From axel.soto at cs.uns.edu.ar Thu Nov 1 10:57:16 2018 From: axel.soto at cs.uns.edu.ar (Axel Soto) Date: Thu, 01 Nov 2018 11:57:16 -0300 Subject: Connectionists: IUI 2019 Student Consortium Call for Papers Message-ID: IUI 2019 Student Consortium Call for Papers Overview The IUI 2019 Student Consortium is intended to provide an opportunity for Doctoral and advanced Masters students to present and receive feedback about their research in an interdisciplinary workshop, under the guidance of a panel of mentors selected from senior people in the field. We invite students who feel they would benefit from this kind of feedback on their research to use this unique opportunity to share their work with students in a similar situation as well as senior researchers in the field. The consortium will be organized with 8 to 12 presentations by the students, whose applications have been selected by the Student Consortium chairs and potentially other reviewers. The strongest candidates will be those who have a clear topic and research approach, and have made some progress, but who are not so far along in their research that they can no longer make changes. The final version of accepted SC submissions will be included in the main conference proceedings published in the ACM DL. Complimentary/reduced conference registration will be available for students. Student Consortium participants will also be given high priority when applying for the student travel awards. Moreover, we are working to provide partial reimbursement of travel/accommodation expenses specifically for the participants of the Student Consortium. More information will come soon. Objectives The objectives of the student consortium are to: 1- Serve as a supportive setting to provide/receive feedback on students' current doctoral and masters' research and guidance on future research directions 2- Offer each student comments and fresh perspectives on their work from researchers and students outside of their own institution 3- Promote the development of a supportive community of scholars and a spirit of collaborative research 4- Contribute to the conference goals through interaction with other researchers and conference events Submission Instructions To apply for the Student Consortium, please submit to the URL below a single PDF containing the following (in order): 1- A brief cover letter containing your full name, contact details, affiliation, web page, expected graduation date and target degree, the name of your thesis advisor, gender (optional), home country (optional), and whether you are a member of an underrepresented minority group (optional) - one page maximum. 2- Your SC submission: a document describing your thesis/dissertation research plan and your progress thus far and should be no more than two pages long, including references. Key points the submission should include: Motivation for your dissertation research, goal and research questions, related work that frames your research, methods/approach to reach the goal, results if any, and next steps for your research. 3- Submissions should follow the standard SigCHI format, using one of the following templates: - Microsoft Word Template for Papers - LaTeX Template for Papers - PDF Example for Papers 4- Your CV (maximum two pages). Submit your single PDF (containing cover letter and SC submission) to https://new.precisionconference.com by November 9th, 2018. In addition, a letter of recommendation from your thesis or doctoral advisor should be sent separately by email to the Student Consortium co-Chairs at sc-iui2019 at acm.org. Student Consortium Chairs Andrea Kleinsmith, the University of Maryland, Baltimore County, USA Tsvi Kuflik, the University of Haifa, Israel Ilaria Torre, the University of Genova, Italy Contact: sc-iui2019 at acm.org From m.plumbley at surrey.ac.uk Thu Nov 1 12:01:11 2018 From: m.plumbley at surrey.ac.uk (m.plumbley at surrey.ac.uk) Date: Thu, 1 Nov 2018 16:01:11 +0000 Subject: Connectionists: Making Sense of Sounds Data Challenge: Deadline extended to 5 Nov 2018 Message-ID: Dear Connectionists, Following a number of requests during this busy period, the submission deadline for the "Making Sense of Sounds" (MSoS) Data Challenge has been extended: ** Submission deadline (Extended): 5 November 2018 ** For more information about the challenge and how to submit, see: http://cvssp.org/projects/making_sense_of_sounds/site/challenge/ Important dates: * Submission deadline: ** 5 Nov 2018 (Extended) ** * Results announced: 19/20 Nov 2018 (at DCASE 2018 Workshop) The MSoS Challenge is jointly organized by University of Salford and University of Surrey. Contact: MSoS.challenge at gmail.com We look forward to your submission! Mark Plumbley On behalf of the MSoS Challenge organisers -- Prof Mark D Plumbley Professor of Signal Processing Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, Guildford, Surrey, GU2 7XH, UK Email: m.plumbley at surrey.ac.uk =================================================================================== DCASE 2018 Workshop on Detection and Classification of Acoustic Scenes and Events 19 - 20 November 2018, Surrey, UK http://dcase.community/workshop2018/ =================================================================================== From pascualm at key.uzh.ch Thu Nov 1 22:05:16 2018 From: pascualm at key.uzh.ch (pascualm at key.uzh.ch) Date: Fri, 2 Nov 2018 11:05:16 +0900 Subject: Connectionists: Comparison of measures of electrophysiological connectivity Message-ID: Dear Colleagues, The preprint entitled: "A comparison of bivariate frequency domain measures of electrophysiological connectivity" at: https://doi.org/10.1101/459503 might be of interest to those performing research related to electrophysiological connectivity inference. 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] [scholar.google.com/citations?user=pascualmarqui] ... Abstract: The problem of interest here concerns electrophysiological signals from two cortical sites, acquired as invasive intracranial recordings, or from non-invasive estimates of cortical electric neuronal activity computed from EEG or MEG recordings (see e.g. https://doi.org/10.1101/269753). In the absence of other sources, these measured signals consist of an instantaneous linear mixture of the true, actual, unobserved local signals, due to low spatial resolution and volume conduction. A connectivity measure is unreliable as a true indicator of electrophysiological connectivity if it is not invariant to mixing, or if it reports a significant connection for a mixture of independent signals. In (Vinck et al 2011 Neuroimage 55:1548) it was shown that coherence, imaginary coherence, and phase locking value are not invariant to mixing, while the phase lag index (PLI) and the weighted version (wPLI) are invariant to mixing. Here we show that the lagged coherence (LagCoh) measure (2007, https://arxiv.org/abs/0711.1455), not studied in Vinck et al, is invariant to mixing. Additionally, we present here a new mixture-invariant connectivity statistic: the "standardized imaginary covariance" (sImCov). We also include in the comparisons the directed PLI (dPLI) by Stam et al (2012 Neuroimage 62:1415). Fourier coefficients for "N" trials are generated from a linear unidirectional causal time domain model with electrophysiological delay "k" and regression coefficient "b". 1000 random data sets of "N" trials are simulated, and for each one, and for each connectivity measure, non-parametric randomization tests are performed. The "true positive detection rate" is calculated as the fraction of 1000 cases that have significant connectivity at p<0.05, 0.1, and 0.2. The connectivity methods were compared in terms of detection rates, under non-mixed and mixed conditions, for small and large sample sizes "N", with and without jitter, and for different values of signal to noise. Under mixing, the results show that LagCoh outperforms wPLI, PLI, dPLI, and sImCov. Without mixing, LagCoh and sImCov outperform wPLI, PLI, and dPLI. Finally, it is shown that dPLI is an invalid estimator of flow direction, i.e. it reverses and "goes against the flow" by merely changing the sign of one of the time series, a fact that violates the basic definition of Granger causality. From luca.oneto at unige.it Fri Nov 2 02:35:34 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Fri, 2 Nov 2018 07:35:34 +0100 Subject: Connectionists: ESANN 2019 SS - Last CFP - Societal Issues in Machine Learning: When Learning from Data is Not Enough Message-ID: [Apologies if you receive multiple copies of this CFP] Call for papers: special session on "Societal Issues in Machine Learning: When Learning from Data is Not Enough" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019). 24-26 April 2019, Bruges, Belgium - http://www.esann.org DESCRIPTION: It has been argued that Artificial Intelligence (AI) is experiencing a fast process of commodification. This characterization is on the interest of big IT companies, but it correctly reflects the current industrialization of AI. This phenomenon means that AI systems and products are reaching the society at large and, therefore, that societal issues related to the use of AI and Machine Learning (ML) cannot be ignored any longer. Designing ML models from this human-centered perspective means incorporating human-relevant requirements such as safety, fairness, privacy, and interpretability, but also considering broad societal issues such as ethics and legislation. These are essential aspects to foster the acceptance of ML-based technologies, as well as to be able to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. This special session aims to put forward the state-of-the-art on these increasingly relevant topics among ML theoretician and practitioners. For this purpose, we welcome both solid contributions and preliminary relevant results showing the potential, the limitations and the challenges of new ideas, refinements, or contaminations between the different fields of research, ML, and related approaches in facing real-world problems involving societal issues. We welcome works on ML theory, applications to topics listed below as well as other topics of social relevance. Studies stemming from major research initiatives and projects focusing on the session topics are particularly welcome. TOPICS OF INTEREST: - Fairness as an element in the development of ML techniques; - Ethical issues in the application of ML and related techniques in areas of social impact; - Privacy as a challenge in ML application to problems in the social domain; - Interpretability and explainability of ML and related approaches; - Safety and Security of ML and related methods in safety critical contexts; - Legislative challenges to the use of ML and related methods; - The challenge of complex data for ML and related methods; - Transparency and open data. SUBMISSION: Prospective authors must submit their paper through the ESANN portal following the instructions provided in https://www.elen.ucl.ac.be/esann/index.php?pg=submission Each paper will undergo a peer reviewing process for its acceptance. Authors should send as soon as possible an e-mail with the tentative title of their contribution to the special session organisers. IMPORTANT DATES: Submission of papers: 19 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Davide Bacciu, University of Pisa (Italy) Battista Biggio, University of Cagliari (Italy) Jos? D. Mart?n, Universitat de Val?ncia (Spain) Luca Oneto, University of Genoa (Italy) Alfredo Vellido, Universitat Polit?cnica de Catalunya (Spain) Paulo J. G. Lisboa, Liverpool John Moores University (UK) ----------------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: Luca.Oneto at unige.it SmartLab Laboratory e-mail: Luca.Oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145 Genoa ITALY Phone: +39-010-3532192 www.smartlab.ws ----------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From ohad.kammar at gmail.com Fri Nov 2 19:12:42 2018 From: ohad.kammar at gmail.com (Ohad Kammar) Date: Fri, 2 Nov 2018 23:12:42 +0000 Subject: Connectionists: LAFI 2019: DEADLINE EXTENSION Languages for Inference In-Reply-To: References: <92509085-e287-4b9c-92e1-6e7a22ad5dfd@googlegroups.com> Message-ID: tl;dr: LAFI submission deadline Tue 6 Nov 2018 (EXTENDED) or earlier! 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) ------------------------------------------------- LAFI submission deadline Tue 6 Nov 2018 (EXTENDED) Notification Mon 3 Dec 2018 Early Registration Deadline Thu 10 Dec 2018 Workshop Tue 15 Jan 2019 ------------------------------------------------- Submission: https://lafi19.hotcrp.com/ Registration: https://popl19.sigplan.org/attending/Registration 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. For a sense of the talks, posters, and blogs in past years, see + PPS-2018: http://conf.researchr.org/track/POPL-2018/pps-2018 blog: http://pps2018.soic.indiana.edu/ + PPS-2017: http://conf.researchr.org/track/POPL-2017/pps-2017 blog: http://pps2017.soic.indiana.edu/) + PPS-2016: http://conf.researchr.org/track/POPL-2016/pps-2016 blog: http://pps2016.soic.indiana.edu/) 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, and we expect to spend only a portion of the workshop day on traditional research talks. 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. Submission guidelines ===================== Extended abstracts are up to 2 pages in PDF format, excluding references. Please submit them by November 6(AoE) using HotCRP at: https://lafi19.hotcrp.com/ 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 angelo.cangelosi at manchester.ac.uk Sat Nov 3 10:28:59 2018 From: angelo.cangelosi at manchester.ac.uk (Angelo Cangelosi) Date: Sat, 3 Nov 2018 14:28:59 +0000 Subject: Connectionists: Research Fellowships (tenure post) in Robotics and/or Machine Learning, University of Manchester UK Message-ID: University of Manchester, UK, Dame Kathleen Ollerenshaw Fellowships Robotics and Machine Learning The University of Manchester, UK, has 8 Dame Kathleen Ollerenshaw Fellowships in the Faculty of Science and Engineering. The fields of robotics and machine learning are amongst the areas of investment of the Faculty. As such, we strongly encourage applicants with expertise in these disciplines, such as in the topics of: - Cognitive robotics - Neuro-robotics and neuromorphic application to robots - Human-Robot Interaction - Social robots for education and/or health and social care - Soft and bio-mimetic robotics - Machine learning - Deep learning - Computational neuroscience These posts consist of an initial 5-year research fellowship to focus primarily on research, leading to full academic tenure on completion, subject to performance and probation. If you are interested in this post, please contact angelo.cangelosi at manchester.ac.uk Application deadline is 23 November 2018. To apply for these posts, go to: https://www.jobs.manchester.ac.uk/displayjob.aspx?jobid=16284 -------------- next part -------------- An HTML attachment was scrubbed... URL: From sylvain.calinon at gmail.com Sun Nov 4 00:36:33 2018 From: sylvain.calinon at gmail.com (Sylvain Calinon) Date: Sun, 4 Nov 2018 05:36:33 +0100 Subject: Connectionists: [jobs] Idiap/EPFL (Switzerland): PhD and Postdoc positions in robot learning from demonstration and manipulation skills transfer Message-ID: <0c1e48bf-03a0-99bc-526d-2293df2ffe6f@gmail.com> Dear Colleagues, Two PhD positions and one Postdoc position in robot learning from demonstration and manipulation skills transfer are currently open in the Robot Learning & Interaction group at the Idiap Research Institute in Switzerland. For more information: http://calinon.ch/open-positions.htm Best regards, Sylvain -- Dr Sylvain Calinon, Idiap Research Institute, Martigny, Switzerland http://calinon.ch From demian.battaglia at univ-amu.fr Sun Nov 4 01:15:41 2018 From: demian.battaglia at univ-amu.fr (BATTAGLIA Demian) Date: Sun, 4 Nov 2018 06:15:41 +0000 Subject: Connectionists: Postdoc at Aix-Marseille University in computational modelling of basal-ganglia-cortico-cerebellar circuits Message-ID: Applications are invited for a: POSTDOCTORAL POSITION at Aix-Marseille University (southern France) under the joint mentoring of Dr. Demian Battaglia (Institute for Systems Neuroscience - INS) and Dr. Nicole Malfait (Institut de Neurosciences de la Timone - INT). This two-years position is funded by the project ANR (Agence National de la Recherche) ?SENCE - Movement disorders in Parkinson?s disease: The role of somatoSENsory deficits and CErebellar anomalies?, involving researchers from Aix-Marseille University and the University of Oxford, as well as clinicians of the H?pital de la Timone (AP-HM). In the context of this project, behavioral, electrophysiological (EEG/subthalamic nucleus LFP) and neuroimaging data will be recorded in patients with Parkinson's disease, under different medication (ON/OFF L-Dopa) and deep brain stimulation (DBS) conditions. In particular, effects of conventional continuous ?open-loop? and "closed-loop" (adaptive) DBS will be contrasted. Rich expertise will be thus available in psychophysics and electrophysiology of sensorimotor systems (Nicole Malfait, INT; Huiling Tan, University of Oxford), structural and functional neuroimaging analyses (Olivier Coulon, INT), basal ganglia involvement in sensorimotor coordination (Andrea Brovelli, INT), and DBS (Alexandre Eusebio, AP-HM; Huiling Tan, University of Oxford) and theoretical and computational modelling of oscillating circuits dynamics (Demian Battaglia, INS). The postdoctoral fellow will participate to the design of circuit models (mean-field and spiking) with realistic anatomy, including known basal ganglia/cortical loops, as well as connections between basal ganglia and cerebellum, whose role has been until now only poorly studied. It has indeed recently been hypothesized that basal ganglia deregulation may directly interact with cerebellar predictive functions contributing to movement disorders in Parkinsons?s disease. Computational simulations of extended BG?cortex?cerebellum circuits will be used to reverse engineer circuit mechanisms responsible for the transition from normal to pathological oscillatory dynamics ?also in relation to Dopamine levels? and to model and optimize the impact of adaptive deep brain stimulation protocols. Candidates should have already acquired experience in the computational modelling of neural circuits during their PhD. Previous experience in the modelling of BG circuits is a plus. Candidates should be able to work in a dynamic, interdisciplinary and international work environment. Salary corresponds to French national guidelines (~2K ? net per month, experience-dependent), with travel and equipment funds. The successful candidate will integrate the Theoretical Neuroscience Group at the Institute for Systems Neuroscience (INS), located on the same campus as the Institut des Neuroscience de la Timone (INT) and the H?pital de la Timone (AP-HM). The integrative and clinical neuroscience community in Marseille is among the most lively in Europe and Marseille is a vibrating city, with wonderful natural surroundings and home to the largest French-speaking university in the world, with an emphasis on interdisciplinary studies. Interested candidates should send a cv, a brief description of qualifications and research interests and the name of two reference contacts to both the co-directors: Demian Battaglia demian.battaglia at univ-amu.fr Nicole Malfait nicole.malfait at univ-amu.fr Feel free to inquire for further information. Applications from under-represented categories in STEM sciences are welcome and supported. -------------- next part -------------- An HTML attachment was scrubbed... URL: From diego.perez at qmul.ac.uk Sun Nov 4 09:51:53 2018 From: diego.perez at qmul.ac.uk (Diego Perez Liebana) Date: Sun, 4 Nov 2018 14:51:53 +0000 Subject: Connectionists: Call for Participation - The 2018 MARLO Competition and AIIDE Workshop Message-ID: Dear all, Submissions are open for the very first MARLO Competition, which will take place at the incoming AIIDE MARLO Workshop this month - https://marlo-ai.github.io The AIIIDE 2018 MARLO Workshop (14th November) presents a great line up of RL and Game AI talks, including a panel and two impressive keynote speakers: - Jesse Cluff (Coalition Games); Title: Game AI: The Appearance of Intelligence - Martin Schmid (Google DeepMind); Title: DeepStack: Expert-Level AI in Heads-Up No-Limit Poker See program details here: https://marlo-ai.github.io/#program and register via the AIIDE registration page. This workshop will also announce the winners of the Kick-off MARLO Competition. This competition (https://www.crowdai.org/challenges/marlo-2018) is a new challenge that proposes research on Multi-Agent Reinforcement Learning using multiple games. Participants would create learning agents that will be able to play multiple 3D games as de?ned in the MalmO platform. The aim of the competition is to encourage AI research on more general approaches via multi-player games. For this, the Challenge will consist of not one but several games, each one of them with several tasks of varying difficulty and settings. Some of these tasks will be public and participants will be able to train on them. Others, however, will be private, only used to determine the ?nal rankings of the competition. You can submit your entry before November 14, 2018 in order to be eligible for our AIIDE prizes: the top 3 teams will be awarded with a MARLO Travel Grant for a maximum value of $2,500 USD for the team members to join a relevant conference to publish their competition result. See all details about the competition, prizes and submission at https://www.crowdai.org/challenges/marlo-2018 Best wishes, The MARLO organisational team (https://marlo-ai.github.io/#contact) Microsoft Research, Queen Mary University of London, ?cole polytechnique f?d?rale de Lausanne and CrowdAI.org --- Diego P?rez Li?bana Lecturer in Computer Games and Artificial Intelligence School of Electronic Engineering and Computer Science Queen Mary University of London (UK) email: diego.perez at qmul.ac.uk web: http://www.diego-perez.net Email notices: 1) You may have seen that I sometimes write emails outside (your) working hours. Please don't take this as an indication that I require an immediate response - we simply may be working at different times. 2) Because of the daily high load of emails, I may take some time to reply to you. If it's important, I may take even more time, because I want to provide an adequate response. If it's urgent, I'll try to reply quickly and maybe just with a very short email. No disrespect, just trying to be efficient - I'd understand if you did the same. -------------- next part -------------- An HTML attachment was scrubbed... URL: From jonizhong at msn.com Sun Nov 4 21:43:37 2018 From: jonizhong at msn.com (Joni Zhong) Date: Mon, 5 Nov 2018 02:43:37 +0000 Subject: Connectionists: [Meetings] Call for Participation: Workshop at Humanoids 2018: From Robotic Dexterous Manipulation to Manual Intelligence Message-ID: Please join us to discuss the next generation of robot dexterous manipulation at Humanoids 2018! IEEE Humanoids 2018 WS: From Robotic Dexterous Manipulation to Manual Intelligence https://ni.www.techfak.uni-bielefeld.de/ICHR2018WS/home ****************************************************************** Call for participation and Discussions >From Robotic Dexterous Manipulation to Manual Intelligence, Nov 6, Beijing, China, held at IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids 2018) (http://humanoids2018.csp.escience.cn/dct/page/1) ******************************************************************** Motivation and Topics Within recent 30 years, we have witnessed the progress of dexterous robotic hands from its designing and controlling aspects. However, how to use these advanced robot hands to implement skillful tasks like human are still very challengeable. Our expectations on the use of the robotic hands are rather high, the use cases in the robotic application are very few. We are considering the following three challenges for available robotic hands: ? It is still difficult to robustly, adaptively and dexterously control a robotic hand given the high mechanical complexity of the devices ? It is not clear how to implement complex tasks using the robotic hand equipped with limited sensing capability in the unstructured environment ? It is still an open question to represent and transfer human?s manipulation skills to a robotic hand which has a similar configuration space In order to solve the aforementioned challenges, one solution will be merging the newest findings in neuroscience, cognitive science, machine representation, and learning domains, e.g. how human are using their hands skillfully and how humans are using their hands as an important recognition tool to explore and learn the unknown world. We believe this can lead to the real ?manual intelligence? which not only can largely improve dexterous control of the robotic hand but also exploiting the robotic hand?s action-perception loop to autonomously understand the unstructured environment. Within this workshop we will bring together experts from the different domains, e.g. the developers of dexterous hands, control scientists focusing on grasping, planning and computer scientists studying machine learning to discuss progress and challenges of hand?s dexterous manipulation, foster potential collaborations, and reinforce the strict link among such interdisciplinary research fields to facilitate progress in this community. Central to the discussion will be three key questions: ? How to integrate multi-modal sensing for improving the robotic hand?s dexterous capability autonomously ? How to represent human?s manual skills and transfer them to robotic hands? ? How to define the benchmark to evaluate the dexterous capability of robotic hands? The workshop topics include but are not limited in the following ? New type of dexterous robotic hand ? Human?s manual skill representation ? Robotic hand?s grasping planning and control ? Unknown objects in-hand manipulation ? Sensory-based robotic hand grasping and manipulation ? Neuro-inspired control for grasping and manipulation ? Machine learning techniques for grasping and manipulation Invited speakers Prof. Tamim Asfour, Karlsruhe Institute of Technology, Germany Prof. Shaowei Fan, Harbin Institute of Technology, China Prof. Huaping Liu, Tsinghua University, China Prof. Abderrahmane Kheddar, CNRS-UM LIRMM, France Prof. Tetsuya Ogata, Waseda University, Japan Prof. Weiwei Wan, Osaka University, Japan Dr. Qiang Li, Bielefeld University, Germany Dr. Maximo Roa, German Aerospace Center, Germany Dr. Filipe Veiga, Technische University Darmstadt, Germany Latest Submission Submission about the latest results is also welcomed! Prospective participants are required to submit a 2-page abstract. Accepted contributions will be presented during the workshop as posters. Submissions must be sent in PDF format, following the IEEE conference style (two-columns), to: qli_AT_techfak_DOT_uni-bielefeld_DOT_de indicating [Humanoids 2018 Workshop] in the e-mail subject. Important Dates Workshop day: November 6 Organizers Dr. Qiang Li, Neuroinformatics Group / CITEC, Bielefeld University, Germany Dr. Zhaopeng Chen, Robotics and Mechatronics Center, German Aerospace Center (DLR), Germany Dr. Junpei Zhong, AI Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Japan Prof. Chenguang Yang, College of Engineering, Swansea University, UK Prof. Helge Ritter, Neuroinformatics Group / CITEC, Bielefeld University, Germany Supported by IEEE TCs: - On Robotic Hands, Grasping and Manipulation - On Robot Learning - On Neuro Robotics System -------------- next part -------------- An HTML attachment was scrubbed... URL: From yiz at soe.ucsc.edu Sun Nov 4 23:39:34 2018 From: yiz at soe.ucsc.edu (Yi Zhang) Date: Sun, 4 Nov 2018 20:39:34 -0800 Subject: Connectionists: 2 NLP faculty positions in University of California Santa Cruz Message-ID: The Department of Computer Science and Engineering at the University of California, Santa Cruz invites applications for two positions in the field of Natural Language Processing. One position is at the tenured Associate or early stage Full Professor level, and the other position is at the tenure track Assistant Professor level. We seek outstanding applicants with research and teaching expertise in all areas of Natural Language Processing. We are especially interested in candidates who have contributed to one or more application areas of Natural Language Processing including but not limited to information extraction, dialogue systems, semantic parsing, sentiment analysis, question answering, and machine translation. Both positions are associated with a proposed Professional MS program in Natural Language Processing to be located in the UCSC Silicon Valley Campus in Santa Clara, California. The successful candidates will play an essential role in developing, growing, and shaping this new program. They are expected to develop a research program, advise Ph.D. students in their research area, obtain external funding, develop and teach courses within the undergraduate and graduate curriculum, perform university, public, and professional service, and interact broadly with the large number of Natural Language Processing practitioners in Silicon Valley industrial research and advanced development labs. The successful candidates should be able to work with students, faculty and staff from a wide range of social and cultural backgrounds. In addition to the basic qualifications, applicants at the Associate or Full Professor level should have a demonstrated record of publications, demonstrated experience in university teaching at the undergraduate and graduate level or closely analogous activities, demonstrated record of extramural funding or similar success with garnering support for research endeavors, experience with research project management, and professional service; we also value industrial experience, and a track record of building product and applications based on NLP technology. We welcome candidates who understand the barriers facing women and minorities who are underrepresented in higher education careers (as evidenced by life experiences and educational background), and who have experience in equity and diversity with respect to teaching, mentoring, research, life experiences, or service towards building an equitable and diverse scholarly environment. The primary offices for these positions are located in Santa Clara, due to the expectation of teaching and mentoring students in this location. Space for PhD students for these positions is also located in Santa Clara. Graduate level teaching duties will be mainly at the Santa Clara campus with undergraduate courses to be taught at the Santa Cruz campus. The successful applicants will typically spend multiple days per week in Santa Clara and are also expected to spend on average one day per week on the Santa Cruz campus (more when teaching an undergraduate class on the Santa Cruz campus). The ability for on-demand transportation between Santa Clara and Santa Cruz with or without accommodations is essential. The Computer Science and Engineering Department has nationally and internationally known research groups in Machine Learning, Data Science, Natural Language Processing and related fields. Our beautiful campus has a long history of embracing groundbreaking interdisciplinary work, and the proximity of the campus to Silicon Valley affords our faculty extensive opportunities for interactions and collaborations with industry. ACADEMIC TITLES Assistant Professor and Associate or early stage Full Professor SALARY Commensurate with qualifications and experience; academic year (9-month basis). BASIC QUALIFICATIONS A Ph.D. or equivalent foreign degree in Computer Science or a relevant field expected to be completed by June 30, 2019; demonstrated record of research and teaching. POSITION AVAILABLE July 1, 2019 (with academic year beginning September 2019). Degree must be in hand by June 30, 2019. APPLICATION REQUIREMENTS Applications are accepted via the UCSC Academic Recruit online system; all documents and materials must be submitted as PDFs. APPLY AT https://recruit.ucsc.edu/apply/JPF00657 Please refer to Position # JPF00657-19 in all correspondence. Documents/Materials ? Letter of application that briefly summarizes your qualifications and interest in the position ? Curriculum vitae ? Statement addressing contributions to diversity through research, teaching, and/or service (required). Guidelines on diversity statements can be viewed at https://senate.ucsc.edu/committees/caad-committee-on-affirmative-action-and-diversity/DivStateGuidelines.pdf . ? Statement of research plans ? Statement of teaching interests and experience ? 3?4 selected publications ? 3 confidential letters of recommendation* Please note that your references, or dossier service, will submit their confidential letters directly to the UC Recruit System. *All letters will be treated as confidential per University of California policy and California state law. For any reference letter provided via a third party (i.e., dossier service, career center), direct the author to UCSC?s confidentiality statement at http://apo.ucsc.edu/confstm.htm. RECRUITMENT PERIOD Full consideration will be given to applications completed by December 3rd, 2018. Applications received after this date will be considered only if the position has not been filled. UC Santa Cruz faculty make significant contributions to the body of research that has earned the University of California the ranking as the foremost public higher education institution in the world. In the process, our faculty demonstrate that cutting-edge research, excellent teaching and outstanding service are mutually supportive. The University of California is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, or protected veteran status. UC Santa Cruz is committed to excellence through diversity and strives to establish a climate that welcomes, celebrates, and promotes respect for the contributions of all students and employees. Inquiries regarding the University?s equal employment opportunity policies may be directed to the Office for Diversity, Equity, and Inclusion at the University of California, Santa Cruz, CA 95064 or by phone at (831) 459-2686. Under Federal law, the University of California may employ only individuals who are legally able to work in the United States as established by providing documents as specified in the Immigration Reform and Control Act of 1986. Certain UCSC positions funded by federal contracts or sub-contracts require the selected candidate to pass an E-Verify check (see https://www.uscis.gov/e-verify). More information is available at the APO website (see https://apo.ucsc.edu/policy/capm/104.000%20.html) or call (831) 459-4300. UCSC is a smoke & tobacco-free campus. If you need accommodation due to a disability, please contact the Academic Personnel Office at apo at ucsc.edu (831) 459-4300. VISIT THE APO WEB SITE AT http://apo.ucsc.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From irina.illina at loria.fr Sun Nov 4 15:56:24 2018 From: irina.illina at loria.fr (Irina Illina) Date: Sun, 4 Nov 2018 21:56:24 +0100 (CET) Subject: Connectionists: Research engineer or post-doc position in Natural Language Processing (LORIA, France) Message-ID: <563224855.15324328.1541364984538.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 hava.siegelmann at gmail.com Mon Nov 5 04:14:54 2018 From: hava.siegelmann at gmail.com (Hava Siegelmann) Date: Mon, 5 Nov 2018 04:14:54 -0500 Subject: Connectionists: Lifelong Learning Bibliography and State of the Art Message-ID: Hello Connectionists: Some of you may be aware that I direct the DARPA's Lifelong Learning Machines. We had a great PI meeting, and both during and after the meeting I was asked to file a bibliography of papers and efforts in this topic. I would like to open the floor and have my bibliography include also the great work that is not DARPA funded, so it has a full usefulness to both DARPA's performers and the general AI/ML community. With this I would like to invite anyone to send me their relevant work in this topic. Best regards - Hava -------------- next part -------------- An HTML attachment was scrubbed... URL: From pkoprinkova at yahoo.com Mon Nov 5 06:40:39 2018 From: pkoprinkova at yahoo.com (Petia Koprinkova) Date: Mon, 5 Nov 2018 11:40:39 +0000 (UTC) Subject: Connectionists: CFP: INISTA 2019 References: <945060595.833487.1541418039798.ref@mail.yahoo.com> Message-ID: <945060595.833487.1541418039798@mail.yahoo.com> Dear Colleagues, InternationalSymposium on INnovations in Intelligent SysTems and Applications (INISTA)has been organized since 2005. It aims to bring together the researchers fromthe entire spectrum of the multi-disciplinary fields of intelligent systems andto establish effective means of communication between them. In particular, itfocuses on all aspects of intelligent systems and the related applications,from the points of view of both theory and practice. Apart of the main track itincludes work-shops, tutorials, special sessions and plenary talks by invitedspeakers. INISTA2019 will held on Sofia, Bulgariafrom 3rd to 5th of July, 2019. It is organized byInstitute of Information and Communication Technologies at Bulgarian Academy ofSciences and IEEE Bulgarian Section in cooperation with Yildiz TechnicalUniversity, Turkey. Prospective authors are invitedto submit their papers to INISTA 2019. The Topics of interest cover theentire spectrum of the multi-disciplinary fields of intelligent systems andrelated applications as follows: | ? Artificial Intelligence Algorithms ? Artificial Neural Networks ? Bioinformatics ? Data Mining ? Evolutionary Computation ? Expert Systems ? Fuzzy Logic ? Genetic Algorithms ? Hardware Implementations for Intelligent Systems ? Human-Computer Interaction ? Intelligent Agents ? Intelligent Applications in Biomedical Engineering ? Intelligent Approaches in Robotic and Automation ? | ? Intelligent Approaches in Signal and Image Processing ? Intelligent Approaches in System Identification and Modeling ? Intelligent Control Systems ? Intelligent Defense/Security Systems ? Intelligent Life ? Intelligent Transportation Systems ? Machine Learning ? Memetic Computing ? Modeling using NLP methods ? Natural Language Processing ? Swarm Intelligence ? Smart Sensors and Materials ? Other topics related to Intelligent Systems ? | Accepted papers will appear inthe conference proceedings, available on IEEE Xplore and submitted to beindexed in the Web of Science Core Collection databases. The authors ofselected best papers will be invited to extend their contributions for specialissues. More information about conferencecan be found at its site: www.inista.org ? Deadlines: | Paper Submission: March 15, 2019 Notification of Acceptance: April 30, 2019 Camera-Ready Submission and Registration: May 10, 2019 | Special Session Proposals: January 25, 2019 Notification of Acceptance: February 10, 2019 Special Session Paper Submission: March 15, 2019 | ? -------------- next part -------------- An HTML attachment was scrubbed... URL: From dominik.endres at uni-marburg.de Mon Nov 5 09:16:52 2018 From: dominik.endres at uni-marburg.de (Dominik Endres) Date: Mon, 05 Nov 2018 15:16:52 +0100 Subject: Connectionists: =?utf-8?q?=5BCFP-Extended=5D_24th_International_C?= =?utf-8?q?onference_on_Conceptual_Structures_=28ICCS=E2=80=9919=29?= Message-ID: <6398648.0fI8PtlgzO@pc04174> [Apologies for multiple postings.] =================================== 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 - Full paper submission deadline: December 7, 2018 - Poster submission deadline: December 21, 2018 (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. -------------- next part -------------- An HTML attachment was scrubbed... URL: From samuel.kaski at aalto.fi Mon Nov 5 12:27:14 2018 From: samuel.kaski at aalto.fi (Kaski Samuel) Date: Mon, 5 Nov 2018 17:27:14 +0000 Subject: Connectionists: Postdoc, Research Fellow and Professor Positions in Machine Learning and AI in Helsinki Message-ID: Postdoc, Research Fellow and Professor Positions in Machine Learning and AI in Helsinki Postdocs and Research Fellows Multiple machine learning and AI postdoc and research fellow positions are available in Helsinki in a joint call, with deadline November 29, 2018. More details at https://www.hiit.fi/calls/postdoc-and-research-fellow-postions-autumn-2018/ Professors The Department of Computer Science at Aalto University invites applications from tenure-track candidates for the Assistant Professor level, as well as from candidates with outstanding records for tenured Associate or Full Professor levels. Deadline January 10, 2019. This is across all of Computer Science, including Machine Learning and AI. More details at https://www.aalto.fi/news/open-positions-professors-in-computer-science -- Samuel Kaski, Academy Professor Finnish Center for Artificial Intelligence FCAI, fcai.fi Department of Computer Science, Aalto University P.O. Box 15400, FI-00076 Aalto, Finland; https://people.aalto.fi/new/samuel.kaski Tel: +358 50 3058694 From Joerg.Lehnert at mis.mpg.de Mon Nov 5 09:44:55 2018 From: Joerg.Lehnert at mis.mpg.de (Joerg Lehnert) Date: Mon, 5 Nov 2018 15:44:55 +0100 Subject: Connectionists: [jobs] MPI MiS (Leipzig/Germany): Several PhD and Postdoc positions available - Deadline December 01, 2018 Message-ID: Dear Connectionists, the Max Planck Institute for Mathematics in the Sciences (MPI MiS) invites applications for several PhD and Postdoc positions. The MPI MiS is located in Leipzig, Germany and cooperates with Leipzig University. Research at the MPI MiS exploits the fruitful interaction between mathematics and the sciences. We hire not only in the classical areas of mathematics but also in fields exploring the interaction of mathematics and the sciences like: Complexity and Cognition Information Theory of Cognitive Systems Mathematical Machine Learning and Theory of Deep Learning Fore details on the postdoc calls, please check https://www.mis.mpg.de/career/postdoc.html (Deadline 01.12.18) and https://www.mis.mpg.de/career/postdoc-active-self.html (Deadline 15.11.2018) For details on the PhD call, please check https://www.imprs-mis.mpg.de/apply.html (Deadline 01.12.2018) Best regards, J?rg -- J?rg Lehnert Scientific coordinator Max Planck Institute for Mathematics in Sciences (MPI MIS) Inselstr. 22, 04103 Leipzig Germany Phone: +49 (0)341 9959 641 -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 5293 bytes Desc: S/MIME Cryptographic Signature URL: From stefano.rovetta at unige.it Mon Nov 5 11:04:10 2018 From: stefano.rovetta at unige.it (Stefano Rovetta) Date: Mon, 5 Nov 2018 17:04:10 +0100 Subject: Connectionists: CFP: Evolving and adaptive fuzzy models for data streams @EUSFLAT2019 Message-ID: <58aac47d-b160-56df-2dc3-9b0de5d98639@unige.it> *** CALL FIR PAPERS *** Evolving and adaptive fuzzy models for data streams 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 timothee.masquelier at alum.mit.edu Mon Nov 5 11:35:58 2018 From: timothee.masquelier at alum.mit.edu (=?UTF-8?Q?Timoth=C3=A9e_Masquelier?=) Date: Mon, 5 Nov 2018 17:35:58 +0100 Subject: Connectionists: Research internship for 2nd year master student in Toulouse, France Message-ID: TOPIC: Spiking neural networks for bird song detection SUPERVISORS: Timoth?e Masquelier (computational neuroscience) and Thomas Pellegrini (machine learning for audio processing) STARTING DATE: early 2019 DURATION: 5 months PLACE: Toulouse, France (Centre de Recherche Cerveau et Cognition and Institut de Recherche en Informatique de Toulouse) STIPEND: 560?/month The goal of the internship is to use spiking neural networks (SNN) to detect bird songs in audio recordings. Several learning rules will be evaluated, including spike-timing-dependent plasticity (STDP). More information: https://www.dropbox.com/s/psvqubjdlral6zf/Masquelier-Pellegrini-AO%20M2%20TMBI%202018.pdf?dl=0 We are looking for an outstanding student with a strong quantitative background (computer science, physics, applied maths...) and a keen interest in neuroscience. Applicants should send their CV and a brief statement of purpose to: timothee.masquelier at cnrs.fr and Thomas.Pellegrini at irit.fr Informal enquiries are welcome. -------------- next part -------------- An HTML attachment was scrubbed... URL: From caspar.schwiedrzik at googlemail.com Tue Nov 6 05:54:19 2018 From: caspar.schwiedrzik at googlemail.com (Caspar M. Schwiedrzik) Date: Tue, 6 Nov 2018 11:54:19 +0100 Subject: Connectionists: =?utf-8?q?Neuroscience_data_analyst_=28f/m=29_ope?= =?utf-8?q?ning_at_ENI_G=C3=B6ttingen=2C_Germany_=28new_opening=29?= Message-ID: The European Neuroscience Institute G?ttingen (Germany) is seeking a *Neuroscience data analyst (f/m) * initially limited until 31.12.2019 with extension options, full-time | salary according to TV-L The European Neuroscience Institute is looking to fill the position of a data analyst (full time). We are looking for a data analyst with interest and experience in systems neuroscience. Research at the European Neuroscience Institute ranges from molecular biology to human psychophysics and involves a range of model organisms (from drosophila to non-human primates), techniques and approaches (electrophysiology, two-photon imaging, fMRI, EEG, behavior). The data analyst will work closely with all of the various research groups at the European Neuroscience Institute, supporting research efforts, e.g., through modelling and statistical analyses of high-dimensional data, image processing, and programming/development of experiments. S/he will have the opportunity to develop and publish, e.g., analytical tools that arise from this work. - The applicant should possess a university degree (minimally M. Sc. or equivalent) in a relevant field, e.g., statistics, biostatistics, informatics, or similar. Prior experience in the field of systems neuroscience is highly desired. - The applicant should have experience in a research setting utilizing quantitative methods and statistics. The applicant shall demonstrate strong analytical skills and knowledge of novel and emerging analysis techniques is highly desired. Future/forward thinking in the area of big data analytics/informatics and applying them to contribute to the research groups? scientific process is expected. - The applicant should be skilled in the analysis of multivariate datasets to reveal patterns and build models; conduct exploratory data analysis, and communicate with team lead/team members; identify improvements for existing data management and recommend requirements for new systems. - Contribute to replicability by making suggestions for existing data management and recommend requirements for new systems and identify potential data integrity issues. We are committed to open data/open science and appreciate interest and expertise in this area. - Utilize programming languages such as Python, Matlab and/or C++. - Good command of English is mandatory. The University Medical Center G?ttingen takes flexible account of the individual design of working hours at the workplace. It is interested in implementing the wishes of its employees as far as possible. If you are interested in this job and have specific questions about working hours, please contact us. Women are especially encouraged to apply. Applicants with disabilities and equal qualifications will be given preferential treatment. We look forward to receiving your application by * November 30th, 2018* University Medical Center G?ttingen European Neuroscience Institute G?ttingen Dr. Caspar Schwiedrzik Group Leader Grisebachstr. 5 37077 G?ttingen Tel.: 0551/39-61371 Fax: 0551/39-61399 E-Mail: c.schwiedrzik at eni-g.de < c.schwiedrzik at eni-g.de> Web: http://www.eni-g.de/ Please send your application only via e-mail as a PDF-file. also see: http://www.med.uni-goettingen.de/de/content/service/stellenanzeigen.php?id=2250 -------------- next part -------------- An HTML attachment was scrubbed... URL: From jorgecbalmeida at gmail.com Tue Nov 6 10:12:06 2018 From: jorgecbalmeida at gmail.com (Jorge Almeida) Date: Tue, 6 Nov 2018 15:12:06 +0000 Subject: Connectionists: One fMRI MVPA Post-Doc (very competitive salary) 5 year position available under an ERC Starting Grant on the organization of object knowledge Message-ID: The Proaction Laboratory (Perception and Recognition of Objects and Actions; http://gaius.fpce.uc.pt/pessoais/jorgealmeida/proaction_home.html; Jorge Almeida?s Lab) at the University of Coimbra (www.uc.pt), Portugal is looking for a motivated and bright Post-doctoral researcher to work on an ERC Starting Grant project (ContentMAP) on the neural organization of object knowledge. In this project we will explore how complex information is topographically organized in the brain using fMRI and state of the art analytical techniques, as well as computational approaches, and neuromodulation. Excellent understanding of and experience with fMRI and data analysis is required. Strong programming skills (matlab, python, etc.) are also a requirement. Experience with data analysis techniques using MVPA and other multivariate approaches (e.g., Representation Similarity Analysis). Very good English (oral and written) communicative skills are necessary. The position is for a maximum of 5 years, and will start in February 2019. The position involves no formal teaching (unless the candidate wants to). It does involve, however, lab mentoring. The salary is extremely competitive ? between 2200 and 2400 euros per month (dependent on experience), tax free (annual 26400-28800 euros tax free). This value is on par with the average salaries at top American institutions, as well as London, Paris, etc. However, the cost of living in Portugal (and particularly in Coimbra) is much lower. According to Numbeo, 2400 euros would be equivalent to 4850 pounds in London/4800 euros in Paris/6615 USD in Boston/6210 USD in Los Angeles/ 8330 USD in New York). The researcher will work directly with Jorge Almeida in Coimbra, but the laboratory has extensive collaborations with researchers throughout the world. In fact, there may be the option of spending some time in another lab as part of the position. The researcher will also be encouraged to develop her/his own projects and look for additional funding so that the stay can be extended. We have access to a 3T MRI scanner with a 32-channel coil (with EEG inside the scanner), to tDCS with neuronavigation, and to a fully set psychophysics lab. We have EEG and eyetracking on site. We also have access, through other collaborations, to a 7T scanner. 