privacy education for user modeling ? Modeling of data protection and privacy requirements ? Economics of privacy and personal data ? Measuring privacy Fairness topics: ? Ethical considerations for user modeling ? UMAP applications for underrepresented groups ? Cultural differences (e.g. culture-aware user modeling) ? Bias and discrimination in user modeling ? Imbalance in meeting the needs of different groups of users ? Balancing needs of users versus system owners ? Ethics of explore/exploit strategies or A/B testing ? ?Filter bubble? or ?balkanization? effects ? Enhancing/embracing diversity in user modeling ? Algorithmic methods for increasing fairness ? User perceptions of fairness ? Measuring fairness Transparency topics: ? User perceptions of transparency ? Transparent algorithms ? Interface innovations that increase transparency ? Explanations for transparency ? Visualizations for transparency ? Adaptive systems for self-actualization ? (User-centric) evaluations of methods that increase transparency ? Measuring transparency Track 7 - Personalized Music Access Chairs: Markus Schedl, University of Linz, markus.schedl at jku.at Nava Tintarev, TU Delft, n.tintarev at tudelft.nl Music access systems (e.g., search, retrieval, and recommendation systems) have experienced a boom during the past decade due to the availability of huge music catalogs to users, anywhere and anytime. These systems record information on user behavior in terms of actions on music items, such as play, skip, or playlist creation and modification. As a result, an abundance of user and usage data has been collected and is available to companies and academics, allowing for user profiling and to create and improve personalized music access. This track addresses unsolved challenges in this area relating to user understanding and modeling, personalization in recommendation and retrieval systems, modeling usage context, and adapting interactive intelligent music interfaces. This track aims to provide a forum for researchers and practitioners for the latest research on? user modeling and personalization for finding, making, and interacting with music. Topics include (but are not limited to): ? Personalized music preference elicitation and preference learning ? Psychological modeling of music listeners (e.g., personality, emotion, etc.) ? Subjective perceptions of music (e.g., similarity, mood, tempo) social and cultural aspects of listening behavior (e.g., for group recommenders) ? Applications for personalized music consumption and creation ? Personalized playlist generation and continuation (e.g., sequences and transitions) ? Personalized music interaction and interface paradigms (e.g., visualization, VR) ? Explainability, transparency, and fairness in personalized music ? Systems user-centric performance measures (e.g., diversity, novelty, serendipity, etc.) ? Datasets (including benchmarks) for personalizing music retrieval and recommendation Track 8 - Personalized Health Chairs: Christoph Trattner, University of Bergen, trattner.christoph at gmail.com David Elsweiler, University of Regensburg, david at elsweiler.co.uk Growing health issues and rising treatment costs mean that technological systems are increasingly important for global health. Personalised systems, tailored to the needs and behaviours of individual patients, are one of the promising approaches to health promotion by encouraging lifestyle change, managing treatment programmes and providing doctors and other healthcare providers with detailed individualized feedback. The challenges to developing such systems, which model user needs and preferences, as well as appropriate medical knowledge to provide assistance and recommendations are plentiful. The diverse technologies which could potentially feature in solutions are equally vast, ranging from AI systems to sensors, from mobile computing, augmented reality and visualization, to mining the web or other data streams to learn about health issues and user behaviour. In this track we invite scholars working in these or related areas to contribute to the discourse on how technology can promote health. This track aims to provide a forum to researchers to discuss open research problems, solid solutions, latest challenges, novel applications and innovative research approaches and in doing so to strengthen the community of researchers working on Personalized Health and attract representatives from from diverse scholarly backgrounds ranging from computer and information science to public health, epidemiology, psychology, medicine, nutrition and fitness. Topics include (but are not limited to): ? Algorithms and Recommendation Strategies to increase health ? Mobile health ? Quantified self ? Applied data analytics and modeling for health ? Health risk modeling and forecasting ? Systems for Preventative Measures ? Medical Evaluation Techniques ? Domain Knowledge Representation ? Behavioral Interventions: Persuasion/Nudging/Behavioral Change ? HCI, Interfaces and Visualisations for health ? Regulations and Standards ? Human/ Expert-in-the-Loop ? Gamification and Serious Games ? Privacy, Trust, Ethics ? Datasets SUBMISSION AND REVIEW PROCESS Papers should be submitted through EasyChair: https://easychair.org/conferences/?conf=acmumap2019 The ACM User Modeling, Adaptation, and Personalization (ACM UMAP) 2019 Conference will include high quality peer-reviewed papers related to the above key areas. Maintaining the high quality and impact of the ACM UMAP series, each paper will have three reviews by program committee members and a meta-review presenting the reviewers? consensual view; the review process will be coordinated by the program chairs in collaboration with the corresponding area chairs. 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. For both long papers and short paper submissions, it is not required to anonymize the manuscripts, i.e., ACM UMAP will apply a single-blind reviewing process. Separation of long and short papers will be strictly enforced so papers will not compete across categories, but only within each category. Papers that receive high scores and are considered promising by reviewers, but didn?t make the acceptance cut, will be directed to the poster session of the conference and will be invited to be resubmitted as posters. Papers must be formatted using the ACM SIG Standard (SIGCONF) proceedings template: https://www.acm.org/publications/proceedings-template . Please note that ACM changed its templates at the start of 2017, so please ensure that you use the new template and do not reuse an old 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. 