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 the application is NOVEMBER 20, but you should apply as soon as you can, as we may fill in the positions sooner than the deadline if there are candidates with a superb fit with the requirements and project. The interested candidates should email Jorge Almeida for questions and applications. Please send an email with the subject ?Post-doc position underERC - ContentMAP? with your*curriculum vitae, list of publications, 2 reference letters, and a short description of your experience in the field and how you fulfill the requirements (fit with the position)* to: jorgealmeida at fpce.uc.pt. -------------- next part -------------- An HTML attachment was scrubbed... URL: From panos at stern.nyu.edu Tue Nov 6 11:34:06 2018 From: panos at stern.nyu.edu (Panos Ipeirotis) Date: Tue, 6 Nov 2018 11:34:06 -0500 Subject: Connectionists: Faculty position at New York University Message-ID: The Information Systems faculty in the Department of Information, Operations & Management Sciences at the Stern School of Business, New York University, invites applications for a tenure-track position at the assistant professor level starting in the 2019-2020 academic year. The Information Systems faculty is a multidisciplinary group of computer scientists, economists, behavioral scientists and data scientists. It has a vibrant PhD program with a history of successful placements at top schools. Our faculty, students and scientists have won numerous awards for their research and scholarship over the last decade. We are especially interested in candidates with discipline-spanning interests whose work complements the research programs of our existing faculty in areas that include, but are not restricted to: Business Analytics, Computational Social Science, Crowdsourcing/Crowdfunding, Data Science, Digital Marketing, Digital Strategy, Labor Markets, Network Science, Online Marketplaces, Open Innovation, Predictive Modeling, Recommender Systems, and the Sharing Economy. A candidate should have a PhD or be assured of its completion within one year of September 2019 and is expected to be an outstanding researcher and teacher at both the undergraduate and graduate levels. To ensure full consideration, the deadline for submitting all application materials is January 5, 2019. However, applications will be accepted and evaluated until the position is filled. We expect to start interviewing candidates in early February and conclude our interviews in March. New York University and the Stern School of Business is committed to building a diverse faculty and invites applications from women, people with disabilities and members of minority groups. Please go to apply.interfolio.com/57485, Stern?s faculty application system, to apply. For questions, please send email to ioms at stern.nyu.edu. -- Panos Ipeirotis Professor of Data Science and Information Systems George A. Kellner Faculty Fellow Stern School of Business, New York University http://www.ipeirotis.com From n.strisciuglio at rug.nl Wed Nov 7 07:32:33 2018 From: n.strisciuglio at rug.nl (Nicola Strisciuglio) Date: Wed, 7 Nov 2018 13:32:33 +0100 Subject: Connectionists: Call for contests at CAIP 2019 in Salerno, Italy (2-5 September 2019) Message-ID: <6e201a0d-ff25-970d-00aa-84ac30df4760@rug.nl> ** *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: nehablhmpoaeipdm.png Type: image/png Size: 54007 bytes Desc: not available URL: From m.gomez.rodriguez at gmail.com Wed Nov 7 11:39:39 2018 From: m.gomez.rodriguez at gmail.com (Manuel Gomez Rodriguez) Date: Wed, 7 Nov 2018 17:39:39 +0100 Subject: Connectionists: Tenure-track openings at MPI-SWS Message-ID: <8B3481D3-9BD2-406C-9C4A-A86BC3EB3C36@gmail.com> Tenure-track openings at MPI-SWS Applications are invited for tenure-track faculty in all areas of computer science. We expect to fill one position. A doctoral degree in computer science or related areas and an outstanding research record are required. Successful candidates are expected to build a team and pursue a highly visible research agenda, both independently and in collaboration with other groups. MPI-SWS is part of a network of over 80 Max Planck Institutes, Germany's premier basic-research organisations. MPIs have an established record of world-class, foundational research in the sciences, technology, and the humanities. The institute offers a unique environment that combines the best aspects of a university department and a research laboratory: Faculty enjoy full academic freedom, lead a team of doctoral students and post-docs, and have the opportunity to teach university courses; at the same time, they enjoy ongoing institutional funding in addition to third-party funds, a technical infrastructure unrivaled for an academic institution, as well as internationally competitive compensation. The institute is located in the German cities of Saarbruecken and Kaiserslautern, in the tri-border area of Germany, France, and Luxembourg. We maintain an international and diverse work environment and seek applications from outstanding researchers worldwide. The working language is English; knowledge of the German language is not required for a successful career at the institute. Qualified candidates should apply on our application website (apply.mpi-sws.org). To receive full consideration, applications should be received by December 1st, 2018. The institute is committed to increasing the representation of women and minorities, as well as of individuals with physical disabilities. We particularly encourage such individuals to apply. The initial tenure-track appointment is for five years; it can be extended to seven years based on a midterm evaluation in the fourth year. A permanent contract can be awarded upon a successful tenure evaluation in the sixth year. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ac1753 at coventry.ac.uk Wed Nov 7 08:44:18 2018 From: ac1753 at coventry.ac.uk (Ariel Ruiz-Garcia) Date: Wed, 7 Nov 2018 13:44:18 +0000 Subject: Connectionists: CFP IEEE TNNLS Special Issue on Deep Representation and Transfer Learning for Smart and Connected Health Message-ID: TL;DR - CFP IEEE TNNLS special issue on Deep Representation and Transfer Learning for Smart and Connected Health. Submission Deadline 31st March 2019. Call for Papers: IEEE Transactions on Neural Networks and Learning Systems Special Issue on Deep Representation and Transfer Learning for Smart and Connected Health Important Dates 31 March 2019 - Deadline for manuscript submission 30 June 2019 - Reviewer's comments to authors 31 August 2019 - Submission of revised papers 31 October 2019 - Final decision of acceptance 30 November 2019 - Camera-ready papers December 2019-February 2020 - Tentative publication date Aims and Scope: Deep neural networks have proven to be efficient learning systems for supervised and unsupervised tasks in a wide range of challenging applications. However, learning complex data representations using deep neural networks can be difficult due to problems such as lack of data, exploding or vanishing gradients, high computational cost, or incorrect parameter initialization, among others. Transfer Learning (TL) can facilitate the learning of data representations by taking advantage of transferable features learned by a model in a source domain, and adapting the model to a new domain. This approach has demonstrated to produce better generalization performance than random weight initialization, and has produced state-of-the-art results in signal and visual processing tasks. Accordingly, emerging and challenging domains, such as smart and connected health (SCH), can benefit from new theoretical advancements in representation and transfer learning (RTL) methods. One of the main advantages of TL is its potential to be applied in a wide range of domains and for different learning tasks. For instance, in facial affect recognition, the representations learned by a deep model trained to recognize faces in an unsupervised fashion can be employed and improved by a second model to perform emotion recognition in supervised manner. Nonetheless, learning data representations that provide a good degree of generalization performance remains a challenge. This is due to issues such as the inherent trade-off between retaining too much information from the input and learning universal features. Similarly, despite the obvious advantages of TL, effective use of parameters learned by a given model in a different domain is a challenge, particularly when there is limited data in the target domain. This challenge increases when the joint distribution of the input features and output labels is different in the target domain. In addition, determining how to reject unrelated information or remove dataset bias during TL is yet to be solved. Other limitations are caused by lack of existing theoretical approaches in RTL capable of explaining or interpreting the learning process of deep models, or determining how to best learn a set of data representations that are ideal for a given task, whether in a regression or classification problem. Therefore, new n theoretical mechanisms and algorithms are required to improve the performance and learning process of deep neural networks. Despite these constraints, RTL will play an essential role in building the next generation of intelligent systems designed to assists humans with their daily needs. Consequently, domains of great interest to human society, such as SCH, will benefit from new advancements in RTL. For instance, one of the main challenges in designing effective SCH applications is overcoming the lack of labelled data. RTL can overcome this limitation by training a model to learn universal data representations on larger corpora in a different domain, and then adapting the model for use in a SCH context. Similarly, RTL can be used in conjunction with generative adversarial networks to overcome class imbalance problems by generating new healthcare-related data, which can also be used to improve the generalization performance of deep models in SCH applications. Furthermore, RTL can be used to initialize and improve the learning of deep reinforcement learning models designed for continuous learning in patient-centered cognitive support systems, among others. Nonetheless, the use of RTL in designing SCH applications requires overcoming problems such as dataset bias or neural network co-adaptation. This special issue on Deep Representation and Transfer Learning for Smart and Connected Health invites researchers and practitioners to present novel contributions addressing theoretical aspects of representation and transfer learning. The special issue will provide a collection of high quality research articles addressing theoretical work aimed to improve the generalization performance of deep models, as well as new theory attempting to explain and interpret both concepts. State-of-the-art works on applying representation and transfer learning for developing smart and connected health intelligent systems are also very welcomed. Topics of interest for this special issue include but are not limited to: Theoretical Methods: * Distributed representation learning; * Transfer learning; * Invariant feature learning; * Domain adaptation; * Neural network interpretability theory; * Deep neural networks; * Deep reinforcement learning; * Imitation learning; * Continuous domain adaptation learning; * Optimization and learning algorithms for DNNs; * Zero and one-shot learning; * Domain invariant learning; * RTL in generative and adversarial learning; * Multi-task learning and Ensemble learning; * New learning criteria and evaluation metrics in RTL; Application Areas: * Health monitoring; * Health diagnosis and interpretation; * Early health detection and prediction; * Virtual patient monitoring; * RTL in medicine; * Biomedical information processing; * Affect recognition and mining; * Health and affective data synthesis; * RTL for virtual reality in healthcare; * Physiological information processing; * Affective human-machine interaction; Guest Editors Vasile Palade, Coventry University, UK Stefan Wermter, University of Hamburg, Germany Ariel Ruiz-Garcia, Coventry University, UK Antonio de Padua Braga, University of Minas Gerais, Brazil Clive Cheong Took, Royal Holloway (University of London), UK Submission Instructions 1. Read the Information for Authors at https://cis.ieee.org/publications/t-neural-networks-and-learning-systems. 2. Submit your manuscript at the TNNLS webpage (http://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript is submitted to this special issue. Send an email to the guest editors Ariel Ruiz-Garcia (ariel.ruiz-garcia at coventry.ac.uk) and Vasile Palade (vasile.palade at coventry.ac.uk) with subject "TNNLS special issue submission" to notify about your submission. 3. Early submissions are welcome. We will start the review process as soon as we receive your contributions. For any other questions please contact Ariel Ruiz-Garcia (ariel.ruiz-garcia at coventry.ac.uk). University of the Year for Student Experience The Times and Sunday Times Good University Guide 2019 2nd for Teaching Excellence Times Higher Education UK (TEF) metrics ranking 2017 - Gold winner 5th UK Student City QS Best Student Cities Index 2018 13th in Guardian University Guide 2019 of 121 UK institutions ranked NOTICE This message and any files transmitted with it is intended for the addressee only and may contain information that is confidential or privileged. Unauthorised use is strictly prohibited. If you are not the addressee, you should not read, copy, disclose or otherwise use this message, except for the purpose of delivery to the addressee. Any views or opinions expressed within this e-mail are those of the author and do not necessarily represent those of Coventry University. -------------- next part -------------- An HTML attachment was scrubbed... URL: From KSCREEN at mgh.harvard.edu Thu Nov 8 16:14:50 2018 From: KSCREEN at mgh.harvard.edu (Screen, Katrina M.) Date: Thu, 8 Nov 2018 21:14:50 +0000 Subject: Connectionists: NINDS Post-Doctoral T32 Training Opportunity Message-ID: <1FF7C30E-7BA8-4002-85C6-342F544C2D73@mgh.harvard.edu> NINDS Post-Doctoral T32 Training Opportunity Training Program in Recovery and Restoration of CNS Health and Function Applications Due January 2nd, 2019 We are pleased to announce that we are accepting applications for our NIH-funded T32 Postdoctoral Training Program in Recovery and Restoration of CNS Health and Function. The goal of this exciting multidisciplinary, multi-institutional training program based at Massachusetts General Hospital and the School of Engineering and the Carney Institute for Brain Science at Brown University, is to enhance recovery from disabling brain injuries by filling a pressing need for clinician-scientists and neuroengineers trained to leverage the computational neurosciences and to develop and test device-based and other interventions for patients. We seek post-doctoral (MD or MD/PhD) clinician-scientists and post-doctoral (PhD) neuroengineers/computational neuroscientists to train under a multidisciplinary training faculty from anesthesia, biomedical engineering, computational neuroscience, neurology, neurosurgery, physical medicine and rehabilitation, psychiatry, and radiology. We would be most appreciative if you could circulate the attached announcement to your senior graduate students, junior postdoctoral researchers, senior residents, clinical fellows and research fellows. The research and training opportunity includes a two year, T32-funded fellowship that is available beginning July 2019. The deadline for applications is January 2nd, 2019. Please see the attached document for more information on program requirements and how to apply. Respectfully, Jonathan Rosand and Leigh Hochberg The information in this e-mail is intended only for the person to whom it is addressed. If you believe this e-mail was sent to you in error and the e-mail contains patient information, please contact the Partners Compliance HelpLine at http://www.partners.org/complianceline . If the e-mail was sent to you in error but does not contain patient information, please contact the sender and properly dispose of the e-mail. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: 2019_CNS_RecoveryRestoration_T32_Advertisement_v2.pdf Type: application/pdf Size: 40848 bytes Desc: 2019_CNS_RecoveryRestoration_T32_Advertisement_v2.pdf URL: From hava.siegelmann at gmail.com Thu Nov 8 09:47:57 2018 From: hava.siegelmann at gmail.com (Hava Siegelmann) Date: Thu, 8 Nov 2018 09:47:57 -0500 Subject: Connectionists: International Neural Networks Society - last call for awards Message-ID: Friends - Its with a great pleasure that I'm sending you a reminder: The INNS yearly award deadline is upcoming - November 13 2018 https://www.inns.org/awards Think of deserved ones, and let us know. I'm waiting with excitements to see the options that we have to chose from this year Best regards - Hava -------------- next part -------------- An HTML attachment was scrubbed... URL: From tomas.hromadka at gmail.com Fri Nov 9 06:27:50 2018 From: tomas.hromadka at gmail.com (Tomas Hromadka) Date: Fri, 9 Nov 2018 12:27:50 +0100 Subject: Connectionists: COSYNE 2019: Abstract submission closes soon; Registration opens; Cosyne 2019 Tutorials Message-ID: ==================================================== Computational and Systems Neuroscience 2019 (Cosyne) MAIN MEETING 28 February - 03 March 2019 Lisbon, Portugal WORKSHOPS 04 March - 05 March 2019 Cascais, Portugal www.cosyne.org ==================================================== IMPORTANT DATES Abstract submission closes soon! Abstract submission deadline: 15 November 2018 Cosyne registration opens: 11 November 2018 ---------------------------------------------------- COSYNE TUTORIALS ---------------------------------------------------- Cosyne 2019 will host two tutorial sessions on 28 February 2019. For details on Cosyne tutorials please visit Cosyne.org -> Tutorials. Cosyne 2019 Tutorial session sponsored by the Simons Foundation Topic: Bayesian modeling of behavior Speaker: Wei Ji Ma Wei Ji Ma is Associate Professor of Neural Science and Psychology at NYU. His lab studies decision-making across domains, including perception, attention, working memory, social cognition, and planning, using a combination of human behavioral experiments and computational modeling. Allen Institute tutorial session Topic: Navigating the Allen Brain Observatory This tutorial will introduce participants to the scientific foundations, data parameters, and practical skills for using the Allen Brain Observatory in computational neuroscience research. ---------------------------------------------------- COSYNE MENTORING FORUM ---------------------------------------------------- Cosyne Mentoring Forum provides a platform for discussions among Cosyne participants, particularly for help with composing abstracts for the meeting and getting feedback before submission. The forum is intended to be a place to connect with other computational and systems neuroscientists. Forum members are encouraged to share advice on everything from writing a great Cosyne abstract to navigating a job search. See Cosyne.org -> Mailing lists for details on how to subscribe and post to the forum. ---------------------------------------------------- COSYNE ---------------------------------------------------- The annual Cosyne meeting provides an inclusive forum for the exchange of empirical and theoretical approaches to problems in systems neuroscience, in order to understand how neural systems function. The MAIN MEETING is single-track. A set of invited talks is selected by the Executive Committee, and additional talks and posters are selected by the Program Committee, based on submitted abstracts. The WORKSHOPS feature in-depth discussion of current topics of interest, in a small group setting. For details on workshop proposals please see below or visit Cosyne.org -> Workshops. Cosyne topics include but are not limited to: neural coding, natural scene statistics, dendritic computation, neural basis of persistent activity, nonlinear receptive field mapping, representations of time and sequence, reward systems, decision-making, synaptic plasticity, map formation and plasticity, population coding, attention, and computation with spiking networks. This year we would like to foster increased participation from experimental groups as well as computational ones. Please circulate widely and encourage your students and postdocs to apply. When preparing an abstract, authors should be aware that not all abstracts can be accepted for the meeting, due to space constraints. Abstracts will be selected based on the clarity with which they convey the substance, significance, and originality of the work to be presented. For more information and details on submitting abstracts please visit Cosyne.org -> Abstracts. COSYNE SPEAKERS Bruno Averbeck (NIMH) Gwyneth Card (Janelia) Kathleen Cullen (John Hopkins) Kenji Doya (OIST) Ken Harris (UCL) Sonja Hofer (Sainsbury Wellcome Centre) Yann LeCun (NYU) Edvard Moser (NTNU) Yiota Poirazi (IMBB-FORTH) Maneesh Sahani (Gatsby-UCL) Eric Shea-Brown (U Washington) Sara Solla (Northwestern) Karel Svoboda (Janelia) Ilana Witten (Princeton) ORGANIZING COMMITTEE General Chairs: Linda Wilbrecht (Berkeley) and Brent Doiron (U Pittsburgh) Program Chairs: Eugenia Chiappe (Champalimaud) and Christian Machens (Champalimaud) Workshop Chairs: Catherine Hartley (NYU) and Ralf Haefner (U Rochester) Undergraduate Travel Chairs: Angela Langdon (Princeton) and Robert Wilson (U Arizona) Publicity Chair: Il Memming Park (Stony Brook) Development Chair: Michael Long (NYU) EXECUTIVE COMMITTEE Stephanie Palmer (U Chicago) Zachary Mainen (Champalimaud) Alexandre Pouget (U Geneva) Anthony Zador (CSHL) CONTACT meeting [at] cosyne.org ---------------------------------------------------- COSYNE MAILING LISTS ---------------------------------------------------- Please consider adding yourself to Cosyne mailing lists (groups) to receive email updates with various Cosyne-related information and join in helpful discussions. See Cosyne.org -> Mailing lists for details. From joern.anemueller at uni-oldenburg.de Fri Nov 9 09:36:17 2018 From: joern.anemueller at uni-oldenburg.de (=?utf-8?Q?J=C3=B6rn_Anem=C3=BCller?=) Date: Fri, 9 Nov 2018 15:36:17 +0100 Subject: Connectionists: Ph.D. position in deep learning for signal processing at University of Oldenburg Message-ID: A Ph.D. position in the field of deep learning for signal processing is available at University of Oldenburg, Germany, within the newly established, DFG-funded collaborative research centre "CRC 1330 - Hearing Acoustics" in the group of J?rn Anem?ller. For details, see below or contact me directly (joern.anemueller at uol.de, https://uol.de/en/computational-audition/statistical-modelling/). Kind regards, J?rn The Computational Audition Group at the Department of Medical Physics and Acoustics, University of Oldenburg, Germany, seeks a highly motivated PhD student (75 % of full time, TV-L E13, 3 years, with possibility of extension) in the field of Deep Learning for Signal Processing Our group investigates audio signal recognition with multi-channel microphone arrays, identifying important sound sources in real-world acoustic scenes, and performing source separation to enhance e.g. an attended speech signal. Applicants for the position must hold an academic university degree (master or equivalent) in physics, engineering, computer science or a related discipline and should have knowledge in at least one of the following fields: - machine learning, - speech recognition, - acoustic event detection, - speech and audio processing. Excellent knowledge of scientific programming languages such as Python or MATLAB, as well as excellent English language skills are required. The position is funded by the newly established DFG collaborative research centre CRC 1330 "Hearing Acoustics", which aims at improving human communication in real-world acoustic scenes and is a long-term collaboration of researchers from Oldenburg, Aachen and Munich. For more information about the CRC see https://www.uni-oldenburg.de/sfb1330. The Computational Audition Group is part of the Department of Medical Physics and Acoustics at University of Oldenburg. We offer an international scientific environment and world-class research facilities. For more information about the group and the department see https://uol.de/computational-audition/ and https://uol.de.de/en/mediphysics-acoustics/. The University of Oldenburg is dedicated to increase the percentage of women in science. Therefore, female candidates are strongly encouraged to apply. In accordance to ? 21 Section 3 NHG, female candidates with equal qualifications will be preferentially considered. Applicants with disabilities will be given preference in case of equal qualification. Applications including a CV, a motivation letter, copies of relevant certificates and the name and contact details of two references should be sent as single pdf-file to joern.anemueller at uni-oldenburg.de or to Dr. J?rn Anem?ller? Faculty VI? Department of Medical Physics and Acoustics? Universit?t Oldenburg? D - 26111 Oldenburg? Tel. (+49) 441 798 3610 The application deadline is 28th of November 2018. ******************************************************* -------------- next part -------------- An HTML attachment was scrubbed... URL: From rloosemore at susaro.com Sat Nov 10 01:00:36 2018 From: rloosemore at susaro.com (Richard Loosemore) Date: Sat, 10 Nov 2018 01:00:36 -0500 Subject: Connectionists: Why is the neural-to-concept mapping issue being ignored (still)? In-Reply-To: References: Message-ID: All, I have bit of a bone to pick, if you don't mind. Why is the question of how concepts relate to neurons so scandalously incoherent, even after this field has been talking about it for at least 35 years? In particular, why do so many papers - multiple thousands, by now - in the neuroscience/connectionist nexus make the naive assumption that a number of neurons (one neuron, a cluster, a distributed cluster, a sparse group) will correspond to one concept?? So much so that when those neurons light up in an fMRI, or are active electrically, people declare that the concept must be 'there'? We have known for a long time that such a naive correspondence has serious problems.? (I say 'long time' because I remember discussing the problems with John Taylor in 1981, and certainly Donald Norman raised them in his chapter at the end of the two PDP volumes)? For example, what happens when I create a brand new concept and name it?? Let's say I decide to give the name "skandulupper" to the concept of "watching all of Tuesday Weld's movies in one week":? does the human brain suddenly manage to find a single neuron or a cluster that just happen to have all the right connections to all the phoneme neurons for that word, and to the concept neurons for "Tuesday Weld", and "movie" and "week"?? (Notice that if the new concept is only hanging around in transient (working memory) storage, with permanent storage in long term memory being assigned during some kind of overnight WM->LTM consolidation, that really only postpones the awkward questions about how the right neurons, with the right connections, are located.) And if the answer to that awkward question about new concepts is "Duh!? Distributed representations, of course!", then what do we do about the next awkward question?? You know the one:? if there is a distributed representation for a concept like, say "cook", then how does the system represent a sentence like "Cook was a good cook, as cooks go; but as good cooks go, Cook went."? The problem is, that there has never been a good answer to these issues, so what the community seems to have done instead is to write a thousand papers describing various neuroscience findings AS IF the representations are pretty much localist, or sparse, or even grandmotherly.? Why is it acceptable to publish papers as if a KNOWN FAILED MODEL is the one that is assumed to be valid?? The whole community seems to be suffering from a collective delusion. Let's try to be absolutely clear, here.? Localist, semi-localist, sparse, and distributed representations do not work as accounts of actual cognition, unless they are used in "toy" models that do nothing more than a fantasy version of what we know the real brain does.? Let's not pretend that just because a lot of people play with toy models, and a lot of people pretend that the toy models mean something, that somehow that changes the reality.? This is especially true of "reinforcement learning" models that claim to show that the brain does RL -- a close examination of these claims hinge on a sudden bait and switch from real neural wiring to a toy model applied to trivial data, which could not possibly scale up. Now, it so happens that there really is a way to imagine a solution to this problem, at the theoretical level.? One simply has to accept that the neural machinery is set up in such a way that the structures corresponding to concepts are neither localist nor distributed, but virtual.? That means that concepts are to the neural hardware what programs in a computer network system are to the physical computers -- concepts are allowed to have two states (active and dormant) and when active the concepts have most of the properties of an old-school symbol processing system.? Any version of this virtual-concept idea would solve the problems inherent in assuming that neurons correspond to concepts. Notice that we do not have to produce a fully-functional simulation of such a virtual-concept system, for it to be a valid competitor to localist, semi-localist, sparse, and distributed representations.? The latter are known failures, and "simulations" of them are invariably toy models that cannot scale up.? In that context, it is enough to point out that the basic properties of a virtual-concept type of model are already superior to the idea that representations are localist, semi-localist, sparse, or distributed.? Calling something a "virtual-concept" system is almost the same as saying that it is a variety of symbolic system ... and there were many dozens of symbolic systems in the 1970s, 80s and 90s that were fully implemented, and that clearly did not suffer the problems shown by localist, semi-localist, sparse, and distributed neural representations. -- I have a personal reason for raising this question. Trevor Harley and I tried to raise this question in a paper we wrote in 2010 [1].? Long story short, we said "Look, any kind of virtual-concept system is the NEXT SIMPLEST theoretical construct up from the two known failed constructs (localist and distributed), so let's see what would happen if some version of that virtual-concept idea turns out to be the way things are."? In particular, we asked two questions:? (1) Would the arguments and conclusions in a selection of popular brain-imaging/neuroscience papers actually make any sense, if the brain really was using this next-best type of system?, and (2) Would the virtual-concept idea give a better account of any of these published neuroscience results? We expanded a little on what the virtual-concept idea might actually mean, so our readers would have a concrete feel for the overall implications.? Then we analysed the chosen set of papers.? Our conclusions were that most of the arguments in the papers fell to pieces if virtual concepts were what the brain was doing, and that the virtual-concept idea gave a better account of many of the published results. And then this happened.? Our paper was a book chapter, and in the same book William Bechtel and Richard C. Richardson decided to go on the offensive and trash every claim we tried to make.? With language like: "Loosemore and Harley [...] evidently do not think of this as a serious model of cognition, but as a kind of toy structure [...]? The model is presented very sketchily, with no empirical backing and no substantive constraints. Loosemore and Harley [...] offer no detailed results to demonstrate that the model could accommodate even the most accepted empirical results about recognition or control. [...] This, however, is a cartoon of serious science [...]? If Loosemore and Harley were right, then evolutionary biologists would need consistently to defend themselves against Creationist contentions" Words cannot express my feelings, here.? What kind of science is this, when someone is compared to a Creationist for discussing a model that, quite simply, is the only kind of model that has any hope of getting out of the known problems of the toy models that are currently accepted as the norm? Richard Loosemore. [1]? Loosemore, R.P.W. & Harley, T.A. (2010). Brains and Minds:? On the Usefulness of Localization Data to Cognitive Psychology. In M. Bunzl & S.J. Hanson (Eds.), Foundational Issues in Human Brain Mapping. Cambridge, MA: MIT Press. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ASIM.ROY at asu.edu Sun Nov 11 02:17:55 2018 From: ASIM.ROY at asu.edu (Asim Roy) Date: Sun, 11 Nov 2018 07:17:55 +0000 Subject: Connectionists: Why is the neural-to-concept mapping issue being ignored (still)? In-Reply-To: References: Message-ID: Dear Richard, Frontiers recently published an e-book on ?Representation in the Brain.? Here?s the link: https://www.frontiersin.org/research-topics/4398/representation-in-the-brain Eleven more articles added to the thousands you mention. Some of the papers argue for localist representation, while others argue for distributed representation. I would argue that localist representation is synonymous with symbolic systems. And localist representation is widely used in the brain. My paper in the e-book is about the brain being a purely abstract system at the single cell (neuron) level and there is plenty of neurophysiological evidence for that from single cell studies. And an abstract system is synonymous with symbolic systems. Here?s the link to the paper: The Theory of Localist Representation and of a Purely Abstract Cognitive System: The Evidence from Cortical Columns, Category Cells, and Multisensory Neurons Here are some related papers: A theory of the brain: localist representation is used widely in the brain An extension of the localist representation theory: grandmother cells are also widely used in the brain Among the neuroscientists, Horace Barlow, great grandson of Darwin (https://en.wikipedia.org/wiki/Horace_Barlow), is perhaps the only one who has argued for grandmother cells in the brain. We have had discussions on these issues in small groups at various times over the last few years. And Barlow was in one of those discussion groups. If there is interest, we can again form a small discussion group to discuss the issues you have raised. I think there is much evidence from single cell studies to claim that the brain is a symbolic system. So, as I see it, there is perhaps some convergence on this issue. All the best, Asim Roy Professor, Information Systems Arizona State University www.lifeboat.com/ex/bios.asim.roy From: Connectionists On Behalf Of Richard Loosemore Sent: Friday, November 09, 2018 11:01 PM To: connectionists at mailman.srv.cs.cmu.edu Subject: Connectionists: Why is the neural-to-concept mapping issue being ignored (still)? All, I have bit of a bone to pick, if you don't mind. Why is the question of how concepts relate to neurons so scandalously incoherent, even after this field has been talking about it for at least 35 years? In particular, why do so many papers - multiple thousands, by now - in the neuroscience/connectionist nexus make the naive assumption that a number of neurons (one neuron, a cluster, a distributed cluster, a sparse group) will correspond to one concept? So much so that when those neurons light up in an fMRI, or are active electrically, people declare that the concept must be 'there'? We have known for a long time that such a naive correspondence has serious problems. (I say 'long time' because I remember discussing the problems with John Taylor in 1981, and certainly Donald Norman raised them in his chapter at the end of the two PDP volumes) For example, what happens when I create a brand new concept and name it? Let's say I decide to give the name "skandulupper" to the concept of "watching all of Tuesday Weld's movies in one week": does the human brain suddenly manage to find a single neuron or a cluster that just happen to have all the right connections to all the phoneme neurons for that word, and to the concept neurons for "Tuesday Weld", and "movie" and "week"? (Notice that if the new concept is only hanging around in transient (working memory) storage, with permanent storage in long term memory being assigned during some kind of overnight WM->LTM consolidation, that really only postpones the awkward questions about how the right neurons, with the right connections, are located.) And if the answer to that awkward question about new concepts is "Duh! Distributed representations, of course!", then what do we do about the next awkward question? You know the one: if there is a distributed representation for a concept like, say "cook", then how does the system represent a sentence like "Cook was a good cook, as cooks go; but as good cooks go, Cook went."? The problem is, that there has never been a good answer to these issues, so what the community seems to have done instead is to write a thousand papers describing various neuroscience findings AS IF the representations are pretty much localist, or sparse, or even grandmotherly. Why is it acceptable to publish papers as if a KNOWN FAILED MODEL is the one that is assumed to be valid? The whole community seems to be suffering from a collective delusion. Let's try to be absolutely clear, here. Localist, semi-localist, sparse, and distributed representations do not work as accounts of actual cognition, unless they are used in "toy" models that do nothing more than a fantasy version of what we know the real brain does. Let's not pretend that just because a lot of people play with toy models, and a lot of people pretend that the toy models mean something, that somehow that changes the reality. This is especially true of "reinforcement learning" models that claim to show that the brain does RL -- a close examination of these claims hinge on a sudden bait and switch from real neural wiring to a toy model applied to trivial data, which could not possibly scale up. Now, it so happens that there really is a way to imagine a solution to this problem, at the theoretical level. One simply has to accept that the neural machinery is set up in such a way that the structures corresponding to concepts are neither localist nor distributed, but virtual. That means that concepts are to the neural hardware what programs in a computer network system are to the physical computers -- concepts are allowed to have two states (active and dormant) and when active the concepts have most of the properties of an old-school symbol processing system. Any version of this virtual-concept idea would solve the problems inherent in assuming that neurons correspond to concepts. Notice that we do not have to produce a fully-functional simulation of such a virtual-concept system, for it to be a valid competitor to localist, semi-localist, sparse, and distributed representations. The latter are known failures, and "simulations" of them are invariably toy models that cannot scale up. In that context, it is enough to point out that the basic properties of a virtual-concept type of model are already superior to the idea that representations are localist, semi-localist, sparse, or distributed. Calling something a "virtual-concept" system is almost the same as saying that it is a variety of symbolic system ... and there were many dozens of symbolic systems in the 1970s, 80s and 90s that were fully implemented, and that clearly did not suffer the problems shown by localist, semi-localist, sparse, and distributed neural representations. -- I have a personal reason for raising this question. Trevor Harley and I tried to raise this question in a paper we wrote in 2010 [1]. Long story short, we said "Look, any kind of virtual-concept system is the NEXT SIMPLEST theoretical construct up from the two known failed constructs (localist and distributed), so let's see what would happen if some version of that virtual-concept idea turns out to be the way things are." In particular, we asked two questions: (1) Would the arguments and conclusions in a selection of popular brain-imaging/neuroscience papers actually make any sense, if the brain really was using this next-best type of system?, and (2) Would the virtual-concept idea give a better account of any of these published neuroscience results? We expanded a little on what the virtual-concept idea might actually mean, so our readers would have a concrete feel for the overall implications. Then we analysed the chosen set of papers. Our conclusions were that most of the arguments in the papers fell to pieces if virtual concepts were what the brain was doing, and that the virtual-concept idea gave a better account of many of the published results. And then this happened. Our paper was a book chapter, and in the same book William Bechtel and Richard C. Richardson decided to go on the offensive and trash every claim we tried to make. With language like: "Loosemore and Harley [...] evidently do not think of this as a serious model of cognition, but as a kind of toy structure [...] The model is presented very sketchily, with no empirical backing and no substantive constraints. Loosemore and Harley [...] offer no detailed results to demonstrate that the model could accommodate even the most accepted empirical results about recognition or control. [...] This, however, is a cartoon of serious science [...] If Loosemore and Harley were right, then evolutionary biologists would need consistently to defend themselves against Creationist contentions" Words cannot express my feelings, here. What kind of science is this, when someone is compared to a Creationist for discussing a model that, quite simply, is the only kind of model that has any hope of getting out of the known problems of the toy models that are currently accepted as the norm? Richard Loosemore. [1] Loosemore, R.P.W. & Harley, T.A. (2010). Brains and Minds: On the Usefulness of Localization Data to Cognitive Psychology. In M. Bunzl & S.J. Hanson (Eds.), Foundational Issues in Human Brain Mapping. Cambridge, MA: MIT Press. -------------- next part -------------- An HTML attachment was scrubbed... URL: From poma at mmmi.sdu.dk Sat Nov 10 17:09:04 2018 From: poma at mmmi.sdu.dk (Poramate Manoonpong) Date: Sat, 10 Nov 2018 22:09:04 +0000 Subject: Connectionists: [news] Ebook on Neural Computation in Embodied Closed-Loop Systems for the Generation of Complex Behavior: From Biology to Technology In-Reply-To: <57c016d507e04ddebe97df5e24edb31b@mmmi.sdu.dk> References: <57c016d507e04ddebe97df5e24edb31b@mmmi.sdu.dk> Message-ID: <4c008fe5dca54e689aefbec4ebe13c6e@mmmi.sdu.dk> Dear Colleagues, We would like to introduce you to the recent Ebook on Neural Computation in Embodied Closed-Loop Systems for the Generation of Complex Behavior: From Biology to Technology [1], published Frontiers in Neurorobotics. The Ebook collects 17 cutting edge research articles, covering neural and morphological computations as well as the transfer of results to real world applications, like prosthesis and orthosis control and neuromorphic hardware implementation. Any comments and suggestions are welcome. [1] https://www.frontiersin.org/research-topics/4674/neural-computation-in-embodied-closed-loop-systems-for-the-generation-of-complex-behavior-from-biolo Best regards, Poramate Manoonpong and Christian Tetzlaff -------------- next part -------------- An HTML attachment was scrubbed... URL: From eero at cns.nyu.edu Sun Nov 11 20:51:58 2018 From: eero at cns.nyu.edu (Eero Simoncelli) Date: Sun, 11 Nov 2018 20:51:58 -0500 (EST) Subject: Connectionists: Doctoral studies in Computational/Theoretical Neuroscience at NYU Message-ID: <201811120151.wAC1pwS10763@calaf.cns.nyu.edu> New York University is home to a thriving interdisciplinary community of researchers using computational and theoretical approaches in neuroscience. We are interested in exceptional PhD candidates with strong quantitative training (e.g., physics, mathematics, engineering) coupled with a clear interest in scientific study of the brain. A listing of faculty, sorted by their primary departmental affiliation, is given below. Doctoral programs are flexible, allowing students to pursue research across departmental boundaries. Nevertheless, admissions are handled separately by each department, and students interested in pursuing graduate studies should submit an application to the program that best fits their goals and interests. Center for Neural Science (CNS), Graduate School of Arts & Sciences (deadline: 1 December) [http://neuroscience.nyu.edu/graduate-programs/, and http://www.cns.nyu.edu/doctoral/] * Andre A. Fenton - Molecular, neural, behavioral, and computational aspects of memory. * Paul W. Glimcher - Decision-making in humans and animals. Neuroeconomics. * Roozbeh Kiani - Vision and decision-making. * Wei Ji Ma (also in Psychology) - Perception, working memory, and decision-making. * Tony Movshon - Vision and visual development. * Bijan Pesaran - Neuronal dynamics and decision-making. * Alex Reyes - Functional interactions of neurons in a network. * John Rinzel (also in Mathematics) - Biophysical mechanisms and theory of neural computation. * Cristina Savin (also in the Center for Data Science) - Computational models of learning and memory, machine learning. * Robert Shapley - Visual physiology and perception. * Eero Simoncelli - Computational vision and audition. * Xiao-Jing Wang - Computational neuroscience, decision-making and working memory, neural circuits. Neuroscience Institute, School of Medicine (deadline: 1 December) [http://neuroscience.nyu.edu/graduate-programs/, and https://med.nyu.edu/departments-institutes/neuroscience/] * Gyorgy Buzsaki - Rhythms in neural networks. * Dmitri Chklovskii (also in the Simons Foundation) - Neural computation and connectomics. * Dmitry Rinberg - Sensory information processing in the behaving animal. * Mario Svirsky - Auditory neural prostheses; experimental/computational studies of speech production/perception. Psychology, Cognition & Perception program (deadline: 1 December) [http://as.nyu.edu/psychology/graduate/phd-cognition-perception.html] * Todd Gureckis - Memory, learning, and decision processes. * David Heeger (also in CNS) - fMRI, computational neuroscience, vision, attention. * Brendan Lake (also in the Center for Data Science) - Computational modeling of cognition. * Michael Landy - Computational approaches to vision. * Laurence Maloney - Mathematical approaches to psychology and neuroscience. * Gary Marcus - Origins of the human mind. * Denis Pelli - Visual object recognition. * Jonathan Winawer - Visual perception and memory. Mathematics (deadline: 18 December) [http://math.nyu.edu/degree/phd/] * David Cai - Nonlinear stochastic behavior in physical and biological systems. * David McLaughlin - Nonlinear wave equations, computational visual neuroscience. * Aaditya Rangan - computational neurobiology, numerical analysis. * Charles Peskin - Mathematical biology. * Michael Shelley - Modeling and large-scale computation, computational visual neuroscience. * Daniel Tranchina - Information processing in the retina. * Lai-Sang Young - Dynamical systems, statistical physics, computational modeling and theoretical neuroscience. Center for Data Science (deadline: 12 December) [https://cds.nyu.edu/academics/phd-in-data-science/] b" Joan Bruna (also in Computer Science) - machine learning, signal/image processing. b" Kyungyun Cho (also in Computer Science) - machine learning, natural language processing. b" Carlos Fernandez-Granda (also in Mathematics) - optimization methods for medical imaging, neuroscience, computer vision. * Brenden Lake - Computational modeling of cognition, deep learning. Physics (deadline: 18 December) [http://physics.as.nyu.edu/page/graduate] * Marc Gershow - Perception, decision-making, and learning in neural circuits. Computer Science (deadline: 12 December) [http://www.cs.nyu.edu/home/phd/] * Davi Geiger - Computational vision and learning. * Yann LeCun - machine learning, computer vision, robotics, computational neuroscience. Economics (deadline: 18 December) [http://as.nyu.edu/econ/degree-programs/phd.html] * Andrew Caplin - Economic theory, neurobiology of decision. * Andrew Schotter - Experimental economics, game theory, neurobiology of decision. From inesdomingues at gmail.com Mon Nov 12 05:38:08 2018 From: inesdomingues at gmail.com (=?UTF-8?Q?In=C3=AAs_Domingues?=) Date: Mon, 12 Nov 2018 10:38:08 +0000 Subject: Connectionists: =?utf-8?q?Special_Issue_Call_for_Papers_-_?= =?utf-8?q?=E2=80=9CMultimedia_Systems_and_Applications_in_Biomedic?= =?utf-8?b?aW5l4oCd?