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.) IMPORTANT DATES ? Abstract: January 25, 2019 (mandatory) ? Full paper: February 1, 2019 ? Notification: March 11, 2019 ? Camera-ready: April 3, 2019 ? Adjunct proceedings, camera ready: April 15, 2018 Note: The submissions times are 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, Demos, 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 shani.shapira at elsc.huji.ac.il Fri Dec 21 10:18:09 2018 From: shani.shapira at elsc.huji.ac.il (Shani Shapira) Date: Fri, 21 Dec 2018 17:18:09 +0200 Subject: Connectionists: =?utf-8?q?Deep_Learning_and_the_Brain-_Invitation?= =?utf-8?q?_to_ELSC_conference=2C_January_20-22=2C_2019=E2=80=8F?= Message-ID: The Edmond and Lily Safra Center for Brain Sciences at The Hebrew University of Jerusalem cordially invites you to the conference: *Deep Learning* *and the Brain* *January 20-22, 2019* The Suzanne and Charles Goodman Brain Sciences Building, Edmond J. Safra Campus, Jerusalem For further information and *REGISTRATION* , please visit our website: http://elsc.huji.ac.il/elsc-conference-10 [image: Deep Learning and the Brain A3 poster.jpg] Best regards, Shani Shapira Events and Publications *Edmond and Lily Safra Center for Brain Sciences* Edmond J. Safra Campus, Jerusalem Hebrew University of Jerusalem 9190401 http://e ls c.huji.ac.il/ -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Deep Learning and the Brain A3 poster.jpg Type: image/jpeg Size: 341105 bytes Desc: not available URL: From uwe.hanebeck at kit.edu Fri Dec 21 12:13:58 2018 From: uwe.hanebeck at kit.edu (Hanebeck, Uwe (IAR)) Date: Fri, 21 Dec 2018 17:13:58 +0000 Subject: Connectionists: =?utf-8?q?4_PhD/PostDoc_Positions_in_=E2=80=9CMac?= =?utf-8?q?hine_Learning_for_Estimation_and_Control=E2=80=9D_at_ISAS=40KIT?= =?utf-8?q?=2C_Germany?= Message-ID: <3df9654c7a014f7bbe47c73b400e02db@kit-msx-31.kit.edu> Four (4) full-time, fully paid PhD/PostDoc positions in ?Machine Learning for Estimation and Control? at the Intelligent Sensor-Actuator-Systems Laboratory (ISAS), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany Karlsruhe Institute of Technology (KIT): KIT combines its three core tasks: research, higher education, and innovation within one mission. With about 9,400 employees and 25,000 students, KIT is one of the big institutions of research and higher education in natural sciences and engineering in Europe. KIT is located in Germany in the medium-sized city of Karlsruhe with a very high quality of life. Chair for Intelligent Sensor-Actuator-Systems (ISAS): ISAS (http://isas.iar.kit.edu/) works on modern machine learning methods for estimation and control with applications to * Optimization of industrial processes, e.g., optical sorting machines, * Traffic management for air traffic control and pedestrian simulation, * Development of assistive functions in telepresence systems and in medical engineering, * Sensor data processing in networks, e.g., industrial process automation and monitoring, and * Measuring, processing, and visualizing spatially distributed data in large environments. Description of Positions: We are seeking to fill four (4) PhD/PostDoc positions with excellent candidates, who will work closely together in the following areas: ? Multi-sensor data fusion in industrial applications in close collaboration with Trumpf & Co. KG. ? Secure remote monitoring using data fusion with homomorphic encryption. ? Estimation and AR/VR visualization of spatial distributions for toxic pollutants. ? Optical belt sorting under dynamic conditions. All positions offer the possibility to cooperate with our network of partners from industry and academia on a national and international basis. We offer intensive mentoring and a quick path to the PhD degree (? 3 years). Besides research, the supervision of bachelor/master theses and participation in teaching is expected. Personal Qualifications: ? Master's degree (or equivalent) or PhD in computer science, electrical engineering, mechanical engineering, mathematics, or a related subject. ? Very good mathematical knowledge. ? Moderate proficiency in programming. ? Know-how in stochastics and signal processing (are advantageous, but not a prerequisite). ? High self-motivation, team working skills, and readiness for interdisciplinary work. ? Proficiency in the English language (spoken and written). ? Commitment to publish research results. ? Willingness to travel internationally (conferences, research stays, ...). Payment: The positions are full-time, fully paid researcher positions according to "Verg?tungsgruppe des Tarifvertrages des ?ffentlichen Dienstes" TV-L E 13. This may increase depending on experience. Contact: Submit applications including cover letter, CV, and academic transcripts by January 30, 2019 in electronic form to: Univ.-Prof. Dr.-Ing. habil. Uwe D. Hanebeck Karlsruhe Institute of Technology (KIT) Department of Informatics Institute for Anthropomatics and Robotics (IAR) Chair for Intelligent Sensor-Actuator-Systems (ISAS) Adenauerring 2 D-76131 Karlsruhe Germany E-Mail: Uwe.Hanebeck at kit.edu KIT is pursuing a gender equality policy and encourages women to apply. Furthermore, in case of equal qualification, preference is given to applicants with disabilities. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 7511 bytes Desc: not available URL: From chriskanan at gmail.com Fri Dec 21 15:31:11 2018 From: chriskanan at gmail.com (Christopher Kanan) Date: Fri, 21 Dec 2018 15:31:11 -0500 Subject: Connectionists: Call for Papers and Abstracts for the 2nd Workshop on Shortcomings in Vision and Language (SiVL) at NAACL Message-ID: *Workshop on Shortcomings in Vision and Language (SiVL)*NAACL-HLT 2019, Minneapolis June, 2019 *https://sites.google.com/view/sivl2019/ * *Purpose* The primary purpose of this workshop is to bring together researchers at the intersection of vision and language to discuss shortcomings of modern approaches, tasks, datasets, and evaluation metrics for problems including image and video captioning, visual question answering, visual dialog, activity recognition, image retrieval and referring expressions. By highlighting common shortcomings in these domains, the workshop aims to facilitate discussion of novel research directions