= Message-ID: -------------------------------------------------------------------------------- Please re-distribute (Apologies for cross posting) -------------------------------------------------------------------------------- -------------------------------------------------------------------------------- CALL FOR PAPERS Special Issue Call for Papers - ?Multimedia Systems and Applications in Biomedicine? -------------------------------------------------------------------------------- Aims and Scope -------------------------------------------------------------------------------- Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization (http://www.tandfonline.com/toc/tciv20/current) invites submissions to the Special Issue on ?Multimedia Systems and Applications in Biomedicine?. Advances in computing techniques, data acquisition technology, hardware, and networks have mutually promoted the development of multimedia analysis approaches. Many machine learning, signal/image processing, and data mining algorithms have been successfully developed for multimedia analysis. WIthin the multimedia domain, medical data analysis has attracted considerable attention due in part to the increase of imaging modalities. Consider the assessment of the functioning of the heart. Physicians have multiple resources and modalities available, including: auscultation which can produce a report in text format; electrocardiograms which result in time series, x-rays saved as images; volumes provided through angiography; temporal information given by echocardiograms, and 4D information extracted through flow MRI. Since gathering medical data is now easier than ever before, existing multimedia learning methods are expected to embrace new challenges to deal with large-scale medical data that may share totally different data distributions or may continuously change over time. This special issue will serve as a way to set the state of the art in the advances in multimedia learning methods for various medical applications. -------------------------------------------------------------------------------- Topics of Interest -------------------------------------------------------------------------------- Topics appropriate for this special issue include (but are not limited to): - 2D/3D Image reconstruction - Computational Bio-imaging and Visualization - Computer-Aided diagnostic systems - Data acquisition - Data Processing and Analysis - Devices for Imaging and Visualization - Disease recognition, classification and retrieval - Human Perception in Imaging and Visualization - Image denoising and enhancement - Image Processing and Analysis - Image registration and calibration - Imaging and Visualization in Biomedical Engineering - Landmark/structure detection - Large scale 3D data indexing - Medical Image Representation - Medical Image Understanding - Medical Imaging and Visualization - Multi-modal Imaging and Visualization - Multiscale Imaging and Visualization - Scientific Visualization - Segmentation/labeling - Software Development for Imaging and Visualization - Surgical and interventional systems - Telemedicine Systems and Applications - Virtual Reality - Visual Data Mining and Knowledge Discovery - Visualization and visual synthesis Manuscripts must clearly delineate the role of multimedia systems and applications in Biomedicine. The manuscript should include new contributions beyond those made in earlier publications. Review works will also be considered in this special issue. Contributions should be described in sufficient detail to be reproducible on the basis of the material and references presented in the paper. -------------------------------------------------------------------------------- Important Dates -------------------------------------------------------------------------------- Manuscript Due : December 10, 2018 First Decision Date : February 11, 2019 Second Revision Due : April 15, 2019 Final Decision Date : June 10, 2019 Camera Ready Version Due : August 12, 2019 -------------------------------------------------------------------------------- PAPER SUBMISSION -------------------------------------------------------------------------------- The paper should be submitted at https://mc.manuscriptcentral.com/tciv, choosing on step 5, the option ?Multimedia Systems and Applications in Biomedicine? -------------------------------------------------------------------------------- Guest Editorial Board -------------------------------------------------------------------------------- In?s Domingues Ana F. Sequeira Carla Pinto ?lvaro Rocha From boris.gutkin at ens.fr Mon Nov 12 04:47:51 2018 From: boris.gutkin at ens.fr (boris gutkin) Date: Mon, 12 Nov 2018 10:47:51 +0100 Subject: Connectionists: Junior Professorship in Computational Neuroscience at Ecole Normale Superieure, Paris France - DEADLINE 15 NOV 2018 Message-ID: Applications are invited for a Junior Professor in Computational Neuroscience position at Ecole Normale Superieure, Paris France Department of Cognitive Studies at the Ecole Normale Superieure (Paris France) seeks candidates for a tenure-track junior professor in computational neuroscience. Candidates in cognitive computational neuroscience, machine learning approaches to neuroscience and statistical neuroscience are particularly encouraged to apply. Successful candidate will join the computational neuroscience core at the Laboratory for Cognitive and Computational Neuroscience (LNC2, https://lnc2.dec.ens.fr/fr). Candidates should show a strong track record of research in computational neuroscience as well as potential for scientific independence and achievement. Candidate will be expected to develop an independent research program during their pre-tenure period In addition to research candidates will spear-head the computational neuroscience track in the Master of Cognitive Sciences at ENS (Cogmaster,www.cogmaster.net/), provide teaching in computational neuroscience at the masters and upper undergraduate level as well as supervise masters and doctoral students.The position offers a 5-year tenure-track contract with an evaluation at the end of the 3rd year. Upon successful evaluation, the candidate will proceed directly to a competition for a full professorship at ENS Paris. Support for national and international grant competitions will be provided.The candidate will join a lively cognitive neuroscience and computational neuroscience community. Notably the computational neuroscience core of the LNC includes research groups of Boris Gutkin, Srdjan Ostojic and Sophie Deneve and counts over 20 members in total. Computational approaches to human cognitive neuroscience and neuroeconomics are also represented by groups of Etienne Koechlin, Valentin Wyart and Stefano Palminteri. Ample interactions with experimental and computational groups in the Paris area are available and encouraged. LNC2-DEC-ENS is located in the heart of Paris in the Quartier Latin.Candidates should send an application package by e-mail to the application email address below. The subject line should include the words COMPUTATIONAL NEUROSCIENCE ENS POSITION followed by the name of the applicant.APPLICATION ADDRESS: recruitment.jp-compneuro at ens.fr The application package should include: a CV, including a list of publications; contacts of 3 referees from whom recommendations letters can be requested; ?a statement outlining both teaching and research goals/experience (up to 3 pages); a research sample consisting of 3 papers. Deadline for the applications is Nov 15 2018. Candidate is expected to start in September 2019. Informal inquiries and Questions can be sent to boris.gutkin at ens.fr -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.hennig at ed.ac.uk Mon Nov 12 07:43:19 2018 From: m.hennig at ed.ac.uk (Matthias Hennig) Date: Mon, 12 Nov 2018 12:43:19 +0000 Subject: Connectionists: PhD in cortical memory storage at the University of Edinburgh Message-ID: <909b0a32-3d62-da13-6a48-cd2faf838dcc@ed.ac.uk> Applications are invited for an EASTBIO-funded PhD position in the labs of Dr. Gulsen Surmeli and Dr. Matthias Hennig. This is an excellent training opportunity for a highly motivated individual to learn both the use of modern in vivo functional neuron imaging technologies and the applications computational methods to address fundamental questions in neuronal computation. Objectives: Cognitive abilities are a result of coordinated activity of billions of neurons. Recent advances in neuroscience research now enables monitoring activity of thousands of neurons during cognitive tasks. Decoding these large ensemble codes enable unprecedented insight into the inner workings of the brain. This project aims to investigate neural ensemble coding of cortical memory networks. In this project, we will investigate the encoding of memories in cortical networks. In Dr. Surmeli?s lab, a miniaturized head attached fluorescent microscope (miniscope) will be used to perform cellular resolution imaging of activity of neuronal ensembles in freely moving mice during memory tasks. Combined with advanced genetic techniques this method allows tracking activity of thousands of neurons during memory formation and recall. Since memory engrams are typically sparse and highly distributed over many neurons, tracking the acquisition of new memories will require advanced analysis methods, which will be developed in collaboration with the second supervisor based in the School of Informatics. Moreover, the results will enable constructing new models of short and long-term memory acquisition that can advance artificial neural networks used in machine learning applications. For conditions of applying and to apply please refer to: https://www.findaphd.com/search/ProjectDetails.aspx?PJID=100855 Download application and reference forms via: https://www.ed.ac.uk/roslin/postgraduate/bbsrc-eastbio-dtp Lab website/Online Profile https://www.ed.ac.uk/discovery-brain-sciences/our-staff/research-groups/dr-gulsen-surmeli http://homepages.inf.ed.ac.uk/mhennig/ -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From jbaimon at sandia.gov Mon Nov 12 16:03:26 2018 From: jbaimon at sandia.gov (Aimone, James Bradley) Date: Mon, 12 Nov 2018 21:03:26 +0000 Subject: Connectionists: Neuro-Inspired Computational Elements (NICE) 2019 Abstract Submission Closes in a week Message-ID: <6b322b1339ee40a4b46078247767ac3c@ES04AMSNLNT.srn.sandia.gov> Dear all: Three notes on the upcoming 2019 NICE Workshop 1. Deadline: Due to a few requests, abstract submission will be kept open for a few extra days. Easychair will be closed to new submissions on Monday, November 19th. 2. Conference Proceedings: As suggested below, NICE will have its first proceedings! We will invite full-length submissions from the top submitted abstracts. Proceedings will be published through ACM?s International Conference Proceedings Series. Details are on the CFP https://easychair.org/cfp/NICE2019 3. Registration: NICE 2019 registration is posted at http://niceworkshop.org/nice-2019/ Best wishes, Brad Aimone From: Aimone, James Bradley Sent: Monday, September 24, 2018 9:03 AM To: Aimone, James Bradley Cc: Murat Okandan (mokandan at niceworkshop.org) Subject: Neuro-Inspired Computational Elements (NICE) 2019 Abstract Submission Open! Dear Colleagues: The call for abstracts for NICE 2019 is open for submissions at https://easychair.org/cfp/NICE2019 As with past NICE workshops, we are seeking submissions describing advances at the intersection of theoretical neuroscience, neural computing hardware and algorithms, and applications of this brain-inspired computing technology. Preference will be given to unpublished results that bridge our community. For agendas and videos of talks from past meetings, please see http://niceworkshop.org Submissions are 2 page extended abstracts, which will be reviewed to select full and short talks, as well as posters. New for NICE this year we are looking at potential options for proceedings papers, to be invited from the top submissions this year. Abstracts are due on November 15th. Registration will open in a few weeks. ---------------- NICE 2019 will be taking place during March 26-29, 2019 in Albany CNSE Campus in Albany, NY Important dates: Abstract call: September 15, 2018 Abstract submission open: September 22, 2018 Abstracts due: November 15, 2018 Selection announcement: January 15, 2019 ----------------- Hope to see you in Albany! Brad Aimone NICE Program Chair -------------------------- James Bradley Aimone, Ph.D. Principal Member of Technical Staff Data-driven and Neural Computing Department Center for Computing Research Sandia National Laboratories Phone: (505) 284-3147 Fax: (505) 844-4728 http://neuroscience.sandia.gov -------------- next part -------------- An HTML attachment was scrubbed... URL: From richard.jiang at northumbria.ac.uk Mon Nov 12 18:18:09 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Mon, 12 Nov 2018 23:18:09 +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 ? Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark Email: weme at dtu.dk ? Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia Email: chli at csu.edu.au ? Professor Christophe Rosenberger Computer Security ENSICAEN ? GREYC, France Email: christophe.rosenberger at ensicaen.fr Contact: All questions about submissions can be emailed to perceptualscience at outlook.com or any editor in the board. Many thanks! Kind Regards, Editors of the Book This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender?s explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. 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 m.hennig at ed.ac.uk Tue Nov 13 06:47:38 2018 From: m.hennig at ed.ac.uk (Matthias Hennig) Date: Tue, 13 Nov 2018 11:47:38 +0000 Subject: Connectionists: PhD positions in computational neuroscience, University of Edinburgh Message-ID: <8c0ab2cd-07f0-6c00-1562-b8bde5485f63@ed.ac.uk> 3 YEAR PhD IN COMPUTATIONAL NEUROSCIENCE, UNIVERSITY OF EDINBURGH. We invite applications for our PhD programme in COMPUTATIONAL NEUROSCIENCE at the Institute for Adaptive and Neural Computation at the University of Edinburgh. The studentships are ideal for students who want to apply their computational and analytical skills to problems in neuroscience and related fields. The following supervisors have openings: Matthias Hennig: Neural network models; homeostasis and development; visual and auditory neuroscience; analysis of large-scale recordings. Arno Onken: Neural coding; machine learning for neural data analysis; multi-modal and multi-scale analysis. Peggy Seri?s: Bayesian approaches to cognition and perception; computational psychiatry. The PhD project can be done in collaboration with one of the many affiliated departments and institutes. Edinburgh has been voted as 'best place to live in Britain', and has many exciting cultural and student activities. Students with a strong background in either computer science, mathematics, physics or engineering are particularly welcome to apply. Motivated students with other backgrounds will also be considered. To apply, visit https://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&edition=2019&id=489 Applications completed by 16. January 2019 will receive full consideration. -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From acarlin at aptima.com Tue Nov 13 10:16:10 2018 From: acarlin at aptima.com (Alan Carlin ) Date: Tue, 13 Nov 2018 15:16:10 +0000 Subject: Connectionists: Call for Papers: Intelligent Learning Technologies track at FLAIRS-32 Message-ID: <5d3671960e30489caf79bee42f777156@aptima.com> Dear Colleagues, Below is a call for papers for the Intelligent Learning Technologies special track at 32nd International Florida AI Research Society (FLAIRS) conference. If you have work related to training or learning (of humans!), we would like to invite you to submit to this track. Call for Papers: Intelligent Learning Technologies Direct Link: https://sites.google.com/view/flairs-ilt2018/home Held at FLAIRS-32. May 19-22 2019, Sarasota, Florida What are Intelligent Learning Technologies? Intelligent learning technologies (ILT) include a diverse array of computer-based systems and tools designed to foster meaningful student learning. These technologies are intelligent to the extent they implement artificial intelligence principles and techniques to create teachable structure from content, analyze and model inputs from the learner, and generate personalized and adaptive feedback and guidance. Intelligent tutoring systems (ITSs) represent a classic example. ITSs, broadly defined, possess an "outer loop" that intelligently selects the next relevant task, or content object, for learners to complete based on prior performance, and an "inner loop" that provides iterative and intelligent feedback as learners work toward completing their tasks. However, intelligent learning technologies encompass more than just intelligent tutors. Increasingly, educational games, automated writing evaluation, virtual pedagogical agents, simulations, virtual worlds, open-ended problem solving, generative concept maps, AI-assisted authoring systems, learning content aggregation programs, and e-textbooks rely on some form of artificial intelligence to enrich the learning experience. What is the GOAL of this track? The purpose of this track is to bring together an international group of scientists to present innovative empirical research, technical innovations, and well-grounded theory related to artificial intelligence in learning technologies. This track will inform attendees about recent developments in the design, implementation, and evaluation of such systems. This track is a continuation of the 2016-2018 FLAIRS ILT track, which naturally emerged from the longstanding Intelligent Tutoring Systems special track. The aim of the Intelligent Learning Technologies track is to be more representative and inclusive of the diverse work being conducted with intelligent systems that support student learning. What kind of studies will be of interest? The Intelligent Learning Technologies special track welcomes original, well-written reports on empirical evaluations of learning technologies, innovative designs and implementations, and theoretical principles that advance the field. The preference for all submissions is to include both substantive references to the existing literature and empirical data. We seek submissions that address a variety of intelligent learning technology issues including, but not limited to: 1. Adaptive scaffolding in open-ended learning environments 2. Assistive technologies for learners with special needs 3. Automated writing evaluation 4. Educational data mining and learning analytics 5. Interaction-based learner modeling from novice or expert populations 6. Effective design principles for intelligent learning technologies 7. Game-based, narrative-based, and virtual learning environments 8. Intelligent tutoring systems 9. Natural language processing to support intelligent interaction and feedback 10. Novel designs, interfaces, and scaffolds 11. Overcoming challenges within the field (e.g., gaming the system, ill-defined domains) 12. Teachable agents, learning companions, and other pedagogical agents 13. Tests of existing intelligent learning technologies 14. Efficient sampling methods for experiments in learning environments 15. Analysis and analytics of Massive Open Online Courses (MOOC) Important Dates November 19, 2018 - Paper submission deadline January 21, 2019 - Paper acceptance notification February 25, 2019 - Camera ready version due May 19-22, 2019 - Conference Track Co-Chairs: Alan Carlin, Aptima, Inc. acarlin at aptima.com Benjamin Nye, University of Southern California Institute for Creative Technologies. nye at ict.usc.edu Stephen E. Fancsali, Carnegie Learning, Inc. sfancsali at carnegielearning.com Conference Proceedings Papers will be refereed and all accepted papers will appear in the conference proceedings, which will be published by AAAI Press. In cooperation with: Association for the Advancement of Artificial Intelligence Submission Guidelines Interested authors should format their papers according to AAAI formatting guidelines. The papers should be original work. Papers should not exceed 6 pages (4 pages for a poster) and are due by November 19, 2018. For FLAIRS-32, the 2019 conference, the reviewing is a double blind process. Fake author names and affiliations must be used on submitted papers to provide double-blind reviewing. Papers must be submitted as PDF through the EasyChair conference system, which can be accessed through the main conference web site. Note: do not use a fake name for your EasyChair login - your EasyChair account information is hidden from reviewers. Authors should indicate the Intelligent Learning Technologies special track for submissions. The proceedings of FLAIRS will be published by the AAAI. Authors of accepted papers will be required to sign a form transferring copyright of their contribution to AAAI. FLAIRS requires that there be at least one full author registration per paper. Submit papers using EasyChair The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender and delete the material from any computer. -------------- next part -------------- An HTML attachment was scrubbed... URL: From massimiliano.pontil at gmail.com Tue Nov 13 12:16:44 2018 From: massimiliano.pontil at gmail.com (massimiliano.pontil at gmail.com) Date: Tue, 13 Nov 2018 17:16:44 +0000 Subject: Connectionists: 2 Postdocs in Machine Learning Message-ID: Two Postdocs to work in Machine Learning at Instituto Italiano di Tecnologia in Genoa. Outstanding candidates will be considered in all areas of Machine Learning with a preference to the following areas: online learning, statistical learning theory, numerical and stochastic optimization. If you are at NIPS, please email me to arrange a meeting in person. Information on how to apply: https://www.iit.it/careers/openings/opening/751-1-postdoctoral-position-in-machine-learning https://www.iit.it/careers/openings/opening/827-1-postdoctoral-position-on-machine-learning Deadline: January 15, 2019. Massimiliano Pontil Istituto Italiano di Tecnologia and University College London https://www.iit.it/research/lines/computational-statistics-and-machine-learning From Samuel.Neymotin at nki.rfmh.org Tue Nov 13 14:20:27 2018 From: Samuel.Neymotin at nki.rfmh.org (Neymotin, Samuel (NKI)) Date: Tue, 13 Nov 2018 19:20:27 +0000 Subject: Connectionists: Postdoc in auditory thalamocortical system modeling & data analysis Message-ID: A computational neuroscience postdoctoral position is available at the Nathan Kline Institute for Psychiatric Research under the auspices of a NIH R01 (MPI: Peter Lakatos, Sam Neymotin). The aim of our project is to develop/utilize computer models of the auditory thalamocortical system to investigate mechanisms and functions of neuronal oscillatory patterns observed in the auditory system in the electrophysiological recordings from Dr. Lakatos' group. The broad goal is to develop a biologically-realistic data-driven computer model of the thalamocortical auditory system that is able to support critical auditory information processing features, with special emphasis on neuronal oscillations. The combined in vivo and in silico results of our project will pave the way for model-driven neuromodulation, offering precise predictions on how to efficiently control biological circuits. Besides modeling, our group also focuses heavily on developing and applying novel signal processing techniques for the analysis of electrophysiological data on multiple spatial scales, from single neurons to ECoG recordings. Applicants should have a strong background in: computer programming, with demonstrated proficiency in Python and Matlab, analysis of electrophysiological data, development of signal processing methods for neural data, detailed computational modeling of neurons/neuronal circuits using NEURON with Python. The job will be based at the Nathan Kline Institute (www.nki.rfmh.org ~1 hour north of NYC), but some telecommuting will be allowed. Applicants should contact Sam Neymotin by email (samuel.neymotin at nki.rfmh.org) with a CV and cover letter. The Nathan Kline Institute is an equal opportunity employer. ________________________________ IMPORTANT NOTICE: This e-mail is meant only for the use of the intended recipient. It may contain confidential information which is legally privileged or otherwise protected by law. If you received this e-mail in error or from someone who was not authorized to send it to you, you are strictly prohibited from reviewing, using, disseminating, distributing or copying the e-mail. PLEASE NOTIFY US IMMEDIATELY OF THE ERROR BY RETURN E-MAIL AND DELETE THIS MESSAGE FROM YOUR SYSTEM. Thank you for your cooperation. -------------- next part -------------- An HTML attachment was scrubbed... URL: From mark.johnson at mq.edu.au Tue Nov 13 14:30:27 2018 From: mark.johnson at mq.edu.au (Mark Johnson) Date: Tue, 13 Nov 2018 19:30:27 +0000 Subject: Connectionists: Postdoctoral position in NLP/ML at Macquarie University and CSIRO's Data61 in Sydney, Australia In-Reply-To: References: Message-ID: The NLP/ML group in the Dept of Computing at Macquarie University, Sydney, Australia is recruiting a post-doctoral researcher for a joint research project "Information Extraction and Parsing Methods for Government and Enterprise Applications" on information and relation extraction involving Macquarie University, CSIRO's Data61 and the University of Edinburgh. The project uses syntactic parsing and deep learning to extract "who did what to whom when" from a large corpus of texts. The research involves integrating information extracted from multiple texts and using this information in creative ways, e.g., building event time-lines for individuals, learning entailments between predicates and relations, etc. The post-doc will report to Professor Mark Johnson in the Department of Computing, Macquarie University and Dr Stephen Wan of CSIRO's Data61, Marsfield, and will be collaborating with Professor Mark Steedman of Edinburgh University. You will need to have a PhD and strong research record in NLP and ML, especially Deep Learning. You will need to show proficiency with Deep Learning toolkits such as TensorFlow and Pytorch. Applications close on the 5th December 2018. For further information and applications see the official advertisement on http://jobs.mq.edu.au/cw/en/job/504833/postdoctoral-research-fellow. -------------- next part -------------- An HTML attachment was scrubbed... URL: From cshelton at cs.ucr.edu Tue Nov 13 15:01:43 2018 From: cshelton at cs.ucr.edu (Christian Shelton) Date: Tue, 13 Nov 2018 12:01:43 -0800 Subject: Connectionists: Open-Rank Tenure/Tenure-Track Position at UC Riverside Message-ID: <20181113200143.GL4174@caylus> The Department of Computer Science & Engineering at the University of California at Riverside is searching for two open-rank professor positions. The first position is for machine learning, natural language processing, or artificial intelligence. The second is for visualization, human-computer interaction, virtual/augmented reality, or algorithms. Assistant Professor Description and Application (either area): https://aprecruit.ucr.edu/apply/JPF00980 Associate/Full Professor Description and Application (either area): https://aprecruit.ucr.edu/apply/JPF00981 Application review will begin Jan. 1, 2019. If you have any questions, please feel free to contact the search chair, Christian Shelton, at hire at cs.ucr.edu. From ogergo at brandeis.edu Tue Nov 13 15:18:13 2018 From: ogergo at brandeis.edu (Gergo Orban) Date: Tue, 13 Nov 2018 21:18:13 +0100 Subject: Connectionists: XI. Dubrovnik Conference on Cognitive Science - Computational Rationality Message-ID: Dear All, We are happy to announce the XI. Dubrovnik Conference on Cognitive Science, which is devoted to the topic of Computational Rationality. The conference will take place between 23-25 May 2019 in Dubrovnik, Croatia. Invited speakers are: Ulrike Hahn (Birkbeck, University of London, UK) Quentin Huys (ETH Z?rich, Switzerland) Julian Jara-Ettinger (Yale University, USA) Mate Lengyel (University of Cambridge, Central European University) Azzurra Ruggeri (Max Planck Institute for Human Development, Berlin, Germany) Laura Schultz (MIT, USA) For more information please visit: http://www.cecog.eu/ducog/page_invitation.php or email us: ducog at cogsci.bme.hu On behalf of the organisers, Oana Stanciu Gerg? Orb?n -------------- next part -------------- An HTML attachment was scrubbed... URL: From richard.jiang at northumbria.ac.uk Mon Nov 12 18:18:09 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Mon, 12 Nov 2018 23:18:09 +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 ? Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark Email: weme at dtu.dk ? Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia Email: chli at csu.edu.au ? Professor Christophe Rosenberger Computer Security ENSICAEN ? GREYC, France Email: christophe.rosenberger at ensicaen.fr Contact: All questions about submissions can be emailed to perceptualscience at outlook.com or any editor in the board. Many thanks! Kind Regards, Editors of the Book This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender?s explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. 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 jimtoer at ifi.uio.no Wed Nov 14 01:38:10 2018 From: jimtoer at ifi.uio.no (=?utf-8?Q?Jim_T=C3=B8rresen?=) Date: Wed, 14 Nov 2018 07:38:10 +0100 Subject: Connectionists: CFP: 2019 Joint IEEE Int. Conf. on Development and Learning and on Epigenetic Robotics Message-ID: Dear Colleagues, [Apologies if you receive multiple copies of this call. Please, feel free to distribute it to those who might be interested.] CALL FOR PAPERS: 9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2019) 19-22 August 2019, Oslo, Norway Web page: https://icdl-epirob2019.org An IEEE Computational Society sponsored conference ==== Important Dates ==== Submission deadline: February 22, 2019 Author notification: May 1, 2019 Camera ready due: June 1, 2019 Conference: August 19-22nd 2019 ==== Overview ==== ICDL-EpiRob is a unique conference gathering researchers from computer science, robotics, psychology and developmental studies to share knowledge and research on how intelligent biological and artificial systems develop sensing, reasoning and actions. This includes development of cognitive and social abilities through dynamic interactions with their physical and social environments. This is with a twofold objective: to gain a better understanding of human and animal intelligence, and to enable artificial systems with more adaptive and flexible behaviors. This will be the ninth time the conference is organized, and we invite submissions for the conference in 2019 to explore, extend, and consolidate the interdisciplinary boundaries of this exciting research field. ==== Scope and Topics ==== Topics of interest include (but are not limited to): * principles and theories of development and learning; * development of skills in biological systems and robots; * nature vs nurture, developmental stages; * models on the contributions of interaction to learning * models on active learning * architectures for lifelong learning; * emergence of body and affordance perception; * analysis and modelling of human motion and state * models for prediction, planning and problem solving; * models of human-human and human-robot interaction; * emergence of verbal and non-verbal communication; * epistemological foundations and philosophical issues; * robot prototyping of human and animal skills * ethics in computational intelligence and robotics ==== Submissions ==== Authors are invited to submit original and unpublished papers of at most 6 pages in IEEE double column format. Submission will undergo peer-review impacting which papers that are selected for either oral presentation or poster presentation. Accepted and presented full six-page paper submissions will be included in the conference proceedings published by IEEE Xplore after the conference. The authors of the best conference papers will be invited to submit an extended version of their papers to be reviewed for inclusion in a "2019 ICDL-EpiRob conference" special issue of IEEE Transactions on Cognitive and Developmental Systems (TCDS). We also invite submissions for the MODELBot Challenge, a paper competition focusing on computational models of human or animal learning, as well as the use of robotic and computational techniques for supporting human learning. Full details are provided on the conference web page. ==== Confirmed Keynote Speakers ==== Prof. Aude Billard, ?cole Polytechnique F?d?rale de Lausanne, Switzerland Prof. Michael J. Frank, Brown University, USA Prof. Dr. Stefanie H?hl, University of Vienna, Austria See https://icdl-epirob2019.org/keynotes/ ==== Organizing committee ==== General chairs: Jim Torresen (University of Oslo, Norway ) and Kerstin Dautenhahn (University of Waterloo, Canada/University of Hertfordshire, UK) Program chairs: Kai Olav Ellefsen (University of Oslo) and Katharina J. Rohlfing (Paderborn University, Germany) Finance / Website Chairs: Kyrre Glette and Charles Martin (University of Oslo) Publicity chairs: Bruno Castro da Silva (UFRGS, Brazil), Kazi Shah Nawaz Ripon (NTNU, Norway) and Ryo Kurazume (Kyushu University, Japan) Bridge chair: Tetsuya Ogata (Waseda University, Japan) and Emre Ugur (Bogazici University, Turkey) Local chairs: Bruno Laeng and Tor Endestad (University of Oslo) Best regards from the organising committee, Bruno Castro da Silva, Kazi Shah Nawaz Ripon and Ryo Kurazume (Publicity chairs) Kai Olav Ellefsen and Katharina J. Rohlfing (Program chairs) Jim Torresen and Kerstin Dautenhahn (General chairs) -------------- next part -------------- An HTML attachment was scrubbed... URL: From luca.oneto at unige.it Wed Nov 14 04:11:37 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Wed, 14 Nov 2018 10:11:37 +0100 Subject: Connectionists: [AI*IA] ESANN 2019 SS - Deadline Extension - Societal Issues in Machine Learning: When Learning from Data is Not Enough Message-ID: [Apologies if you receive multiple copies of this CFP] Submission deadline has been extended to November, 26 (2018) Call for papers: special session on "Societal Issues in Machine Learning: When Learning from Data is Not Enough" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019). 24-26 April 2019, Bruges, Belgium - http://www.esann.org DESCRIPTION: It has been argued that Artificial Intelligence (AI) is experiencing a fast process of commodification. This characterization is on the interest of big IT companies, but it correctly reflects the current industrialization of AI. This phenomenon means that AI systems and products are reaching the society at large and, therefore, that societal issues related to the use of AI and Machine Learning (ML) cannot be ignored any longer. Designing ML models from this human-centered perspective means incorporating human-relevant requirements such as safety, fairness, privacy, and interpretability, but also considering broad societal issues such as ethics and legislation. These are essential aspects to foster the acceptance of ML-based technologies, as well as to be able to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. This special session aims to put forward the state-of-the-art on these increasingly relevant topics among ML theoretician and practitioners. For this purpose, we welcome both solid contributions and preliminary relevant results showing the potential, the limitations and the challenges of new ideas, refinements, or contaminations between the different fields of research, ML, and related approaches in facing real-world problems involving societal issues. We welcome works on ML theory, applications to topics listed below as well as other topics of social relevance. Studies stemming from major research initiatives and projects focusing on the session topics are particularly welcome. TOPICS OF INTEREST: - Fairness as an element in the development of ML techniques; - Ethical issues in the application of ML and related techniques in areas of social impact; - Privacy as a challenge in ML application to problems in the social domain; - Interpretability and explainability of ML and related approaches; - Safety and Security of ML and related methods in safety critical contexts; - Legislative challenges to the use of ML and related methods; - The challenge of complex data for ML and related methods; - Transparency and open data. SUBMISSION: Prospective authors must submit their paper through the ESANN portal following the instructions provided in https://www.elen.ucl.ac.be/esann/index.php?pg=submission Each paper will undergo a peer reviewing process for its acceptance. Authors should send as soon as possible an e-mail with the tentative title of their contribution to the special session organisers. IMPORTANT DATES: Submission of papers: 26 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Davide Bacciu, University of Pisa (Italy) Battista Biggio, University of Cagliari (Italy) Jos? D. Mart?n, Universitat de Val?ncia (Spain) Luca Oneto, University of Genoa (Italy) Alfredo Vellido, Universitat Polit?cnica de Catalunya (Spain) Paulo J. G. Lisboa, Liverpool John Moores University (UK) ----------------------------------------------------------------------------------- Luca Oneto, PhD University of Genoa web: www.lucaoneto.com DIBRIS Department e-mail: Luca.Oneto at unige.it SmartLab Laboratory e-mail: Luca.Oneto at gmail.com Via Opera Pia 11a Fax: +39-010-3532897 16145 Genoa ITALY Phone: +39-010-3532192 www.smartlab.ws ----------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Wed Nov 14 05:36:00 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Wed, 14 Nov 2018 12:36:00 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): First Call for Tutorial Proposals In-Reply-To: References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> Message-ID: <1C6C9A37-056D-4C73-ACFF-6A5D72802CF1@cs.ucy.ac.cy> *** FIRST 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 barros at informatik.uni-hamburg.de Wed Nov 14 05:43:14 2018 From: barros at informatik.uni-hamburg.de (Pablo Barros) Date: Wed, 14 Nov 2018 11:43:14 +0100 Subject: Connectionists: 2nd CFP: The OMG-Empathy Prediction Challenge Message-ID: 2nd CALL FOR PARTICIPATION The One-Minute Gradual-Empathy Prediction (OMG-Empathy) Competition held in partnership with the IEEE International Conference on Automatic Face and Gesture Recognition 2019 in Lille, France. https://www2.informatik.uni-hamburg.de/wtm/omgchallenges/omg_empathy.html I. Aim and Scope The ability to perceive, understand and respond to social interactions in a human-like manner is one of the most desired capabilities in artificial agents, particularly social robots. These skills are highly complex and require a focus on several different aspects of research, including affective understanding. An agent which is able to recognize, understand and, most importantly, adapt to different human affective behaviors can increase its own social capabilities by being able to interact and communicate in a natural way. Emotional expression perception and categorization are extremely popular in the affective computing community. However, the inclusion of emotions in the decision-making process of an agent is not considered in most of the research in this field. To treat emotion expressions as the final goal, although necessary, reduces the usability of such solutions in more complex scenarios. To create a general affective model to be used as a modulator for learning different cognitive tasks, such as modeling intrinsic motivation, creativity, dialog processing, grounded learning, and human-level communication, only emotion perception cannot be the pivotal focus. The integration of perception with intrinsic concepts of emotional understanding, such as a dynamic and evolving mood and affective memory, is required to model the necessary complexity of an interaction and realize adaptability in an agent's social behavior. Such models are most necessary for the development of real-world social systems, which would communicate and interact with humans in a natural way on a day-to-day basis. This could become the next goal for research on Human-Robot Interaction (HRI) and could be an essential part of the next generation of social robots. For this challenge, we designed, collected and annotated a novel corpus based on human-human interaction. This novel corpus builds on top of the experience we gathered while organizing the OMG-Emotion Recognition Challenge, making use of state-of-the-art frameworks for data collection and annotation. The One-Minute Gradual Empathy datasets (OMG-Empathy) contain multi-modal recordings of different individuals discussing predefined topics. One of them, the actor, shares a story about themselves while the other, the listener, reacts to it emotionally. We annotated each interaction based on the listener's own assessment of how they felt while the interaction was taking place. We encourage the participants to propose state-of-the-art solutions not only based on deep, recurrent and self-organizing neural networks but also traditional methods for feature representation and data processing. We also enforce that the use of contextual information, as well as personalized solutions for empathy assessment, will be extremely important for the development of competitive solutions. II. Competition Tracks We let available for the challenge a pre-defined set of training, validation and testing samples. We separate our samples based on each story: 4 stories for training, 1 for validation and 3 for testing. Each story sample is composed of 10 videos with interactions, one for each listener. Although using the same training, validation and testing data split, we propose two tracks which will measure different aspects of self-assessed empathy: The Personalized Empathy track, where each team must predict the empathy of a specific person. We will evaluate the ability of proposed models to learn the empathic behavior of each of the subjects over a newly perceived story. We encourage the teams to develop models which take into consideration the individual behavior of each subject in the training data. The Generalized Empathy track, where the teams must predict the general behavior of all the participants over each story. We will measure the performance of the proposed models to learn a general empathic measure for each of the stories individually. We encourage the proposed models to take into consideration the aggregated behavior of all the participants for each story and to generalize this behavior in a newly perceived story. The training and validation samples will be given to the participants at the beginning of the challenge together with all the associated labels. The test set will be given to the participants without the associated labels. The team`s predictions on the test set will be used to calculate the final metrics of the challenge. III. How to Participate To participate in the challenge, please send us an email to barros @ informatik.uni-hamburg.de with the title "OMG-Empathy Team Registration". This e-mail must contain the following information: Team Name Team Members Affiliation Participating tracks We split the corpus into three subsets: training, validation, and testing. The participants will receive the training and validation sets, together with the associated annotations once they subscribe to the challenge. The subscription will be done via e-mail. Each participating team must consist of 1 to 5 participants and must agree to use the data only for scientific purposes. Each team can choose to take part in one or both the tracks. After the training period is over, the testing set will be released without the associated annotations. Each team must submit, via e-mail, their final predictions as a .csv file for each video on the test set. Together with the final submission, each team must send a short 2-4 pages paper describing their solution published on Arxiv and the link for a GitHub page to their solution. If a team fails to submit any of these items, their submission will be invalidated. Each team can submit 3 complete submissions for each track. IV. Important Dates 25th of September 2018 - Opening of the Challenge - Team registrations begin 1st of October 2018 - Training/validation data and annotation available 3rd of December 2018 - Test data release 5th of December 2018 - Final submission (Results and code) 7th of December 2018 - Final submission (Paper) 10th of December 2018 - Announcement of the winners V. Organization Pablo Barros, University of Hamburg, Germany Nikhil Churamani, University of Cambridge, United Kingdom Angelica Lim, Simon Fraser University, Canada Stefan Wermter, Hamburg University, Germany -- Dr. 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 boubchir at ai.univ-paris8.fr Wed Nov 14 05:04:26 2018 From: boubchir at ai.univ-paris8.fr (Larbi Boubchir) Date: Wed, 14 Nov 2018 11:04:26 +0100 Subject: Connectionists: Special Issue "Machine Learning for EEG Signal Processing (MLESP 2018)" In-Reply-To: <25138e15-9b8c-5ef7-38be-f580cf7c8c9a@ai.univ-paris8.fr> References: <25138e15-9b8c-5ef7-38be-f580cf7c8c9a@ai.univ-paris8.fr> Message-ID: <00a62430-30c0-070d-aa57-9253edae84c0@ai.univ-paris8.fr> Dear colleagues, 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 The call for papers is available at this link: https://www.mdpi.com/journal/computers/special_issues/MLESP_2018 Best regards, Dr. Larbi Boubchir /Guest Editor/ -- _____________________________________________________ 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 mtista at gmail.com Wed Nov 14 06:39:01 2018 From: mtista at gmail.com (Massimo Tistarelli) Date: Wed, 14 Nov 2018 12:39:01 +0100 Subject: Connectionists: Call for applications - 16th Int.l Summer School on Biometrics 2019 In-Reply-To: References: Message-ID: <9d82c837-a55e-e707-1de8-952ed8c0b35f@gmail.com> ?? Please accept our sincere apologies for receiving multiple copies of this announcement ?? * * *16^th Int.l Summer School for Advanced Studies on Biometrics for Secure Authentication:* * * *BIOMETRICS AND FORENSIC SCIENCE* *IN THE DEEP LEARNING ERA* * * *Alghero, Italy ? May 27-31 2019* *Contact:*_tista at uniss.it http://biometrics.uniss.it_ *APPLICATION DEADLINE:*February 15^th 2019 (download the application form at: _http://biometrics.uniss.it_) From the early days, when security was the driving force behind biometric research, today?s challenges go far beyond security. Machine learning, Image understanding, Signal analysis, Neuroscience, Forensic science, Digital forensics and other disciplines, converged in a truly multidisciplinary effort to devise and build advanced systems to facilitate the interpretation of signals recorded from individuals acting in a given environment. This is what we simply call today ?Biometrics?. *For the last sixteen years, the International Summer School on Biometrics has been closely following the developments in science and technology to offer a cutting edge, intensive training course, always up to date with the current state-of-the-art.* What are the most up-to-date core biometric technologies developed in the field? What is the potential impact of biometrics in forensic investigation and crime prevention? How to detect impersonation attacks and disguise? What can we learn from human perception? What is a /biometric recognition system/? This school follows the successful track of the International Summer Schools on Biometrics held since 2003. In this 16^th edition, the courses will mainly focus on new and emerging issues: ?*How Biometrics can deal with emerging applications;* ?*How to exploit new biometric technologies in forensic and security applications;* ?*Evaluation and assessment of biometric and forensic applications.* ?*Biometrics, Forensic identification and deep learning: What is next?* The courses will provide a clear and in-depth picture on the state-of-the-art in biometric verification/identification technology, both under the theoretical and scientific point of view as well as in diverse application domains. The lectures will be given by 18 outstanding experts in the field, from both academia and industry. *A special keynote lecture will be given from:* ** *prof. Tomaso POGGIO * *Massachusetts Institute of Technology, Mc Govern Institute for Brain Research*** *An advanced feature of this summer school will be some practical sessions to better understand, ?hands on?, the real potential of today?s biometric technologies.* *The school will be held in conjunction with the International Conference on Biometrics (ICB 2019 - http://www.icb2019.org)* *_Participant application_* The school will be open to about 50 highly qualified, motivated and pre-selected applicants. Phd students, post-docs, researchers, forensic examiners, police officers and professionals are encouraged to apply. The expected school fees will be in the order of 1,550 ? for Phd students and 2,100 ? for others (subject to change). The fees will include full board accommodation, all courses and handling material. *A limited number of scholarships, covering a portion of the fees, will be awarded to Phd students*, selected on the basis of their scientific background and on-going research work. Precedence will be given to members of the EU H2020 IDENTITY consortium, and active members of IAPR and IEEE. The scholarship request form can be downloaded from the school web site */_http://biometrics.uniss.it_/*. Phd students, researchers and post-docs are encouraged to submit a short paper (6 pages maximum) for an oral presentation on their recent research activity. Poster boards will be also available to all participants to display their current research advances. Send a filled application form (download from _http://biometrics.uniss.it_)//together with a short curriculum vitae to:** *Prof. Massimo Tistarelli ?*e-mail: *_biometricsummerschool at gmail.com _* *_Advance pre-registration is strictly required by February 15^th _**_2019_* *_School location_* The school will be hosted by HotelEl Faro (*/_http://www.elfarohotel.it/_/*) in the Capo Caccia bay, near Alghero, Sardinia. This is one of the most beautiful resorts in the Mediterranean sea. The property is beautifully immersed into the Capo Caccia bay. The hotel El Faro has a recently renovated conference center, fully equipped for scientific events. The school venue, as well as the surroundings, proved to be a perfect environment for the school activities. *_School Committee:_* *Massimo Tistarelli* Computer Vision Laboratory ? University of Sassari, Italy *Josef Bigun * Department of Computer Science ? Halmstad University, Sweden *Enrico Grosso* Computer Vision Laboratory ? University of Sassari, Italy *Anil K. Jain* Biometrics laboratory ? Michigan State University, USA *_Distinguished lecturers from past school editions_* *Josef **Bigun* Halmstad University ? Sweden *Aldo Mattei* Arma dei Carabinieri ? Italy *Thirimachos Bourlai* West Virginia University ? USA *David Meuwly* Netherlands Forensic Institute ? NL *Vincent Bouatou* Safran Morpho ? France *Emilio Mordini MD* Responsible Technologies ? Italy *Deepak Chandra * Google Inc. ? USA *Mark Nixon* University of Southampton ? UK *Rama Chellappa* University of Maryland ? USA *Alice O?Toole* University of Texas ? USA *John Daugman* University of Cambridge ? UK *Maja Pantic* Imperial College ? UK *Farzin Deravi* University of Kent ? UK *Johnathon Phillips* NIST ? USA *James Haxby* Dartmouth University ? USA *Arun Ross* Michigan State University ? USA *Anil K. Jain* Michigan State University ? USA *Tieniu Tan * CASIA-NLPR ? China *Joseph Kittler* University of Surrey ? UK *Massimo Tistarelli* Universit? di Sassari ? Italy *Davide Maltoni* Universit? di Bologna ? Italy *Alessandro Verri* Universit? di Genova ? Italy *John Mason* Swansea University ? UK *James Wayman* University of San Jos? ? USA -------------- next part -------------- An HTML attachment was scrubbed... URL: From fmschleif at googlemail.com Wed Nov 14 10:08:09 2018 From: fmschleif at googlemail.com (Frank-Michael Schleif) Date: Wed, 14 Nov 2018 16:08:09 +0100 Subject: Connectionists: (extended deadline) ESANN special session about Streaming data analysis, concept drift and analysis of dynamic data sets Message-ID: -- Apologies in advance for multiple postings -- Call for Papers Special Session on 'Streaming data analysis, concept drift and analysis of dynamic data sets ' 24-26 April 2019, Bruges, Belgium https://www.elen.ucl.ac.be/esann/index.php?pg=specsess#streaming AIMS AND SCOPE Today many real life data are given in the form of streaming data. Prominent examples can be found in the context of IoT, in form of twitter feeds, click stream data, trading data and many other. Learning from this huge, heterogeneous and growing amount of data requires flexible learning models that can adapt over time and are capable to deal with potentially non-i.i.d., non-stationary input data. Additionally the underlying algorithms aim on processing of high-velocity and multi-channel data and have also to deal with a variety of phenomena like concept drift and novelty detection. This special session welcomes novel research about learning from data streams addressing common problem in the field of streaming data analysis. Computational intelligence methods have the potential to be used for efficient data streams processing but novel methods and mathematical and algorithmic approaches are needed. TOPICS We encourage submission of papers on novel methods for streaming data processing and streaming data analysis by means of computational intelligence and machine learning approaches, including but not limited to: - data analysis and pattern recognition approaches for streaming data - preprocessing approaches for streaming data - learning of heterogeneous data streams - adaptive data pre-processing and knowledge discovery - methods employing ex- and implicit data knowledge for non-stationary data - representation and modeling of multi-channel streaming data - approximation techniques for streaming data - online and incremental learning (dimensionality reduction, classification, clustering and regression, outlier detection) with a particular design for streaming data - data drift and shift handling, transfer learning - graph stream algorithms - security and privacy preservation on streaming data - active learning for data streams - application of deep learning with streaming data - particular interesting applications for streaming data analysis e.g. in IoT, recommender systems, social networks, sensor networks, web mining, text processing medicine ... IMPORTANT DATES Paper submission deadline : 26 November 2018 Notification of acceptance : 31 January 2019 Deadline for final papers : 20 February 2019 The ESANN 2019 conference : 24-26 April 2019 SPECIAL SESSION ORGANIZERS: Albert Bifet LTCI, T?l?com ParisTech - Universit? Paris-Saclay Paris, FRANCE Barbara Hammer, University of Bielefeld, Germany Frank-Michael Schleif, University of Appl. Sc. Wuerzburg-Schweinfurt, Germany and University of Birmingham, Birmingham, UK -- ------------------------------------------------------- Prof. Dr. rer. nat. habil. Frank-Michael Schleif School of Computer Science University of Applied Sciences W?rzburg-Schweinfurt Sanderheinrichsleitenweg 20 Raum I-3.35 Tel.: +49(0) 931 351 18127 97074 W?rzburg Honorable Research Fellow The University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom - email: frank-michael.schleif at fhws.de http://promos-science.blogspot.de/ https://www.techfak.uni-bielefeld.de/~fschleif/ ------------------------------------------------------- From felipe at cos.ufrj.br Wed Nov 14 12:00:57 2018 From: felipe at cos.ufrj.br (Felipe Maia Galvao Franca) Date: Wed, 14 Nov 2018 15:00:57 -0200 Subject: Connectionists: Extended DEADLINE: "60 Years of Weightless Neural Systems" at ESANN 2019 Message-ID: Call for papers: special session on "60 Years of Weightless Neural Systems" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019). 24-26 April 2019, Bruges, Belgium - http://www.esann.org Mimicking biological neurons by focusing on the decoding performed by the dendritic trees is an attractive alternative to the integrate-and-fire McCullogh-Pitts neuron stylisation. RAM-based, or Boolean neurons, and weightless neural systems have been studied and applied in a broad spectrum of situations, resulting in theoretical findings and the development of exciting applications to an ample set of domains, ranging from natural language processing to game playing, including memory transfer mechanisms, biomedical applications, computational vision, hardware security, and quantum learning. The year of 2019 marks the 60-years anniversary of the seminal paper on n-tuple classifiers by Bledsoe and Browning, as well as the 35-years of the WiSARD model, and the tenth anniversary of the first special session on weightless neural systems at ESANN. This session invites original contributions on theoretical and practical aspects of weightless neural systems at all levels of abstraction, as well as their relationship to themes of current interest such as: deep learning, convolutional neural models, adversarial learning, etc. SUBMISSION: Prospective authors must submit their paper through the ESANN portal following the instructions provided in https://www.elen.ucl.ac.be/esann /index.php?pg=submission Each paper will undergo a peer reviewing process for its acceptance. Authors should send as soon as possible an e-mail with the tentative title of their contribution to the special session organisers. IMPORTANT DATES: Submission of papers: *26 November 2018* Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Priscila M. V. Lima, Universidade Federal do Rio de Janeiro (Brazil) Felipe M. G. Fran?a, Universidade Federal do Rio de Janeiro (Brazil) Massimo De Gregorio, Ist. di Sci. Appl. e Sistemi Intelligenti (Italy) Wilson R. de Oliveira, Univ. Fed. Rural Pernambuco (Brazil) -- ??????????????????????????????? Felipe M. G. Fran?a, PhD Professor of Computer Science and Engineering Systems Engineering and Computer Science Program, COPPE Universidade Federal do Rio de Janeiro P.O. Box 68511, 21941-972, Rio de Janeiro, RJ, Brazil felipe at ieee.org felipe at cos.ufrj.br ??????????????????????????????? -------------- next part -------------- An HTML attachment was scrubbed... URL: From eero at cns.nyu.edu Wed Nov 14 11:46:36 2018 From: eero at cns.nyu.edu (Eero Simoncelli) Date: Wed, 14 Nov 2018 11:46:36 -0500 (EST) Subject: Connectionists: Joint faculty opening in Data Science and Neural Science at NYU Message-ID: <201811141646.wAEGkaF24913@calaf.cns.nyu.edu> Dear Colleagues, The Center for Neural Science (CNS) and the Center for Data Science (CDS) at New York University invite applications for an open rank joint faculty position, anticipated to begin September 2019. Appointments may be made at either junior or senior level. We seek exceptional candidates that can carry out research programs aimed at quantitative analysis and modeling of neural data, and developing related data science tools and methods, leveraging existing strengths of CNS and CDS. We are particularly interested in scholars with cross-disciplinary research interests that complement those of our existing faculty. The successful candidate will be a faculty member in both units, with teaching, service, and other professional duties split between them. Applications and supporting documents received by 31 December 2018 will receive full consideration. Further information about the position, the two units, and the University: * http://www.cns.nyu.edu/faculty-search/ * https://cds.nyu.edu/our-people/jobs/ Best, Eero Simoncelli New York University From m.biehl at rug.nl Wed Nov 14 13:01:11 2018 From: m.biehl at rug.nl (Michael Biehl) Date: Wed, 14 Nov 2018 19:01:11 +0100 Subject: Connectionists: Deadline extended: ESANN special session on Statistical Physics of Learning Message-ID: Apologies in advance for multiple postings. *DEADLINE EXTENSION:* Special Session *"Statistical Physics of Learning and Inference" at ESANN 2019*NEW deadline for submission of papers: *November 26, 2018.* Please contact the organizers directly if you intend to submit a contribution but might have difficulties to meet the deadline. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN2019). 24-26 April 2019, Bruges, Belgium http://www.esann.org Description: This special session is meant to attract researchers who exploit analogies and concepts from statistical physics in the context of machine learning, inference, optimization, and related fields. The exchange of ideas between statistical physics and computer science has been very fruitful and is currently gaining momentum again as a consequence of the revived interest in neural networks, machine learning and inference in general. Statistical physics methods complement other approaches to the theoretical understanding of machine learning processes and inference in stochasic modeling. They facilitate, for instance, the study of dynamical and equilibrium properties of randomized training processes in model situations. At the same time, the approach inspires novel and efficient algorithms and facilitates interdisciplinary applications in a variety of scientific and technical disciplines. The tools and concepts applied in this context include information theory, the mathematical analysis of stochastic differential equations, methods borrowed from the statistical mechanics of disorder, mean field theory, variational calculus, renormalization group and other methods. Potential topics include, but are not limited to: - Probabilistic inference in, e.g., stochastic dynamical systems and complex networks - Learning in Deep Networks and other architectures - Complex optimization problems - Emergent behavior in societies of agents - Transient dynamics and equilibrium phenomena in machine learning - The relation of statistical mechanics with information theory and mathematical statistics - Applications, for instance in: - systems biology and bioinformatics - neuroscience - environmental modelling - social systems - signal processing - complex optimization SUBMISSION: Authors must submit their paper through the ESANN portal following the instructions provided at https://www.elen.ucl.ac.be/esann/index.php?pg=submission We encourage authors to contact the organizers of the session beforehand. Each paper will undergo a peer reviewing process for its acceptance. IMPORTANT DATES: *Submission of papers: 26 November 2018* Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 SPECIAL SESSION ORGANISERS: Michael Biehl, University of Groningen, The Netherlands Nestor Caticha, University of Sao Paulo, Brazil Manfred Opper, Technical University Berlin, Germany Thomas Villmann, University of Applied Sciences Mittweida, Germany ---------------------------------------------------------- Prof. Dr. Michael Biehl Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence P.O. Box 407, 9700 AK Groningen The Netherlands Tel. +31 50 363 3997 www.cs.rug.nl/~biehl m.biehl at rug.nl -------------- next part -------------- An HTML attachment was scrubbed... URL: From michel.verleysen at uclouvain.be Wed Nov 14 14:16:46 2018 From: michel.verleysen at uclouvain.be (Michel Verleysen) Date: Wed, 14 Nov 2018 19:16:46 +0000 Subject: Connectionists: ESANN 2019 deadline extension Message-ID: ====================================================== ESANN 2019 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges (Belgium) - April 24-25-26, 2019 http://www.esann.org/ *** Submission deadline extension *** ====================================================== Due to numerous requests, the deadline to submit papers to the ESANN 2019 conference has been extended to November 26, 2018. Please note that no further extension will be given. Looking forward to seeing you at ESANN 2019, The organizing committee. ======================================================== ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning http://www.esann.org/ * For submissions of papers, reviews, registrations: Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at uclouvain.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at uclouvain.be ======================================================== -------------- next part -------------- An HTML attachment was scrubbed... URL: From bremeseiro at uniovi.es Wed Nov 14 14:50:41 2018 From: bremeseiro at uniovi.es (BEATRIZ REMESEIRO LOPEZ) Date: Wed, 14 Nov 2018 19:50:41 +0000 Subject: Connectionists: [New Deadline: Nov 26] CFP ESANN'19 - Special Session on "Parallel and Distributed Machine Learning: Theory and Applications" In-Reply-To: References: Message-ID: <8CD0C6EA-73CA-42FC-A5DD-D5C04452EDB9@uniovi.es> [Apologies if you receive multiple copies of this CFP] Call for papers: special session on "Parallel and Distributed Machine Learning: Theory and Applications" at ESANN 2019 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019) 24-26 April 2019, Bruges (Belgium) - http://www.esann.org Parallel and Distributed Machine Learning: Theory and Applications Organized by: Beatriz Remeseiro (Universidad de Oviedo, Spain), Ver?nica Bol?n-Canedo, Jorge Gonz?lez-Dom?nguez, Amparo Alonso-Betanzos (Universidade da Coru?a, Spain) The spread of Internet and the technological advances have resulted in huge volumes of data, very valuable for different agents in the industrial world that are interested in analyzing them for different purposes. Machine Learning (ML) algorithms play a key role in this context, being able to learn from and make predictions on data. Their increasing complexity, since they have to deal now with millions of parameters, as well as their computational cost lead to new research opportunities and technical challenges. This continuous increase of data involved in ML analyses leads to a growing interest in the design and implementation of parallel and distributed ML algorithms. The efficient exploitation of the vast aggregate main memory and processing power of High Performance Computing (HPC) resources such as multicore CPUs, hardware accelerators (GPUs, Intel Xeon Phi coprocessors, FPGAs, etc.), clusters or cloud-based systems can significantly accelerate many ML algorithms. However, the development of efficient parallel algorithms is not trivial, as we must pay much attention to the data organization and decomposition strategy in order to balance the workload among resources while minimizing data dependencies as well as synchronization and communication overhead. We invite papers on both practical and theoretical issues about incorporating parallel and distributed approaches into ML problems, as well as review papers with the state-of-art techniques and the open challenges encountered in this field. In particular, topics of interest include, but are not limited to: - Development of parallel ML algorithms on multicore and manycore architectures: multithreading, GPUs, Intel Xeon Phi coprocessor, FPGAs, etc. - Exploitation of cloud, grid and distributed-memory systems to accelerate ML algorithms: Spark, Hadoop, MPI, etc. - Deep learning models trained across multicore CPUs, GPUs or clusters of computers. - Development of distributed ML algorithms. - Novel programming paradigms to support HPC for ML. - Middleware, programming models, tools, and environments for HPC in ML. - Caching, streaming, pipelining, and other optimization techniques for data management in HPC for ML. - Benchmarking and performance studies of high-performance ML applications. - Parallel databases and I/O systems to store ML data. - Applications and services: bioinformatics, medicine, multimedia, video surveillance, etc. Submitted papers will be reviewed according to the ESANN reviewing process and will be evaluated on their scientific value: originality, correctness, and writing style. IMPORTANT DATES: Paper submission deadline: 26 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24-26 April 2019 -------------- next part -------------- An HTML attachment was scrubbed... URL: From robert.jenssen at uit.no Thu Nov 15 05:33:06 2018 From: robert.jenssen at uit.no (Robert Jenssen) Date: Thu, 15 Nov 2018 10:33:06 +0000 Subject: Connectionists: Deadline extended to 23rd Nov for abstracts to the Northern Lights Deep Learning Workshop 9-10 January 2019, Tromso, "north pole" Message-ID: Dear all, We will be very happy to welcome more participants and presenters for the Northern Lights Deep Learning Workshop, 9-10 January 2019, Tromso, "North Pole", Norway. We have for this reason extended the deadline for abstracts to 23rd November 2018. For more information, please see nldl2019.org for call for contributions and more info. Confirmed keynote speakers are: * Klaus-Robert M?ller, Technical University of Berlin * Jose Principe, University of Florida * Marleen de Bruijne, Erasmus MC Rotterdam and University of Copenhagen * Wojciech Samek, Fraunhofer Heinrich Hertz Insitute, Berlin * Maurizio Filippone, Eurecom, France The workshop continues the success of the 1st such workshop in 2018, a cozy small workshop with good opportunities for discussions and social interaction (and - hopefully - some northern lights). Please see nldl2018.org --- Robert Jenssen UiT Machine Learning Group http://machine-learning.uit.no http://site.uit.no/ml Department of Physics and Technology University of Tromso (UiT) - The Arctic University of Norway -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Thu Nov 15 08:56:41 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Thu, 15 Nov 2018 15:56:41 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): First Call for Doctoral Consortium Submissions In-Reply-To: References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> Message-ID: <5962584F-05E9-4303-939E-C271AFCF429C@cs.ucy.ac.cy> *** FIRST 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: 1st March, 2019 ? Notification to authors: 22nd March 2019 ? Camera ready submission: 3rd April 2019 ? ACM UMAP 2019 DC Session: 11th and 12th June 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 benjamin.lindner at physik.hu-berlin.de Thu Nov 15 09:30:20 2018 From: benjamin.lindner at physik.hu-berlin.de (Benjamin Lindner) Date: Thu, 15 Nov 2018 15:30:20 +0100 Subject: Connectionists: PhD position at HU Berlin (Physics Dep.) available Message-ID: <5BED82FC.5010707@physik.hu-berlin.de> *Calcium spiking with cumulative refractoriness - statistics of the fluctuations and implications for Calcium signaling** *We are looking for a PhD candidate to theoretically explore models of noisy spike-generating cellular signalling systems for which the intracellular Calcium dynamics is a prominent example. Methods will be developed within the frameworks of the theory of stochastic processes, statistical physics and nonlinear dynamics. The project is a collaboration between the research groups of Martin Falcke (Max-Delbrueck Center for Molecular Medicine Berlin and Humboldt University Berlin) and Benjamin Lindner (Bernstein Center for Computational Neuroscience Berlin and Humboldt University Berlin) and the PhD students of both groups are expected to closely collaborate. The successful candidate should have a degree in physics (a background in physical biology is desirable but not obligatory), expertise in analytical calculations, programming skills (C++ or C, Python, LaTeX, Linux), and excellent command of the English language, good communication skills, and team spirit. Funding is provided for three years, starting at the latest February 1, 2019. For details on the doctoral examination process at the Physics Department of Humboldt University Berlin, see https://fakultaeten.hu-berlin.de/en/mnf/wisskar/promotionen/index_html?set_language=en. Applications, including a letter of motivation, a CV, and a list of three potential referees should be sent by email to me benjamin.lindner at physik.hu-berlin.de (cc to nikola.schrenk at bccn-berlin.de) The deadline for applications is December 31st 2018, however, later applications might also be considered. HU is seeking to increase the proportion of women in research and teaching, and specifically encourages qualified female scholars to apply. Severely disabled applicants with equivalent qualifications will be given preferential consideration. People with an immigration background are specifically encouraged to apply. Since we will not return your documents, please submit copies in the application only. Kind regards, Benjamin Lindner -------------------------------------------------------------------------------------------------------------------- Benjamin Lindner Professor for Theory of Complex Systems and Neurophysics Bernstein Center for Computational Neuroscience Berlin Philippstr. 13, Haus 2, 10115 Berlin Room: 1.17, phone: 0049(0)302093 6336 Department of Physics Humboldt University Berlin Newtonstr. 15 12489 Berlin Room: 3.408, phone: 0049(0)302093 7934 http://people.physik.hu-berlin.de/~lindner/index.html -------------------------------------------------------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From hi.yangyang at hotmail.com Thu Nov 15 10:39:32 2018 From: hi.yangyang at hotmail.com (Yang Yang) Date: Thu, 15 Nov 2018 15:39:32 +0000 Subject: Connectionists: [Call for Participation] Brain Informatics 2018 Message-ID: [Apologies if you receive this more than once] CALL FOR PARTICIPATION The 11th International Conference on Brain Informatics (BI'18) December 7-9, 2018, Arlington, Texas, USA Homepage: http://uta.engineering/conferences/bi-2018/ ------------------------------------------------------ ---Advancing BI Technologies from Basic Science Research to Real-World Practice--- ------------------------------------------------------ The International Conference on Brain Informatics series (BI) has established itself as the world?s premier research forum that brings together researchers and practitioners from neuroscience, cognitive science, computer science, data science, artificial intelligence, information communication technologies, and neuroimaging technologies with the purpose of exploring the fundamental roles, interactions as well as practical impacts of Brain Informatics. The BI'18 will provide a broad forum that academia, professionals and industry people can exchange their ideas, findings, and strategies in brain informatics research and brain-inspired concepts and technologies. It welcomes emerging technologies for addressing fundamental neurobiological questions about healthy brain function, laying the groundwork for advancing treatments for brain disorders or injury, and for generating brain-inspired "smart" artificial intelligence and computing technologies to meet future societal needs. It will educate and expand the brain informatics workforce and create new career opportunities for brain research and related innovations. *** Keynote Talks *** "Neuroimaging and Informatics in Alzheimer's Disease Research" Speaker: Arthur Toga, University of Southern California, USA "How to Understand Our Brain and Intelligence: >From Epileptic Network to Brain-Computer Interface" Speaker: Guoming Luan, Capital Medical University, China "Next Generation Hardware for Large-Scale Brain Modeling and AI Applications" Speaker: Chris Eliasmith, University of Waterloo, Canada "The Fabric of the Neocortex: A Less-Artificial Intelligence" Speaker: Andreas Tolias, Baylor College of Medicine, USA *** Workshops/Special Sessions *** Computationally Intelligent Methods in Processing and Analysis of Neuronal Big Data Organizers: Mufti Mahmud, Nottingham Trent University, UK M Shamim Kaiser, Jahangirnagar University, Bangladesh Ning Zhong, Maebashi Institute of Technology, Japan Nitish V Thakor, National University of Singapore, Singapore The International Workshop on Computational Intelligence for processing Brain Images Organizers: Abdel-Badeeh M. Salem, Ain Sham University, Egypt Frank Lievens, ISfTeH, Belgium Marco Alfonse, Ain Shams University, Egypt Wael Khalifa, Ain Shams University, Egypt The 1st International Workshop on Cognitive Neuroscience of Thinking and Reasoning Organizers: Jing Luo (Capital Normal University, China)? Vinod Goel (York University, Canada)? Hong Li ?Shenzhen University, China), and Peipeng Liang (Capital Normal University, China) The 1st International Workshop on Neuromodulation and Brain-Machine Intelligence Organizers: Qian Wang, Sanbo Brain Hospital, Capital Normal University, China Guoming Luan, Sanbo Brain Hospital, Capital Normal University, China Yang Yang, Maebashi Institute of Technology, Japan *** Topics and Areas for Parallel Presentations *** BI'18 has collected high-quality original research and application papers (both full paper and abstract submissions). The authors of the submissions will give oral presentations during the conference.Relevant topics include but are not limited to: Track 1: Cognitive and Computational Foundations of Brain Science Track 2: Human Information Processing Systems Track 3: Brain Big Data Analytics, Curation and Management Track 4: Informatics Paradigms for Brain and Mental Health Research Track 5: Brain-Machine Intelligence and Brain-Inspired Computing IMPORTANT DATES: ================ December 7, 2018: Workshops & Special Sessions December 8-9, 2018: Main conference Conference Venue ================ Hilton Arlington 2401 East Lamar Boulevard Arlington, Texas 76006-7503, USA Tel: +1-817-640-3322 Fax: +1-817-633-1430 ORGANIZERS ========== General Chairs Tom Mitchell (Carnegie Mellon University, USA) Leon Iasemidis (Louisiana Tech, University, USA) Ning Zhong (Maebashi Institute of Technology, Japan) Program Committee Chairs Jianzhong Su (University of Texas at Arlington, USA) Vicky Yamamoto (University of South California, USA) Yu-Ping Wang (Tulane University, USA) Organizing Chairs Shouyi Wang (University of Texas at Arlington, USA) Erick Jones (University of Texas at Arlington, USA) Fenghua Tian (University of Texas at Arlington, USA) Workshop/Special-Session Chairs Chou, Chun-An (Northwestern University, USA) Xiangnan Kong (Worcester Polytechnic Institute, USA) Felicia Jefferson (Fort Valley State University, USA) Jing Qin (Montana State University, USA) Panel/Tutorial Chairs Yang Yang (Maebashi Institute of Technology, Japan) Vassiliy Tsytsarev (University of Maryland, USA) Publicity Chairs Paul Wen (University of Southern Queensland, Australia) Huiguang He (Chinese Academy of Sciences, China) Mufti Mahmud (University of Padova, Italy) Steering Committee Chairs Ning Zhong (Maebashi Institute of Technology, Japan) Hanchuan Peng (Allen Institute for Brain Science, USA) *** Contact Information *** Shouyi Wang Email: shouyiw at uta.edu Vicky Yamamoto Email: Vicky.Yamamoto at med.usc.edu Yang Yang Email: yang at maebashi-it.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From avellido at cs.upc.edu Fri Nov 16 06:45:31 2018 From: avellido at cs.upc.edu (Alfredo Vellido) Date: Fri, 16 Nov 2018 12:45:31 +0100 Subject: Connectionists: WSOM+2019, Barcelona. 2nd CFP, 13th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization Message-ID: <6184c56f-31ee-313a-7705-7e2670c87445@cs.upc.edu> SUBMISSION NOW OPEN: https://easychair.org/conferences/?conf=wsom2019 ************ 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 2nd Call for Papers 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 visithttps://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 george at cs.ucy.ac.cy Fri Nov 16 07:26:11 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Fri, 16 Nov 2018 14:26:11 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Second Call for Workshop Proposals In-Reply-To: References: <9D907F9B-A04A-43F0-8623-6D92E4132AC9@cs.ucy.ac.cy> <46CA4E92-4B9B-4D1B-8B60-A1D0C2701DE3@cs.ucy.ac.cy> Message-ID: <24094F96-58F5-466E-A748-E91B9EC6E8A2@cs.ucy.ac.cy> *** SECOND 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 richard.jiang at northumbria.ac.uk Fri Nov 16 08:32:55 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Fri, 16 Nov 2018 13:32:55 +0000 Subject: Connectionists: Call for Book Chapters on Deep Biometrics - Submit now 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 * Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark Email: weme at dtu.dk * Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia Email: chli at csu.edu.au * Professor Christophe Rosenberger Computer Security ENSICAEN - GREYC, France Email: christophe.rosenberger at ensicaen.fr Contact: All questions about submissions can be emailed to perceptualscience at outlook.com or any editor in the board. Many thanks! Kind Regards, Editors of the Book -- This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender's explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. -------------- next part -------------- An HTML attachment was scrubbed... URL: From demian.battaglia at univ-amu.fr Fri Nov 16 09:24:05 2018 From: demian.battaglia at univ-amu.fr (BATTAGLIA Demian) Date: Fri, 16 Nov 2018 14:24:05 +0000 Subject: Connectionists: PhD fellowship on analysis/large-scale modelling of cross-frequency coupling and stimulation Message-ID: Applications are invited for a: PhD fellowship at Aix-Marseille University (AMU, southern France) under the mentoring of Dr. Demian Battaglia (Institute for Systems Neuroscience - INS). This three-years fellowship is funded by the ANR grant (Agence National de la Recherche) ?ERMUNDY (Exact Reduction of Multiscale Neural Dynamics)?. In the context of this project we will develop computational multi-scale models of cortical oscillatory dynamics (multiple frequencies, cross-frequency coupling?) and of its control via stimulation. The used models (from the regional to the whole-brain level) will be constrained by realistic information on the phase response properties of actual neural populations, which will be inferred from both extra-cranial (TMS) and intra-cranial (sEEG) stimulation data, acquired in house at AMU. Interactions with other researchers will take place as well, including experimentalists located in AMU, and theorists at Cergy-Pontoise University (Alessandro Torcini) and Ecole Normale Sup?rieure in Paris (Boris Gutkin). The PhD fellow will participate to both experimental data analysis (extraction of Phase Response Curves, functional connectivity analyses?) and model design and simulation. The successful candidate will integrate the Theoretical Neuroscience Group at the Institute for Systems Neuroscience (INS), located on the same campus of the Timone University hospital (AP-HM). The integrative and clinical neuroscience community in Marseille is among the most lively in Europe and Marseille is a vibrating city, with wonderful natural surroundings and home to the largest French-speaking university in the world, with an emphasis on interdisciplinary studies. Salary (~1.4k euros net, after all taxes and full social security coverage) is defined according to French national guidelines and cannot be negotiated. Interested candidates should send a cv, a brief description of qualifications and research interests and the name of one or two reference contacts to: Demian Battaglia demian.battaglia at univ-amu.fr Feel free to inquire for further information. Applications from under-represented categories in STEM sciences are welcome and supported. -------------- next part -------------- An HTML attachment was scrubbed... URL: From deneux at unic.cnrs-gif.fr Fri Nov 16 09:50:47 2018 From: deneux at unic.cnrs-gif.fr (Thomas Deneux) Date: Fri, 16 Nov 2018 15:50:47 +0100 Subject: Connectionists: Open engineer position: Bio-inspired toy robot with reinforcement learning In-Reply-To: References: Message-ID: ------------------------------------------------------------------------ *Engineer position: Bio-inspired toy robot with reinforcement learning * We are looking for an engineer with skills in reinforcement learning, programming, and/or robotics to contribute to the development of an educational toy robot embedded with learning capabilities. The Computing and Data Science team at CNRS laboratory UNIC (Unit of Neuroscience, Information and Complexity) develops a bio-inspired robot for future neuroscience research, which will also be commercialized as an educative toy to teach children about artificial intelligence. The current prototype is the object of regular school classes? demonstrations. The engineer will contribute principally to the artificial intelligence of the robot, using modern RL algorithms to improve its learning capabilities and handle a wider range of sensors (e.g. camera) and reward modes. In addition, and depending on its qualification, he will also contribute to hardware prototyping and hardware/software integration. Applicants should hold a PhD or a Master degree in computer science or related fields, display advanced programming skills and be trained in machine learning (ideally in the RL field). Salary: CNRS Research Engineer, gross salary 2,471? to 2,664? per month according to experience. The position is for one year. If the project is successful, the engineer will have an opportunity to participate to the creation of the ?Naivia? startup by becoming an early employee or? co-founder if appropriate. Web page: https://www.unic.cnrs-gif.fr/teams/Computing and Data Science . Contact: thomas.deneux at unic.cnrs-gif.fr . ------------------------------------------------------------------------ -- Dr. Thomas Deneux Research Engineer, Data Analysis and Software & Head of IT service CNRS, Neuroscience, Information & Complexity Unit (UNIC) https://www.unic.cnrs-gif.fr/people/Thomas_Deneux 1 av. de la Terrasse 91198 Gif sur Yvette, France +33 1 69823403 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: 2018-10-31 bio-inspired toy robot - engineer position.pdf Type: application/pdf Size: 385885 bytes Desc: not available URL: From Oscar.Woolnough at uth.tmc.edu Fri Nov 16 11:39:54 2018 From: Oscar.Woolnough at uth.tmc.edu (Woolnough, Oscar) Date: Fri, 16 Nov 2018 16:39:54 +0000 Subject: Connectionists: Multiple Postdocs available in the Neurobiology of Language Message-ID: <064DCE91-3B14-4E59-91E5-F1AD8A0EE289@uth.tmc.edu> POSTDOCTORAL RESEARCH POSITIONS Multiple Postdoctoral research positions are available in the Tandon Lab at The University of Texas in Houston as part of the newly formed Texas Epilepsy Neurotechnologies and Neuroinformatics (TENN) Institute. Positions are funded either via multi year Institute funding or by NIH funds (an R01 and a U01). The lab uses multimodal approaches ? fMRI, lesional analysis following epilepsy surgery, intracranial recordings and direct stimulation to create validate network level representations of language. Lab Collaborators include Greg Hickok (UCI), Stanislas Dehaene (NeuroSpin), Nathan Crone (JHU), Simon Fisher Baum (Rice) and Xaq Pitkow (Rice-Baylor); the post-doc will benefit from a close interaction with these experts in the fields of reading, semantics, speech production and computational neuroscience. The selected individual must have a Ph.D. in one or more of the following: neuroscience, psychology, cognitive science, mathematics, electrical engineering or computer science. Previous experience in neural time series data analysis, functional imaging studies of language, or studies of speech production are desirable ? but not crucial. They must possess the ability to independently code in any or all of the following: MATLAB, R or python. They are expected to be highly motivated, team players with a passion to study cognitive processes using any or all of the various modalities available in the lab - imaging, direct recordings and closed-loop cortical stimulation in humans. Given the multiple unpredictable variables and privacy issues around data collection in human patients, the individual must possess high ethical and professional standards and be adaptable. A strong publication record and excellent academic credentials are highly desirable. CONTACT: Nitin.Tandon at uth.tmc.edu Eliana.Klier at uth.tmc.edu More information @ www.tandonlab.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From dayan at tue.mpg.de Fri Nov 16 18:19:33 2018 From: dayan at tue.mpg.de (Peter Dayan) Date: Sat, 17 Nov 2018 00:19:33 +0100 Subject: Connectionists: postdoc positions with Peter Dayan Message-ID: <20181116231933.GA6735@tuebingen.mpg.de> From: Peter Dayan I have moved my lab to the Max Planck Institute for Biological Cybernetics in Tuebingen. I am therefore recruiting one or more postdocs working in the areas of neural reinforcement learning and computational psychiatry. I am planning particular emphases in neuromodulation, meta-control, behavioural analysis and all areas of dysfunctional decision-making. The aim of the MPI for Biological Cybernetics as a whole is to understand information processing in the brains of humans and animals. We use experimental, theoretical and computational methods to elucidate the characteristics and implementations of the cascades of plastic and recurrent interactions that transform sensory data into perceptions, memories, appropriate choices of actions, and motor output. We are richly multidisciplinary, have excellent facilities, and are building close links with neighbouring Max Planck Institutes and the University of Tuebingen that cover systems neuroscience, machine learning, and beyond. The working language of the Institute is English. Remuneration will depend on experience. The position will be for two years. Applications should include a CV, a list of publications, summaries of scientific achievements and research plans, and the names and contact details of three referees. Applications should be sent in PDF format no later than 16th December 2018 to: kyb-application at tuebingen.mpg.de My lab, the Institute and the Max Planck Society intend to enhance the proportion of women and minorities in areas where they are underrepresented, and they are therefore specially encouraged to apply. Informal inquiries can be addressed to Peter Dayan: kyb-inquiry at tuebingen.mpg.de From dayan at tue.mpg.de Fri Nov 16 18:01:25 2018 From: dayan at tue.mpg.de (Peter Dayan) Date: Sat, 17 Nov 2018 00:01:25 +0100 Subject: Connectionists: Independent Junior Groups at the Max Planck for Biological Cybernetics Message-ID: <20181116230125.GA6367@tuebingen.mpg.de> Max Planck Research Group Leaders at the MPI for Biological Cybernetics, Tuebingen, Germany. The aim of the MPI for Biological Cybernetics is to understand information processing in the brains of humans and animals. We use experimental, theoretical and computational methods to elucidate the characteristics and implementations of the cascades of plastic and recurrent interactions that transform sensory data into perceptions, memories, appropriate choices of actions, and motor output. We are richly multidisciplinary, have excellent facilities for human and animal neurophysiology and functional neuroimaging, and are building close links with neighbouring Max Planck Institutes and the University of Tuebingen that cover systems neuroscience, machine learning, and beyond. The working language of the Institute is English. We are developing a new organizational structure that will include a substantial number of independent research groups working in relevant areas and collaborating with each other, departments at the Institute and beyond. Funding covers a set-up package, the position of the group leader (equivalent to a W2 professorship), one post-doctoral and two PhD student fellowships, a technician, secretarial support, plus consumables. It lasts in the first instance for 5 years, with the possibility of merit-based extensions for up to 4 more years. We seek talented candidates with successful track records who are interested in coming to build a Max Planck Research Group in this environment. Applications should include a CV, a list of publications, summaries of scientific achievements and research plans, and the names and contact details of three referees. Applications should be sent in PDF format no later than 2nd January 2019 to: kyb-application at tuebingen.mpg.de Shortlisted candidates will be invited to an on-site interview on 27th February 2019. The Institute and the Max-Planck-Gesellschaft intend to enhance the proportion of women and minorities in areas where they are underrepresented, and they are therefore specially encouraged to apply. Informal inquiries can be addressed to Peter Dayan: kyb-inquiry at tuebingen.mpg.de The Max-Planck-Gesellschaft is an independent, non-profit research organization that primarily promotes and supports basic research. The society currently operates over 80 institutes and research facilities with more than 23,400 employees, including 4,400 scientists. From juyang.weng at gmail.com Fri Nov 16 15:21:34 2018 From: juyang.weng at gmail.com (Juyang Weng) Date: Fri, 16 Nov 2018 15:21:34 -0500 Subject: Connectionists: A through light after we scientists are in the dark brain-mind tunnel for 70 years In-Reply-To: References: Message-ID: Dear All: If we do not get back to much earlier non-computational studies, it was Alan Turing 1936 who proposed what is now called universal Turing machines (Alan Tring's meaning "computable numbers" has been enriched later to all possible computer programs). Alan Turing 1950 asked: "Can machines think?". Let us use 1950 as the starting year for scientists to start this extremely challenging computational question. This is probably of one of the the most important issues for modern time. John Tsotsos and his coworker has a recent review Jan. 13, 2018, "A Review of 40 Years of Cognitive Architecture Research: Core Cognitive Abilities and Practical Applications," available from ArXiv. From this review, we can see that the problem we face is an extremely challenging one. Nov. 10, 2018, Richard Loosemore wrote on this post: "Why is the question of how concepts relate to neurons so scandalously incoherent, even after this field has been talking about it for at least 35 years?" Loosemore, R.P.W. & Harley, T.A. (2010) wrote: "If you look through a journal such as Science or Nature, you will find that most articles on psychology contain or refer to imaging. And what now passes as psychology in the popular press is mostly reports on brain imaging studies. The brain is back in cognitive psychology. But is this change for the better?" Nov. 11, 2018, Asim Roy wrote: "I would argue that localist representation is synonymous with symbolic systems." All the above questions are good, but such partial questions only lead to partial solutions that do not address more fundamental issues, only delaying them. I proposed to ask a more holistic question below. This question has been positively answered through (1) a theory, (2) a fully detailed algorithm, (3) an optimality proof, (4) experiments with impressive performances verified by several independent groups during the AIML Contest 2016. "How machines auto-program for general purposes (through a single lifetime learning in the natural world)?" This question is concise but avoids many pitfalls that many partial questions left to us and misled us. The following freely available technical report provides a solution to this question: Juyang Weng: "A Model for Auto-Programming for General Purposes" https://arxiv.org/abs/1810.05764v1 Of course, this report did not solve all problems. The following are some key points: (1) Liberate symbols to overcome the limitation that a set of symbols is handcrafted only after a specific task is given. Weng modeled that emergent numeric vectors correspond to muscles neurons on the motor end. These numeric vectors liberate (i.e., without the limitations of using) symbols because they emerge automatically. (2) As a bridge for understanding, Weng used symbols to explain how a DN learns emergent Universal Turing machines, which is a model of modern general-purpose computers. (3) Generality: Such emergent vectors on the motor end correspond to all motor-expressible (e.g., spoken or hand-written) spatiotemporal concepts (not just mental states), such as states, actions, plans, goals, intents, costs, plans, goodness, badness, and novelties. (4) Skull-closed: the model (DN)'s skull-internal learning is always unsupervised, similar to the skull that closes the human brain, off limit to human teachers. (5) Top-down weights: Each hidden neuron has two types of weight vectors, top-down weight vectors (this is fundamentally new compared with all feedforward and recurrent neural networks) and bottom-up weight vectors (typically local). (6) The model is without any rigid boarders between ?lower processing? and ?high processing? where ?lower? sensory inputs (e.g., vision, audition, and text) and ?higher? context inputs (e.g., cognition, planning, and natural languages) are tightly integrated. -John Weng -------------- next part -------------- An HTML attachment was scrubbed... URL: From micheli at di.unipi.it Sat Nov 17 12:41:26 2018 From: micheli at di.unipi.it (Alessio Micheli) Date: Sat, 17 Nov 2018 18:41:26 +0100 Subject: Connectionists: CfP: 'Embeddings and Representation Learning for Structured Data' (Extended deadline) for ESANN special session In-Reply-To: References: Message-ID: <6c7a14a8edc2704cef89bf6619fc8ec7@mailbox.unipi.it> Dear all, the deadline to submit papers to the special session on 'Embeddings and Representation Learning for Structured Data' (ESANN 2019 conference) has been extended to November 26, 2018. # SPECIAL SESSION DESCRIPTION Learning models of structured data, such as sequences, trees, and graphs, has become a rich and promising research objective in many fields of machine learning, such as (deep) neural networks, probabilistic models, kernels, metric learning, and dimensionality reduction. All these seemingly disparate approaches are connected by their construction of vectorial representations and embeddings of structured data, be it implicit or explicit, fixed or learned, deterministic or stochastic. Such embeddings can not only be utilized for classification or regression, but for generation of structured data, visualization, and interpretation. # TOPICS OF INTEREST This session calls for contributions which provide novel methods to construct embeddings of structured data, new methods to utilize existing embeddings, and theoretic research regarding the properties of such embeddings. More specifically, topics of interest include, but are not limited to, the following: * Recurrent and recursive neural networks for structured data * Neural networks for graphs * Auto-Encoding models for structured data * Generative adversarial networks for structured data * Representation Learning for structured data * Deep models of structured data * Sequence, tree, and graph kernels with explicit vectorial representations * Kernel methods for structured data * Markov models for representation of sequences, trees, or graphs * Theoretical considerations on learning theory and dimensionality of embeddings of structured data * Metric learning for structured data * Dimensionality reduction techniques for structured data * Interpretability of vectorial representations of structured data # SUBMISSION Submissions must be made on the ESANN website via the following link: https://www.elen.ucl.ac.be/esann/index.php?pg=submission Each paper submission will be peer-reviewed and authors will receive a notification of acceptance at *January 31st, 2019* as either an oral or poster presentation. All papers are six pages and will be published in the ESANN proceedings ( https://www.elen.ucl.ac.be/esann/proceedings/electronicproceedings.htm ). # IMPORTANT DATES Submission of papers (extended): 26 November 2018 Notification of acceptance: 31 January 2019 ESANN conference: 24 - 26 April 2019 # SPECIAL SESSION ORGANIZERS * Benjamin Paa?en, Bielefeld University, Germany * Claudio Gallicchio, University of Pisa, Italy * Alessio Micheli, University of Pisa, Italy * Alessandro Sperduti, University of Padova, Italy _________________________________________________________________ Prof. Alessio Micheli Computational Intelligence and Machine Learning Group Universita` di Pisa - Dipartimento di Informatica Largo Bruno Pontecorvo 3, 56127 Pisa, ITALY E_mail: micheli at di.unipi.it Phone: +39-050-2212798 http://pages.di.unipi.it/micheli _________________________________________________________________ _________________________________________________________________ From luca.oneto at unige.it Sun Nov 18 08:57:54 2018 From: luca.oneto at unige.it (Luca Oneto) Date: Sun, 18 Nov 2018 14:57:54 +0100 Subject: Connectionists: [INNS-BDDL 2019] - Submission Deadline Postponed to the 30th of November Message-ID: [Apologies if you receive multiple copies of this CFP] Due to many requests the submission deadline has been postponed to the 30th of November. ########################################################### 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: November 30, 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 richard.jiang at northumbria.ac.uk Sun Nov 18 10:05:32 2018 From: richard.jiang at northumbria.ac.uk (Richard Jiang) Date: Sun, 18 Nov 2018 15:05:32 +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 ? Dr Weizhi Meng Applied Mathematics & Computer Science Technical University of Denmark, Denmark Email: weme at dtu.dk ? Professor Chang-Tsun Li School of Computing and Mathematics, Charles Sturt University, Australia Email: chli at csu.edu.au ? Professor Christophe Rosenberger Computer Security ENSICAEN ? GREYC, France Email: christophe.rosenberger at ensicaen.fr Contact: All questions about submissions can be emailed to perceptualscience at outlook.com or any editor in the board. Many thanks! Kind Regards, Editors of the Book -- This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender?s explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended. -------------- next part -------------- An HTML attachment was scrubbed... URL: From jose at rubic.rutgers.edu Sun Nov 18 14:23:39 2018 From: jose at rubic.rutgers.edu (Stephen Jose Hanson) Date: Sun, 18 Nov 2018 14:23:39 -0500 Subject: Connectionists: Virtual concepts Message-ID: Hi Richard, you raise many good points which I agree with and agreed with when I read and edited your chapter. (Btw the actual Reference is :?? Loosemore, R.P.W. & Harley, T.A. (2010). Brains and Minds:? On the Usefulness of Localization Data to Cognitive Psychology. In SJ Hanson & M. Bunzl (Eds.), Foundational Issues in Human Brain Mapping. Cambridge, MA: MIT Press--. just for the record) Clearly single cell recording? or even an average? voxel with 14 million neurons that are response to say "faces", should not be prima facie evidence for a "face area" or "face concept area"? or "face category/intension area of the brain". I am unclear what you mean by "symbol" tho in this context.? Virtual concepts seems to be a fine way of thinking of conceptual function, but still needs some sort of brain mechanism--no? I think DL models are likely to provide some more options for what you describe as a "virtual concept".?? The scale of these systems make them difficult to characterize in some principled way.?? 100s of layers, 100s of millions of weights 100s of thousands of hidden units.. this is simply a qualitatively different type of representational system then what we were dealing with 30 years ago. One recent paper on concept representation and DL you might find interesting: https://www.frontiersin.org/articles/10.3389/fpsyg.2018.00374/full Steve Hanson -- Stephen Jos? Hanson Professor Director RUBIC (University-Wide) Department of Psychology (NK) Cognitive Science Center (NB) -------------- next part -------------- An HTML attachment was scrubbed... URL: From hava.siegelmann at gmail.com Mon Nov 19 07:09:09 2018 From: hava.siegelmann at gmail.com (Hava Siegelmann) Date: Mon, 19 Nov 2018 07:09:09 -0500 Subject: Connectionists: Congratulations INNS Award Recipients- To be awarded this year in Budapest Message-ID: * Congratulations INNS Award Recipients! * *The INNS Awards -- **Donald O. Hebb Award.** The award recognizes outstanding achievements in biological learning. **Hermann von Helmholtz Award.** The award recognizes outstanding achievements in perception.