and to steer the community towards high-level challenges affecting the vision and language community broadly. *Call for Papers and Abstracts* We call for papers and abstracts exploring shortcomings in current vision and language models covering topics including but not limited to: - Analysis of current vision and language models - Analysis of current tasks and datasets - Novel evaluation metrics - Novel language and vision tasks - Other pertinent work about shortcomings of vision and language Papers must describe substantial, original, completed and unpublished work. Paper submissions must be anonymous and will receive at least two peer-reviews. They may consist of up to eight (8) pages of content, plus unlimited pages for references and must be prepared as specified in the NAACL guidelines (https://naacl2019.org/calls/papers/). Camera-ready versions of accepted papers will be given one additional page of content (up to 9 pages) so that reviewers? comments can be taken into account. All paper submissions will be presented in the Poster Session and a few selected works will also be presented as Spotlight talks. Paper submissions will be published in the ACL Anthology. Abstracts can describe work in progress, work under review, accepted to be published elsewhere or already published work. They may consist of up to two (2) page of content, plus additional pages for references. Abstract submissions are subject to single-blind review to evaluate relevance to the workshop topics. Accepted abstracts will be posted online on the workshop website and will be presented only at the Poster session. Abstracts are not published in the ACL Anthology. Submission Instructions are available on the workshop website. *Important Dates* February 27, 2019: Workshop Paper Due Date March 27, 2019: Notification of Acceptance April 5, 2019: Camera-ready papers due (firm deadline) June 6-7, 2019: Workshop Dates All deadlines are 11:59 PM in UTC -12h timezone. *Invited Speakers:*Yoav Artzi, Cornell Tech Angeliki Lazaridou, DeepMind Margaret Mitchell, Google Research *Organizers*: Raffaella Bernardi, University of Trento Raquel Fernandez, University of Amsterdam Spandana Gella, University of Edinburgh Kushal Kafle, Rochester Institute of Technology Christopher Kanan, Rochester Institute of Technology Stefan Lee, Georgia Institute of Technology Moin Nabi, SAP SE The workshop is sponsored by SAP SE. *Contact Email*: sivl2019 at googlegroups.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From boubchir at ai.univ-paris8.fr Sat Dec 22 03:34:06 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Sat, 22 Dec 2018 09:34:06 +0100 Subject: Connectionists: Special Issue on Recent Advances in Biometrics and its Applications - Electronics journal Message-ID: *Special Issue "Recent Advances in Biometrics and its Applications" - Electronics journal (IF 2.11)* https://www.mdpi.com/journal/electronics/special_issues/biometrics_applications Biometric recognition has become a burgeoning research area due to the industrial and government needs for security and privacy concerns. It has also become a center of focus for many authentication and identification applications in the civil and forensic fields. This Special Issue aims to solicit original research papers, as well as review articles focusing on recent advances in biometrics and its applications. We are inviting original research work covering novel theories, innovative methods, and meaningful applications that can potentially lead to significant advances in biometrics. In addition, the authors of the papers which will be presented at the 3rd International Workshop on "Recent Advances in Biometrics and its Applications" that we are organizing within the framework of the 2019 42nd International Conference on Telecommunications and Signal Processing (TSP) are invited to submit their extended versions to this Special Issue of the Journal Electronics after the conference. Submitted papers should be extended to the size of regular research or review articles, with at least a 50% extension of new results. There are no page limitations for this journal. Topics of interest include, but are not limited to, the following: - Biometrics based authentication and identification; - Physiological and behavioral biometrics (e.g., finger, palm, face, eye, ear, iris, retina, gait, handwriting, voice, etc.); - Biometric feature extraction and matching; - Signal, image, and video processing in biometrics; - Advanced pattern recognition in biometrics; - Machine learning and deep learning in biometrics; - Fusion techniques in biometrics; - Soft biometrics; - Multimodal biometrics; - Security and privacy in biometrics; - Big data challenges in biometrics; - Online biometric systems; - Embedded biometric systems; - Emerging biometrics; - Related applications *Guest Editors* Assoc. Prof. Dr. Larbi Boubchir (larbi.boubchir at ai.univ-paris8.fr) Prof. Dr. Boubaker Daachi (bd at ai.univ-paris8.fr) -- _____________________________________________________ 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 decebalmocanu at gmail.com Sat Dec 22 12:08:09 2018 From: decebalmocanu at gmail.com (Decebal Mocanu) Date: Sat, 22 Dec 2018 18:08:09 +0100 Subject: Connectionists: PhD position - scalable deep learning and generative models for continual learning at TU Eindhoven Message-ID: Dear all, We have an open PhD position on scalable deep learning and generative models for continual learning at Eindhoven University of Technology, the Netherlands. Here are some (possible) starting point references on the topic: 1) "*Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science*", *Nature Communications*, 2018, https://www.nature.com/articles/s41467-018-04316-3; Code: https://github.com/dcmocanu/sparse-evolutionary-artificial-neural-networks 2) "*One-Shot Learning using Mixture of Variational Autoencoders: a Generalization Learning approach*", *AAMAS* 2018, https://arxiv.org/abs/1804.07645 3) "*Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data*"*,* 2016, https://arxiv.org/abs/1610.05555 4) "*Factored four way conditional restricted Boltzmann machines for activity recognition*", *Pattern Recognition Letters*, 2015, https://pure.tue.nl/ws/portalfiles/portal/3945755/45733135134994.pdf For informal inquires please feel free to contact me at d.c.mocanu at tue.nl (please use "PhD position - generative models" in the subject). Working language is English. The PhD student will