**Dennis Gabor Award**. The award recognizes outstanding achievements in neural engineering. **Ada Lovelace Service Award** recognizes meritorious service to the neural community. Aharon Katzir **Young Investigator Award** is conferred to a most promising young investigator in the field of neural networks. * *All of the awards will be ceremonially presented at the 2019 IJCNN Conference. This year in beautiful Budapest. * *INNS congratulates this year's five recipients:* *Stephen Grossberg - Donald O. Hebb Award* *Bernard Baars - Hermann von Helmholtz Award* *Danilo Mandic - Dennis Gabor Award* *Don Wunsch - Ada Lovelace Service Award* *Zhen Ni - Aharon Katzir Young Investigator Award* *Come to celebrate with us and them -* *Hava Siegelmann ? Chair, INNS Awards Committee * -------------- next part -------------- An HTML attachment was scrubbed... URL: From M.Goodfellow at exeter.ac.uk Mon Nov 19 07:53:24 2018 From: M.Goodfellow at exeter.ac.uk (Goodfellow, Marc) Date: Mon, 19 Nov 2018 12:53:24 +0000 Subject: Connectionists: PhD studentship, University of Exeter Message-ID: A fully funded studentship is available to work with Dr. Marc Goodfellow (University of Exeter, UK) and Prof. George Augustine (NTU, Singapore). The deadline for applications is 31st January 2019. Healthy brain function is mediated by the coordination of neuronal activity - both locally and across different brain regions - giving rise to large-scale brain dynamics. These dynamics are measured using a variety of techniques, for example magneto-/electro-encephalography or functional MRI in humans, or by fluorescence-based imaging of voltage- or calcium-sensitive indicators in animal models in vivo. Uncovering the nature and mechanisms of large-scale brain dynamics at rest, or during sensory processing, remains a fundamental challenge in neuroscience. In addition to basic insight, improving our understanding of healthy brain dynamics will help us elucidate reasons why abnormal dynamics occur, for example in neurological or neuropsychiatric disorders. This studentship will develop a novel program of interdisciplinary research across in vivo (mouse) experimentation and mathematical modelling. The overall aim is to construct and validate mathematical models of large-scale brain dynamics that are able to explain the spontaneous activity of the rodent brain in vivo. The student will train in optogenetic technologies and in vivo imaging, as well as mathematical model development, multi-variate time series analysis and parameter fitting tools, thus placing them at the forefront of interdisciplinary neuroscience. In a first step, targeted optogenetic stimuli will be combined with voltage sensitive dye imaging in awake mice to probe the response of brain tissue to excitatory and inhibitory afferent stimuli. Neural mass models will be fit to these data, using machine learning approaches (for example random forests). This information will be compiled into a predictive model of cortical dynamics and tested against experimental recordings of spontaneous activity. The studentship is part of a joint program between The University of Exeter (UoE) and Nanyang Technological University (NTU), Singapore. They are offering six fully funded postgraduate studentships to undertake collaborative research projects at the two institutions, leading to PhD degrees (split-site) to be conferred either by the UoE or NTU. Students pursuing these postgraduate research projects will benefit from the unique opportunity to conduct their research at both institutions. Students will be registered at one or other institution, where they will be based for the majority of their time, but will spend at least 12 and not more than 18 months at the partner institution over the duration of the programme. The frequency and length of stays at each institution will be agreed with successful candidates prior to offers being made. All six projects are advertised concurrently at both institutions and three will be allocated to each institution after the deadline has passed, based on a collaborative decision made between the UoE and NTU. The final decision on the successful applicant for each project will be made by the institution hosting the project. Project allocation will be based on the applicant's best fit to a project, following a review of applications submitted to each institution. Applications to undertake the projects at the UoE and NTU are open to all nationalities. The programme start dates are August 2019 for NTU and September 2019 for UoE The home institution will determine the regulations that will apply to the successful applicant. The student's main supervisor will be based at the home institution. For further information and to register interest, please contact Dr. Marc Goodfellow (m.goodfellow at exeter.ac.uk). To apply and for further details, please see http://www.exeter.ac.uk/studying/funding/award/?id=3058 -------------- next part -------------- An HTML attachment was scrubbed... URL: From Pavis at iit.it Mon Nov 19 11:23:49 2018 From: Pavis at iit.it (Pavis) Date: Mon, 19 Nov 2018 16:23:49 +0000 Subject: Connectionists: Postdoctoral position in Computer Vision & Machine Learning - [ Postdoc ] BC 75470 In-Reply-To: <66247ad0c4834cb3a5c664a2a45fb12d@iit.it> References: <66247ad0c4834cb3a5c664a2a45fb12d@iit.it> Message-ID: <8f86f36ce4574028b9908d305c77660f@iit.it> Postdoctoral position in Computer Vision & Machine Learning - [ Postdoc ] BC 75470 Workplace: Genova, IIT, Italy Added on: 26/06/2018 - Expires on 31/12/2018 The Pattern Analysis and Computer Vision Research Line (PAVIS) at IIT in Genova is looking for a highly qualified post doc with a strong background in Computer Vision, Pattern Recognition and Machine Learning, with particular emphasis on recognition, video analysis, behavior understanding, and prediction. As the activities may be carried out in collaboration with other IIT research units, the previous multidisciplinary experience is an added value which will be duly considered. The main mission of PAVIS is to design and develop innovative image- and video-based intelligent systems, characterized by the use of highly functional smart sensors and advanced data analytics features. PAVIS also plays an active role in supporting the other IIT research units providing scientists in Neuroscience, Nanophysics and other IIT departments/centers with ad-hoc solutions. To this end, the group is involved in activities concerning computer vision and pattern recognition, machine learning, multimodal\multimedia data analysis and sensor fusion, and embedded computer vision systems. The lab will pursue this goal by working collaboratively and in cooperation with external private and public partners. In particular, this call aims at consolidating PAVIS expertise in the video surveillance area and especially on action/activity recognition and scene understanding from video sequences and other sensory modalities. In particular, the following topics are of interest: Analysis of static and dynamic scenes. Recognition (objects, scenes, actions, events, etc.) and reconstruction. Behavior Analysis and Activity Recognition (individuals, groups, crowd). Prediction of intentions. Domain Adaptation. Multimodal data analysis Zero-shot Learning >From the methodological standpoint, the ideal candidate should be familiar with one or more of the following subjects (it?s not an exhaustive list): Deep Learning, Graphical Models, Topic Models, Representation/Feature Learning, Sparse and Dictionary Learning, Clustering, Kernel methods, Manifold Learning and Statistical and Probabilistic Models in general. Candidates to this position have a Ph.D. in Computer Vision, Machine Learning, Pattern Recognition or related areas. Research experience and qualification in computer vision and pattern recognition/machine learning are clearly a must and evidence of top quality research on the above-specified areas in the form of published papers in top conferences/journals and/or patents is mandatory. Moreover, experience in the preparation and management of research proposals (EU, US, national) and industrial research projects, a few years of postdoc experience, either in academia or in an industrial lab, will also be duly considered. The winning candidate will also be asked to contribute to setting up new (funding) project proposals and will participate in funding activities. He/she is also expected to publish his/her research results in leading international journals and conferences, supervise Ph.D. candidates and collaborate with other scientists, also with different expertise. Salary will be commensurate to qualification and experience and in line with international standards. Further details and informal inquiries can be made by email to pavis at iit.it quoting PAVIS-PD 75470 as the reference number. Please send your completed application forms by December 31, 2018. The application must include: a curriculum listing all publications (possibly including a pdf of your most representative publications), a research statement describing your previous research experience and outlining its relevance to the above topics and the name of 2 referees by email to pavis at iit.it quoting PAVIS-PD 75470 as the reference number. IIT was established in 2003 and successfully created a large-scale infrastructure in Genova, a network of 10-state-of-the-art laboratories countrywide and recruited an international staff of about 1100 people from more than 50 countries. IIT's research endeavor focuses on high-tech and innovation, representing the forefront of technology with possible applications from medicine to industry, computer science, robotics, life sciences, and nanobiotechnologies. We inform you that the information you provide will be used solely for the purposes of evaluating and selecting professional profiles 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). Istituto Italiano di Tecnologia is an Equal Opportunity Employer that actively seeks diversity in the workforce. -------------- next part -------------- An HTML attachment was scrubbed... URL: From hal.greenwald at us.af.mil Mon Nov 19 16:12:45 2018 From: hal.greenwald at us.af.mil (GREENWALD, HAL S DR-04 USAF AFMC AFOSR/RTA) Date: Mon, 19 Nov 2018 21:12:45 +0000 Subject: Connectionists: New AFOSR Cognitive & Computational Neuroscience research funding portfolio Message-ID: Dear Colleagues, Please check out AFOSR's new research funding portfolio in Cognitive and Computational Neuroscience! The Cognitive and Computational Neuroscience program funds high-risk, high-potential basic research that uses experimental and computational modeling techniques from systems neuroscience, cognitive neuroscience, computational/theoretical neuroscience, cognitive science, and cognitive psychology to understand the neural mechanisms responsible for perception, cognition, and behavior. The program also supports brain-inspired algorithm and hardware development provided these are useful for testing proposed neuroscience theories and/or enabling novel capabilities in computing, artificial intelligence, or autonomous systems. The Broad Agency Announcement is posted at https://www.grants.gov/web/grants/view-opportunity.html?oppId=305996 (see file FA9550-18-S-0003 Amendment 002.pdf) Awards under this BAA are not limited to US researchers. Although the BAA remains open year round, to be considered for FY19 funding, full proposals should be submitted via grants.gov no later than mid-February. Emailed pre-proposals in the form of white papers (approximately 3-5 pages, excluding references) describing specific research questions and approaches are encouraged. Regards, Hal Greenwald Hal S. Greenwald, Ph.D. Program Officer, Cognitive & Computational Neuroscience Air Force Office of Scientific Research (AFOSR/RTA) 875 N. Randolph St. Arlington, VA 22203-1768 (703) 588-8441 neuroscience at us.af.mil -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 5472 bytes Desc: not available URL: From yang at maebashi-it.org Mon Nov 19 20:43:18 2018 From: yang at maebashi-it.org (Yang) Date: Tue, 20 Nov 2018 10:43:18 +0900 Subject: Connectionists: [BI 2018] Call for Participation Message-ID: <378780711DDE4514955B3BD1714B465F@yangPC> [Apologies if you receive this more than once] CALL FOR PARTICIPATION The 11th International Conference on Brain Informatics (BI'18) December 7-9, 2018, Arlington, Texas, USA Homepage: http://uta.engineering/conferences/bi-2018/ ------------------------------------------------------ ---Advancing BI Technologies from Basic Science Research to Real-World Practice--- ------------------------------------------------------ The International Conference on Brain Informatics series (BI) has established itself as the world?s premier research forum that brings together researchers and practitioners from neuroscience, cognitive science, computer science, data science, artificial intelligence, information communication technologies, and neuroimaging technologies with the purpose of exploring the fundamental roles, interactions as well as practical impacts of Brain Informatics. The BI'18 will provide a broad forum that academia, professionals and industry people can exchange their ideas, findings, and strategies in brain informatics research and brain-inspired concepts and technologies. It welcomes emerging technologies for addressing fundamental neurobiological questions about healthy brain function, laying the groundwork for advancing treatments for brain disorders or injury, and for generating brain-inspired "smart" artificial intelligence and computing technologies to meet future societal needs. It will educate and expand the brain informatics workforce and create new career opportunities for brain research and related innovations. *** Keynote Talks *** "Neuroimaging and Informatics in Alzheimer's Disease Research" Speaker: Arthur Toga, University of Southern California, USA "How to Understand Our Brain and Intelligence: >From Epileptic Network to Brain-Computer Interface" Speaker: Guoming Luan, Capital Medical University, China "Next Generation Hardware for Large-Scale Brain Modeling and AI Applications" Speaker: Chris Eliasmith, University of Waterloo, Canada "The Fabric of the Neocortex: A Less-Artificial Intelligence" Speaker: Andreas Tolias, Baylor College of Medicine, USA *** Workshops/Special Sessions *** Computationally Intelligent Methods in Processing and Analysis of Neuronal Big Data Organizers: Mufti Mahmud, Nottingham Trent University, UK M Shamim Kaiser, Jahangirnagar University, Bangladesh Ning Zhong, Maebashi Institute of Technology, Japan Nitish V Thakor, National University of Singapore, Singapore The International Workshop on Computational Intelligence for processing Brain Images Organizers: Abdel-Badeeh M. Salem, Ain Sham University, Egypt Frank Lievens, ISfTeH, Belgium Marco Alfonse, Ain Shams University, Egypt Wael Khalifa, Ain Shams University, Egypt The 1st International Workshop on Cognitive Neuroscience of Thinking and Reasoning Organizers: Jing Luo (Capital Normal University, China)? Vinod Goel (York University, Canada)? Hong Li ?Shenzhen University, China), and Peipeng Liang (Capital Normal University, China) The 1st International Workshop on Neuromodulation and Brain-Machine Intelligence Organizers: Qian Wang, Sanbo Brain Hospital, Capital Normal University, China Guoming Luan, Sanbo Brain Hospital, Capital Normal University, China Yang Yang, Maebashi Institute of Technology, Japan The 3rd International Workshop on Neuroimaging Analytics for Brain and Mental Health Organizers: Shouyi Wang, The University of Texas at Arlington, USA Fenghua Tian, The University of Texas at Arlington, USA Jianzhong Su, The University of Texas at Arlington, USA *** Topics and Areas for Parallel Presentations *** BI'18 has collected high-quality original research and application papers (both full paper and abstract submissions). The authors of the submissions will give oral presentations during the conference.Relevant topics include but are not limited to: Track 1: Cognitive and Computational Foundations of Brain Science Track 2: Human Information Processing Systems Track 3: Brain Big Data Analytics, Curation and Management Track 4: Informatics Paradigms for Brain and Mental Health Research Track 5: Brain-Machine Intelligence and Brain-Inspired Computing IMPORTANT DATES: ================ December 7, 2018: Workshops & Special Sessions December 8-9, 2018: Main conference Conference Venue ================ Hilton Arlington 2401 East Lamar Boulevard Arlington, Texas 76006-7503, USA Tel: +1-817-640-3322 Fax: +1-817-633-1430 ORGANIZERS ========== General Chairs Tom Mitchell (Carnegie Mellon University, USA) Leon Iasemidis (Louisiana Tech, University, USA) Ning Zhong (Maebashi Institute of Technology, Japan) Program Committee Chairs Jianzhong Su (University of Texas at Arlington, USA) Vicky Yamamoto (University of South California, USA) Yu-Ping Wang (Tulane University, USA) Organizing Chairs Shouyi Wang (University of Texas at Arlington, USA) Erick Jones (University of Texas at Arlington, USA) Fenghua Tian (University of Texas at Arlington, USA) Workshop/Special-Session Chairs Chou, Chun-An (Northwestern University, USA) Xiangnan Kong (Worcester Polytechnic Institute, USA) Felicia Jefferson (Fort Valley State University, USA) Jing Qin (Montana State University, USA) Panel/Tutorial Chairs Yang Yang (Maebashi Institute of Technology, Japan) Vassiliy Tsytsarev (University of Maryland, USA) Publicity Chairs Paul Wen (University of Southern Queensland, Australia) Huiguang He (Chinese Academy of Sciences, China) Mufti Mahmud (University of Padova, Italy) Steering Committee Chairs Ning Zhong (Maebashi Institute of Technology, Japan) Hanchuan Peng (Allen Institute for Brain Science, USA) *** Contact Information *** Shouyi Wang Email: shouyiw at uta.edu Vicky Yamamoto Email: Vicky.Yamamoto at med.usc.edu Yang Yang Email: yang at maebashi-it.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From o.e.scharenborg at tudelft.nl Tue Nov 20 04:11:01 2018 From: o.e.scharenborg at tudelft.nl (Odette Scharenborg) Date: Tue, 20 Nov 2018 10:11:01 +0100 Subject: Connectionists: postdoc opening @ Laboratoire des Sciences Cognitives et Psycholinguistique (LSCP), Paris In-Reply-To: References: Message-ID: Dear colleagues, see the post-doc position below. Females are especially encouraged to apply. Best wishes Odette Scharenborg Laboratoire des Sciences Cognitives et Psycholinguistique (LSCP) UMR 8554 - EHESS - ENS - CNRS 29 rue d?Ulm, 75005 Paris We are looking for a highly motivated postdoctoral fellow with a strong background in speech technology. The two-years post-doctoral fellowship will take place at the Laboratoire de Sciences Cognitives et Psycholinguistique, part of the D?partement d'?tudes Cognitives (DEC) of the Ecole Normale Sup?rieure in Paris, under the joint supervision of Emmanuel Dupoux and Alex Cristia. Female candidates are encouraged to apply. The postdoctoral fellow would ideally become involved in one or more of several ongoing projects, including: The organization of challenges and workshops like the Zero Resource Speech Challenge The development of speech technology/machine learning algorithms inspired by how infants learn language, i.e, with little or no supervision The development of speech technology solutions applicable to naturalistic, large-scale recordings, in order to derive measures of language production and conversational dynamic Requirements: The candidate should have a PhD in speech technology and related fields. Experience managing large datasets is required along with strong programming (experience with python and open source projects is a plus). Strong English language and writing skills are required (note: speaking French is not required). Experience with linguistics and child language is appreciated but not required. Salary: The salary will be adjusted to the candidate?s post-doctoral experience (start salary for a 1st year post doc: 33,000 euros/year net; 5 years of experience: 38,000) Start date: The position should ideally start before March 2019 but there is some flexibility if this is not possible. Applications and requests for information: Please send by December 7, 2019 to syntheticlearner at gmail.com : a complete CV, a 2-page cover letter explaining how you fit the requirements, a sample of own writing (e.g., a publication where you wrote the bulk of the text for), (a link to) a sample of computer code you produced, and contact information of two references Feel free to contact us for more information! --- Deze e-mail is gecontroleerd op virussen door AVG. http://www.avg.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From irina.illina at loria.fr Tue Nov 20 03:52:47 2018 From: irina.illina at loria.fr (Irina Illina) Date: Tue, 20 Nov 2018 09:52:47 +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: <1405387991.21186394.1542703967147.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 -- 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 Pavis at iit.it Tue Nov 20 09:32:27 2018 From: Pavis at iit.it (Pavis) Date: Tue, 20 Nov 2018 14:32:27 +0000 Subject: Connectionists: Postdoc Position on dynamic scene understanding at Istituto Italiano di Tecnologia (IIT - Genova) - [ Postdoc ] BC 76193 Message-ID: <31c4303e5fec4c839bf302e8cb62d057@iit.it> Postdoc Position on dynamic scene understanding at Istituto Italiano di Tecnologia (IIT - Genova) - [ Postdoc ] Workplace: Genova, IIT, Italia Added on: 20/11/2018 - Expires on 21/12/2018 The Visual Geometry and Modelling (VGM, https://vgm.iit.it/) Research Line at Istituto Italiano di Tecnologia (IIT) invites qualified applicants to submit their CV's for a Postdoc position in Genova, Italy, under the supervision of Dr. Alessio Del Bue. The VGM mission is to provide computational tools for the large-scale understanding of image and video data for an autonomous system for different application domains in engineering, life science, and robotics. The scientific core of the VGM Lab relates to the research fields of Computer Vision, Signal Processing and Machine Learning with the primary goal to provide algorithms for: - Dynamic 3D scene understanding from video and RGBD data; - Reality Capture: 3D reconstruction from images, sound and range data; - Large-scale data understanding and modeling for Life Science and Engineering. Expertise in these research fields applies to several practical and challenging problems in the industry with ongoing collaboration with world-leading companies in machine vision, robotics, automation, energy, avionics, photonics, and fashion industries. VGM is opening a postdoc position to work on dynamic 3D scene understanding with topics related to semantic simultaneous localization and mapping (S-SLAM) and semantic structure from motion (S-SfM) which are core research themes of the Lab (Crocco et al., CVPR 2016), (Magerand & Del Bue, ICCV2017), (Rubino et al., PAMI 2018). As these previous works mainly deal with static scenes, the VGM lab will push forward these activities developing computational methods for geometric and semantic understanding in challenging dynamic and non-rigid environments. The key aspect of the research carried at VGM will focus on the fusion of state of the art deep architectures with 3D reasoning from multi-view images or RGBD data. Required qualifications: - A Ph.D. in computer science or related field (with specialization in either computer vision, information retrieval or machine learning); - Proficiency in programming languages, in particular, Python, C/C++, and MATLAB; - Experience on SLAM and multi-view geometry approaches for sparse and dense 3D reconstruction; - Publication in major Computer Vision conferences/journals (e.g. CVPR, ICCV, ECCV, TPAMI, IJCV, IVC, CVIU); - Good communication skills and ability to cooperate; - Proficient in English language (written and oral). Desirable skills: - Practical experience on Deep Learning algorithms and relevant platforms for geometric learning (e.g. TensorFlow, PyTorch, etc.); - Knowledge of OpenCV, PCL, and Open3D libraries; - Experience in graph structure applications e.g. scene graph estimation, matching, retrieval or inference; The salary offered to the successful candidate will be 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 December 21, 2018. Please send your application to pavis at iit.it and applications at iit.it quoting "BC 76193 - VGM Postdoc Position on dynamic scene understanding" in the e-mail subject. Your application shall contain a detailed CV, a one-page research statement and 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. Istituto Italiano di Tecnologia, based in Genoa, Via Morego 30, will process your data 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 francisco.pereira at gmail.com Tue Nov 20 09:55:53 2018 From: francisco.pereira at gmail.com (Francisco Pereira) Date: Tue, 20 Nov 2018 09:55:53 -0500 Subject: Connectionists: job post: machine learning research assistant Message-ID: The Machine Learning Team at the National Institute of Mental Health in Bethesda, MD, has an open position for a research assistant, under the National Institutes of Health IRTA program. Our mission is to help local scientists use machine learning methods to address research problems in clinical and cognitive psychology and neuroscience. We work with very large brain imaging datasets, in many different imaging modalities, as well as behavioral data, picture and text corpora, etc. We also develop new machine learning methods and publish in the main machine learning conferences, and in psychology and neuroscience journals. You would be working with us on all of these activities and have the opportunity to be the lead on some of the projects, as well as co-author on other publications. As part of these efforts, you would actively contribute (e.g. write python code and design experiments), as well as learn more about machine learning (e.g. read papers, attend courses and conferences, and be taught one-on-one). We have very good computational resources, both of our own (tens of GPUs for deep learning) and shared with other institutes (a top-100 supercomputer with hundreds of thousands of CPUs, and hundreds of GPUs). This is an ideal position for someone who plans on applying to graduate school in machine learning or a related discipline. The knowledge you will acquire, the potential publication record, and our support in preparing your graduate application will both improve your prospects, and help you in any other career path. You can find more about our work here https://cmn.nimh.nih.gov/mlt and the National Institutes of Health IRTA training program here https://www.training.nih.gov/programs/postbac_irta Candidates should be in the final year of an undergraduate degree in computer science, mathematics, statistics, biomedical engineering, or physics; we can also consider other areas, given adequate programming and research experience. If you would like to be considered for this position, please email francisco.pereira at nih.gov an application letter and a CV, highlighting your programming experience and participation in research projects. Other inquiries are also welcome. Thank you for your interest! Applications received by January 7th, 2019 will receive full consideration, but applications will be accepted until the position is filled. DHHS and NIH are Equal Opportunity Employers. -------------- next part -------------- An HTML attachment was scrubbed... URL: From travis.e.baker.phd at gmail.com Tue Nov 20 12:57:22 2018 From: travis.e.baker.phd at gmail.com (Travis Baker) Date: Tue, 20 Nov 2018 12:57:22 -0500 Subject: Connectionists: PhD Studentships available at the Center for Molecular and Behavioral Neuroscience, Rutgers University Message-ID: PhD Studentships available *Deadline: December 15, 2018* The Center for Molecular and Behavioral Neuroscience (CMBN) at *Rutgers University ? Newark* is inviting students to apply to its *Behavioral and Neural Sciences *Graduate Program for the 2019 admissions cycle. CMBN?s mission is to advance understanding of the brain?s structure and function through excellence in neuroscience research and training. We believe this goal can only be reached through an integrative approach that cuts across the boundaries of traditional disciplines. Thus, CMBN researchers combine molecular, electrophysiological, optogenetics, neurochemical, anatomical and functional neuroimaging, behavioral, pharmacogenetics, and neuropsychological methods to analyze how the brain works, develops, interacts with the environment, and is modified by experience in health and disease. The program trains students for scientific research careers in neuroscience and prepares students to take positions in academic, medical and industrial research settings. Our focus is on multidisciplinary training of students across the domains of neuroscience. Students are trained to conduct independent research and to present and discuss research ideas and results both orally and in written form. Students also gain experience in both undergraduate and graduate teaching. The program benefits from the active participation of the graduate faculties of Rutgers University-Newark from the CMBN, the Department of Biological Sciences, and the Department of Psychology. The PhD program lasts four to five years. Starting in year one, students do semester-long research rotations in laboratories of one or more faculty members to learn about different aspects of neuroscience research. Dissertation research can also be completed under the supervision of more than one faculty member, to broaden student training. The course curriculum has been developed to bring students with diverse backgrounds (neuroscience, psychology, cognitive neuroscience, mathematics, neuroimaging, and engineering) up to speed on the topics they will need for their research projects. Most classes involve extensive discussions with faculty, hands-on learning, critical thinking, and scientific writing. Interested students are encouraged to contact potential supervisors in advance to learn more about their research program. All students are fully funded, regardless of nationality. The program also welcomes applications from students with pre-secured funding or who are currently soliciting other scholarship/studentships. PhD students receive a 12-month renewable graduate assistantship of $29,605 plus tuition remission and a medical benefits plan. Further, the President of Rutgers, The State University of New Jersey, invites outstanding candidates to apply to Ph.D. programs for consideration as Presidential Fellows ($35,000 annual fellowship stipends for 2 years). Full details of our program, and how to apply, are available at: *bns.rutgers.edu * For further details of research interests please see individual CMBN faculty webpages at CMBN: *cmbn.rutgers.edu * Informal enquiries may be addressed to Dr. Travis Baker (*travis.e.baker at rutgers.edu *), Dr. Vince McGinty (*vince.mcginty at rutgers.edu *), Dr. Juan Mena-Segovia, (juan.mena at rutgers.edu ). *Now accepting PhD students at the Laboratory for Cognitive Neuroimaging and Stimulation, Rutgers University* Fully-funded PhD positions are available in the Laboratory for Cognitive Neuroimaging and Stimulation (www.neurostimlab.com) at the Center for Molecular and Behavioral Neuroscience (CMBN), Rutgers University, *http://cmbn.rutgers.edu *. CMBN is located in Newark NJ, a short commute from New York City. The laboratory of Dr. Travis E Baker employs multimodal neuroimaging techniques, involving both typical and atypical populations, to characterize the neural and cognitive mechanisms underlying goal-directed behavior and navigation. The clinical goal of the laboratory is to understand how these functions are disrupted in psychiatric populations (e.g. addictions, affective disorders, neurodegenerative disorders), and to identify image-based biomarkers (e.g. EEG/ERPs, fMRI) and neuromodulation procedures aimed to alleviate their cognitive and behavioral impairments. This position offers an excellent opportunity to develop research expertise in neuroimaging and neuromodulation. Dr. Baker?s laboratory houses an Adept Viper s850 robotic arm used for robot-assisted image-guided transcranial magnetic stimulation (Ri-TMS), two parallel systems for recording EEG/ERPs, an eyetracking system, a virtual reality system (HTC vive), and has the capabilities of recording and analyzing simultaneous EEG and fMRI, and simultaneous EEG and Ri-rTMS. CMBN benefits from on-site access to Rutgers University Brain Imaging Center (RUBIC), a research-dedicated facility equipped with a 3T fMRI scanner (Siemens TRIO) for imaging both humans and animals (*http://rubic.rutgers.edu *). For those with an interest in working with clinical populations, we have superb cooperation with our medical school faculty in neurology, psychiatry, and neurosurgery, as well as collaborations with several medical centers in nearby New York City. Informal enquiries may be addressed to Dr. Travis Baker at travis.e.baker @rutgers.edu no later than December 1st, 2018 and should include a cover letter summarizing research interests, and a curriculum vita. Further details about Dr. Baker?s research interests can be found at www.neurostimlab.com. Rutgers University is an equal opportunity educator and employer. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Rutgers-BNS-grad-program-2019 (2).pdf Type: application/pdf Size: 1366082 bytes Desc: not available URL: From travis.e.baker.phd at gmail.com Tue Nov 20 20:11:45 2018 From: travis.e.baker.phd at gmail.com (Travis Baker) Date: Tue, 20 Nov 2018 20:11:45 -0500 Subject: Connectionists: PhD Studentships available at the Center for Molecular and Behavioral Neuroscience, Rutgers University In-Reply-To: References: Message-ID: PhD Studentships available *Deadline: December 15, 2018* The Center for Molecular and Behavioral Neuroscience (CMBN) at *Rutgers University ? Newark* is inviting students to apply to its *Behavioral and Neural Sciences *Graduate Program for the 2019 admissions cycle. CMBN?s mission is to advance understanding of the brain?s structure and function through excellence in neuroscience research and training. CMBN researchers combine molecular, electrophysiological, optogenetics, neurochemical, anatomical and functional neuroimaging, behavioral, pharmacogenetics, and neuropsychological methods to analyze how the brain works, develops, interacts with the environment, and is modified by experience in health and disease. The program trains students for scientific research careers in neuroscience and prepares students to take positions in academic, medical and industrial research settings. Students are trained to conduct independent research and to present and discuss research ideas and results both orally and in written form. The PhD program lasts four to five years. All students are fully funded, regardless of nationality. The program also welcomes applications from students with pre-secured funding or who are currently soliciting other scholarship/studentships. PhD students receive a 12-month renewable graduate assistantship of $29,605 plus tuition remission and a medical benefits plan. Further, the President of Rutgers, The State University of New Jersey, invites outstanding candidates to apply to Ph.D. programs for consideration as Presidential Fellows ($35,000 annual fellowship stipends for 2 years). Full details of our program, and how to apply, are available at: *bns.rutgers.edu * For further details of research interests please see individual CMBN faculty webpages at CMBN: *cmbn.rutgers.edu * Informal enquiries may be addressed to Dr. Travis Baker (*travis.e.baker at rutgers.edu *), Dr. Vince McGinty (*vince.mcginty at rutgers.edu *), Dr. Juan Mena-Segovia, (juan.mena at rutgers.edu ). *Now accepting PhD students at the Laboratory for Cognitive Neuroimaging and Stimulation, Rutgers University* Fully-funded PhD positions are available in the Laboratory for Cognitive Neuroimaging and Stimulation (www.neurostimlab.com) at the Center for Molecular and Behavioral Neuroscience (CMBN), Rutgers University, *http://cmbn.rutgers.edu *. CMBN is located in Newark NJ, a short commute from New York City. The laboratory of Dr. Travis E Baker employs multimodal neuroimaging techniques, involving both typical and atypical populations, to characterize the neural and cognitive mechanisms underlying goal-directed behavior and navigation. The clinical goal of the laboratory is to understand how these functions are disrupted in psychiatric populations (e.g. addictions, affective disorders, neurodegenerative disorders), and to identify image-based biomarkers (e.g. EEG/ERPs, fMRI) and neuromodulation procedures aimed to alleviate their cognitive and behavioral impairments. This position offers an excellent opportunity to develop research expertise in neuroimaging and neuromodulation. Dr. Baker?s laboratory houses an Adept Viper s850 robotic arm used for robot-assisted image-guided transcranial magnetic stimulation (Ri-TMS), two parallel systems for recording EEG/ERPs, an eyetracking system, a virtual reality system (HTC vive), and has the capabilities of recording and analyzing simultaneous EEG and fMRI, and simultaneous EEG and Ri-rTMS. CMBN benefits from on-site access to Rutgers University Brain Imaging Center (RUBIC), a research-dedicated facility equipped with a 3T fMRI scanner (Siemens TRIO) for imaging both humans and animals (*http://rubic.rutgers.edu *). For those with an interest in working with clinical populations, we have superb cooperation with our medical school faculty in neurology, psychiatry, and neurosurgery, as well as collaborations with several medical centers in nearby New York City. Informal enquiries may be addressed to Dr. Travis Baker at travis.e.baker @rutgers.edu no later than December 1st, 2018 and should include a cover letter summarizing research interests, and a curriculum vita. Further details about Dr. Baker?s research interests can be found at www.neurostimlab.com. Rutgers University is an equal opportunity educator and employer. > > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From pblouw at uwaterloo.ca Wed Nov 21 00:41:58 2018 From: pblouw at uwaterloo.ca (Peter Blouw) Date: Wed, 21 Nov 2018 00:41:58 -0500 Subject: Connectionists: Call for applications - 2019 Nengo Summer School Message-ID: [All details about this school can be found online at https://www.nengo.ai/summerschool] The Centre for Theoretical Neuroscience at the University of Waterloo is excited to announce our 6th annual Nengo summer school on large-scale brain modelling and neuromorphic computing. This two-week school will teach participants to use the Nengo simulation package to build state-of-the-art cognitive and neural models to run both in simulation and on neuromorphic hardware. Summer school participants will be given on-site access to Loihi, Intel?s new neuromorphic research chip [1], and will learn to run high-level applications on Loihi using Nengo! More generally, Nengo provides users with a versatile and powerful environment for designing cognitive and neural systems, and has been used to build what is currently the world's largest functional brain model, Spaun [2], which includes spiking deep learning, reinforcement learning, adaptive motor control, and cognitive control networks. For a look at last year's summer school, check out this short video: https://www.youtube.com/watch?v=NwtYgBB2N6I We welcome applications from all interested graduate students, postdocs, professors, and industry professionals with a relevant background. [1] Davies, et al. (2018). Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro. Vol. 38 no. 1 pp. 82-99. [ https://ieeexplore.ieee.org/document/8259423] [2] Eliasmith, C., Stewart T. C., Choo X., Bekolay T., DeWolf T., Tang Y., Rasmussen, D. (2012). A large-scale model of the functioning brain. Science. Vol. 338 no. 6111 pp. 1202-1205. DOI: 10.1126/science.1225266. [ http://compneuro.uwaterloo.ca/files/publications/eliasmith.2012.pdf] ***Application Deadline: February 15, 2019*** Format: A combination of tutorials and project-based work. Participants are encouraged to bring their own ideas for projects, which may focus on testing hypotheses, modeling neural or cognitive data, implementing specific behavioural functions with neurons, expanding past models, or providing a proof-of-concept of various neural mechanisms. Hands-on tutorials, work on individual or group projects, and talks from invited faculty members will make up the bulk of day-to-day activities. A project demonstration event will be held on the last day of the school, with prizes for strong projects! Participants will have the opportunity to learn how to: - interface Nengo with neuromorphic hardware (e.g. Loihi, SpiNNaker) - build perceptual, motor, and cognitive models using spiking neurons - model anatomical, electrophysiological, cognitive, and behavioural data - use a variety of single cell models within a large-scale model - integrate machine learning methods into biologically oriented models - interface Nengo with cameras and robotic systems - implement modern nonlinear control methods in neural models - and much more? Date and Location: June 9th to June 21st, 2019 at the University of Waterloo, Ontario, Canada. Applications: Please visit http://www.nengo.ai/summerschool, where you can find more information regarding costs, travel, lodging, along with an application form listing required materials. If you have any questions about the school or the application process, please contact Peter Blouw (peter.blouw at appliedbrainresearch.com). The school is also partly supported by ONR and ABR, Inc. We look forward to hearing from you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From axel.soto at cs.uns.edu.ar Tue Nov 20 16:11:06 2018 From: axel.soto at cs.uns.edu.ar (Axel Soto) Date: Tue, 20 Nov 2018 18:11:06 -0300 Subject: Connectionists: 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 ac1753 at coventry.ac.uk Wed Nov 21 06:25:00 2018 From: ac1753 at coventry.ac.uk (Ariel Ruiz-Garcia) Date: Wed, 21 Nov 2018 11:25:00 +0000 Subject: Connectionists: CFP: IJCNN 2019 special session on Deep and Generative Adversarial Learning Message-ID: CFP: Special Session on Deep and Generative Adversarial Learning 2019 International Joint Conference on Neural Networks (IJCNN) July 14-19 2019, Budapest, Hungary https://www.ijcnn.org/ Important Dates: Paper submission: 15 December 2018 Notification of acceptance: 30 January 2019 Aims and Scope: Deep Generative Adversarial Networks (GANs) are one of the most recent breakthroughs in deep learning (DL) and neural networks. One of the main advantages of GANs over other deep learning systems is their ability to learn from unlabelled data, as well as their ability to generate new data from random distributions. However, generating realistic data using GANs remains a challenge, particularly when specific features are required; e.g., constraining the latent aggregate distribution space does not guarantee that the generator will produce an image with a specific attribute. New advancements in deep representation learning (RL) can help improve the learning process in GANs. For instance, RL can help address issues such as dataset bias and network co-adaptation, and help identify a set of features that are ideal for a given task. Practical applications of GANs include: realistic data synthesis, generation of speech or images from text, image denoising and completion, artificial environment generation for reinforcement learning problems, conversion of satellite images into maps, class imbalance learning, or other unsupervised and supervised learning tasks. Nonetheless, GANs have yet to overcome several challenges. They often fail to converge and are very sensitive to parameter and hyperparameter initialization. Simultaneous learning of a generator and a discriminator network also makes the learning process more difficult and often results in overfitting or vanishing gradients in the generator network. Moreover, the generator model is prone to mode collapse which results in failure to generate data with several variations. New theoretical methods in deep learning and GANs are therefore required to improve the learning process and generalization performance of GANs. Topics of interest for this special session include, but are not limited to: * Generative adversarial learning methods and theory; * Representation learning methods and theory; * Adversarial representation learning for domain adaptation; * Interpretable representation adversarial learning; * Adversarial feature learning; * RL and GANs for data augmentation and class imbalance; * New GAN models and learning criteria; * RL and GANs in classification; * Image completion and super-resolution; * RL and GANs in Deep Reinforcement Learning; * Deep learning and GANs for image and video synthesis; * Deep Learning and GANs for speech and audio synthesis; * RL and GANs and for In-painting and Sketch to image; * Representation and Adversarial Learning in Machine Translation; * RL and GANs in other application domains. Submission: For paper guidelines please visit https://www.ijcnn.org/paper-submission-guidelines and for submissions please select Special Session S06. Deep and Generative Adversarial Learning as the main research topic at https://ieee-cis.org/conferences/ijcnn2019/upload.php Organizers: Ariel Ruiz-Garcia (ariel.ruiz-garcia at coventry.ac.uk) Vasile Palade (vasile.palade at coventry.ac.uk) Clive Cheong Took (clive.cheongtook at rhul.ac.uk) University of the Year for Student Experience The Times and Sunday Times Good University Guide 2019 2nd for Teaching Excellence Times Higher Education UK (TEF) metrics ranking 2017 - Gold winner 5th UK Student City QS Best Student Cities Index 2018 13th in Guardian University Guide 2019 of 121 UK institutions ranked NOTICE This message and any files transmitted with it is intended for the addressee only and may contain information that is confidential or privileged. Unauthorised use is strictly prohibited. If you are not the addressee, you should not read, copy, disclose or otherwise use this message, except for the purpose of delivery to the addressee. Any views or opinions expressed within this e-mail are those of the author and do not necessarily represent those of Coventry University. -------------- next part -------------- An HTML attachment was scrubbed... URL: From felipe at cos.ufrj.br Wed Nov 21 08:36:54 2018 From: felipe at cos.ufrj.br (Felipe Maia Galvao Franca) Date: Wed, 21 Nov 2018 11:36:54 -0200 Subject: Connectionists: MPP 2019 -- 8th Workshop on Parallel Programming Models - Special Edition on IoT and Machine Learning Message-ID: MPP 2019 -- 8th Workshop on Parallel Programming Models - Special Edition on IoT and Machine Learning http://mpp-conf.org In Conjunction with IPDPS 2019, Rio de Janeiro, Brazil http://www.ipdps.org Call for Papers Recent trends in artificial neural networks, such as deep neural networks, and the Internet-of-Things ? IoT, indicate that an increasing number of artificial intelligence -based applications will be running on smartphones, sensors and other IoT devices collecting and processing large amounts of data. Most of those devices have limited processing power and often rely on cloud services for compute-intensive tasks. However, real-time applications may not tolerate the latency of offloading tasks to a cloud server. Another important aspect to consider, especially in applications that run on big systems and manipulate big data sets, is the trade-off between moving data to a remote processing element to increase parallelism and computing things locally to reduce communication and energy costs while keeping performance levels. Edge/Fog computing proposes bringing computation closer to where data is sitting, by adding computational capabilities to network devices and adding edge gateways/servers, possibly in multiple layers with different latencies and computing performance. Moreover, such systems are expected to be heterogeneous, including multi-core processors, GPUs, FPGAs, and even processors that are customized for certain applications. In this scenario, writing parallel applications is a non-trivial task, but also mandatory if one wants to explore the potential of the aforementioned modern computing platforms, imposing new challenges to the scientific community: the creation of models and alternatives to ease parallelism exploitation by the average programmer, considering the peculiarities of the different computation devices. Moreover, the proposed solutions should tackle problems such as application deployment, resilience and scheduling/offloading of tasks, considering latency, bandwidth, response time and computing power. In these complex environments, Machine Learning is becoming an important trend for the autonomic operation. MPP aims at bringing together researchers interested in presenting contributions to the evolution of existing models or in proposing novel ones, considering the trends on IoT and Machine Learning. MPP 2019 will be held in conjunction with The 33rd IEEE International Parallel and Distributed Processing Symposium (IPDPS 2019), in Rio de Janeiro, Brazil on May 20-24, 2019. Submission Guidelines MPP invites authors to submit unpublished full and short papers on the subjects. Submissions must be in English, 8 pages maximum for full papers and 4 pages for short papers, following the IEEE formatting guidelines. Page limits include references. List of Topics Topics of interest include (with special emphasis on IoT, Fog, Edge Computing, and Machine Learning) : - Novel execution models and languages for parallelism; - Novel parallel programming techniques and architectures; - Heterogeneous programming models; - Synchronization mechanisms; - Storage techniques; - Load-balancing and scheduling mechanisms; - Error detection/recovery; - Theoretical analysis of systems; - Smart network devices; - Software-defined networks; - Integration of IoT, Fog, Edge and Cloud Computing; - Neural Networks inference and training on IoT, Fog, Edge and cloud environments; - Performance analysis; and - Applications. Important Dates - ?Paper submission deadline: February 4, 2019 - Author notification: February 25, 2019 - Camera-ready: ?????March 15, 2019 Publication The proceedings of MPP will be submitted to IEEE Xplore and Computer Society Digital Library. MPP is currently seeking for a journal to publish selected papers after the conference. Venue MPP 2018 will be co-held with IPDPS at Hilton Rio de Janeiro Copacabana, Rio de Janeiro, Brazil. More information will be available at the Conference website http://www.ipdps.org/ . Contact All questions about submissions should be emailed to mpp2019 at googlegroups.com . General co-chairs - Leandro A. J. Marzulo - Google Research, USA - Felipe M. G. Fran?a - Universidade Federal do Rio de Janeiro (UFRJ), Brazil Program co-chairs - Cristiana Bentes - Universidade do Estado do Rio de Janeiro (UERJ), Brazil - Gabriele Mencagli - University of Pisa, Italy Steering co-chairs - Andrew Putnam - Microsoft Research, USA - Mauricio Pilla - Universidade Federal de Pelotas, Brazil Steering Committee - Daniel Mosse - University of Pittsburgh, USA - Edson Borin - Universidade Estadual de Campinas (UNICAMP), Brazil - L?cia Drummond - Universidade Federal Fluminense (UFF), Brazil - Mario Dantas - Universidade Federal de Santa Catarina (UFSC), Brazil - Nader Bagherzadeh - University of California Irvine, USA - Nelson Amaral - University of Alberta, USA - Rodolfo Azevedo - UNICAMP, Brazil - Sandip Kundu - University of Massachusetts Amherst, USA - Vladimir Alves - NGD Systems, USA Program Committee - Albert Y. Zomaya - University of Sydney, Australia - Alet?ia Ara?jo - Universidade de Bras?lia, Brazil - Alexandre da Costa Sena - Universidade do Estado do Rio de Janeiro (UERJ), Brazil - Alexandre Solon Nery - Universidade de Bras?lia (UnB), Brazil - Alexandre Sztajnberg - Universidade do Estado do Rio de Janeiro (UERJ), Brazil - Arthur Francisco Lorenzon - Universidade Federal do Pampa (UNIPAMPA), Brazil - Carla Osthoff - Laborat?rio Nacional de Computa??o Cient?fica (LNCC), Brazil - Claudia Di Napoli - CNR, Italy - Claude Tadonki - Mines - ParisTech, France - Cristina Boeres - Universidade Federal Fluminense (UFF), Brazil - Dalvan Griebler - Pontif?cia Universidade Cat?lica do Rio Grande do Sul, Brazil - Diego Dutra - Universidade Federal do Rio de Janeiro (UFRJ), Brazil - Edward Moreno - Universidade Federal do Sergipe, Brazil - Elias Mizan - Wave Computing, USA - Flavia Delicato - Universidade Federal do Rio de Janeiro (UFRJ), Brazil - Gabriel Paillard - Universidade Federal do Cear? (UFC), Brazil - Igor Machado Coelho - Universidade do Estado do Rio de Janeiro (UERJ), Brazil - Kazutomo Yoshii - Argonne National Laboratory, USA - Krommydas Konstantinos - Intel, USA - Luciana Arantes - Universit? Paris 6 Pierre et Marie Curie, France - Maria Clicia Stelling de Castro - Universidade do Estado do Rio de Janeiro (UERJ), Brazil - Mauricio Breternitz - Instituto Universitario de Lisboa, Portugal - Michael Frank - MagiCore Inc., USA - Rajesh Sankaran - Argonne National Laboratory, USA - Rafael dos Santos - ARM, United Kingdom - Rekai Gonzalez Alberquilla - ARM, UK - Roberto Souto - Laborat?rio Nacional de Computa??o Cient?fica (LNCC), Brazil - Silvio Stanzani - Universidade Estadual Paulista (UNESP), Brazil - Tiago A. O. Alves ? Universidade do Estado do Rio de Janeiro (UERJ), Brazil - Walid Najjar - University of California Riverside, USA - Wei Li - University of Sydney, Australia - Zehra Sura - IBM, USA -- ??????????????????????????????? Felipe M. G. Fran?a, PhD Professor of Computer Science and Engineering Systems Engineering and Computer Science Program, COPPE Universidade Federal do Rio de Janeiro P.O. Box 68511, 21941-972, Rio de Janeiro, RJ, Brazil felipe at ieee.org felipe at cos.ufrj.br ??????????????????????????????? -------------- next part -------------- An HTML attachment was scrubbed... URL: From btuller at nsf.gov Wed Nov 21 12:26:37 2018 From: btuller at nsf.gov (Tuller, Betty K.) Date: Wed, 21 Nov 2018 17:26:37 +0000 Subject: Connectionists: Cognitive Neuroscience Program Director Opening at NSF Message-ID: <35E40C3B-DA4F-4F21-AD30-013F47E05643@contoso.com> APOLOGIES FOR MULTIPLE POSTINGS NSF is advertising for a Cognitive Neuroscience Program Director. Details about the Cognitive Neuroscience position is on usajobs: https://www.usajobs.gov/GetJob/ViewDetails/517138700. The position is as a ?rotator? ? you spend 2 or more years at NSF, on loan from your university (about half of the NSF Program Directors are rotators). More information on being a Program Director can be found at https://www.nsf.gov/careers/rotator/. If you are interested, please apply! Working at NSF is really interesting experience and a chance to help your discipline. Feel free to pass this on, if someone you know might be interested. For more information, contact Kurt Thoroughman (kthoroug at nsf.gov). Betty Tuller, Ph.D. Director, Program in Perception, Action, and Cognition National Science Foundation 2415 Eisenhower Avenue Alexandria, VA 22314 Tel: 703.292.7238 Fax: 703.292.9068 The PAC program has additional requirements for submission: http://www.nsf.gov/funding/pgm_summ.jsp?pims_id=5686. A new Proposal and Award Policies and Procedures Guide is now available at https://www.nsf.gov/publications/pub_summ.jsp?ods_key=nsf18001&org=NSF -------------- next part -------------- An HTML attachment was scrubbed... URL: From caspar.schwiedrzik at googlemail.com Thu Nov 22 04:26:08 2018 From: caspar.schwiedrzik at googlemail.com (Caspar M. Schwiedrzik) Date: Thu, 22 Nov 2018 10:26:08 +0100 Subject: Connectionists: =?utf-8?q?Deadline_approaching=3A_Neuroscience_da?= =?utf-8?q?ta_analyst_=28f/m=29_opening_at_ENI_G=C3=B6ttingen=2C_Ge?= =?utf-8?q?rmany_=28new_opening=29?= In-Reply-To: References: Message-ID: The European Neuroscience Institute G?ttingen (Germany) is seeking a *Neuroscience data analyst (f/m) * initially limited until 31.12.2019 with extension options, full-time | salary according to TV-L The European Neuroscience Institute is looking to fill the position of a data analyst (full time). We are looking for a data analyst with interest and experience in systems neuroscience. Research at the European Neuroscience Institute ranges from molecular biology to human psychophysics and involves a range of model organisms (from drosophila to non-human primates), techniques and approaches (electrophysiology, two-photon imaging, fMRI, EEG, behavior). The data analyst will work closely with all of the various research groups at the European Neuroscience Institute, supporting research efforts, e.g., through modelling and statistical analyses of high-dimensional data, image processing, and programming/development of experiments. S/he will have the opportunity to develop and publish, e.g., analytical tools that arise from this work. - The applicant should possess a university degree (minimally M. Sc. or equivalent) in a relevant field, e.g., statistics, biostatistics, informatics, or similar. Prior experience in the field of systems neuroscience is highly desired. - The applicant should have experience in a research setting utilizing quantitative methods and statistics. The applicant shall demonstrate strong analytical skills and knowledge of novel and emerging analysis techniques is highly desired. Future/forward thinking in the area of big data analytics/informatics and applying them to contribute to the research groups? scientific process is expected. - The applicant should be skilled in the analysis of multivariate datasets to reveal patterns and build models; conduct exploratory data analysis, and communicate with team lead/team members; identify improvements for existing data management and recommend requirements for new systems. - Contribute to replicability by making suggestions for existing data management and recommend requirements for new systems and identify potential data integrity issues. We are committed to open data/open science and appreciate interest and expertise in this area. - Utilize programming languages such as Python, Matlab and/or C++. - Good command of English is mandatory. The University Medical Center G?ttingen takes flexible account of the individual design of working hours at the workplace. It is interested in implementing the wishes of its employees as far as possible. If you are interested in this job and have specific questions about working hours, please contact us. Women are especially encouraged to apply. Applicants with disabilities and equal qualifications will be given preferential treatment. We look forward to receiving your application by * November 30th, 2018* University Medical Center G?ttingen European Neuroscience Institute G?ttingen Dr. Caspar Schwiedrzik Group Leader Grisebachstr. 5 37077 G?ttingen Tel.: 0551/39-61371 Fax: 0551/39-61399 E-Mail: c.schwiedrzik at eni-g.de <+c.schwiedrzik at eni-g.de> Web: http://www.eni-g.de/ Please send your application only via e-mail as a PDF-file. also see: http://www.med.uni-goettingen.de/de/content/service/stellenanzeigen.php?id=2250 -------------- next part -------------- An HTML attachment was scrubbed... URL: From gmichel at ini.phys.ethz.ch Thu Nov 22 11:04:08 2018 From: gmichel at ini.phys.ethz.ch (Gabriela Michel) Date: Thu, 22 Nov 2018 17:04:08 +0100 Subject: Connectionists: [CapoCaccia Neuromorphic Engineering Workshop 2019] Save the date Message-ID: Dear fellow Neuromorphs, We are happy to announce that the 2019 CapoCaccia Cognitive Neuromorphic Engineering Workshop will take place from April 23rd to May 4th at the usual Hotel Dei Pini, in Alghero, Italy. CapoCaccia is a unique workshop that brings together experts in neuroscience, neuromorphic engineering, cognitive science, and robotics. The workshop is designed to foster discussions amongst participants to leverage the potential of the different disciplines. Save the date to be part of it! Soon you will be able to find all information about the workshop schedule, the invited speakers and topics at the workshop web-site: http://capocaccia.cc We will continuously update the website with more information, stay tuned. The registration will open on December 1st and remain open till March 10th. Looking forward to seeing you there! The workshop coordinators (Rodney Douglas and Giacomo Indiveri) and the program committee (Gabriela Michel, Chiara Bartolozzi, Emre Neftci, Florian Engert, Valerio Mante and Moritz Milde). -------------- next part -------------- An HTML attachment was scrubbed... URL: From terry at salk.edu Thu Nov 22 13:02:28 2018 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 22 Nov 2018 10:02:28 -0800 Subject: Connectionists: NEURAL COMPUTATION - December 1, 2018 In-Reply-To: Message-ID: Neural Computation - Volume 30, Number 12 - December 1, 2018 Available online for download now: http://www.mitpressjournals.org/toc/neco/30/12 ----- Article Dense Associative Memory Is Robust to Adversarial Inputs Dmitry Krotov and John Hopfield Letters Unconscious Biases in Neural Populations Coding Multiple Stimuli Sander W. Keemink, Dharmesh V. Tailor, and Mark C. W. van Rossum Nonlinear Modeling of Neural Interaction for Spike Prediction Using the Staged Point-Process Model Cunle Qian, Xuyun Sun, Shaomin Zhang, Dong Xing, Hongbao Li, Xiaoxiang Zheng, Gang Pan, and Yiwen Wang Omitted Variable Bias in GLMs of Neural Spiking Activity Ian H. Stevenson Tensor Representation of Topographically Organized Semantic Spaces Andres Pomi, Eduardo Mizraji, and Juan Lin Multi-Instance Dimensionality Reduction via Sparsity and Orthogonality Hong Zhu, Li-Zhi Liao, and Michael K. Ng Use of a Deep Belief Network for Small High-Level Abstraction Data Sets Using Artificial Intelligence with Rule Extraction Yoichi Hayashi Limitations of Proposed Signatures of Bayesian Confidence William T. Adler and Wei Ji Ma Bayesian Modeling of Motion Perception Using Dynamical Stochastic Textures Jonathan Vacher, Andrew Isaac Meso, Laurent U. Perrinet, and Gabriel Peyre ------------ ON-LINE -- http://www.mitpressjournals.org/neuralcomp MIT Press Journals, One Rogers Street, Cambridge, MA 02142-1209 Tel: (617) 253-2889 FAX: (617) 577-1545 journals-cs at mit.edu ------------ From marcel.van.gerven at gmail.com Thu Nov 22 15:56:23 2018 From: marcel.van.gerven at gmail.com (Marcel van Gerven) Date: Thu, 22 Nov 2018 21:56:23 +0100 Subject: Connectionists: Vacancies in AI at the Donders Institute Message-ID: The Donders Centre for Cognition (DCC), embedded in the Donders Institute for Brain, Cognition and Behaviour, and the School of Artificial Intelligence at Radboud University are looking for two Assistant/Associate Professors of Artificial Intelligence. With these new positions, the goal is to advance fundamental research in brain-inspired computing and machine learning, broadly relevant to the themes of the Donders Institute, as well as to develop new human-centered intelligent technology to improve the well-being of people in their environment. We seek excellent candidates who conduct theoretical research on core AI techniques and/or apply such techniques in particular application domains that have a potential for benefiting society. As an Assistant or Associate Professor you will be expected to: develop and conduct AI teaching at undergraduate and post-graduate levels; perform top-quality research in Artificial Intelligence and establish an externally funded research programme; interact and collaborate with other researchers and specialists in academia and/or industry; be an inspiring member of our staff with excellent communication skills. For more information on the application procedure, please consult the following webpage: https://www.ru.nl/werken/details/details_vacature_0/?recid=601780 -------------- next part -------------- An HTML attachment was scrubbed... URL: From blextar at gmail.com Fri Nov 23 01:13:46 2018 From: blextar at gmail.com (Luca Rossi) Date: Fri, 23 Nov 2018 14:13:46 +0800 Subject: Connectionists: PhD/RA/Postdoc positions in CS at SUSTech Message-ID: I'm looking for highly motivated PhD students, Research Assistants, and Postdoctoral Researchers to join my lab in the Southern University of Science and Technology, Shenzhen, China. Established in 2011, SUSTech ( http://www.sustc.edu.cn/) is one of the fastest growing institutions in the world and it?s based in what has been dubbed "the Silicon Valley of China". Depending on the position, applicants should have demonstrable experience of working in one or more of the following areas: machine learning, particularly structural pattern recognition and/or deep learning for structured data, data/network science, quantum information. For prospective PhD students, a strong mathematical background and a solid knowledge of machine learning are required. For further details and to learn about the available funding opportunities interested applicants should contact Dr. Luca Rossi (rossil_at_sustc.edu.cn) or Ms. Xiaolin Yang (yangxl3_at_mail.sustc.edu.cn). Review of applications will begin immediately and continue until the positions are filled. -- Luca Rossi Assistant Professor School of Computer Science and Engineering Southern University of Science and Technology - SUSTech Web: http://www.cs.aston.ac.uk/~rossil/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From poma at mmmi.sdu.dk Fri Nov 23 12:05:03 2018 From: poma at mmmi.sdu.dk (Poramate Manoonpong) Date: Fri, 23 Nov 2018 17:05:03 +0000 Subject: Connectionists: [jobs] Fully funded MS/PhD student positions in Data Science, Computer Vision, Bio-inspired Robotics, and Neural Engineering at IST, VISTEC, Thailand In-Reply-To: <84b5c80b890b49efa21441c4c69f3540@mmmi.sdu.dk> References: <84b5c80b890b49efa21441c4c69f3540@mmmi.sdu.dk> Message-ID: <9fe6bb25c25643009e9ff376d28df87c@mmmi.sdu.dk> Dear Colleagues, The School of Information Science and Technology (IST) at Vidyasirimedhi Institute of Science and Technology (VISTEC), Thailand, welcomes all applicants for our international Master's and Doctoral degree program. Our school offers a competitive, English language, interdisciplinary, world-class PhD training and research program in Information Science and Technology. We have up to 20 fully funded Master and PhD student positions. Our program includes 2-years MS, 5-years MS+PhD, and 3-years PhD options. The students will be formally affiliated with the Master/PhD program at IST, VISTEC, Thailand. They will have the opportunity to develop new algorithms and research ideas and perform experiments on real hardware, e.g., High performance computing, Big data, Computer vision, Advanced robotic systems, Exoskeleton, and Brain computer interface systems. Our basic research under the IST umbrella focuses on main areas: Data Science, Cloud/HPC, Computer Vision, IOT, Bio-inspired Robotics, and Neural Engineering. Data Science and Engineering (Large-Scale Analytics, Data Engineering, Data Mining, Artificial Intelligence and Machine Learning): We address various scalability issues in machine learning, data mining, database query processing. We are especially interested in developing solutions for machine learning problems with an extremely large number of classes and a scalable system for managing and storing various forms of high-dimensional data. Our application domains include (but not limited to) natural language processing, time series data management, geospatial data mining, business intelligence, IoT data analytics, and health data analytics. Bio-inspired robotics: We address how to develop brain-like mechanisms for adaptive motor control and autonomous learning of embodied multi-sensorimotor robotic systems (i.e., bio-inspired robots, exoskeleton). We also transfer the developed mechanisms (BRAIN technology) to application areas like human-machine interaction, brain-machine interface, and rehabilitation (see https://brain.vistec.ac.th/ for more details). Neural Engineering: We address an investigation of closed-loop EEG-based Brain Computer Interface (BCI) helps bridge the gap in communication between man and machine. Understanding patterns of brain activity from basic neuroscience research will help engineering to optimize the BCI system that could be applied in the real-world environment. Advanced signal processing techniques and pattern recognition methods such as machine learning, artificial neural network, and deep learning can improve the efficiency of BCI by increasing information transfer rate and accuracy. Ultimately, research based on BCI could lead to the development of novel tools used in both clinical and healthy populations (see https://brain.vistec.ac.th/ for more details). Financial Support: This studentship includes 1) fee bursary to cover the tuition fee rate 2) a maintenance allowance during the study, 3) grant of 1 Million Bath scholarship for international research experience. Person Specification: The successful applicant from any nationality will have a strong undergraduate (first class or upper second class) and/or Master's degree in 1) Science (Physics, Mathematics, Computer and related fields) 2)Engineering (Computer, Mechanical, Electrical, Robotics, and related fields) 3) Applied Science (Information Technology, ICT, Machine Learning, and related fields) Applicants with excellent programming and analytical/mathematical skills as well as expertise and research interests lying at the intersection of Data science, Bio-inspired Robotics, and Neural Engineering are particularly welcome to apply. Applicants from non-English speaking countries will need to satisfy English language entry requirements. Application Documents: 1. CV 2. Official Transcripts 3. Statement of Purpose/ Statement of research interest Optional: 4. Letters of recommendation 5. English test score (TOEFL, IELTS, or other tests) 6. Publications, awards & honors 7. Portfolio and other relevant documents Applications should be submitted online by December 31st, 2018. https://www.vistec.ac.th/admission/form.php https://www.vistec.ac.th/admission/ For further information or questions please contact Assoc. Prof. Dr. Sarana Nutanong E-mail: snutanon at vistec.ac.th Vidyasirimedhi Institute of Science and Technology, Wangchan Valley 555 Moo1 Payupnai, Wangchan, Rayong 21210 Thailand Website of VISTEC: https://www.vistec.ac.th -------------- next part -------------- An HTML attachment was scrubbed... URL: From george at cs.ucy.ac.cy Fri Nov 23 07:37:52 2018 From: george at cs.ucy.ac.cy (George Angelos Papadopoulos) Date: Fri, 23 Nov 2018 14:37:52 +0200 Subject: Connectionists: The 27th ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2019): Third Call for Papers 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: <0D77B354-7638-44A6-AECC-6F764DC0B938@cs.ucy.ac.cy> *** THIRD 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 For details, see the conference website ( https://www.um.org/umap2019/ ). ? Track 1 - Personalized Recommender Systems ? Track 2 - Adaptive Hypermedia and the Semantic Web ? Track 3 - Intelligent User Interfaces ? Track 4 - Personalized Social Web ? Track 5 - Technology-Enhanced Adaptive Learning ? Track 6 - Privacy and Fairness ? Track 7 - Personalized Music Access ? Track 8 - Personalized Health SUBMISSION AND REVIEW PROCESS Papers have to be submitted through EasyChair: https://easychair.org/conferences/?conf=acmumap2019 Long (8 pages + references) and Short (4 pages + references) papers in ACM style, peer reviewed, original, and principled research papers addressing both the theory and practice of UMAP and papers showcasing innovative use of UMAP and exploring the benefits and challenges of applying UMAP technology in real-life applications and contexts are welcome. Long papers should present original reports of substantive new research techniques, findings, and applications of UMAP. They should place the work within the field and clearly indicate innovative aspects. Research procedures and technical methods should be presented in sufficient detail to ensure scrutiny and reproducibility. Results should be clearly communicated and implications of the contributions/findings for UMAP and beyond should be explicitly discussed. Short papers should present original and highly promising research or applications. Merit will be assessed in terms of originality and importance rather than maturity, extensive technical validation, and user studies. Papers must be formatted using the ACM SIG Standard (SIGCONF) proceedings template: https://www.acm.org/publications/proceedings-template . All accepted papers will be published by ACM and will be available via the ACM Digital Library. At least one author of each accepted paper must register for the conference and present the paper there. IMPORTANT DATES ? Abstracts: January 25, 2019 (mandatory) ? Full paper: February 1, 2019 ? Notification: March 11, 2019 ? Camera-ready: April 3, 2019 Note: The submission time is 11:59pm AoE time (Anywhere on Earth). GENERAL CHAIRS ? George A. Papadopoulos, University of Cyprus, Cyprus ? George Samaras, University of Cyprus, Cyprus ? Stephan Weibelzahl, PFH Private University of Applied Sciences, G?ttingen, Germany RELATED EVENTS Separate calls will be later sent for Workshops and Tutorials, Doctoral Consortium, 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 frank.ritter at psu.edu Sat Nov 24 15:29:54 2018 From: frank.ritter at psu.edu (Frank Ritter) Date: Sat, 24 Nov 2018 16:29:54 -0400 Subject: Connectionists: [plz fwd]: ICCM 2019: announcement, resources, jobs Message-ID: This is driven by ICCM announcement of place and time (#1) and to pass numerous job opportunities. Happy thanksgiving to those in the US. cheers, Frank **************************************************************** Table of Contents **************************************************************** CONFERENCES 1. ICCM 19, Montreal, CAN, estimated Jul 20-23 2. IJCNN 19 in Budapest, 14 -19 Jul 19 https://www.ijcnn.org/ 3. CogSci 2019 RESOURCES 4. Interactive Task Learning Humans, Robots, and Agents Acquiring New Tasks through Natural Interactions https://mitpress.mit.edu/books/interactive-task-learning 5. Graduate funding for US citizens, future problem for ONR and DoD 6. A new journal of the Society for Mathematical Psychology https://www.editorialmanager.com/cobb/default.aspx 7. ARL STRONG Program, due 21 Dec 18 https://www.fbo.gov/index?s=opportunity&mode=form&id=a33549b6039752990aaf6f50777f1379&tab=core&_cview=0 8. Nengo Summer School https://www.nengo.ai/summerschool 9. Travel fund in memory of Sayan Gul https://www.gofundme.com/travel-fund-in-honor-of-sayan-gul 10. Research on enhancing video game / eSports performance? JOBS 11. Job teaching in IST at Penn State https://psu.jobs/job/82796 12. Need For Program officers 13. Faculty Hire. Assistant Prof Indiana in Machine and Human Learning 14. Cognitive Scientist, Open Rank, U of Rochester http://www.sas.rochester.edu/bcs/jobs/faculty.html 15. Assistant Professor, CS (Computational Analysis of Behavior) Saskatchewan https://usask.csod.com/ats/careersite/JobDetails.aspx?id=2953&site=14 16. Associate or Full Professor of Usability Studies, U of Arizona https://uacareers.com/postings/31719 Deadline: Oct 1 17. (tenure-track) Assistant Professor position at Rutgers U https://jobs.rutgers.edu/postings/74628 18. 6 faculty positions in data analytics, Industrial and System Engineering, U. of FL http://www.ise.ufl.edu/about/careers/ 19. UF-ISE Human Systems Tenure Track Positions http://explore.jobs.ufl.edu/cw/en-us/job/505562/assistantassociatefull-professor 20. Tenure Track Search - Cognitive Modeling, RIT https://sjobs.brassring.com/TGnewUI/Search/Home/Home?partnerid=25483&siteid=5291#home 21. Positions at RIT 22. Tenure track position in computational language science (U of Florida) (Edith Kaan) Application Deadline: 18 Nov, 18 23. Sloan Scholars job board https://sloan-scholars.ssrc.org/resources/index/ 24. Professor in Data Science, Geovisualization and Design http://seas.umich.edu/node/2132 25. Cognitive Science Lecturer, U of Michigan due 30 nov 18 26. Post-doc in Gronigen, due 'soon' 27. ISO two postdocs to work on models of learning from instruction AFRL, Dayton, OH 28. 3 years independent research fellowship in Computational Neuroscience https://www.nottingham.ac.uk/jobs/currentvacancies/ref/SCI219418 29. PhD / Postdoc position in the CRC EASE, U of Bremen 30. Penn State Earth and Mineral Sciences Looking for Post-Doc https://psu.jobs/job/79865 **************************************************************** 1. ICCM 19, Montreal, CAN, estimated Jul 20-23 ICCM 19 will be held with Math Psych, which will be held near the Cognitive Science Conference in space and time (which is the next announcement). Details as they become available. Terry.Stewart at gmail.com will be acting as the chair or co-chair. Submissions open 30 Nov **************************************************************** 2. IJCNN 19 in Budapest, 14 -19 Jul 19 https://www.ijcnn.org/ IJCNN19 Budapest - Plenary Speakers International Joint Conference on Neural Networks - IJCNN 19 On behalf of the Organizing Committee, it is our great pleasure to invite you to the International Joint Conference on Neural Networks (IJCNN 19). The conference is organized by the https://www.inns.org/ International Neural Network Society (INNS) in cooperation with the https://cis.ieee.org Computational Intelligence Society (IEEE-CIS), and is the premier international meeting for researchers and other professionals in neural networks and related areas. It will feature invited plenary talks by world-renowned speakers in the areas of neural network theory and applications, computational neuroscience, robotics, and distributed intelligence. Important dates: Paper submissions due: 15 Dec 18 Paper Acceptance Notifications: 30 Jan 19 Conference Dates: 14-19 JUL 19 Call for Papers: https://www.ijcnn.org/callforpapers Paper Submissions guidelines https://www.ijcnn.org/paper-submission-guidelines site includes a link for uploading papers, plus brief instructions for paper formatting and submission. More detail is available in the Authors' Guide for young researchers and those unfamiliar with the IEEE Paper submission system and IJCNN conference requirements. Lists of the approved [Tutorials, Competitions, Workshops, Panels, Special Sessions] will be posted soon. Confirmed Plenary Speakers: Lee Giles is the David Reese Professor at the College of Information Sciences and Technology at the Pennsylvania State U, U Park, PA. He is also graduate college Professor of Computer Science and Engineering, courtesy Professor of Supply Chain and Information Systems, and Director of the Intelligent Systems Research Laboratory. Isabelle Guyon obtained a engineering diploma from the Ecole Superieure de Physique et Chimie Industrielles de Paris, Paris, in 85, and a PhD degree in Physical Sciences from the Universite Pierre et Marie Curie, Paris, in 1988. She joined AT&T Bell Labs Research , Homdel, NJ, in Jan 89. In Jan 96, she left AT&T to try her luck with a startup company, CyberGold, which she left in Apr of the same year to start her own consulting company, ClopiNet. Recently, she also served as Vice President of a bioinformatics startup called BIOwulf. Nicola Kasabov is the Director of the Knowledge Engineering and Discovery Research Centre (KEDRI) and Personal Chair of Knowledge Engineering in the School of Engineering, Computing and Mathematical Sciences at AUT. His main interests are in the areas of: computational intelligence, neuro-computing, bioinformatics, neuroinformatics, speech and image processing, novel methods for data mining and knowledge discovery. Vera Kurkova received PhD in mathematics from the Charles U, Prague, and DrSc. (Prof.) in theoretical computer science from the Czech Academy of Sciences. She is a senior scientist in the Department of Machine Learning, Institute of CS, Czech Academy of Sciences. In 02-09 she was the Head of the Department of Theoretical CS. Adam Miklosi is a Hungarian ethologist, expert on dog cognition and behavior. He is a full professor and the head of the Ethology Department at the E?tv?s Lor?nd U in Budapest, Hungary. In 16 he was elected as a corresponding member of the Hungarian Academy of Sciences. He is the co-founder and leader of the Family Dog Project, which aims to study human-dog interaction from an ethological perspective. In 14 he published the 2nd edition of an academic volume entitled Dog Behaviour, Evolution, and Cognition by Oxford U Press. Errki Oja is a Finnish computer scientist and Aalto Distinguished Professor in the Department of Information and Computer Science at Aalto U School of Science. He is recognized for developing Oja's rule, which is a model of how neurons in the brain or in artificial neural networks learn over time. He is a Fellow of the International Association for Pattern Recognition and the IEEE, and a member of the Finnish Academy of Sciences. He served as chairman of the European Neural Network Society between 2000 and 05, and as the chairman of the Academy of Finland?s Research Council for Natural Sciences and Engineering between 07 and 12. Danil Prokhorov received his Diploma in Robotics with Honors from the St. Petersburg State U of Aerospace Instrumentation, Russia, in 92. He then worked in the St. Petersburg Institute for Informatics and Automation. After receiving PhD in 97, he joined the staff of Ford Scientific Research Laboratory, Dearborn, Michigan. While at Ford he was engaged in application-driven studies of intelligent technologies, developing new and improving existing machine learning/computational intelligence algorithms and applying them to problems in system modeling, control, diagnostics and optimization. Since 11 he has been in charge of future mobility research department of Toyota NA. Wolf Singer studied Medicine in Munich and Paris, obtained his MD from the Ludwig Maximilian U in Munich, and his PhD from the Technical U in Munich. He is Director em. at the Max Planck Institute for Brain Research in Frankfurt, Founding Director both of the Frankfurt Institute for Advanced Studies (FIAS) and of the Ernst Str?ngmann Institute for Neuroscience (ESI) and Director of the Ernst Str?ngmann Forum. Ichiro Tsuda holds the position of Professor at Chubu U Academy of Emerging Sciences, Professor Emeritus of Hokkaido U, and Visiting Professor at Osaka U, Tamagawa U and at many other universities. He has been Associate Member of Science Council of Japan since 14. He received a degree of Doctor of Science (DSc) from Kyoto U in 82. He has published widely in the field of chaotic dynamical systems and complex systems, and also in the field of cognitive neurodynamics. Call for Sponsor and Exhibits: IJCNN19 is a great opportunity to promote your brand and to show off your neural network success stories as well as leading edge products to a world wide audience of people and organization in neural networks research and development. Please contact : Bill at BillHowell.ca Bill Howell, Sponsors & Exhibits Chair, Alberta, Canada Topics and Areas include, but not limited to Neural Networks Theory Deep Learning Deep Neuro Fuzzy Systems Computational Neuroscience Cognitive Models Brain-Machine Interfaces Embodied Robotics Evolving Neural Networks Neurodynamics Neuroinformatics Neuroengineering Connectomics Neural Networks and Big Data Pattern Recognition Machine Learning Collective Intelligence Hybrid Systems Self-aware Systems Data Mining Sensor Networks Hardware, Memristors Agent-based Systems Machine Perception Bioinformatics Artificial Life Neural Network Applications Social Media Philosophical Issues IJCNN 19 General Co-Chairs : https://www.brookes.ac.uk/templates/pages/staff.aspx?uid=p0085348 Chrisina Jayne INNS Director Head of Engineering-Computing-Mathematics Oxford Brooks U, UK Zolt?n Somogyv?ri somogyvari.zf at gmail.com Wigner Institute Hungarian Academy of Sciences Budapest, Hungary P?ter ?rdi perdi at kzoo.edu Honorary General Co-Chair INNS VP Membership Kalamazoo College Michigan, USA Young researchers, and experienced researchers who are not familiar with the IJCNN processes and IEEE [paper submissions, formatting, copyrights, plagiarism checks], may find the http://www.billhowell.ca/Neural%20nets/Conference%20guides/Author%20guide%20website/Author%20guide.html Authors' Guide to be of some help. **************************************************************** 3. CogSci 2019 41st Annual Meeting of the Cognitive Science Society Creativity+Cognition+Computation Montreal, Canada 24-27 Jul 19 Plenary Speakers: Elizabeth Churchill, Google Mary Lou Maher, U of North Carolina Takeshi Okada, U of Tokyo Rumelhart Prize Presentation: Michelene Chi, Arizona State U Carvalho-Heineken Prize Presentation: Nancy Kanwisher, MIT Cognitive scientists from around the world are invited to attend CogSci 19. The Annual Meeting of the Cognitive Science Society is the world's premiere annual conference for the interdisciplinary study of cognition. Cognitive Science draws upon a broad spectrum of disciplines, topics, and methodologies; in addition, CogSci 19 will highlight the theme of creativity in plenary presentations, and we invite submissions representing diverse approaches to creativity, cognition, and computation. We solicit your submissions of high-quality research on all topics within Cognitive Science. Each submission will be competitively peer-reviewed in the categories of research papers, publication-based talks, and member abstracts. Submitted proposals for symposia, tutorials, and workshops are also requested. Submissions may report on work involving any approach to Cognitive Science, including anthropology, artificial intelligence, computational models, cognitive development, cognitive neuroscience, cognitive psychology, education, evolution of cognition, linguistics, logic, machine learning, network analysis, neural networks, philosophy, and robotics. Please see the submissions page on the conference website for submission details. The deadline for submissions is 1 Feb 19 (UTC-11 by midnight) Please note the below important deadlines: Submissions open: 30 Nov 18 Submissions closed: 1 Feb 19 Member abstract submissions closed: 1 Feb 19 Notifications of decision sent: 12 Apr 19 Accepted submissions due in final form: 10 May 19 Presenting author registration deadline: 13 May 19 Sincerely, Ashok Goel, Colleen Seifert, Christian Freksa CogSci 19 Program Committee cogsci19 at gmail.com **************************************************************** 4. Interactive Task Learning Humans, Robots, and Agents Acquiring New Tasks through Natural Interactions https://mitpress.mit.edu/books/interactive-task-learning Edited by Kevin Gluck and John Laird. Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Str?ngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming. **************************************************************** 5. Graduate funding for US citizens, future problem for ONR and DoD At the BRIMS meeting, the funding panel got asked about graduate fellowships for US citizens. I've noticed that this is a potential problem in my own department. Nearly all of our graduate students are not US citizens. This makes some work (not even near classified) difficult. The Smart program was mentioned, and found. https://dodstem.us/stem-programs/scholarships I [Ritter] also just checked, and the fellowship I had has been replaced by this program, the National Defense Science and Engineering graduate fellowship: https://ndseg.asee.org/ I am just following up with a conversation with Q and with John, that the lack of US citizens in graduate school appears to a problem for the future. And the existing programs are little known and perhaps not large enough. The use of ONR grant and project funds help, but they are hard to use to recruit new students with. cheers, Frank **************************************************************** 6. A new journal of the Society for Mathematical Psychology https://www.editorialmanager.com/cobb/default.aspx The Society for Mathematical Psychology has a new official journal, with some exciting manuscripts in the pipeline. One of the aims of the new journal is to publish a diverse range of work. To this end, we need manuscripts submitted from a wide selection of people, and in a variety of formats. This might include further developments or expansions of work previously submitted as CogSci proceedings papers, for example. If you have something appropriate, please consider sending it in. If you are unsure, send me (Scott Brown) an email. The new journal, Computational Brain & Behavior, publishes research across a wide range of topics using mathematical modelling, computer simulation, and empirical work. We emphasise scientific rigour, and the insights that quantitative modelling can provide. The journal is published by Springer and supported by a great editorial board, listed below. Manuscripts can be submitted for initial review in a very flexible range of formats and styles, through this website: https://www.editorialmanager.com/cobb/default.aspx You can find more about our journal's progress online, here: FACEBOOK https://www.facebook.com/CompBrainBeh/ TWITTER @CompBrainBeh WEB https://www.springer.com/psychology/cognitive+psychology/journal/42113 Yours, Scott Brown scott.brown at newcastle.edu.au Editor EDITORIAL BOARD John Anderson, CMU Jerome Busemeyer, Indiana U Amy Criss, Syracuse U Birte Forstmann, U of Amsterdam Charles (Randy) Gallistel, Rutgers U Isabel Gauthier, Vanderbilt U Andrew Heathcote, U of Tasmania, Hobart, Australia Mark Howard, Boston U Eileen Kowler, Rutgers U Rich Shiffrin, Indiana U Mark Steyvers, U of California-Irvine Eric-Jan Wagenmakers, U of Amsterdam **************************************************************** 7. ARL STRONG Program, due 21 Dec 18 https://www.fbo.gov/index?s=opportunity&mode=form&id=a33549b6039752990aaf6f50777f1379&tab=core&_cview=0 A new external US Army Research Laboratory Program Announcement for the STRONG program (Strengthening Teamwork for Robust Operations in Novel Groups), which focuses on enhancing teamwork in Human Agent Teams using individualized, adaptive approaches, was published on FBO and grants.gov. Cycle 1 proposals are due 21 Dec 18. https://www.fbo.gov/index?s=opportunity&mode=form&id=a33549b6039752990aaf6f50777f1379&tab=core&_cview=0 If you have any further questions, you can submit them on the website (https://www.arl.army.mil/www/default.cfm?page=3501) as well as join the Opportunities Webinar on 15 Nov at 1300 EST. Matthew Marge, PhD, matthew.r.marge.civ at mail.mil Computer Scientist U.S. Army Research Laboratory Computational & Information Sciences Directorate **************************************************************** 8. Nengo Summer School https://www.nengo.ai/summerschool The Centre for Theoretical Neuroscience at the University of Waterloo is excited to announce our 6th annual Nengo summer school on large-scale brain modelling and neuromorphic computing. This two-week school will teach participants to use the Nengo simulation package to build state-of-the-art cognitive and neural models to run both in simulation and on neuromorphic hardware. Summer school participants will be given on-site access to Loihi, Intel's new neuromorphic research chip [1], and will learn to run high-level applications on Loihi using Nengo! More generally, Nengo provides users with a versatile and powerful environment for designing cognitive and neural systems, and has been used to build what is currently the world's largest functional brain model, Spaun [2], which includes spiking deep learning, reinforcement learning, adaptive motor control, and cognitive control networks. For a look at last year's summer school, check out this short video: https://www.youtube.com/watch?v=NwtYgBB2N6I We welcome applications from all interested graduate students, postdocs, professors, and industry professionals with a relevant background. [1] Davies, et al. (2018). Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro. Vol. 38 no. 1 pp. 82-99. [https://ieeexplore.ieee.org/document/8259423] [2] Eliasmith, C., Stewart T. C., Choo X., Bekolay T., DeWolf T., Tang Y., Rasmussen, D. (2012). A large-scale model of the functioning brain. Science. Vol. 338 no. 6111 pp. 1202-1205. DOI: 10.1126/science.1225266. [http://compneuro.uwaterloo.ca/files/publications/eliasmith.2012.pdf] *************************************************************** 9. Travel fund in memory of Sayan Gul https://www.gofundme.com/travel-fund-in-honor-of-sayan-gul Sayan Gul, who had recently finished his undergraduate degree at Berkeley, died suddenly this summer after having a heart attack on the way to the Annual Conference of the Cognitive Science Society. His friends, family, and colleagues are raising funds to contribute to the Society to start a travel award in his name supporting similarly exceptional undergraduates presenting research at the conference. If you knew Sayan or would like to support undergraduate research in cognitive science please consider contributing: https://www.gofundme.com/travel-fund-in-honor-of-sayan-gul Tom Griffiths Professor of Psychology and Computer Science Princeton U **************************************************************** 10. Research on enhancing video game / eSports performance? I am interested in connecting with folks who are researching the cognitive and/or neurocognitive aspects of video game performance, both in the context of competitive video gaming/eSports as well as more broadly. If you or your colleagues are looking into how cognitive and/or physiological factors influence game performance, and what can be done to enhance player performance (as opposed to the cognitive/neurocognitive benefits of playing video games, of which there is already plenty of extant research), please reach out! I'd also be very grateful for any pointers to people/groups I should contact. Many thanks in advance for your time! Mark J. W. Lee Adjunct Senior Lecturer, School of Education, Charles Sturt U, Australia Visiting Faculty, Entertainment Technology Center, Carnegie Mellon U, USA malee at csu.edu.au / mjwlee at cmu.edu **************************************************************** 11. Job teaching in IST at Penn State https://psu.jobs/job/82796 [if you apply, please let me know if you wish or contact me with questions] The College of IST (http://ist.psu.edu) at the Pennsylvania State U in University Park, Pennsylvania invites applications for a tenure-track Assistant Professor in Human-Centered Design (HCD) to begin Aug 19. We seek exceptional candidates with high quality research and publications to strengthen and complement our current research programs We are especially interested in areas related to any or all of the following topics: the design of data, algorithms, and interactions that are useful and transparent to people; human-computer interaction (HCI) and design, ubiquitous computing and mobile systems; tangible and embodied interaction; computer-supported cooperative work (CSCW); computer-mediated communication (CMC); human-robot interaction (HRI); information visualization; and technology-mediated complexity and nuance. Penn State has many other programs related to human-centered design and to computing and information technology, including the Social Science Research Institute, the Institute for CyberScience, the Hershey Medical Center, and programs throughout Penn State's other colleges and campuses. We seek to strengthen our collaborations with these groups. Candidates should be prepared to teach undergraduate and graduate courses in HCD and contribute to the College's service and outreach objectives. All candidates must have a PhD or a terminal degree in information science or a closely related field. The successful candidates for the Assistant Professor rank must have demonstrated ability as a researcher and shown evidence of continuous scholarship. All candidates must have received their PhD or a terminal degree no later than the time of appointment. All successful candidates must pass a background check. TO APPLY: Visit https://www.ist.psu.edu/node/3757 basic personal information is required, but not other information listed below). IN ADDITION, applicants must submit the following material to https://academicjobsonline.org/ajo/jobs/12172 [awkward privacy policy]: (1) a cover letter, (2) a Curriculum Vitae, (3) 3-5 page research statement, (4) a one-page teaching statement, (5) contact information of 3-5 professional references. Review of applications will begin on 1 Nov 18, and will continue until the position is filled. Inquires about the position may be directed to facultyrecruiting at ist.psu.edu. The Penn State is the land grant institution of Pennsylvania. University Park is the largest of Penn State's 24 campuses, with undergraduate enrollment of approximately 44,000 students and offering more than 150 programs of graduate study. The College of IST has award-winning faculty and state-of-the-art facilities. Both faculty and students are dedicated to collaboration and applying knowledge to make our lives better. **************************************************************** 12. Need For Program officers There is a continued need for program officers at a variety of organizations, primarily in the DC area. I know a couple and it is a possible career for PhDs. Similar positions are available in nearly all other governments. If you are interested, please feel free to call me. I know of two slots that I think will be open in our area, broadly defined, and I know of other programs that routinely are looking for program officers. I can refer you to existing officers in NiH, ONR, NSF, for further information. If for some odd reason you want to write a book, there is a book missing in this area, about how to be a program officer. The existing program officers don't have time, and most others don't know enough to write it. Frank **************************************************************** 13. Faculty Hire. Assistant Prof Indiana in Machine and Human Learning This hire is part of Indiana University's Emerging Area of Research Initiative -Learning: Brains, Machines and Children, http://www.indiana.edu/~earbmc/ . Last year, we hired in the in Brain area, Richard Betzel. This year, the focus is on Machines and the position will be in Computer Science at the Assistant Professor Level. The goal of the Emerging Area Initiative is to promote the study of learning across disciplinary boundaries bridging the gap between the study of human and machine learning. Individuals with integrated research programs or an open-minded interest in these questions are encouraged to apply. The Indiana University initiative on learning will continue over the next few years by promoting additional faculty lines with synergistic research programs to address the important topic of learning in humans and machines. The job posting and path to application is here: https://indiana.peopleadmin.com/postings/6576 Cognitive Science, Computational Neuroscience, Psychology, Informatics, and Computer Science at Indiana form an invigorating, innovative, synergistic and intellectually fun community in which young scientists thrive and break barriers. Linda B. Smith Distinguished Professor Psychological and Brain Sciences Indiana University Bloomington IN 47405 *************************************************************** 14. Cognitive Scientist, Open Rank, U of Rochester http://www.sas.rochester.edu/bcs/jobs/faculty.html The Department of Brain and Cognitive Sciences at the U of Rochester is seeking to hire multiple faculty members in the area of decision making and cognitive or sensorimotor planning at the Assistant (tenure-track) or Associate Professor level. Areas of interest include the roles of learning, prediction, memory, and attention in guiding goal-directed behavior, especially within complex, naturalistic environments. We are primarily interested in candidates using neuroimaging, computational (e.g., Bayesian decision theory, reinforcement learning), behavioral (including technology-driven approaches such as virtual reality), and/or developmental approaches. Both individuals and teams are encouraged to apply. Successful candidates will join a dynamic department with interests in the study of perception, motor control, learning, cognition, language, and development through combined neurobiological, computational, and behavioral research (http://www.sas.rochester.edu/bcs/); she or he will also be part of a U-wide community engaged in graduate and undergraduate education. Candidates should hold a PhD degree (or equivalent) in cognitive science, psychology, neuroscience, or another relevant domain, and should have considerable research experience. Applicants should submit a CV, a statement of research and teaching interests, and contact information for three referees via https://www.rochester.edu/faculty-recruiting/login In addition, team applications should include a joint statement that describes the research synergies of the team. Questions concerning this position can be addressed to Robert Jacobs (rjacobs at ur.rochester.edu) and Duje Tadin (dtadin at ur.rochester.edu), co-chairs of the search committee. Review of applications will begin on 1 Nov 18. The U of Rochester is an Equal Opportunity Employer with a strong commitment to diversity, and actively encourages applications from candidates from groups underrepresented in higher education. **************************************************************** 15. Assistant Professor, CS (Computational Analysis of Behavior), Saskatchewan https://usask.csod.com/ats/careersite/JobDetails.aspx?id=2953&site=14 Requisition: req2953 Open Date: 7/9/18 Applications are invited from qualified individuals for a tenure track position at the rank of Assistant Professor with the College of Arts and Science in the Department of Computer Science. The U of Saskatchewan, the College of Arts and Science and the Department of Computer Science are strongly committed to diversity. Applications from Indigenous persons and women are especially encouraged and will be given preference. The successful candidate will build a substantial, externally funded research program in Analytics, with an emphasis on understanding human behavior, broadly defined. While all aspects of analytics will be considered, preference will be given to research in mining and analysis of digital records of human behavior such social media posts, game logs, or interaction logs. The successful candidate will teach at both the undergraduate and graduate level. As the current U vision emphasizes collaborative research, the successful candidate will be able to identify how they will work with other faculty members in the department, units on campus, and external and academic partners, while maintaining an analytics research program. Prospective candidates are encouraged to visit the departmental website (https://www.cs.usask.ca/) for program details. The Department of CS is the home of 23 faculty, 10 staff, and more than 130 graduate students and postdoctoral fellows working in diverse areas of computer science. The U of Saskatchewan is home to the Social Sciences Research Laboratory, a CFI endowed Social Sciences research facility. The Department of Computer Science is home to the Human Computer Interaction Lab, one of the most per capita productive HCI research groups in the world, including ACM CHI Academy Fellow Carl Gutwin, and Steacie-Award winning Regan Mandryk, and former WISE Chair Julita Vassileva. The Department and U have diverse collaboration opportunities in the area of the computational analysis of behavior including the MADMAC, CEPHIL, DISUCS and BIG labs, and potential collaborators in the social and medical sciences. The U of Saskatchewan's main campus is situated on Treaty 6 Territory and the Homeland of the M?tis. The U of Saskatchewan is located in Saskatoon, Saskatchewan, a city with a diverse and thriving economic base, a vibrant arts community and a full range of leisure opportunities. The U has a reputation for excellence in teaching, research and scholarly activities and offers a full range of undergraduate, graduate, and professional programs to a student population of over 24,000. Qualifications The successful candidate will have a PhD in Computer Science or related discipline, from a reputable institution. We are seeking candidates who have a strong research record evidenced by publications at recognized Computer Science venues, and evidence of teaching. Teaching, particularly in analytics and in upper division courses, would be an asset. Evidence of an ability to attract external grant funding would be an asset. Evidence of professional service or outreach activities would be an asset. Salary bands at the U of Saskatchewan are as follows: Assistant Professor: $93,293 to $112,109; Associate Professor: $112,109 to $130,925; and Professor $130,925 to $152,877. The position is anticipated to be at the Assistant Professor level. This position includes a comprehensive benefits package which includes a dental, health and extended vision care plan; pension plan, life insurance (compulsory and voluntary), academic long term disability, sick leave, travel insurance, death benefits, an employee assistance program, a professional expense allowance, and a flexible health and wellness spending program. Interested candidates must submit, via email, a cover letter, a detailed curriculum vitae, a research statement; a teaching statement, and the contact information of at least three references to faculty.recruiting at cs.usask.ca . In addition to its usual content, the cover letter should clearly state the position the candidate is applying for, and the Canadian citizenship or immigration status of the applicant. We encourage all candidates to self-identify as a member of an equity group (women, members of visible minorities, Indigenous persons, and persons with disabilities) in their letter of application. For additional information or questions, please contact Kevin Stanley, kevin.stanley at usask.ca Head, Department of Computer Science 110 Science Place U of Saskatchewan Saskatoon,SK S7N 5C9 Telephone: (306) 966-4886 Review of applications will begin 15 Sep 18; however, applications will be accepted and evaluated until the position is filled. The anticipated start date is 1 Jul 19. This position is in scope of USFA **************************************************************** 16. Associate or Full Professor of Usability Studies, U of Arizona https://uacareers.com/postings/31719 Deadline: Oct 1 Associate or Full Professor of Usability Studies w/ tenure at the School of Information at the U of Arizona We are searching for an associate or full professor of usability studies with tenure at the School of Information at the U of Arizona. The job advertisement can be seen here: https://uacareers.com/postings/31719 For questions on the position, you can contact the search committee chair at hongcui at email.arizona.edu As the reviews will begin soon, early application is strongly recommended. The deadline for application is 1 Oct 18. [might be too late, might not] **************************************************************** 17. (tenure-track) Assistant Professor position at Rutgers U https://jobs.rutgers.edu/postings/74628 I am writing to draw your attention to the (tenure-track) Assistant Professor position we just posted (https://jobs.rutgers.edu/postings/74628). The target research area for this position is very broad -- the ad says: "any of three broad areas: (1) cognitive neuroscience; (2) computational approaches to cognition; or (3) experimental approaches to development, language, or decision making." But basically we are looking for the kind of person who might be working as a graduate student or postdoc in YOUR lab. I hope you'll think about whether any of your students or postdocs might be suitable for this position, and if so urge them to apply. The cognitive area in the Psychology department at Rutgers is a very cohesive and strong unit with particular expertise in cognitive development, memory, decision making, language, visual perception, motor control, and categorization. Faculty include: Jacob Feldman, Arnold Glass, Pernille Hemmer, Judith Hudson, David Kleinschmidt, Eileen Kowler, Alan Leslie, Melchi Michel, Julien Musolino, Manish Singh, Karin Stromswold and Elizabeth Torres. We also have strong connections to the Rutgers Center for Cognitive Science (RuCCS), the Rutgers Center for Computational Biomedicine Imaging and Modeling, the Rutgers Brain Health Institute, and the Robert Wood Johnson Medical School. Please tell your students and postdocs to apply! Jacob Feldman jacob at ruccs.rutgers.edu Professor Department of Psychology Center for Cognitive Science Rutgers U - New Brunswick 152 Frelinghuysen Rd. Piscataway, NJ 08854 https://ruccs.rutgers.edu/jacob **************************************************************** 18. 