be an employee of the university and will have a broad package of fringe benefits, e.g. excellent sports facilities, pension scheme, holiday allowance, end year bonus; and he/she may be eligible for 30% ruling. The application procedure (for this vacancy please mention *Position A. EDIC - Deep Learning* in your cover letter), detailed information, deadlines, and 3 other related PhD vacancies from my colleagues (exceptional model mining and predictive analytics for time evolving data) can be found at: https://jobs.tue.nl/en/vacancy/four-phd-positions-in-the-data-mining-group-419202.html Happy holidays and best wishes for 2019, Decebal ==================== Decebal Mocanu, PhD Assistant Professor in Machine Learning and Artificial Intelligence Member of TU/e Young Academy of Engineering Department of Mathematics and Computer Science Eindhoven University of Technology, Netherlands E-mail: d.c.mocanu at tue.nl Web: https://research.tue.nl/en/persons/decebal-c-mocanu/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From dwang at cse.ohio-state.edu Sun Dec 23 15:56:55 2018 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Sun, 23 Dec 2018 15:56:55 -0500 Subject: Connectionists: NEURAL NETWORKS, Jan. 2019 Message-ID: <626d19f3-fac9-2130-c52a-d2f62877ebc1@cse.ohio-state.edu> Neural Networks - Volume 109, January 2019 http://www.journals.elsevier.com/neural-networks Editorial: Breaking out to new highs Kenji Doya, DeLiang Wang Dual vigilance fuzzy adaptive resonance theory Leonardo Enzo Brito da Silva, Islam Elnabarawy, Donald C. Wunsch The importance of recurrent top-down synaptic connections for the anticipation of dynamic emotions Martial Mermillod, Yannick Bourrier, Erwan David, Louise Kauffmann, ... Carole Peyrin Evaluating performance of neural codes in model neural communication networks Chris G. Antonopoulos, Ezequiel Bianco-Martinez, Murilo S. Baptista Roles for globus pallidus externa revealed in a computational model of action selection in the basal ganglia Shreyas M. Suryanarayana, Jeanette Hellgren Kotaleski, Sten Grillner, Kevin N. Gurney Estimation of neuronal dynamics based on sparse modeling Shinya Otsuka, Toshiaki Omori Neighborhood preserving neural network for fault detection Haitao Zhao, Zhihui Lai A fully convolutional two-stream fusion network for interactive image segmentation Yang Hu, Andrea Soltoggio, Russell Lock, Steve Carter Variational inference with Gaussian mixture model and householder flow GuoJun Liu, Yang Liu, MaoZu Guo, Peng Li, MingYu Li Unsupervised feature extraction by low-rank and sparsity preserving embedding Shanhua Zhan, Jigang Wu, Na Han, Jie Wen, Xiaozhao Fang Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks Daniel Tanneberg, Jan Peters, Elmar Rueckert Implicit incremental natural actor critic algorithm Ryo Iwaki, Minoru Asada Fixed-time synchronization of inertial memristor-based neural networks with discrete delay Chuan Chen, Lixiang Li, Haipeng Peng, Yixian Yang A neurodynamic approach to nonlinear optimization problems with affine equality and convex inequality constraints Na Liu, Sitian Qin Passivity analysis of delayed reaction?iffusion memristor-based neural networks Yanyi Cao, Yuting Cao, Shiping Wen, Tingwen Huang, Zhigang Zeng From byronyu at cmu.edu Sun Dec 23 23:21:51 2018 From: byronyu at cmu.edu (Byron Yu) Date: Sun, 23 Dec 2018 23:21:51 -0500 Subject: Connectionists: SAVE THE DATE for SAND9 In-Reply-To: References: Message-ID: The ninth international workshop on Statistical Analysis of Neural Data (SAND9) will take place on May 21-23, 2019, in Pittsburgh, PA. Please mark your calendar. Registration will open in January. More details can be found at the SAND9 website: http://sand.stat.cmu.edu Confirmed keynote speakers and panelists include: Marlene Cohen, University of Pittsburgh Xue Han, Boston University Tim Harris, Janelia Farm Elizabeth Hillman, Columbia Dion Khodagholy, Columbia Dayu Lin, NYU Dan O'Connor, Johns Hopkins University Bijan Persaran, NYU Spencer Smith, University of California, Santa Barbara Nick Steinmetz, University of Washington Jonathan Viventi, Duke The organizers are Zhe (Sage) Chen, Matthew Harrison, Rob Kass, Sri Sarma, Byron Yu. From erhan at atr.jp Mon Dec 24 02:20:21 2018 From: erhan at atr.jp (Erhan Oztop) Date: Mon, 24 Dec 2018 10:20:21 +0300 Subject: Connectionists: Call for papers: IEEE TCDS Special Issue on Continual Unsupervised Sensorimotor Learning In-Reply-To: <55f1e947-abc9-1c4a-a6ee-9e1319575e8b@atr.jp> References: <55f1e947-abc9-1c4a-a6ee-9e1319575e8b@atr.jp> Message-ID: <23079e98-4aed-d813-c98c-94b7c62094d9@atr.jp> Dear Colleagues, We are preparing a special issue in IEEE Transactions on Cognitive and Developmental Systems on "Continual Unsupervised Sensorimotor Learning", and would like to invite you to contribute a research article or a review for the SI. The deadline is set as February 28th, 2019. The scope, aim, submission and other details are given below. URL: http://projects.au.dk/socialrobotics/news-events/show/artikel/special-issue-on-continual-unsupervised-sensorimotor-learning/ 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 https://cis.ieee.org/publications/t-cognitive-and-developmental-systems/tcds-information-for-authors. 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 28th February 2019 ? Paper submission deadline 15th April 2019 ? Notification for authors 16th June 2019 ? Deadline revised papers submission 16th July 2019 ? Final notification for authors 18th August 2019 ? Deadline for camera-ready versions September 2019 ? Expected publication date 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, France nguyensmai at gmail.com Erhan Oztop Ozye?in University, Turkey erhan.oztop at ozyegin.edu.tr Junpei Zhong National Institute of Advanced Industrial Science and Technology (AIST), Japan joni.zhong at aist.go.jp With my best wishes, Erhan -- Erhan Oztop, PhD ATR external collaborator and Computer Science Dept. Ozyegin University, Istanbul, Turkey erhan.oztop at ozyegin.edu.tr, phone: +90 216 5649392 From taislee at andrew.cmu.edu Tue Dec 25 12:30:05 2018 From: taislee at andrew.cmu.edu (Tai-Sing Lee) Date: Tue, 25 Dec 2018 12:30:05 -0500 Subject: Connectionists: Carnegie Mellon - University of Pittsburgh Joint Summer Undergraduate Program in Computational Neuroscience References: Message-ID: <96994DD2-14EF-4B9A-882F-6D8FBBE972B5@andrew.cmu.edu> Carnegie Mellon - University of Pittsburgh Joint Summer Undergraduate Program