6 faculty positions in data analytics, Industrial and System Engineering, U. of FL http://www.ise.ufl.edu/about/careers/ See link. **************************************************************** 19. UF-ISE Human Systems Tenure Track Positions http://explore.jobs.ufl.edu/cw/en-us/job/505562/assistantassociatefull-professor I am writing to let you know of exciting open-rank tenure-track opportunities within Industrial and Systems Engineering at the U of Florida. We are currently building a strong team of faculty within the applied area of Human Systems Engineering. This past year the department hired three faculty in this area including our current department chair, Dr. Kaber. This year, we are continuing our growth by seeking candidates with expertise in transportation human factors and human-robot interaction, among other topics. In general, we are interested in candidates pursuing HSE research with broad societal implications (e.g., improving automated vehicle design and transportation networks; promoting safety in human-in-the-loop systems). We are still seeking new applicants, and we are currently looking to hire at all levels. Please let me know if you have any questions about the position or the UF ISE department. Wayne C.W. Giang, PhD | Assistant Professor Industrial & Systems Engineering Herbert Wertheim College of Engineering U of Florida wayne.giang at ise.ufl.edu | 352-294-7729 *************************************************************** 20. Tenure Track Search - Cognitive Modeling, RIT https://sjobs.brassring.com/TGnewUI/Search/Home/Home?partnerid=25483&siteid=5291#home I'm reaching out just to spread the word that our department will be advertising for an assistant professor tenure track position in cognitive psychology with a preference for expertise in cognitive modeling or game theory. If you know of anyone (e.g., students, postdocs or other colleagues) that might be looking for a position at a school with a dual emphasis on research and teaching, please feel free to pass along the attached advertisement. The Dept of Psychology at the Rochester Institute of Technology (http://www.rit.edu/cla/psychology/) invites candidates to apply for a tenure-track assistant professor position starting Mid-Aug 19. We are looking for an energetic and enthusiastic psychologist who will serve as an instructor, researcher, and mentor to students. Candidates should have expertise in the area of Cognitive Psychology, preferably with expertise in modeling of cognition or game theory. The Department of Psychology at RIT serves a rapidly expanding student population. The position requires a strong commitment to teaching, active research and publication, and a strong potential to attract external funding. Faculty are expected to supervise graduate and undergraduate students in research. The hire will be expected to contribute to the Department's undergraduate and graduate programs, as well as the Human Centered Computing (http://hcc.rit.edu/) program, through the teaching of our research method courses and cognitive psychology courses. We are seeking an individual who has the ability and interest in contributing to RIT's core values, honor code, and statement of diversity. REQUIRED MINIMUM QUALIFICATIONS Have PhD, or PhD expected by 1 Jul 19 in cognitive psychology or related specialty; Have demonstrated ability to conduct independent research in psychology; Have consistently and recently published; Have demonstrated teaching ability and have taught college courses independently beyond TA; Have demonstrated ability to supervise student research; Show external research grant attainment potential; Show a career trajectory that emphasizes a balance between teaching and research; Show a fit with the department of psychology's general mission, teaching, research, and resources. Ability to contribute in meaningful ways to the college's continuing commitment to cultural diversity, pluralism, and individual differences. HOW TO APPLY Read the full ad and apply online at https://sjobs.brassring.com/TGnewUI/Search/Home/Home?partnerid=25483&siteid=5291#home; search openings, then Keyword Search 4009BR. Please submit your application, curriculum vitae, cover letter addressing the listed qualifications and upload the following attachments: A brief teaching philosophy A research statement that includes information about previous grant work, the potential for future grants, and information about one-on-one supervision of student research The names, addresses and phone numbers for three references Contribution to Diversity Statement You can contact the search committee with questions on the position at: Dr. Esa Rantanen (esa.rantanen at rit.edu) To receive full consideration, all application materials should be received by 1 Oct 18. The position will be kept open until a suitable candidate is found. ************************************************ 21. Positions at RIT I am happy share that RIT has launched a research-cluster faculty search in the areas of HCI and accessibility this year, with three openings at the assistant, associate, or full professor rank. I was hoping you might be able to share this opportunity with any Penn State students who are entering the job market this year. https://sjobs.brassring.com/TGnewUI/Search/home/HomeWithPreLoad?PageType=JobDetails&partnerid=25483&siteid=5291&jobid=1462074#jobDetails=1462074_5291 Information about HCI at RIT: http://hci-research.rit.edu/ **************************************************************** 22. Tenure track position in computational language science (U of Florida) (Edith Kaan) Application Deadline: 18 Nov, 18 https://apply.interfolio.com/56557 [has an awkward privacy policy] The U of Florida invites applications for a tenure-track appointment in computational language science at the rank of assistant professor, effective Aug 16, 19. This is a 9-month position. Applicants are expected to have a PhD in linguistics, computer science, or a closely-related field. Candidates should have an active research agenda studying language from a computational perspective. Specialization is open, including but not limited to sociolinguistics, neuro/psycholinguistics, corpus linguistics, and/or language documentation. UF Linguistics seeks to train the next generation of linguists who are comfortable integrating and evaluating computational approaches in their research. To this end, ability to teach computationally-oriented courses is required. Candidates must hold the PhD by the starting date. The successful candidate will be expected to 1) maintain an active research agenda, 2) pursue external research funding, 3) teach two courses per semester at the undergraduate and/or graduate level, 4) provide service to the department, the U, and the profession, and 5) seek collaborations within the department as well as with other units on campus such as the UF Data Science and Information Technology Center, the UF Informatics Institute, or the McKnight Brain Institute. The Department is committed to creating an environment that affirms diversity and inclusion across a variety of dimensions, including ability, class, ethnicity/race, religion and/or cultural background, gender identity and expression. We particularly welcome applicants who can contribute to such an environment through their scholarship, teaching, mentoring, and professional service. The U and greater Gainesville community enjoy a diversity of cultural events, restaurants, year-round outdoor recreational activities, and social opportunities Salary is competitive, commensurate with qualifications and experience, and includes a full benefits package. The Linguistics Department at the U of Florida is a vibrant and congenial unit consisting of 11 full-time faculty and 15 affiliated faculty in the departments of Anthropology; Languages, Literatures, and Cultures; Spanish and Portuguese; and the Dial Center for Written & Oral Communication. We offer a BA, MA and PhD in Linguistics, as well as an undergraduate minor and undergraduate certificate in TESL and a graduate certificate in Second Language Acquisition and Teaching. We have faculty expertise in a wide range of linguistic subfields, and particular strengths in the areas of bilingualism, language documentation, psycholinguistics, sociolinguistics, and African linguistics. Please see our website, lin.ufl.edu, for more information about the department. For full consideration, applications must be submitted online at https://apply.interfolio.com/56557 and must include: (1) a brief cover letter, (2) a statement of teaching and research interests, (3) a CV, (4) 1-3 sample publications, (5) the names and email addresses for three references, and (6) representative teaching evaluations if available. After initial review, letters of recommendation will be requested for selected applicants. Review of applications will begin on 18 Nov 18 and will continue until the position is filled. All candidates for employment are subject to a pre-employment screening which includes a review of criminal records, reference checks, and verification of education. **************************************************************** 23. Sloan Scholars job board https://sloan-scholars.ssrc.org/resources/index/ As the 19-20 job postings start circulating, we will be adding opportunities that come our way to https://sloan-scholars.ssrc.org/resources/index/ our job posting board on the SSMN website. As we will not post every job to the listserv, if you are on the market, be sure to check the board regularly. If your university and/or department is hiring and you would like to share these opportunities with the Sloan Network, please feel free to forward them (sloan-network at ssrc.org) to the listserv, particularly if you are willing to field questions about the position, the department, or the U environment. All members of this listserv may also post to it. Alma M. Granado, PhD Program Officer | Sloan Scholars Mentoring Network granado at ssrc.orggranado@ssrc.org | 718-517-3640 https://www.ssrc.org/ Social Science Research Council **************************************************************** 24. Professor in Data Science, Geovisualization and Design http://seas.umich.edu/node/2132 Assistant Professor in Data Science, Geovisualization and Design The School for Environment and Sustainability (SEAS) at the U of Michigan is seeking applications for a full-time, nine-month, tenure-track Assistant Professor in Data Science, Geovisualization and Design. We seek candidates whose work focuses on the theory and application of data analytics, design and geovisualization within the interdisciplinary field of environment and sustainability. Candidates should be pursuing hypothesis driven research on analyzing, designing and visualizing spatial complexity in environmental systems for sustainability efforts. Topic areas include, but are not limited to, data science techniques, digital and critical cartography, and how humans understand and communicate spatial relationships. http://seas.umich.edu/employment/assistant_or_associate_professor_energy_systems_analysis Assistant or Associate Professor in Energy Systems Analysis The School for Environment and Sustainability (SEAS) at the U of Michigan is seeking applicants for a full-time, nine-month, tenure-track Assistant/Associate Professor in Energy Systems Analysis. We seek a scholar with demonstrated excellence in research and teaching in the energy systems analysis field. This position focuses on integration across technology, science and policy, toward a goal of accelerating adoption of renewable energy technology, energy efficiency, energy demand shifts, and other climate mitigation strategies. Examples of relevant methods/areas of expertise include system dynamics, agent-based modeling, decision-support, life cycle assessment, techno-economic analysis, and policy analysis and design. http://seas.umich.edu/employment/assistant_or_associate_professor_spatial_science_coupled_natural_human_systems Assistant or Associate Professor in Spatial Science of Coupled Natural-Human Systems The School for Environment and Sustainability (SEAS) at the U of Michigan is seeking applications for a full-time, nine-month, tenure-track Assistant or Associate Professor in Spatial Science of Coupled Natural-Human Systems. We seek applicants whose work advances the frontiers of knowledge in natural-human system processes and relationships at diverse scales using theories, methods, and tools of spatial science. Topical areas of interest are broad. These could include human dimensions of global change as they relate to biodiversity loss, land-cover/land-use change, urbanization, climate change, ecosystem services and valuation, material and energy flows, and environmental degradation, among others. http://seas.umich.edu/employment/faculty_position_water_policy_politics_and_planning Faculty Position in Water Policy, Politics and Planning The School for Environment and Sustainability (SEAS) at the U of Michigan (UM) seeks applicants for a full-time, nine-month, tenure-track Assistant Professor position in Water Policy, Politics and Planning. Applicants should have a PhD in environmental policy or planning, political science, public policy, water resource management, or a closely related discipline, or a JD in environmental law with a demonstrated record of scholarly research. http://seas.umich.edu/employment Assistant Professor in Data Science, Geovisualization and Design http://seas.umich.edu/ School for Environment and Sustainability The School for Environment and Sustainability (SEAS) at the U of Michigan is seeking applications for a full-time, nine-month, tenure-track Assistant Professor in Data Science, Geovisualization and Design. We seek candidates whose work focuses on the theory and application of data analytics, design and geovisualization within the interdisciplinary field of environment and sustainability. Candidates should be pursuing hypothesis driven research on analyzing, designing and visualizing spatial complexity in environmental systems for sustainability efforts. Topic areas include, but are not limited to, data science techniques, digital and critical cartography, and how humans understand and communicate spatial relationships. Post-doctoral experience is preferred, but we welcome candidates with exceptional PhDs in geography, computer science, information sciences, ecology, landscape architecture, urban planning, art and design or closely related disciplines. Applicants must demonstrate a strong record of scholarly publication, evidence of teaching potential in a multidisciplinary setting, and evidence of potential for and/or trajectory towards national and international recognition. Importantly, we are seeking candidates with a history of using their research to help solve real-world sustainability problems. Therefore, candidates should have the potential and willingness to engage stakeholders in their work, and evidence of collaboration across disciplinary boundaries to develop implementable solutions to sustainability challenges. SEAS's mission is to contribute to the protection of the Earth's resources and the achievement of a sustainable and just society. The School contributes new scientific knowledge, visionary leadership, and trained professionals toward that end. The faculty of the School is diverse, with natural scientists, social scientists, engineers, and designers working collaboratively in an integrative setting. A professional school set within a major research U, SEAS provides a model of interdisciplinary and applied research and a focal point of research, teaching and societal engagement on sustainability. Recently renamed with an expanded mission, the School is hiring six new faculty during 18. The School focuses on key cross-cutting sustainability themes, including climate and energy; water; food, land use, and agriculture; conservation and restoration; and cities, the built environment, and mobility. The School offers a PhD as well as both research and professional MS degrees in six fields of study: conservation ecology; geospatial data science; sustainable systems; environmental policy and planning; behavior, education and communication; and environmental justice. The School also offers a Master's degree in Landscape Architecture (MLA) and a cross-campus undergraduate program in the environment. The student body includes over 350 MS/MLA. and 60 doctoral students. SEAS also participates in dual degree programs with the Schools of Architecture and Urban Planning, Business, Engineering, Law, Public Health, and Public Policy. Additional information about the School can be found at http://seas.umich.edu/ The successful candidate will be expected to: 1) Develop a widely recognized research program that attracts external funding and contributes to the interdisciplinary mission of the School; 2) Support SEAS's teaching mission at both graduate and undergraduate levels, including mentoring and supervising doctoral and master's students; 3) Contribute to the stewardship of SEAS, the U, relevant professions and society through service, collaboration and engagement. The position will be filled at the assistant professor (tenure-track) level. Applications should include (1) a cover letter; (2) CV; (3) a concise personal statement describing your vision and plans for research, teaching and societal engagement; (4) a one-page statement on how you have or plan to contribute to diversity efforts, and (5) a list of three academic references with contact information. To apply, submit application materials (in a single PDF file), via the following web address: http://seas.umich.edu/employment For assistance or further information, you may contact SEAS.faculty.search.staff at umich.edu Review of applications will begin on Sept 14, 18 and continue until the position is filled. SEAS hopes to appoint a faculty member to this position to begin Fall 19. **************************************************************** 25. Cognitive Science Lecturer, U of Michigan due 30 nov 18 The Weinberg Institute for Cognitive Science in the College of Literature, Science, and the Arts at the U of Michigan seeks applicants for a new full-time (100%) academic year position: Lecturer and Assistant Director of the Cognitive Science Major. The position will start as early as 1 Jan 19, but not later than 1 Sep 19, pending final authorization. This is a non-tenure track position classified as Lecturer-III within U-M, with a university-year nine-month appointment from 1 Sep through 31 May each year, with salary paid over a 12-month period, and benefits-eligible. The initial appointment will be for three academic years, contingent upon satisfactory performance, need and available funding. The Institute expects that, for the suitable candidate, this will be a long-term position extending beyond the initial appointment. How to Apply Candidates should submit a single attachment (in PDF format) to the University of Michigan posting #163328 with the following required materials: 1. Letter of Application (no more than two pages) 2. CV 3. Teaching Statement (no more than 3 pages; includes teaching philosophy and experience) 4. Evidence of Teaching Excellence 5. Two sample syllabi (from courses previously taught) 6. Names and contact information of three recommenders who can comment on the applicant's qualifications for this position. Letters are not required in the initial application submission stage. Responsibilities The new Lecturer and Assistant Director of the Cognitive Science Major appointed in the Weinberg Institute for Cognitive Science will help support the instructional and administrative demands of the Cognitive Science major by (a) teaching the gateway course Introduction to Cognitive Science (COGSCI200) at least once per year; (b) providing additional upper division course offerings in at least one of the four tracks of the undergraduate major (Computation and Cognition, Decision and Cognition, Language and Cognition, or Philosophy and Cognition); and (c) providing administrative oversight of advising and student enrichment activities. Instructional duties The position requires teaching three courses per year. At least one course will be Introduction to Cognitive Science, the interdisciplinary gateway course for the Cognitive Science major (COGSCI200), either alone or as co-teacher with one other existing faculty. The other two courses will be upper-level undergraduate offerings that help to meet curricular needs in one or more of the four tracks of the major. Administrative duties The position involves approximately 13-16 hours per week of administrative activities. More specifically, these activities will encompass at least the following four areas of responsibility: (i) oversight of peer academic advising; (ii) oversight of the creation and execution of student-enrichment activities focused on academic, intellectual, and career development; (iii) some academic and career advising; and (iv) oversight of the communication and administration of Institute-funded opportunities for cognitive science majors. All of these responsibilities will be carried out with guidance from and in coordination with the Institute Director, the Institute Chief Administrator, the Institute Undergraduate Committee, and the communications and events staff. Required Qualifications We expect that a successful applicant will hold a PhD in Cognitive Science or one of the related core disciplines (e.g. Computer Science, Linguistics, Psychology, Philosophy). The applicant must have interdisciplinary teaching interests and experience, evidenced by interests and experience that span at least two of the core disciplines. The applicant must also be capable of contributing to the upper division offerings in one or more of the four tracks of the Cognitive Science major. Demonstrated excellence in teaching and engagement with diverse student populations will be an important criterion in our selection process. We expect that the applicant will be a visible and engaged faculty member in the Institute. Desired Qualifications We are especially interested in applicants who can teach large lecture courses in Cognitive Science as well as upper division courses or seminars that will contribute to at least one of the four tracks of the Cognitive Science major. Questions regarding problems with application upload can be directed to Weinberg.Institute.HR at umich.edu. Application Deadline The application deadline for full consideration is 30 Nov 18. **************************************************************** 26. Post-doc in Gronigen, due soon We have a postdoc vacancy here in Groningen for up to four years. The research should be within cognitive modeling, but the topic is open. The application deadline is within a week, so if you are interested apply soon! Best, Niels https://www.rug.nl/about-us/work-with-us/job-opportunities/overview?details=00347-02S0006MZP The FSE Fellowship programme Our unique FSE fellowship programme offers temporary positions for talented junior researchers who want to further develop both their research and teaching skills. You will have an appointment for four years during which you can do challenging research, have various teaching responsibilities (approximately 30% of the time), and be offered opportunities for training and career orientation. >From the start, you will have a personal Work and Development Plan (WDP) that describes the specific research, teaching and training activities that you will undertake. You will receive didactic training in your first year and have the opportunity to obtain a University Teaching Qualification. In addition to the yearly Result and Development Interviews with your supervisors, you will have a yearly meeting with a career counsellor to discuss your career development and plans. A personal budget of a ? 1,000 per year is dedicated for additional training and career activities. We currently offer 15 fellow positions in a broad range of scientific fields. The preferred starting date of the fellows is before April 2019. Niels Taatgen - Professor Chair of the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence University of Groningen http://www.ai.rug.nl/~niels n.a.taatgen at rug.nl +31 50 3636435 **************************************************************** 27. ISO two postdocs to work on models of learning from instruction AFRL, Dayton, OH I am looking for two bright and energetic individuals who are interested in conducting postdoctoral research on developing computational cognitive processes models capable of learning from instruction. The selectees will work closely with myself & Dr. Christopher Stevens of the Cognitive Science, Models, & Agents Branch at the Air Force Research Laboratory (AFRL). The positions will also involve close collaboration with Dr. Dario Salvucci (Drexel), Dr. Pascal Hitzler (Wright-State U), and Dr. Benji Maruyama (Materials & Manufacturing Directorate, AFRL). Qualified candidates must be U.S. citizens, have (or will soon receive) a doctoral degree in cognitive science, psychology, AI/computer science, or a related field. Strong applicants will have expertise in computational modeling and programming. Awardees will receive a pre-tax annual salary of $70,000 (plus a travel stipend) and will be required to relocate to wild and wonderful Dayton, OH. Further inquiries regarding the positions should be sent to Dr. Myers (christopher.myers.29 at us.af.mil) & Dr. Stevens (christopher.stevens.28 at us.af.mil). To apply for a position, please provide a copy of your graduate school transcripts, a curriculum vitae, and references with their contact information. Thanks for the help! CHRISTOPHER MYERS, PHD Senior Cognitive Scientist Cognitive Models Core Research Area Lead Cognitive Science, Models, & Agents 711th Human Performance Wing 2620 Q Street B852 Wright-Patterson AFB, 45433-7955 C: 937-723-0186 O: 937-938-4044 **************************************************************** 28. 3 years independent research fellowship in Computational Neuroscience https://www.nottingham.ac.uk/jobs/currentvacancies/ref/SCI219418 Fantastic job opportunity here at Nottingham: 3 years independent research fellowship in Computational Neuroscience (joint post with Psych/Maths). Several (up to 3?) posts @CogNeuroJobs **************************************************************** 29. PhD / Postdoc position in the CRC EASE, U of Bremen in the scope of the project P3 (Spatial Reasoning in Everyday Activity) of the Collaborative Research Center EASE, I am looking for a PhD student or Postdoc (see attachement). The CRC EASE comprises 12 projects that bring together expertise from AI, Robotics, Linguistics, and Cognitive (Neuro)Science to ultimately enable robots to master everyday activities. The CRC features project-spanning working groups on ontologies, machine learning, and human activity data as well as its own Grad School (with regular meetings and a spring and a fall school each year). The project P3 focusses on analyzing and formalizing human processing principles that allow keeping spatial problems arising in everyday activities managable. Holger OPEN POSITION 1 full Postgraduate Position / Junior Researcher at the Collaborative Research Center SFB 1320 Everyday Activity Science and Engineering, Universitaet Bremen Project P03 - Spatial Reasoning in Everyday Activity Under the condition of job release / reference number: A161/18 Project Description Despite the seeming ease with which humans perform everyday activities such as, for example, (un)loading a dishwasher or setting the table, mastery of everyday activities by artificial cognitive agents has yet to be achieved. By focusing on the processing of spatial information, the aim of this project is to facilitate building artificial cognitive agents that master complex human-scale manipulation tasks. To this end project work will (a) investigate human processing of spatial information in everyday activities, (b) formalize human spatial cognition in computational cognitive models, and (c) employ the insight gained on the mechanisms governing human performance to provide information processing principles allowing to master everyday activities to a robotic platform. A particular focus of the project will be on principles that allow humans to keep the size of spatial problems manageable as well as on principles that allow direct action-based problem solving by exploiting the structure of the physical world.. Qualifications Applicants should have expertise in computer science / artificial intelligence and cognitive science and should hold a master or diploma degree in computer science, cognitive science, or a related field. They should be committed to interdisciplinary, team-based research and be fluent in spoken and written English. Ideally, an applicant will also have knowledge of / interest in one or more of the following areas: computational cognitive modeling of human (spatial) cognition; qualitative spatial reasoning; affordance-driven information processing Additional training will be provided on the job. Main Tasks * Contributing to conceptual and computational modeling of human information processing (in particular, processing of spatial information when performing everyday activities). * Planning and conducting exploratory studies and analyzing human activity patterns. * Preparing manuscripts for publication in international journals / at conferences. Conditions of Employment Salary is according to the German Federal pay scale (TV-L 13, approx. EUR 44,000 p.a.). The position is available as soon as possible until the end of Jun 2021. Application Deadline Aug 25th, or until a suitable candidate is found (timely informal requests or statements of interest are very welcome) As the U of Bremen intends to increase the proportion of female employees in science, women are particularly encouraged to apply. In case of equal personal aptitudes and qualification, disabled persons will be given priority. Applicants with a migration background are welcome. How to Apply & What to Do in Case of Questions Please address questions about the position and send your application under the reference number (preferably by email) to: PD Dr. Holger Schultheis schulth at informatik.uni-bremen.de Bremen Spatial Cognition Center Universitaet Bremen P.O. Box 330 440 28334 Bremen / Germany For a paper-based application, please make sure to only send document copies as all received application material will be destroyed after the selection process. *************************************************************** 30. Penn State Earth and Mineral Sciences Looking for Post-Doc https://psu.jobs/job/79865 The College of Earth and Mineral Sciences, at The Pennsylvania State U, invites applications for a post-doctoral research position in adapting deep learning methods for use in the earth sciences. This position will provide the successful candidate with experience conducting cross-cutting research working under the supervision of three faculty members Dr. Guido Cervone from the Dept. of Geography, Dr. Christelle Wauthier from the Dept. of Geosciences, and Dr. Melissa Gervais from the Dept. of Meteorology and Atmospheric Sciences. They will conduct collaborative research that will advance the use of deep learning within the earth sciences through its application to several scientific questions that require the identification of patterns of spatio-temporal variability. The successful candidate will have access to significant computing resources and be involved in the high performance computing activities of the Institute for CyberScience at Penn State. Applications can be submitted at: https://psu.jobs/job/79865 **************************************************************** -30- From xhx at ics.uci.edu Sun Nov 25 23:53:19 2018 From: xhx at ics.uci.edu (Xiaohui Xie) Date: Sun, 25 Nov 2018 20:53:19 -0800 Subject: Connectionists: Open Rank Faculty Positions in Computer Science at UC Irvine Message-ID: University of California, Irvine Donald Bren School of Information and Computer Sciences Department of Computer Science Open Rank Faculty Positions in Computer Science: Bioinformatics The Department of Computer Science in the Donald Bren School of Information and Computer Sciences (ICS) at the University of California, Irvine (UCI) invites applications for tenure-track assistant professor or tenured associate/full professor positions beginning July 1, 2019. The Department is interested in individuals with a strong research background in bioinformatics, broadly defined to be in the general area of applying computational and/or machine learning methods to study biology and/or medicine. The Computer Science Department's curricula, faculty and research focus on an array of topics including: computer architecture, system software, networking and distributed computing, data and information systems, artificial intelligence, and computer graphics; while also pursuing interdisciplinary topics such as bioinformatics, data mining, security and privacy, and ubiquitous computing. At UCI, ICS brings together three unique departments (Computer Science, Informatics, and Statistics), thus strategically positioning itself to meet the technical and social challenges of computing and information systems in the coming decades. The U.S. News and World Report 2018 Best Global Universities ranking identifies UCI as a top 75 university in computer science and one of the top 30 universities for computer science in the United States. ICS is one of only five computing-focused schools among the Association of American Universities (AAU) members. Our 90+ faculty members include 2 NAE Members, 14 ACM Fellows, 9 IEEE Fellows, 9 AAAS Fellows and many other national award winners. For eight consecutive years the University of California, Irvine has been named a top 10 ?Coolest School? by Sierra magazine for our innovative sustainable practices. UCI is also ranked as a top ten public university by U.S. News and World Report, and has been identified by the New York Times as No. 1 among U.S. universities that do the most for low-income students. UCI is located in Orange County, 4 miles from the Pacific Ocean and 45 miles south of Los Angeles. Irvine is one of the safest communities in the U.S. and offers a very pleasant year-round climate, numerous recreational and cultural opportunities, and one of the highest-ranked public school systems in the nation. Applicants should hold a Ph.D. or equivalent in computer science or closely related field. Completed applications containing a cover letter, curriculum vitae, all available teaching evaluations, statements on diversity, teaching, and research, three letters of recommendation, and sample research publications should be uploaded electronically. Please refer to the following website for instructions: https://recruit.ap.uci.edu/apply/JPF04949 Applications received by January 1, 2019 will receive fullest consideration. The University of California, Irvine is an Equal Opportunity/Affirmative Action Employer advancing inclusive excellence. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, protected veteran status, or other protected categories covered by the UC nondiscrimination policy. A recipient of an NSF ADVANCE award for gender equity, UCI is responsive to the needs of dual career couples, supports work-life balance through an array of family-friendly policies, and is dedicated to broadening participation in higher education. From jiankliu at gmail.com Mon Nov 26 05:19:30 2018 From: jiankliu at gmail.com (Jian Liu) Date: Mon, 26 Nov 2018 10:19:30 +0000 Subject: Connectionists: Frontiers Research Topic "Discrimination of Genuine and Posed Facial Expressions of Emotion" In-Reply-To: References: Message-ID: Call for Papers: Frontiers Research Topic "Discrimination of Genuine and Posed Facial Expressions of Emotion" More information: https://www.frontiersin.org/research-topics/9221/discrimination-of-genuine-and-posed-facial-expressions-of-emotion About this Research Topic Facial expressions demonstrate one emotional states in interpersonal situations. Evidence shows that part of the facial display reflects the emotional experience that is literally felt by the expresser. Interestingly, human beings are capable of identifying facial expressions of the felt emotions as a form of intentional deception to conduct social interaction and to stage displays that have the support of others. Staged or posed facial expressions implement an emotion that an expresser intends to convey, where genuine expressions are considered as the companion of spontaneous emotional expressions. The ability to differentiate genuine displays of emotional experience from posed ones is very important for dealing with day-to-day social interactions. Recent work has been conducted on whether or not people can distinguish between posed and genuine displays of emotion. In spite of few studies to investigate this ability, most prior research suggests that people have the ability to judge genuine and posed facial displays. Unfortunately, previous research has suffered from two major shortcomings: (1) the mixture of staged and genuine displays due to the lack of accounting for possible effects of intentional manipulation, and (2) struggling to consider dynamic aspects when people prepare facial stimuli for experimental investigation. This Research Topic encourages the submission of theoretical and experimental perspectives to broaden understanding of the importance of the discrimination of genuine and posed facial expressions of emotion. These may be new theoretical approaches, those from other disciplines of psychology not usually utilized within the discrimination of genuine and staged emotion identification or new theories and designs. We seek articles that present new hypotheses, concepts, experimental observations, and theories or models; demonstrate how theories adapted from other disciplines may be utilized for emotion identification or provide recommendations to improve current models or theories to enhance their capacity. We look for papers that may combine critical analysis of current models, synthesis of early empirical work by single- or multi-modality analysis (e.g. video, ECG, EEG, fMRI, and single cells in humans and/or animals), and explore the potential for their development applied to the context of emotion recognition. Submissions of systematic reviews and meta-analysis should discuss and promote comprehensive approaches to update and evolve concepts, hypotheses, and theories with potential applications in the community. Keywords: face expression, discrimination, genuine, posed, emotion Guest editors: Huiyu Zhou, Department of Informatics, University of Leicester, United Kingdom. Caroline Ling Li, School of Computing, University of Kent, United Kingdom. Shiguang Shan, Institute of Computing Technology, Chinese Academy of Sciences, China. Shuo Wang, Chemical and Biomedical Engineering, West Virginia University, United States. Jian Liu, Centre for Systems Neuroscience, University of Leicester, United Kingdom. -------------- next part -------------- An HTML attachment was scrubbed... URL: From felipe at cos.ufrj.br Mon Nov 26 06:05:23 2018 From: felipe at cos.ufrj.br (Felipe Maia Galvao Franca) Date: Mon, 26 Nov 2018 09:05:23 -0200 Subject: Connectionists: PAISE 2019: 1st Workshop on Parallel AI and Systems for the Edge Message-ID: PAISE 2019: 1st Workshop on Parallel AI and Systems for the Edge Held in conjunction with IPDPS, 24th May 2019, Rio de Janeiro, Brazil http://paise-conf.science http://bit.ly/PAISE2019 Applications involving voluminous data but needing low-latency computation and local feedback require that the computing be performed as close to the data source as possible ? often at the interface to the physical world. Communication constraints and the need for privacy-preserving approaches also dictate the need for computing at the edge. Given the growth in such application scenarios and the recent advances in algorithms and techniques, machine learning and inference at the edge are unfolding and growing at a rapid pace. In support of these applications, a wide range of hardware (CPUs, GPUs, FPGAs, ASICs) is venturing farther away from the center, closer to the physical world. The diversity in edge-computing hardware in terms of capabilities, architectures, and programming models poses several new challenges. The goal of this workshop is to gather the community working in three broad areas: processing ? artificial intelligence, computer vision, machine learning; management ? parallel and distributed programming models for resource-constrained and domain-specific hardware, containers, remote resource management, runtime-system design, and cybersecurity; and hardware ? systems and devices conducive to use in resource-constrained (energy, space, etc.) applications. The workshop will provide a critically needed opportunity to discuss the current trends and issues, to share visions, and to present solutions. The following paper categories are welcome: - ? Full Papers: Research papers should describe original work and be 8 or 10 pages in length. - ? Short Papers: Short research papers, 4 pages in length, should contain enough information for the program committee to understand the scope of the project & evaluate the novelty of the problem. - ? Emerging Platforms and Practitioner Reports: Short reports, 3-6 pages in length, describing novel hardware & Software platforms, including initial proof-of-concept design & implementation. List of Topics Edge Inference, Hardware for Edge-computing and Machine Learning, Energy Efficient Processors for Training and Inference, Computer Vision at the Edge, Cyber Security for Edge Computing, Software and Hardware Multitenancy at the Edge, Machine Learning Hardware, Blockchains for Edge Computing, Programming Models for Edge Computing, Coupling HPC to Edge Applications, and Communication and Control Strategies for Deploying and Managing Applications at the Edge. Important Dates - ? Submission deadline: February 1st, 2019 - ? Notification of acceptance: March 1st, 2019 - ? Workshop camera-ready papers due: March 11th, 2019 -- ??????????????????????????????? Felipe M. G. Fran?a, PhD Professor of Computer Science and Engineering Systems Engineering and Computer Science Program, COPPE Universidade Federal do Rio de Janeiro P.O. Box 68511, 21941-972, Rio de Janeiro, RJ, Brazil felipe at ieee.org felipe at cos.ufrj.br ??????????????????????????????? -------------- next part -------------- An HTML attachment was scrubbed... URL: From thomaskreuz at gmail.com Mon Nov 26 10:35:28 2018 From: thomaskreuz at gmail.com (Thomas Kreuz) Date: Mon, 26 Nov 2018 16:35:28 +0100 Subject: Connectionists: Using spike train distances to identify the most discriminative neuronal subpopulation In-Reply-To: References: Message-ID: Dear all, may I kindly draw your attention to our most recent paper which contains several new algorithms to address neuronal population coding using spike train distances: Satuvuori E, Mulansky M, Daffertshofer A, Kreuz T: Using spike train distances to identify the most discriminative neuronal subpopulation JNeurosci Methods, 308, 354 [PDF ] and arXiv [PDF ] (2018). For the abstract see below. This paper is part of the dissertation "Spike train distances and neuronal coding " of my PhD student Eero Satuvuori whose full thesis can now be found here . Besides some original parts and the paper cited above it also contains these recent works: Satuvuori E, Kreuz T: Which spike train distance is most suitable for distinguishing rate and temporal coding? JNeurosci Methods 299, 22 [PDF ] and arXiv [PDF ] (2018). Kreuz T, Satuvuori E, Pofahl M, Mulansky M: Leaders and followers: Quantifying consistency in spatio-temporal propagation patterns New J. Phys., 19, 043028 [PDF ] and arXiv [PDF ] (2017). Satuvuori E, Mulansky M, Bozanic N, Malvestio I, Zeldenrust F, Lenk K, Kreuz T: Measures of spike train synchrony for data with multiple time-scales JNeurosci Methods 287, 25 [PDF ] and arXiv [PDF ] (2017). All the best, Thomas Kreuz PS: Satuvuori E, Mulansky M, Daffertshofer A, Kreuz T: Using spike train distances to identify the most discriminative neuronal subpopulation JNeurosci Methods, 308, 354 [PDF ] and arXiv [PDF ] (2018). Abstract: Background Spike trains of multiple neurons can be analyzed following the summed population (SP) or the labeled line (LL) hypothesis. Responses to external stimuli are generated by a neuronal population as a whole or the individual neurons have encoding capacities of their own. The SPIKE-distance estimated either for a single, pooled spike train over a population or for each neuron separately can serve to quantify these responses. New method For the SP case we compare three algorithms that search for the most discriminative subpopulation over all stimulus pairs. For the LL case we introduce a new algorithm that combines neurons that individually separate different pairs of stimuli best. Results The best approach for SP is a brute force search over all possible subpopulations. However, it is only feasible for small populations. For more realistic settings, simulated annealing clearly outperforms gradient algorithms with only a limited increase in computational load. Our novel LL approach can handle very involved coding scenarios despite its computational ease. Comparison with existing methods Spike train distances have been extended to the analysis of neural populations interpolating between SP and LL coding. This includes parametrizing the importance of distinguishing spikes being fired in different neurons. Yet, these approaches only consider the population as a whole. The explicit focus on subpopulations render our algorithms complimentary. Conclusions The spectrum of encoding possibilities in neural populations is broad. The SP and LL cases are two extremes for which our algorithms provide correct identification results. -- Institute for complex systems, CNR Via Madonna del Piano 10 50119 Sesto Fiorentino (Italy) Tel: +39-349-0748506 Email: thomas.kreuz at cnr.it Webpage: http://www.fi.isc.cnr.it/users/thomas.kreuz/ -- Institute for complex systems, CNR Via Madonna del Piano 10 50119 Sesto Fiorentino (Italy) Tel: +39-349-0748506 Email: thomas.kreuz at cnr.it Webpage: http://www.fi.isc.cnr.it/users/thomas.kreuz/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.russo at hsantalucia.it Mon Nov 26 11:40:07 2018 From: m.russo at hsantalucia.it (Marta Russo) Date: Mon, 26 Nov 2018 11:40:07 -0500 Subject: Connectionists: open rank faculty position in Human Movement Science at Northeastern, Boston, MA In-Reply-To: References: Message-ID: The Department of Biology at College of Science and the Department of Physical Therapy, Movement and Rehabilitation Science at the Bouve College of Health Sciences invites nominations and applications for a tenure track faculty position (open rank, from the Assistant to the Full Professor rank). Applicants are encouraged to submit their application by November 29, 2018 to receive full considerations, but review of applications will continue until the position is filled. More info can be found below or here . Informal inquiries can be addressed to: Dr. Dagmar Sternad, Chair of the Search Committee (d.sternad at northeastern.edu). Apologies for multiple posting. -- Marta Russo, PhD Postdoctoral Research Associate Action Lab Office: 503 Richards Hall Mail: 134 Mugar Life Sciences Building Northeastern University 360 Huntington Avenue Boston, MA 02115 m.russo at northeastern.edu *Faculty Position in Human Movement Science* *Northeastern University, Boston, MA* *Assistant, Associate, or Full Professor* *A tenure-track position is open in Human Movement Sciences in the Department of Biology, College of Science and the Department of Physical Therapy, Movement and Rehabilitation Science, Bouve College of Health Sciences, at Northeastern University.* The position is open for applicants from the Assistant to the Full Professor rank. The candidate?s research can be in the areas of experimental, computational, or clinical human movement, with a possible bridge to prosthetics and robotics. This position is part of a growing university-wide cluster in the science of human movement, spanning research strengths from basic experimental and computational research to rehabilitation science, robotics, and neuroengineering. Priority will be placed on research strengths that complement existing strengths in computational human movement science, rehabilitation science, neurophysiology, neuroimaging, and control theory, although excellence is of top-most priority. Depending on the research profile, an affiliated appointment with Bioengineering or Electrical and Mechanical Engineering is possible. The anticipated start date is Fall Semester, 2019. Responsibilities will include conducting an independent, externally funded research program, teaching undergraduate and graduate courses, and participating in departmental, college and university service. Qualified candidates should have experience in, or be able to demonstrate a commitment to, working with diverse student populations and/or in a culturally diverse work and educational environment. The Department of Biology is strongly interdisciplinary, with 20 tenured and tenure-track faculty in Biology and an additional 9 faculty with joint appointments in other departments. The department administers programs in the College of Science at Northeastern University for 1,200 undergraduates, and 100 students in Ph.D., Masters, and Professional Masters programs. The Department of Physical Therapy, Movement and Rehabilitation Sciences, located within Bouv? College of Health Sciences, is comprised of 10 tenured and tenure track faculty and 20 clinical faculty. The Department offers a Ph.D. program in Human Movement and Rehabilitation Sciences, as well as one of the oldest and largest Doctorate in Physical Therapy (DPT) programs in the country. Grounded in its signature co-op program, Northeastern provides unprecedented global experiential learning opportunities. Northeastern University occupies a vibrant 67-acre campus in the heart of Boston, surrounded by other leading educational, health care, technological, and research institutions, as well as world-renowned venues for art and music. Applicants must have a PhD in the life sciences, including physical medicine and physical therapy, neuroscience, neurophysiology, bioengineering, electrical or mechanical engineering, kinesiology, rehabilitation sciences, or other related disciplines. All applicants should have a strong record of scholarly accomplishment that demonstrate research productivity and the ability to perform cutting edge research. Candidates seeking appointment at the associate or full professor level should have substantial research productivity and a history of grant support and academic service. *Please submit a curriculum vitae, cover letter, a two-page description of research accomplishments and plans, a statement on teaching, and the name and contact information for three references through the application portal* https://neu.peopleadmin.com/postings/57607 . Review of applications will begin immediately and will continue until the position is filled. Applications should be submitted by November 29, 2018 to receive full considerations. Informal inquiries can be addressed to: Dr. Dagmar Sternad, Chair of the Search Committee (d.sternad at northeastern.edu). -- *Rispetta l'ambiente: se non ti ? necessario, non stampare questo messaggio -?**Please consider the environment before printing this email.* -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: OpenRank.Position.Movement Science.Final.pdf Type: application/pdf Size: 103689 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: ATPFile_CE6EEE48-3663-4393-AEBB-9A55F7C1723F.token Type: application/octet-stream Size: 35 bytes Desc: not available URL: From thomas.j.palmeri at vanderbilt.edu Mon Nov 26 11:31:06 2018 From: thomas.j.palmeri at vanderbilt.edu (Palmeri, Thomas J) Date: Mon, 26 Nov 2018 16:31:06 +0000 Subject: Connectionists: Data Science Postdoctoral Fellowships at Vanderbilt University Message-ID: <1EAC99BB-65F5-4A73-B3BE-692DCFD04AEE@vanderbilt.edu> The Data Science Institute (DSI) at Vanderbilt University (https://www.vanderbilt.edu//datascience/) invites applications for its first cohort of DSI postdoctoral fellows. Fellows will be expected to carry out an independent research program in collaboration with one or more faculty mentors who are affiliated with the DSI. Fellows will come from a diverse range of backgrounds and domains, but their work will generally fall into one of three categories: (1) foundational data science, the development of data science methods, (2) the application of data science to one or more fields in the physical, life and social sciences, engineering, or humanities (3) the study of the impact of data on society and its institutions. Fellows will be expected to interact with each other and with students, faculty and researchers affiliated with the DSI, and to contribute to the vibrant culture of the DSI. Fellowship Details Fellowships will begin in the summer of 2019 and will be renewable for up to three years. Fellows will receive annual salary support of $65,000, a competitive benefits package, and an annual research budget of $10,000 that can be used for travel, equipment, software, or other research expenses. Eligibility Candidates should have a PhD or be on track to earn a PhD before they begin their tenure as DSI fellows. Successful candidates will have a strong record in data science related research or a compelling proposal to carry out such research at Vanderbilt. Candidates who propose to engage in interdisciplinary work are especially encouraged to apply. Application Procedure Candidates must identify at least one primary faculty mentor from the list of affiliated DSI faculty (https://www.vanderbilt.edu/datascience/people/affiliates/) and have that mentor submit a letter of support. Preference will be given to candidates who propose to work with two or more faculty from different disciplines. To apply, please submit the following materials to: datascience-jobs at vanderbilt.edu * A brief cover letter that states the overall goals and motivation for applying, as well as the choice of DSI mentors (1 page) * A curriculum vitae (including a list of publications) * A single document containing a brief statement of past research accomplishments (1 page) and a proposal of research to be conducted at the DSI (2 pages) * Three letters of reference submitted directly by the recommenders to datascience-jobs at vanderbilt.edu * A letter of support from the primary DSI mentor submitted directly by the mentor to datascience-jobs at vanderbilt.edu (Please include the applicant?s full name in the subject of all emails.) Evaluation of applications will begin on Jan 15, 2019 and decisions will be made in March, 2019. -------------- next part -------------- An HTML attachment was scrubbed... URL: From bruno.cessac at inria.fr Tue Nov 27 02:39:42 2018 From: bruno.cessac at inria.fr (Bruno Cessac) Date: Tue, 27 Nov 2018 08:39:42 +0100 (CET) Subject: Connectionists: Junior research scientist position at Inria, France Message-ID: <372538038.1211807.1543304382977.JavaMail.zimbra@inria.fr> Junior research scientist position at Inria, France ?? The Biovision team from Inria Sophia Antipolis M?diterran?e invites applications for a junior research scientist position (permanent research position without teaching duty). The goal of the Biovision team is to investigate new solutions to help vision impaired people, through fundamental research as well as innovative technological developments. We strongly encourage highly qualified candidates in the field of computational neuroscience and vision science with a strong interest in low vision. Candidates will have to apply to the Inria's 2019 recruiting campaign starting in February. The application, about 15-20 pages long, includes a summary of past research and future projects, and can be in English. Short-listing decision of candidates is due by end of March 2019. Short-listed candidates will be invited for an oral presentation by beginning of May. Final hiring decisions will be made in June. The candidates are strongly advised to contact *as soon as possible* the faculty members of the group (bruno.cessac at inria.fr and pierre.kornprobst at inria.fr) and to provide a CV, significant published papers and a preliminary research project explaining how you would integrate the team (research goals, PhD supervision, collaborations, fundings). For more information: - Inria: Inria, the French research institute for computer science, promotes scientific excellence and technology transfer to maximise its impact. It employs 2,400 people. Its 200 agile project teams, generally with academic partners, involve more than 3,000 scientists in meeting the challenges of computer science and mathematics, often at the interface of other disciplines. - Biovision: http://www-sop.inria.fr/biovision - Recruiting campaign: https://www.inria.fr/en/institute/recruitment/join-us/working-as-a-researcher-at-inria https://www.inria.fr/en/institute/recruitment/offers/young-graduate-scientist/competitive-selection-crcn -------------- next part -------------- An HTML attachment was scrubbed... URL: From o.e.scharenborg at tudelft.nl Tue Nov 27 03:00:51 2018 From: o.e.scharenborg at tudelft.nl (Odette Scharenborg) Date: Tue, 27 Nov 2018 09:00:51 +0100 Subject: Connectionists: Call for Proposals: ISCA Christian Benoit Award In-Reply-To: <1692979712.14627602.1543240459581.JavaMail.zimbra@grenoble-inp.fr> References: <91b6c012184199acdfe68600c6d5ccc4@ampere-bal-1.ampere.inpg.fr> <7dc5ebac511e464ca0d3abb7203afc42@utdallas.edu> <13f64e5b13344705a7aeec2292a66570@utdallas.edu> <1455021432.4373851.1541610960513.JavaMail.zimbra@grenoble-inp.fr> <5cc4fc1c89844beb9c0f4e843e356e1f@utdallas.edu> <8125747.14477178.1543232003891.JavaMail.zimbra@grenoble-inp.fr> <1692979712.14627602.1543240459581.JavaMail.zimbra@grenoble-inp.fr> Message-ID: Dear colleagues, Please find attached the call for proposals for the Christian Benoit Award. The Christian Beno?t Award is awarded through a competitive nomination and review process to promising young scientists in the domain of SPEECH COMMUNICATION to further their career in the field. The focus of the award?s research topic may emphasize basic science or applied research projects. Award prize: EUR 7500 Deadline of submission: 15 May 2019 Best wishes Odette Scharenborg --- Deze e-mail is gecontroleerd op virussen door AVG. http://www.avg.com -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: CfP_CB_Award10.pdf Type: application/pdf Size: 135327 bytes Desc: not available URL: From juergen at idsia.ch Tue Nov 27 05:42:35 2018 From: juergen at idsia.ch (Schmidhuber Juergen) Date: Tue, 27 Nov 2018 11:42:35 +0100 Subject: Connectionists: [jobs] PostDocs & PhD Students at the Swiss AI Lab, IDSIA In-Reply-To: References: <9667B353-CDB2-44BF-9CEF-ADB78ACAABA4@idsia.ch> <8503A3E7-AC1B-4C66-A720-6A5CBA5CB14E@idsia.ch> Message-ID: We intend to interview prospective PhD students and postdocs on Dec 1-9 at NeurIPS 2018 in Montreal. Please find application instructions under http://people.idsia.ch/~juergen/erc2017.html Also check out 4 presentations at NeurIPS (2 oral) with co-authors now working in my group at IDSIA. NNAISENSE will also present at NeurIPS, and is also hiring: https://nnaisense.com/careers.html J?rgen Schmidhuber Scientific Director, Swiss AI Lab, IDSIA Professor of AI, USI & SUPSI, Switzerland Chief Scientist, NNAISENSE http://people.idsia.ch/~juergen/whatsnew.html . From garrickorchard at gmail.com Tue Nov 27 07:08:37 2018 From: garrickorchard at gmail.com (Garrick Orchard) Date: Tue, 27 Nov 2018 20:08:37 +0800 Subject: Connectionists: Post-doc and Research Assistant positions in Neuromorphic Computing Message-ID: We have several positions available within our lab at National University Singapore for Post-docs and Research Assistants. Please find the advertisement below, or the online version at this link *https://www.garrickorchard.com/hiring * Best, Garrick *Post-doc and Research Assistant openings in Embedded Neuromorphic Computing:* We have several openings available at National University of Singapore within Temasek Labs and the Singapore Institute for Neurotechnology (SINAPSE). The lab focuses on bio-inspired sensing and computation. We leverage exciting technologies including silicon retina sensors and neural processors such as the Spiking Neural Network architecture (SpiNNaker) and IBM's TrueNorth to build bio-inspired embedded sensory systems for autonomous vehicles and remote sensing applications. *Post-Doctoral Research Scientist* Required Qualifications: - Ph.D in Electrical/Computer Engineering, Computer Science or similar - Strong programming skills - Record of publication - Good communication skills and ability to work in a team - Preference will be given to candidates with background in programming, embedded hardware, computer vision, and neuromorphic engineering *Research Assistant* Required Qualifications: - A degree in Electrical/Computer Engineering, Computer Science or similar - Strong programming skills - Good communication skills and ability to work in a team - Preference will be given to candidates with background in programming, embedded hardware, computer vision, and neuromorphic engineering How to apply Interested applicants should contact garrickorchard at gmail.com with a CV for more information regarding the research programs and positions. Positions will remain open until filled. Only shortlisted applicants will be notified. -- Garrick Orchard Senior Research Scientist, National University Singapore, www.garrickorchard.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From gdcc at cin.ufpe.br Tue Nov 27 20:12:54 2018 From: gdcc at cin.ufpe.br (George Darmiton da Cunha Cavalcanti) Date: Tue, 27 Nov 2018 22:12:54 -0300 Subject: Connectionists: CFP: IJCNN 2019 special session on "Ensemble Learning and Applications" Message-ID: ------------------------------------------------------------ --------------------------- CFP: Special Session on "Ensemble Learning and Applications" 2019 International Joint Conference on Neural Networks (IJCNN) July 14-19 2019, Budapest, Hungary https://www.ijcnn.org/ Important Dates: Paper submission: 15 December 2018 Notification of acceptance: 30 January 2019 Aims and Scope: Ensemble Learning (EL) aims at combining multiple classifiers/regressors to increase the precision of a whole system. Ensembles are often much more accurate than the base-classifiers that compose it. EL has been successfully used in a lot of fields covered by the IJCNN conference, such as machine learning, data mining, pattern recognition, bioinformatics, and collective intelligence. This special session aims to bring together the current research progress on Ensemble Learning theories and their Applications. Original contributions are welcome, covering the whole range of theoretical and practical aspects, technologies and systems for Ensemble Learning. The main topics of this special session include, but are not limited to, the following: - Ensemble Learning - Multiple Classifier/Regressor Systems - Dynamic Classifier/Regressor Selection - Dynamic Ensemble Selection - Ensemble of One-class classification - Ensemble and Semi-supervised learning - Applications that combine multiple classifiers/regressors Submission: - For paper guidelines please visit https://www.ijcnn.org/paper-submission-guidelines - For submissions please select the single topic "S19. Ensemble Learning and Applications" from the "S. SPECIAL SESSIONS" category as the main research topic on https://ieee-cis.org/conferences/ijcnn2019/upload.php Organizers: - Prof. George Darmiton da Cunha Cavalcanti, UFPE, Recife, Brazil (gdcc at cin.ufpe.br) - Prof. Laurent Heutte, NormaSTIC/LITIS, Universit? de Rouen, France (laurent.heutte at univ-rouen.fr) - Prof. Alceu S. Britto Jr, PUCPR, Curitiba, Brazil (alceu at ppgia.pucpr.br) ------------------------------------------------------------ --------------------------- -- George Darmiton da Cunha Cavalcanti, Dr Associate Professor, CIn-UFPE cin.ufpe.br/~gdcc -------------- next part -------------- An HTML attachment was scrubbed... URL: From borisyuk at math.utah.edu Tue Nov 27 18:17:26 2018 From: borisyuk at math.utah.edu (Alla Borisyuk) Date: Tue, 27 Nov 2018 16:17:26 -0700 Subject: Connectionists: Tenure-track position, computational neuroscience In-Reply-To: References: Message-ID: Applications are being considered for a computational neuroscience tenure-track position in the University of Utah. Interested candidates should apply as soon as possible. The proposed position is part of a cluster that comprises multiple tenure-track faculty positions; departmental appointments may be in Physics, Biology, Chemistry, Mathematics or Biochemistry. Ideal candidates would have a demonstrated interdisciplinary experience - for example, have a degree in Math and active collaborations, grants and publications with experimentalists. For formal description of the position and to apply, please see: https://utah.peopleadmin.com/postings/81886 With questions, please contact Alla Borisyuk at borisyuk at math.utah.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From hausser at gmail.com Wed Nov 28 04:03:06 2018 From: hausser at gmail.com (Michael Hausser) Date: Wed, 28 Nov 2018 09:03:06 +0000 Subject: Connectionists: International Brain Laboratory postdoctoral position at UCL Message-ID: We are seeking a highly motivated postdoctoral fellow to join the International Brain Laboratory in order to probe the links between activity in neural circuits and behaviour. The project will be co-supervised by Michael Hausser and Matteo Carandini, and involves using ?Neuropixels? probes (http://www.ucl.ac.uk/neuropixels) to make massively parallel recordings from large populations of neurons in the brains of awake behaving mice. The successful applicant will join a thriving international collaboration ( http://www.internationalbrainlab.com) which aims to understand the neural circuit basis of decisionmaking in the mouse. Neuropixels recordings will be integrated with other techniques such as two-photon microscopy, two-photon optogenetics, and behavioral paradigms in virtual reality. The post will be based at UCL, but opportunities exist for collaborations with experimental and theoretical colleagues across the 21 labs in 6 countries which comprise the International Brain Laboratory. The successful candidate will be expected to take a leading role in all aspects of the project, from designing and performing experiments, developing technical advances, performing data analysis and presenting the results. The post is funded for 2 years in the first instance and is available immediately. You should apply for this post (Ref #: 1767183) through UCL's online recruitment website, www.ucl.ac.uk/hr/jobs. Closing date for applications is *Monday 3 December 2018.* For informal inquiries please contact Michael Hausser (m.hausser at ucl.ac.uk) or Matteo Carandini (m.carandini at ucl.ac.uk). ---------------------------------------------------------- Michael Hausser Wolfson Institute for Biomedical Research University College London Gower Street London WC1E 6BT UK tel +44-20-7679-6756 email m.hausser at ucl.ac.uk http://www.dendrites.org/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.hennig at ed.ac.uk Wed Nov 28 10:26:32 2018 From: m.hennig at ed.ac.uk (Matthias Hennig) Date: Wed, 28 Nov 2018 15:26:32 +0000 Subject: Connectionists: Faculty position in Computational Neuroscience and AI at the University of Edinburgh Message-ID: The Institute for Adaptive and Neural Computation at the University of Edinburgh is inviting applications for a Lecturer/Senior Lecturer/Reader (Assistant/Associate professor) position in Computational Neuroscience and Artificial Intelligence. This position is part of an expansion of research and teaching in cognition, neuroscience, and AI. Candidates should have inter-disciplinary research interests, combining computational and machine learning based methods and cognitive science, and be able to teach undergraduate and master?s level courses in areas such as AI and machine learning, in addition to teaching in cognitive science. The closing date is 15. Jan 2019. For further details and to apply, go to: https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=046052 Edinburgh is also recruiting faculty in Computational Cognitive Science: https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=046051 -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From Jakob.Macke at caesar.de Wed Nov 28 10:42:07 2018 From: Jakob.Macke at caesar.de (Jakob Macke) Date: Wed, 28 Nov 2018 15:42:07 +0000 Subject: Connectionists: Wanted: Postdoc for joint project on bio-inspired control and ML (EPFL/TUM) Message-ID: <3AA1AA2B-27D4-4312-AB50-CB35CFE81C9D@caesar.de> Dear colleagues, Pavan Ramdya?s Laboratory of Neuroengineering (EPFL, Lausanne, Switzerland) and Jakob Macke?s Computational Neuroengineering Group (TU Munich, Germany) invite applicants for a joint Postdoctoral position in bioinspired control and machine learning. We will ideally support the candidate in an application through he Eurotech Postdoc initiative (http://postdoc.eurotech-universities.eu, proposal deadline 28.02.2019), but alternative funding sources are available. The Postdoctoral Fellow will explore deep networks and bioinspired neural network controllers to actuate an in silico model of Drosophila melanogaster. These investigations will inform and be performed in dialogue with colleagues performing in vivo functional imaging experiments and quantitative behaviour in tethered, behaving flies. They will enjoy a competitive salary, benefits, and a high quality of life in either the French-speaking part of Switzerland (Lausanne) or in Munich, but in an English-speaking setting. They will be expected to have a PhD providing them with experience in computational neuroscience, machine learning, or a related discipline. Female applicants are strongly encouraged to apply. Interested Postdoctoral applicants should contact Pavan Ramdya (pavan.ramdya at epfl.ch) or Jakob Macke (macke at tum.de) with their CV, an informal Statement of Interest, and the contact information for 3 Reference Letter Providers as soon as possible. Further information about our research can be found at https://ramdya-lab.epfl.ch/ (Pamdya), http:www.ei.tum.de/cne and www.mackelab.org (Macke). Best, Jakob Macke ? Prof. Dr. rer. nat. Jakob Macke Technical University of Munich Department of Electrical and Computer Engineering Professorship for Computational Neuroengineering www.ei.tum.de/cne, www.mackelab.org macke at tum.de +49 89 289 26902 Office: Alexandra Petelski Alexandra.Petelski at tum.de Tel.: +49 (0)89 - 289 26900 Fax: +49 (0)89 - 289 26901 -------------- next part -------------- An HTML attachment was scrubbed... URL: From m.a.wiering at rug.nl Wed Nov 28 10:24:47 2018 From: m.a.wiering at rug.nl (Wiering, M.A.) Date: Wed, 28 Nov 2018 16:24:47 +0100 Subject: Connectionists: Call for Papers: Special Session on Multimodal and Lifelong Learning at ICAART Message-ID: Dear colleagues, Hereby you are invited to submit a paper to a special session on Multimodal and Lifelong Learning (MALM) organized at ICAART 2019 in Prague, see: http://www.icaart.org/MALM.aspx Modern machine learning has proven to be very successful in unimodal applications (image OR text OR sound). Furthermore, the successes are usually based on idealized training conditions with nicely packaged benchmark tests. The reality of historical-document retrieval is quite different. Optical character recognition is too limited to handle the variety of visual patterns in such image collections: text, graphics, tabular structures, doodles and diverse image problems make this a challenging playing field. Such systems start with zero labels, the labels change over time and the data is neither stationary nor ergodic. This session is intended for researchers who have picked up challenges in multimodal machine learning, possibly even in a time-varying context. Topics: - Multimodal Deep Learning - Image and Text Correspondence - Data-driven Semantics - Deep Multimodal Semantic Embeddings - Historical Documents - Interactive Data Mining Organizers: Prof. dr. Lambert Schomaker, University of Groningen Dr. Marco Wiering, University of Groningen IMPORTANT DATES Paper Submission: December 20, 2018 Authors Notification: January 7, 2019 Camera Ready and Registration: January 15, 2019 Conference: February 19-21, 2019 Submitted papers should be between 6 and 12 pages long. Please note that a double-blind reviewing system is used. For more information about paper guidelines, please see: http://www.icaart.org/CallForPapers.aspx -------------- next part -------------- An HTML attachment was scrubbed... URL: From fateme.khatami at gmail.com Wed Nov 28 15:12:51 2018 From: fateme.khatami at gmail.com (Fateme Khatami) Date: Wed, 28 Nov 2018 12:12:51 -0800 Subject: Connectionists: New publication at Pols Computational Biology: Origins of scale invariance in vocalization sequences and speech Message-ID: Dear Colleagues, We would like to introduce you to the recent publication on *Origins of scale invariance in vocalization sequences and speech*, published at Plos Computational Biology.Please find the article in below links. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5919684/ https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005996 Best Regards, -- Fatemeh Khatami -- Fatemeh Khatami -------------- next part -------------- An HTML attachment was scrubbed... URL: From leila.kosseim at concordia.ca Wed Nov 28 19:06:42 2018 From: leila.kosseim at concordia.ca (Leila Kosseim) Date: Wed, 28 Nov 2018 19:06:42 -0500 Subject: Connectionists: Endowed Chair in Artificial Intelligence, Concordia University, Montreal Message-ID: <72fc4fed-86f1-a4c7-a195-28459029d2e9@concordia.ca> ** Apologies for cross-posting** Gina Cody Research Chair in Artificial Intelligence The Department of Computer Science and Software Engineering at Concordia University, in Montreal, seeks an outstanding candidate for the Gina Cody Research Chair in Artificial Intelligence at the rank of Associate or Full Professor. The five year research chair is renewable and comes with an attractive research package. The ideal candidate is an internationally recognized researcher with an exceptional scholarly record, and has proven leadership qualities, and the ability to collaborate with industry. She/he is expected to demonstrate a commitment to the supervision of Masters and PhD students and attract strong external funding. Areas of expertise include, but are not limited to: fundamental research in machine learning or deep learning, and applications to areas such as natural language processing, computer vision, robotics, and medical imaging. The successful candidate will assume a leadership role in artificial intelligence in the department and have rich opportunities for intellectual interaction and collaboration with other leading researchers and in industry. Membership or eligibility for membership in a Canadian professional engineering association as well as knowledge of French would be considered assets. Ranked among the top ten engineering schools in Canada, the Gina Cody School of Engineering and Computer Science is home to over 10,000 engineering and computer science students and a faculty complement of 230 professors. The Gina Cody School of Engineering and Computer Science has about 4,500 graduate students enrolled in 35 graduate programs. The School?s research profile continues to grow as it fosters multidisciplinary approaches to finding solutions to a broad range of societal challenges. For more information on the School, please visit:concordia.ca/ginacody The Department of Computer Science and Software Engineering has over 45 faculty members, working in varied fields in computer science and software engineering, including several strong researchers in Artificial Intelligence and has seen a major expansion in recent years. The Department is dedicated to multidisciplinary research and training of undergraduate and graduate students, offering undergraduate and graduate degrees in Computer Science and in Software Engineering. Montreal has emerged as a global hub in artificial intelligence, and is synergistically benefitting from a number of university researchers and research institutes collaborating with established companies as well as startups on the next breakthrough discoveries. More information about the department is available at:concordia.ca/csse Applications must include a cover letter, detailed curriculum vitae, teaching and research statements, and names of four referees. Electronic applications should be submitted by January 15th 2019 (revised deadline) and will be reviewed on an ongoing basis until a suitable candidate has been identified. Only short-listed applicants are notified. The appointment is expected to commence in July 2019 or shortly thereafter. Kindly forward your electronic applications to:AI-hiring at cse.concordia.ca For more information:https://www.concordia.ca/ginacody/about/jobs/csse/artificial-intelligence.html -- Leila Kosseim Professor Computer Science & Software Engineering Concordia University CAIAC Executive - Vice President -------------- next part -------------- An HTML attachment was scrubbed... URL: From shobeir at gmail.com Thu Nov 29 01:25:30 2018 From: shobeir at gmail.com (Shobeir Fakhraei) Date: Wed, 28 Nov 2018 22:25:30 -0800 Subject: Connectionists: CFP: Machine Learning with Graphs (Applied Network Science Journal Special Issue) Message-ID: Call for Papers: Applied Network Science Special Issue on Machine Learning with Graphs https://appliednetsci.springeropen.com/cfp-mlgraphs Data that are best represented as a graph such as social, biological, communication, or transportation networks, and energy grids are ubiquitous in our world today. As more of such structured and semi-structured data is becoming available, the machine learning methods that can leverage the signal in these data are becoming more valuable, and the importance of being able to effectively mine and learn from such data is growing. These graphs are typically multi-relational, dynamic, and large-scale. Understanding the different techniques applicable to graph data, dealing with their heterogeneity and applications of methods for information integration and alignment, handling dynamic and changing graphs, and addressing each of these issues at scale are some of the challenges in developing machine learning methods for graph data that appear in a variety of applications. In this special issue, we aim to publish articles that help us better understand the principles, limitations, and applications of current graph-based machine learning methods, and to inspire research on new algorithms, techniques, and domain analysis for machine learning with graphs. We encourage submissions on theory, methods, and applications focusing on a broad range of graph-based machine learning approaches in various domains. Topics of interest include but are not limited to theoretical aspects, algorithms, and methods such as: - Learning and mining algorithms - Graph mining approaches - Link and relationship strength prediction - Learning to rank in networks - Similarity measures and graph kernel methods - Graph alignment, matching, and identification - Network summarization and compression - Learning from partially-observed networks - Semi-supervised learning, active learning, transductive inference, and transfer learning in the context of graphs - Large-scale analysis and models for graph data - Evaluation issues in graph-based algorithms - Anomaly detection with graph data - Embeddings and factorization methods - Network embedding methods and manifold learning - Matrix and tensor factorization methods - Deep learning on graphs - Learning with dynamic and complex networks - Models to learn from dynamic graph data - Heterogeneous, signed, attributed, and multi-relational graph mining methods - Online learning with graphs - Statistical and probabilistic methods - Computational or statistical learning theory related to graphs - Statistical models of graph structures - Probabilistic and graphical models for structured data - Statistical relational learning - Sampling graph data - Theory - Theoretical analysis of graph-based machine learning algorithms or models - Combinatorial graph methods We also encourage submissions focused on machine learning applications that use graph data. Such applications include, but are not limited to: - Biomedicine and medical networks - Social network analysis - The World Wide Web - Neuroscience and neural networks - Transportation systems and physical infrastructure - Knowledge graphs - Recommender systems Survey and review papers as well as submissions that are significant extension (more than 30%) of previously published work are welcome. Important Dates - Abstract submission: Dec 20, 2018 - Abstract feedback notification: Jan 10, 2019 - Paper submission deadline: Mar 1, 2019 - Target publication: Jul 30, 2019 We encourage to submit the papers prior to these deadlines. Papers will be subject to a fast track review procedure that will start as soon as they are submitted, and are published upon acceptance, regardless of the special Issue publication date. Guest Editors Austin Benson, Computer Science Department, Cornell University, arb at cs.cornell.edu Ciro Cattuto, ISI Foundation, ciro.cattuto at isi.it Shobeir Fakhraei, Information Sciences Institute, Univ. of Southern California, fakhraei at usc.edu Danai Koutra, Computer Science & Engineering, University of Michigan, dkoutra at umich.edu Vagelis Papalexakis, Computer Science & Engineering, UC Riverside, epapalex at cs.ucr.edu Jiliang Tang, Computer Science & Engineering Dept., Michigan State Univ., tangjili at msu.edu For more information, please direct your questions to the Lead Guest Editor: Shobeir Fakhraei fakhraei at usc.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From barros at informatik.uni-hamburg.de Thu Nov 29 05:00:25 2018 From: barros at informatik.uni-hamburg.de (Pablo Barros) Date: Thu, 29 Nov 2018 11:00:25 +0100 Subject: Connectionists: CFP Frontiers Research Topic: Closing the Loop: From Human Behavior to Multisensory Robots Message-ID: Call For Papers - Frontiers Research Topic: Closing the Loop: From Human Behavior to Multisensory Robots I. Aim and Scope The ability to efficiently process crossmodal information is a key feature of the human brain that provides a robust perceptual experience and behavioral responses. Consequently, the processing and integration of multisensory information streams such as vision, audio, haptics, and proprioception play a crucial role in the development of autonomous agents and cognitive robots, yielding an efficient interaction with the environment also under conditions of sensory uncertainty. This Research Topic invites authors to submit new findings, theories, systems, and trends in multisensory learning for intelligent agents and robots with the aim to foster the development of novel and impactful research which will contribute to the understanding of human behavior and the development of artificial systems operating in real-world environments. II. Potential Topics Topics include, but are not limited to: - New methods and applications for crossmodal processing and multisensory integration (e.g. vision, audio, haptics, proprioception) - Machine learning and neural networks for multisensory robot perception - Computational models of crossmodal attention and perception - Bio-inspired approaches for crossmodal learning - Multisensory conflict resolution and executive control - Sensorimotor learning for autonomous agents and robots - Crossmodal learning for embodied and cognitive robots III. Submission - Abstract - 18th January 2019 - Paper Submission - 12th May 2019 More information: https://www.frontiersin.org/research-topics/9321/closing-the-loop-from-human-behavior-to-multisensory-robots IV. Guest Editors Pablo Barros, University of Hamburg, Germany Doreen Jirak, Hamburg University, Germany German I. Parisi, Apprente, Inc., USA Jun Tani, Okinawa Institute of Science and Technology, Japan -- 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 eneftci at uci.edu Thu Nov 29 12:40:09 2018 From: eneftci at uci.edu (Emre Neftci) Date: Thu, 29 Nov 2018 09:40:09 -0800 Subject: Connectionists: Call for Telluride Neuromorphic Cognition Engineering Workshop Topic Area Proposal Deadline Jan 4, 2019 Message-ID: <1543513209.2481288.1593380440.2891984F@webmail.messagingengine.com> Dear all, We are now accepting proposals for Topic Areas in the 2019 Telluride Neuromorphic Cognition Engineering Workshop. The workshop has been running successfully for over 20 years, and has been influential in shaping the field of neuromorphic engineering and serving as a forum connecting across disciplines such as neuroscience, cognitive science, machine learning, robotics, computer vision, signal processing, and electrical engineering. The 2019 theme for the workshop is Embodied Learning and Intelligence. Deadline for proposals is Jan 4, 2019. See further details here: https://sites.google.com/view/telluride2019/apply/topic-area-proposals We look forward to your proposals. Regards, The 2019 Telluride Workshop Organizing Team https://sites.google.com/view/telluride2019/organizers -- workshop website: https://sites.google.com/view/telluride2019 --- ----- Emre Neftci, PhD, Assistant Professor, Neuromorphic Machine Intelligence Lab (http://nmi-lab.org/), Department of Cognitive Sciences, Department of Computer Sciences, 2308 Social & Behavioral Sciences Gateway Building, UC Irvine 92697-5100 From m.plumbley at surrey.ac.uk Fri Nov 30 07:54:54 2018 From: m.plumbley at surrey.ac.uk (m.plumbley at surrey.ac.uk) Date: Fri, 30 Nov 2018 12:54:54 +0000 Subject: Connectionists: Deadline Approaching [Mon 3 Dec]: PhD Studentships for Machine Audition at University of Surrey Message-ID: Dear Connectionists, The studentships below may be of interest to people interested in machine learning applied to audio. Best wishes, Mark ---- PhD Studentships for Machine Audition at University of Surrey ** Deadline approaching to apply for PhD programme (Stage 1): 12:00 noon GMT Monday 3 December 2018 ** The University of Surrey currently has opportunities for Vice-Chancellor's Studentships and Doctoral College Studentships, suitable to support PhD study in Machine Audition in the Centre for Vision, Speech and Signal Processing (CVSSP). Note: this is a 2-stage process. To be eligible for these studentships, you must FIRST apply for a place on a PhD programme by 12:00 midday GMT, Monday 3 December 2018 (Stage 1). You then apply for the Studentship Award itself by 11 January 2019 (Stage 2). ** Research in Machine Audition at the University of Surrey In the A-Lab in the Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey, we undertake research into technologies for sound-related machine perception, augmentation and reproduction of sound scenes. Our current activities include research into spatial audio production and reproduction; audio source separation, localisation and tracking; detection and classification of audio scenes and events; and audio-visual speech processing. Other areas for future research will include areas such as object-based audio; analysis of large-scale datasets; and audio-visual sensing, combining audio and visual perception. For more details about staff interests in Machine Audition, see individual pages at: * Dr Philip Jackson https://www.surrey.ac.uk/people/philip-jackson * Prof Mark Plumbley https://www.surrey.ac.uk/people/mark-plumbley * Dr Wenwu Wang https://www.surrey.ac.uk/people/wenwu-wang Deadline to submit an application for a place on a postgraduate research course is 12:00 GMT on Monday 3 December 2018. ** How to apply for these PhD Studentships (1) Find out more about Machine Audition and the A-Lab at https://www.surrey.ac.uk/centre-vision-speech-signal-processing/research/a-lab-machine-audition, and PhD study in CVSSP at https://www.surrey.ac.uk/centre-vision-speech-signal-processing/phd-study (2) Apply for "Vision, Speech and Signal Processing PhD" at https://www.surrey.ac.uk/postgraduate/vision-speech-and-signal-processing-phd [By 12:00 noon GMT Monday 3 December 2018] On your application, indicate that you are applying for the Vice-Chancellor's Studentship Award (international students) or the Doctoral College Studentship Award (DCSA3) (UK and European students). ** IMPORTANT: To be eligible for a Vice-Chancellor's Studentship or Doctoral College Studentship, you MUST submit your application to the PhD programme by 12:00 noon GMT Monday 3 December 2018. (If you are not able to include all documents requested, submit your application with what documentation you have. Any applications submitted after 12:00 noon GMT Monday 3 December 2018 will not be eligible to apply for the studentships at Stage 2.) (3) Complete the application for Vice-Chancellor's Studentship Award or Doctoral College Studentship Award [by 12:00 noon GMT Friday 11 January 2019] For more information about the studentships see: * Vice-Chancellor's Studentship Award (for international students): https://www.surrey.ac.uk/fees-and-funding/studentships/vice-chancellors-studentship-award-2019-entry * Doctoral College Studentship Award (for UK and European students): https://www.surrey.ac.uk/fees-and-funding/studentships/doctoral-college-studentship-award-2019-entry -- Prof Mark D Plumbley Professor of Signal Processing Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, Guildford, Surrey, GU2 7XH, UK Email: m.plumbley at surrey.ac.uk From diego.perez at qmul.ac.uk Fri Nov 30 07:16:18 2018 From: diego.perez at qmul.ac.uk (Diego Perez Liebana) Date: Fri, 30 Nov 2018 12:16:18 +0000 Subject: Connectionists: Fully-funded PhD studentships in Intelligent Games and Game Intelligence (IGGI) Message-ID: EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI) Up to 12 fully-funded PhD studentships to start September 2019 Covers fees at Home/EU rate and a stipend for four years IGGI is an exciting opportunity for you to undertake a four-year PhD in Intelligent Games and Game Intelligence, working with top games companies and world-leading academics in games research. We currently have 60 students conducting interdisciplinary research in areas such as: ? Artificial Intelligence (AI) and Machine Learning (ML) to create interesting, fun, believable game agents, ? interaction and user experience design for games, ? ML and data science to understand player behaviour and psychology, ? using games for learning and wellbeing, ? game audio, graphics and animation ? games with a purpose/games for good: citizen science and gamification, ? computational creativity: procedural content generation for audio, graphics, gameplay, ?, ? emotion and immersion in games, ? AI-assisted game design and testing. IGGI is a collaboration between the University of York and Queen Mary, University of London. The programme trains PhD researchers who will become the next generation of leaders in research, design, development and entrepreneurship in digital games. We have a diverse group of students and encourage diverse applicants. We are awaiting a final funding decision (expected December 2018), which will give us 12 studentships available for 2019/20 entry (starting September 2019), which will fund full fees (at a Home/ EU rate) plus a tax-free living stipend, for a 4-year PhD programme. Could you join our large and growing group of games researchers in the world?s largest games research programme? Why IGGI? IGGI gives you the opportunity to work with our industry partners, allowing you the possibility to contribute directly to the future of games. You will have the opportunity to undertake industrial placements during the IGGI programme, giving you first-hand experience of the games industry. These placements will contribute to your research, ensuring its relevance, as well as giving you the skills needed to succeed in a career in the games industry or games research. Our students have completed, or are currently on, placements with partner companies such as Sony Interactive Entertainment, Bossa Studios, Google, Bloomberg, PROWLER.io, Media Molecule, BT, Splash Damage, and MindArk. Other partners include organisations such as Electronic Arts, Creative Assembly, Rebellion, Revolution, AI Factory and over 50 games companies and organisations which use games in creative ways (see http://www.iggi.org.uk/industry-partners/) Your research work with partners like these will advance the creation of more fun and profitable games that exploit research advances, and help to increase the use of games as tools for research in behavioural science and for societal benefit. You?ll also learn through teamwork and inspiring events such as: ? the IGGI Game Jam, a 48 hour game development challenge as part of the Global Game Jam, enhancing your skills in game design, development, and teamwork; ? the IGGI Conference, showcasing student research alongside industry and academic speakers; ? student-led events such as the IGGI Game Creator?s Club, research seminars, games evenings. You?ll receive focused skills training from a range of academic research leaders, covering topics including Games Development, Games Design and Research Skills as well as a range of optional topics in areas such as AI, HCI, graphics, audio and design. Apply for IGGI If funded, we will have 12 studentships to award to outstanding students which cover fees and an annual tax-free stipend of ?14,777 (plus London weighting if studying at Queen Mary) for four years (at 2018/19 rates - this is likely to increase for September 2019 starters). Even if not funded we will have more than four standard PhD studentships, though we are hopeful following positive reviews and a positive final interview. An IGGI application should consist of your statement of planned research, proposed supervisor(s), your CV and a covering letter explaining your motivation and suitability for the IGGI programme. You will also be asked for evidence of your programming skills during the application process, either through your qualifications, previous employment or examples of games you have developed. You can contact potential supervisors directly (see http://www.iggi.org.uk/supervisors/ for a list), or contact us at the email address below and we can help you to choose a principal supervisor from York or Queen Mary based on your interests and background. IGGI students are a diverse group, and admission judgements are made exclusively on the basis of experience and potential to do excellent research and contribute to IGGI?s goals. We especially welcome applications from female and minority ethnic candidates as well as other groups that are under-represented in areas related to IGGI. We expect substantial competition for IGGI studentships and we encourage good students to submit applications as early as possible. The deadline for applications is 23:59 (GMT) on Thursday 31st January 2019. Interviews will take place at Queen Mary University of London on Friday 15th March 2019. Please email your CV, covering letter, supervisor information and statement of planned research to apply at iggi.org.uk. Enquiries should be sent to the same email address. The deadline for applications is 31st January 2019, but we strongly encourage you to get in touch with potential supervisors before then in order to craft the best possible application. --- Diego P?rez Li?bana Lecturer in Computer Games and Artificial Intelligence School of Electronic Engineering and Computer Science Queen Mary University of London (UK) email: diego.perez at qmul.ac.uk web: http://www.diego-perez.net -------------- next part -------------- An HTML attachment was scrubbed... URL: From dwang at cse.ohio-state.edu Fri Nov 30 16:42:03 2018 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Fri, 30 Nov 2018 16:42:03 -0500 Subject: Connectionists: NEURAL NETWORKS, Dec. 2018 Message-ID: <0dee20e3-6d01-0414-8f29-4998ec0ad440@cse.ohio-state.edu> Neural Networks - Volume 108, December 2018 http://www.journals.elsevier.com/neural-networks Evolving Spiking Neural Networks for online learning over drifting data streams Jesus L. Lobo, Ibai Lana, Javier Del Ser, Miren Nekane Bilbao, Nikola Kasabov State representation learning for control: An overview Timothee Lesort, Natalia Diaz-Rodriguez, Jean-Frano?is Goudou, David Filliat Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks Andrea Soltoggio, Kenneth O. Stanley, Sebastian Risi Soft + Hardwired attention: An LSTM framework for human trajectory prediction and abnormal event detection Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes Estimation of neural connections from partially observed neural spikes Taishi Iwasaki, Hideitsu Hino, Masami Tatsuno, Shotaro Akaho, Noboru Murata A video-driven model of response statistics in the primate middle temporal area Omid Rezai, Pinar Boyraz Jentsch, Bryan Tripp Fuzzy c-means-based architecture reduction of a probabilistic neural network Maciej Kusy Design of deep echo state networks Claudio Gallicchio, Alessio Micheli, Luca Pedrelli Low-rank representation with adaptive graph regularization Jie Wen, Xiaozhao Fang, Yong Xu, Chunwei Tian, Lunke Fei A model of operant learning based on chaotically varying synaptic strength Tianqi Wei, Barbara Webb Adaptive non-negative projective semi-supervised learning for inductive classification Zhao Zhang, Lei Jia, Mingbo Zhao, Qiaolin Ye, ... Meng Wang Multi-view clustering on unmapped data via constrained non-negative matrix factorization Linlin Zong, Xianchao Zhang, Xinyue Liu Low-rank and sparse embedding for dimensionality reduction Na Han, Jigang Wu, Yingyi Liang, Xiaozhao Fang, ... Shaohua Teng Sign backpropagation: An on-chip learning algorithm for analog RRAM neuromorphic computing systems Qingtian Zhang, Huaqiang Wu, Peng Yao, Wenqiang Zhang, ... He Qian Distant supervision for relation extraction with hierarchical selective attention Peng Zhou, Jiaming Xu, Zhenyu Qi, Hongyun Bao, ... Bo Xu Trainable spectral difference learning with spatial starting for hyperspectral image denoising Weiying Xie, Yunsong Li, Jing Hu, Duan-Yu Chen Transfer collaborative filtering from multiple sources via consensus regularization Fuzhen Zhuang, Jing Zheng, Jingwu Chen, Xiangliang Zhang, ... Qing He A novel training method to preserve generalization of RBPNN classifiers applied to ECG signals diagnosis Francesco Beritelli, Giacomo Capizzi, Grazia Lo Sciuto, Christian Napoli, Marcin Wozniak An improved robust heteroscedastic probabilistic neural network based trust prediction approach for cloud service selection Nivethitha Somu, Gauthama Raman M.R., Kalpana V., Kannan Kirthivasan, Shankar Sriram V.S. The impact of encoding-decoding schemes and weight normalization in spiking neural networks Zhengzhong Liang, David Schwartz, Gregory Ditzler, O. Ozan Koyluoglu LCD: A Fast Contrastive Divergence Based Algorithm for Restricted Boltzmann Machine Lin Ning, Randall Pittman, Xipeng Shen Cost-sensitive multi-label learning with positive and negative label pairwise correlations Guoqiang Wu, Yingjie Tian, Dalian Liu Estimation theory and Neural Networks revisited: REKF and RSVSF as optimization techniques for Deep-Learning Mahmoud Ismail, Mina Attari, Saeid Habibi, Samir Ziada DGCNN: A convolutional neural network over large-scale labeled graphs Anh Viet Phan, Minh Le Nguyen, Yen Lam Hoang Nguyen, Lam Thu Bui EEG dipole source localization with information criteria for multiple particle filters Sho Sonoda, Keita Nakamura, Yuki Kaneda, Hideitsu Hino, ... Masahiro Kawasaki Bipartite synchronization in coupled delayed neural networks under pinning control Fang Liu, Qiang Song, Guanghui Wen, Jinde Cao, Xinsong Yang Exponential consensus of discrete-time non-linear multi-agent systems via relative state-dependent impulsive protocols Yiyan Han, Chuandong Li, Zhigang Zeng, Hongfei Li The Vapnik-Chervonenkis dimension of graph and recursive neural networks Franco Scarselli, Ah Chung Tsoi, Markus Hagenbuchner Global exponential synchronization of multiple coupled inertial memristive neural networks with time-varying delay via nonlinear coupling Zhenyuan Guo, Shuqing Gong, Shaofu Yang, Tingwen Huang Optimal approximation of piecewise smooth functions using deep ReLU neural networks Philipp Petersen, Felix Voigtlaender Protocol-based state estimation for delayed Markovian jumping neural networks Jiahui Li, Hongli Dong, Zidong Wang, Weidong Zhang UKF-based remote state estimation for discrete artificial neural networks with communication bandwidth constraints Yang Liu, Zidong Wang, Donghua Zhou An improved stability result for delayed Takagi-Sugeno fuzzy Cohen-Grossberg neural networks Zeynep Orman Multiple Mittag-Leffler stability of fractional-order competitive neural networks with Gaussian activation functions Pingping Liu, Xiaobing Nie, Jinling Liang, Jinde Cao Learning in the machine: Recirculation is random backpropagation P. Baldi, P. Sadowski Echo state networks are universal Lyudmila Grigoryeva, Juan-Pablo Ortega Reachable set estimation for Markovian jump neural networks with time-varying delay Wen-Juan Lin, Yong He, Min Wu, Qingping Liu Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning Andres Schmidt, Whitney Creason, Beverly E. Law Monostable multivibrators as novel artificial neurons Lars Keuninckx, Jan Danckaert, Guy Van der Sande