in Computational Neuroscience Undergraduates interested in receiving research training in computational neuroscience are encouraged to apply to an NIH-sponsored summer program at the Center for the Neural Basis of Cognition (CNBC) in Pittsburgh, PA. The CNBC is a joint interdisciplinary program of Carnegie Mellon University and the University of Pittsburgh. Starting in late May each year, a select group of talented undergraduates will embark on a 10-week residential program that provides intensive, mentored research experiences in computational and theoretical neuroscience. Admitted students will receive a stipend and university dormitory housing. The core of the program is the opportunity to carry out an individual mentored research project working closely with a faculty mentor. Other aspects of the scientific program include: faculty research talks, student presentations and discussion of articles from the scientific literature, presentations on career options and scientific ethics, and a concluding symposium in which students present their research. This program is intended for students who wish to pursue a Ph.D. after graduation. Any undergraduate may apply, but we are especially interested in attracting students with strong quantitative backgrounds. Many of our trainees are from colleges and universities that do not have extensive research programs, but all must be United States citizens or permanent residents, must be enrolled at a 4-year accredited institution, and must be in their sophomore or junior year at the time of application. CNBC is dedicated to creating an inclusive and welcoming environment for all students and we encourage applications from women, under-represented minorities, and individuals with disabilities. Additional information and the application can be found here , a showcase of scheduled speakers for each of the summer uPNC 2018 and summer uPNC 2017 mentored research is also available. Application Receipt Deadline: February 15, 2019 Please encourage your computationally oriented undergraduates to apply! _________________________________________________________ Linda Moya, Ph.D. Electrical and Computer Engineering, and Social and Decision Sciences Center for the Neural Basis of Cognition Carnegie Mellon University Pittsburgh, PA 15213 -------------- next part -------------- An HTML attachment was scrubbed... URL: From amir.aly at em.ci.ritsumei.ac.jp Wed Dec 26 08:59:41 2018 From: amir.aly at em.ci.ritsumei.ac.jp (Amir Aly) Date: Wed, 26 Dec 2018 22:59:41 +0900 Subject: Connectionists: SoAIR 2019 [Extended Deadline]: JST-CREST / IEEE-RAS Spring School on "Social and Artificial Intelligence for User-Friendly Robots" in Japan Message-ID: CALL FOR APPLICATIONS **Apologies for cross posting ** We are pleased to call for applications for the *JST-CREST / IEEE-RAS* spring school on: "*Social and Artificial Intelligence for User-Friendly Robots*" * Which will be held from 17-24 March, 2019 in Shonan Village, Japan *after the *Human-Robot Interaction (HRI)* conference that will be held in the near South Korea. *Webpage: **https://inic8.bitbucket.io/SoAIR19/* *I. Aim and Scope *Autonomous and intelligent systems are progressively moving into spaces, which have previously been predominantly shaped by human agency. Unlike in the past where machines obediently served their human operators, machines now increasingly act without the intervention of a human. Artificial intelligence is meeting new challenges in the world, though human-like intelligence may still be a distant goal. Robots in factories are coming out of their cages. Autonomous cars are being tested on streets with regular human-driven cars. The private household is changing with the appearance of not only robotic vacuum cleaners, but also with the first-generation of social robots and smart devices. The challenges that face both the robotics and artificial intelligence communities are how the necessary intelligence for such new environments can be created as well as how to make artificial agents capable of not only solving tasks at hand but also considering social environments around them during interaction with human users so as to behave appropriately. Within the school, we plan to address the tension created by the balance between task-specific artificial intelligence and the demands of sociability required to function effectively in human-centered environments. ** *Who should apply?* We invite *Masters and PhD students* as well as *post-doctoral candidates and researchers from industry* with relevant research background to apply for this spring school. *Additional support could be available based on eligibility.* ** *This spring school is a Technical Education Program (TEP) endorsed and supported by JST-CREST / IEEE-RAS*. ** *The school aims at bridging the gap between social and cognitive Human-Robot Interaction (HRI), Artificial Intelligence (AI), and Autonomous Vehicles (AV) through high level talks, tutorials, and hands-on workshops (the program will be announced soon).* *II. Keynote Speakers: * 1. * Takayuki Nagai, *Osaka University, Japan 2. * Jun Tani *? Okinawa Institute of Science and Technology (OIST), Japan 3. *Daniele Magazzeni *? King's College London, UK 4. * Yukie Nagai *? National Institute of Information and Communications Technology (NICT), Japan 5. * Tetsuya Ogata* ? Waseda University, Japan 6. *Mohamed Chetouani *? University of Pierre and Marie Curie (UPMC), France 7. *Silvia Rossi* ? University of Naples, Italy 8. *Agnieszka Wykowska *? Italian Institute of Technology (IIT), Italy 9. *Tetsunari Inamura *? National Institute of Informatics (NII), Japan 10. *Amit Kumar Pandey *? SoftBank (Aldebaran) Robotics, France 11. *Mehul Bhatt* ? Orebro University, Sweden (Tutorial) 12. *Mohsen Kaboli ?* Bavarian Motor Works (BMW), Germany (Tutorial) 13. *Francesco Maurelli *? Jacobs University, Germany (Preparing Marie Curie funding proposal) 14. *Atsuko Nakatsuka* ? Japan Society for the Promotion of Science (JSPS), Japan (Preparing JSPS funding proposal) *III. Submission * The applications must include the following files (combined into one file). No other documents would be necessary (More information is available on the school's webpage). 1. *Curriculum vitae*: A CV detailing relevant aspects of the candidate's academic career that demonstrates her/his relevance to the school theme. Please consider including the list of publications. 2. *Research abstract*: A 200-word research abstract that the candidate intends to present during the school. 3. *Letter of recommendation*: A brief letter from the academic advisor or the employer of the candidate supporting her/his application. Please also indicate if additional support would be required to attend the school. *Application submission*: Please use the following EasyChair web link:* Application Submission .* *IV. Important Dates * 1. Application submission *[Extended]*: *10-January, 2019 * 2. Notification of acceptance: *14-January, 2019 * 3. Spring School: *17-24 March, 2019* *V. Organizers * 1. *Amir Aly *? Ritsumeikan University ? Japan 2. *Franziska Kirstein *? Blue Ocean Robotics, Denmark 3. * Shashank Pathak *? Visteon Corporation, Germany --------------------- *Amir Aly, Ph.D.* Senior Researcher Emergent Systems Laboratory College of Information Science and Engineering Ritsumeikan University 1-1-1 Noji Higashi, Kusatsu, Shiga 525-8577 Japan -------------- next part -------------- An HTML attachment was scrubbed... URL: From jiankliu at gmail.com Wed Dec 26 12:10:02 2018 From: jiankliu at gmail.com (Jian Liu) Date: Wed, 26 Dec 2018 17:10:02 +0000 Subject: Connectionists: PhD Studentships in Systems/Computational Neuroscience Message-ID: PhD Studentships in Systems/Computational Neuroscience Centre for Systems Neuroscience at the University of Leicester, UK. www.le.ac.uk/csn A number of PhD studentships are available in a wide range of research topics. Please find the details of all the projects below. The deadlines are different. Please contact the PIs on the list, or Dr. Jian K. Liu directly: Project: Neural mechanisms of memory formation, consolidation and recall PI: Prof R Quian Quiroga https://www.findaphd.com/phds/project/neural-mechanisms-of-memory-formation-consolidation-and-recall/?p104074 Project: Towards a Functional Model for Associative Learning and Memory Formation PI: Dr Jian K. Liu, Prof Rodrigo Quian Quiroga https://www.findaphd.com/phds/project/towards-a-functional-model-for-associative-learning-and-memory-formation/?p105552 Project: Dynamics of a minimal neuronal network with multisynaptic dendrites PI: Dr Jian K. Liu, Dr. V Marra https://www.findaphd.com/phds/project/dynamics-of-a-minimal-neuronal-network-with-multisynaptic-dendrites/?p104048 Project: Interpretation of social behaviours among mice with Parkinson?s disease PI: Dr. H Zhou, Dr Jian K. Liu https://www.findaphd.com/phds/project/interpretation-of-social-behaviours-among-mice-with-parkinson-s-disease/?p104799 Project: Serotonergic modulation of functional connectivity in cortical microcircuits PI: Dr M Okun, Prof Rodrigo Quian Quiroga https://www.findaphd.com/phds/project/serotonergic-modulation-of-functional-connectivity-in-cortical-microcircuits/?p105561 -- ************************************************************************** Jian K. Liu, Ph.D. Mathematics Centre for Systems Neuroscience Department of Neuroscience, Psychology and Behaviour University of Leicester, Leicester, UK Phone: +44 (0)116 373-6860 email: jian.liu at leicester.ac.uk Webpage: https://sites.google.com/site/jiankliu ************************************************************************** Virus-free. www.avg.com <#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2> -------------- next part -------------- An HTML attachment was scrubbed... URL: From D.hupkes at uva.nl Fri Dec 28 04:25:49 2018 From: D.hupkes at uva.nl (Dieuwke Hupkes) Date: Fri, 28 Dec 2018 10:25:49 +0100 Subject: Connectionists: BlackboxNLP 2019 - Call For Papers In-Reply-To: References: Message-ID: BlackboxNLP 2019: Analyzing and interpreting neural networks for NLP -- ACL 2019 Workshop ACL, Florence, Italy Conference website: http://www.acl2019.org Workshop website: https://blackboxnlp.github.io/ Submission deadline: April 19 ====================================================== Neural networks have rapidly become a central component in NLP systems in the last few years. The improvement in accuracy and performance brought by the introduction of neural networks has typically come at the cost of our understanding of the system: How do we assess what the representations and computations are that the network learns? The goal of this workshop is to bring together people who are attempting to peek inside the neural network black box, taking inspiration from machine learning, psychology, linguistics, and neuroscience. The topics of the workshop will include, but are not limited to: - Applying analysis techniques from neuroscience to analyze high-dimensional vector representations (such as Haxby et al., 2001; Kriegeskorte, 2008) in artificial neural networks; - Analyzing the network's response to strategically chosen inputs in order to infer the linguistic generalizations that the network has acquired (e.g., Linzen et al., 2016; Loula et al., 2018); - Examining the performance of the network on simplified or formal languages (e.g., Hupkes et al., 2018; Lake et al., 2018); - Proposing modifications to neural network architectures that can make them more interpretable (e.g., Palanki et al., 2017); - Scaling up neural network analysis techniques developed in the connectionist literature in the 1990s (Elman, 1991); - Testing whether interpretable information can be decoded from intermediate representations (e.g., Adi et al., 2017; Chrupa?a et al., 2017; Hupkes et al., 2017); - Translating insights on neural networks interpretation from the vision domain (e.g., Zeiler & Fergus, 2014) to language; - Explaining model predictions (e.g., Lei et al., 2016; Alvarez-Melis & Jaakkola, 2017): What are ways to explain specific decisions made by neural networks? - Adversarial examples in NLP (e.g., Ebrahimi et al., 2018; Belinkov & Bisk, 2018): How to generate them and how to evaluate their quality? - Open-source tools for analyzing neural networks in NLP (e.g., Strobelt et al., 2018; Rikters, 2018). - Evaluation of analysis results: How do we know that the analysis is valid? BlackboxNLP 2019 is the second BlackboxNLP workshop. The programme and proceedings of the previous edition, which was held at EMNLP 2018, can be found here: https://blackboxnlp.github.io/2018/. ====================================================== We call for two types of papers: - Archival papers. These are papers reporting on completed, original and unpublished research, with maximum length of 8 pages + references. Papers shorter than this maximum are also welcome. Accepted papers are expected to be presented at the workshop and will be published in the workshop proceedings. They should report on obtained results rather than intended work. These papers will undergo double-blind peer-review, and should thus be anonymized. - Extended abstracts. These may report on work in progress or may be cross submissions that have already appeared in a non-NLP venue. The extended abstracts are of maximum 2 pages + references. These submissions are non-archival in order to allow submission to another venue. The selection will not be based on a double-blind review and thus submissions of this type need not be anonymized. Submission information: - Submissions should follow the official ACL 2019 style guidelines. - Submissions should be made through the Sonftconf START system: https://www.softconf.com/acl2019/blackboxnlp. ====================================================== Important dates: April 19 - Submission deadline May 17 - Notification of acceptance June 3 - Camera ready deadline August 1 - Workshop Note: All deadlines are 11:59PM UTC-12:00 ("anywhere on Earth"). ====================================================== -------------- next part -------------- An HTML attachment was scrubbed... URL: From gustau.camps at uv.es Fri Dec 28 04:36:16 2018 From: gustau.camps at uv.es (Gustau Camps-Valls) Date: Fri, 28 Dec 2018 10:36:16 +0100 Subject: Connectionists: Post-doc position in Causal Inference for Geosciences [ERC project] Message-ID: --------------------------------------------------------------------------- Post-doc position in Causal Inference for Geosciences [ERC project] --------------------------------------------------------------------------- We are looking for outstanding postdoc candidates with a strong interest in machine learning and geosciences to cover a post-doc position in the Image and Signal Processing (ISP) group in the Universitat de Valencia, Spain, http://isp.uv.es. The position is fully funded by an ERC Consolidator Grant 2015-2020 entitled "Statistical Learning for Earth Observation Data Analysis" (SEDAL), http://isp.uv.es/sedal.html, under the direction of Prof. Gustau Camps-Valls. *** The project and job description This particular position is focused on learning causal models to explain complex interactions in essential climate variables and remote sensing observations, and discover hidden essential drivers and confounding factors in Climate/Geo Sciences applications. *** Who Highly motivated researchers with a PhD degree in computer science, statistics, machine learning, electrical engineering, physics, or mathematics are encouraged to apply. All candidates should have a solid understanding and knowledge of machine learning and statistics, and being particularly interested in remote sensing and/or geoscience problems. Good programming skills (Matlab/Python/R/C++), a critical and organized sense for data analysis, as well as commitment, strong communication, presentation and writing skills are a big plus. *** Application details - Deadline: Send your application as soon as possible. Positions will be filled as soon as we have the right candidate! - How? Send me: 2-pages CV, and a list of your 3 most representative papers - Who: PhD in maths, physics, machine learning, or related disciplines. Also, we care about the gender issue! - How long? 1+1 years contract - How much? Salary according to UV scales including social security, health insurance benefits, and travel money - Where? Valencia, Spain, Mediterranean city, nice weather, hike and beach. Excellent cost-of-living index = 55 ------------------------------------------- Prof. Gustau Camps-Valls Image Processing Laboratory (IPL) Universitat de Val?ncia Tlf: +34 963 544 064 http://isp.uv.es ------------------------------------------- From boubchir at ai.univ-paris8.fr Sat Dec 29 03:36:09 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Sat, 29 Dec 2018 09:36:09 +0100 Subject: Connectionists: Special Issue "Machine Learning for EEG Signal Processing (MLESP 2018)" In-Reply-To: <0984b094-ce45-d9da-0b9f-6a29b68c8f2e@ai.univ-paris8.fr> References: <0984b094-ce45-d9da-0b9f-6a29b68c8f2e@ai.univ-paris8.fr> Message-ID: <04420922-4cd4-3964-e91a-075ff4870ca0@ai.univ-paris8.fr> *********************************************************************** Apologize if you receive multiple copies of this message. Please disseminate this CFP to your colleagues and contacts. *********************************************************************** *Special Issue "Machine Learning for EEG Signal Processing (MLESP 2018)"* https://www.mdpi.com/journal/computers/special_issues/MLESP_2018 The 1^st International Workshop on Machine Learning for EEG Signal Processing (MLESP 2018) will be held in Madrid, Spain, 3?6 December, 2018. The aim of this workshop is to present and discuss the recent advances in machine learning for EEG signal analysis and processing. For more information about the workshop, please use this link:https://mlesp2018.sciencesconf.org/ Selected papers which presented at the workshop are invited to submit their extended versions to this Special Issue of the journal /Computers/ after the conference. Submitted papers should be extended to the size of regular research or review articles, with at least 40% extension of new results. All submitted papers will undergo our standard peer-review procedure. Accepted papers will be published in open access format in /Computers/ and collected together in this Special Issue website. There are no page limitations for this journal. We are also inviting original research work covering novel theories, innovative methods, and meaningful applications that can potentially lead to significant advances in EEG data analytics. The main topics include, but are 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 Dr. Larbi Boubchir /Guest Editor/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From Johan.Suykens at esat.kuleuven.be Mon Dec 31 09:43:16 2018 From: Johan.Suykens at esat.kuleuven.be (Johan Suykens) Date: Mon, 31 Dec 2018 15:43:16 +0100 Subject: Connectionists: European Commission draft ethics guidelines for trustworthy artificial intelligence In-Reply-To: <0aa39aefc37e9fc5994ce1331de14610@esat.kuleuven.be> References: <3F54F57C-8D5C-453B-A0E2-D6161B4FC8AB@fct.unl.pt> <717B436F-E9B7-434B-86B3-1D55AD9330F2@gmail.com> <7e709145-b07a-c142-55ed-2775f4c16430@esat.kuleuven.be> <0aa39aefc37e9fc5994ce1331de14610@esat.kuleuven.be> Message-ID: Dear all, Please consider giving input and feedback on the draft ethics guidelines for trustworthy artificial intelligence. All information is provided below in the message of Nathalie Smuha. Best regards, Johan Suykens ------------------------------------ The European Commission's High-Level Expert Group on AI (AI HLEG) published a draft of its AI Ethics Guidelines (see press release with information here ) The AI HLEG was established by the European Commission in June 2018 to support the implementation of its Strategy on Artificial Intelligence and to prepare two deliverables: (1) AI Ethics Guidelines and (2) Policy and Investment Recommendations. The draft Guidelines are now open for consultation between 18 December and 18 January. All stakeholders are invited to comment on or contribute to the individual sections of the draft, as well as to provide general feedback through the following consultation form . The AI HLEG also published a Definition on artificial intelligence which accompanies its deliverable. Following the consultation, the AI HLEG will finalise the Guidelines, which it aims to present to the Commission in March 2019. For more information about the High-Level Expert Group on AI, click here . For more information on the European AI Alliance, click here . If you wish to participate in the further discussion on Artificial Intelligence in Europe, please follow the two-step-registration process: 1. Join Futurium 2. Become a member of the European AI Alliance. *Nathalie Smuha* Assistant Lecturer & PhD Fellow *Faculty of Law* Tiensestraat 41 3000 Leuven tel. +32 16 19 31 37 From april.robocup at gmail.com Mon Dec 31 14:48:50 2018 From: april.robocup at gmail.com (April Foster) Date: Mon, 31 Dec 2018 14:48:50 -0500 Subject: Connectionists: RoboCup Visiting Fellows Program - Call for Applications - Due Feb. 15 In-Reply-To: References: Message-ID: RoboCup Visiting Fellows Program - Call for Applications - Due Feb. 15 ====================================================================== Ever since 1997, The RoboCup Federation has been holding annual international research competitions and symposia in an effort to push the state of the art in robotics, artificial intelligence, and related fields. The community remains healthy and vibrant, with students, postdocs, professors, and industry professionals meeting each year to compete and share their knowledge in a wide range of research competitions. Based on the beliefs that 1) RoboCup is a unique and special community and venue within the research community, and 2) that the only way to fully appreciate what it has to offer is to experience it firsthand, the RCF is pleased to announce a new RoboCup Visiting Fellows program. Successful applicants will receive: - full travel support for two people from your home institution and free registration to the 2019 international RoboCup Sydney, Australia July 3-8, 2019 as an honored guest and observer. - up to an additional $10k USD in reimbursements of start-up expenses needed to start a new team for entry in 2020 and/or 2021 RoboCup events. - detailed, behind-the-scenes education about how the RoboCup community works, including meetings with current organizers and participants. The ideal applicants will be: - a pair of University faculty and a Ph.D. student or postdoc who have never participated in RoboCup, and are interested in learning about and becoming a part of the community. Application Requirements: - please send your CVs and a 2-page statement of interest that includes research interests, how RoboCup could support those interests, and possible RoboCup league(s) of interest. - a statement detailing what exposure the applicants have had to RoboCup in the past, if any, as well as a statement of commitment to attend RoboCup in Sydney for 6 days, from July 3rd-8th. We particularly encourage applications from people from underrepresented groups within the RoboCup community based on gender, ethnicity, or geography. Submission Details: - please send your application materials by February 15th to april.robocup at gmail.com Requirements: - In addition to attending RoboCup 2019, RoboCup Visiting Fellows will be asked to submit a report within a month after the event summarizing their overall impressions as well as a proposed budget of up to $10k for startup costs of a new team. We look forward to receiving your applications! Sincerely, The RoboCup Federation Visiting Fellows Committee Minoru Asada Pedro Lima Peter Stone Rong Xiong -------------- next part -------------- An HTML attachment was scrubbed... URL: From pascualm at key.uzh.ch Sun Dec 30 22:06:56 2018 From: pascualm at key.uzh.ch (pascualm at key.uzh.ch) Date: Mon, 31 Dec 2018 12:06:56 +0900 Subject: Connectionists: Measuring Granger-causal effects in multivariate time series by system editing Message-ID: Dear Colleagues, The preprint entitled "Measuring Granger-causal effects in multivariate time series by system editing" is available at bioRxiv https://doi.org/10.1101/504068 and includes supplementary material for the sake of reproducible research: program codes (PASCAL), executable file, & toy data in human readable format. The abstract can be found below. Cordially, Roberto ... Roberto D. Pascual-Marqui, PhD, PD The KEY Institute for Brain-Mind Research, University of Zurich Visiting Professor at Neuropsychiatry, Kansai Medical University, Osaka [https://www.uzh.ch/keyinst/loreta] [https://scholar.google.com/citations?user=pascualmarqui] ... Abstract: What is the role of each node in a system of many interconnected nodes? This can be quantified by comparing the dynamics of the nodes in the intact system, with their modified dynamics in the edited system, where one node is deleted. In detail, the spectra are calculated from a causal multivariate autoregressive model for the intact system. Next, without re-estimation, one node is deleted from the model and the modified spectra at all other nodes are re-calculated. The change in spectra from the edited system to the intact system quantifies the role of the deleted node, giving a measure of its Granger-causal effects (CFX) on the system. A generalization of this novel measure is available for networks (i.e. for groups of nodes), which quantifies the role of each network in a system of many networks. For the sake of reproducible research, program codes (PASCAL), executable file, and toy data in human readable format are included in the supplementary material.