- Comp-neuro - lists.cnsorg.org

PhD positions in Lifelong Reinforcement Learning at Loughborough University

by Andrea Soltoggio

Dear all, I am currently considering applications for fully funded PhD positions in Lifelong Machine (Reinforcement) Learning. The projects aim to advance SoTA lifelong learning AI algorithms towards better knowledge reuse, composability, scalability and transparency. Application areas include Robotics, Cybersecurity and medical data. Some specific projects with application links (more to come soon): * Lifelong Learning for cybersecurity systems: https://www.lboro.ac.uk/departments/compsci/research-degrees/darktrace-stud… * Lifelong machine learning for medical data and personalised medicine https://www.lboro.ac.uk/study/postgraduate/research-degrees/phd-opportuniti… The following recent papers can be helpful to get an overview of our research focus: * Ben-Iwhiwhu, E., Nath, S., Pilly, P. K., Kolouri, S., & Soltoggio, A. (2023). Lifelong reinforcement learning with modulating masks. Transactions on Machine Learning Research https://openreview.net/pdf?id=V7tahqGrOq * Nath, S., Peridis, C., Ben-Iwhiwhu, E., Liu, X., Dora, S., Liu, C., Kolouri, S. and Soltoggio, A., (2023). Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks. Second Conference on Lifelong Learning Agents (CoLLAs) https://arxiv.org/abs/2305.10997 * Ben-Iwhiwhu, E., Dick, J., Ketz, N. A., Pilly, P. K., & Soltoggio, A. (2022). Context meta-reinforcement learning via neuromodulation. Neural Networks, 152, 70-79. https://www.sciencedirect.com/science/article/pii/S0893608022001368 * Kudithipudi, Dhireesha, et al. (2022). Biological underpinnings for lifelong learning machines. Nature Machine Intelligence 4.3 (2022): 196-210. The positions will be at Loughborough, UK. Loughborough University is renowned for its strong emphasis on practical innovation and industry collaboration. In REF 2021, 94% of the work submitted was judged to be top-rated as 'world-leading' or 'internationally excellent'. The Computer Science Department has a growing research team dedicated to various AI themes and robotics, as well as theoretical Computer Science, cybersecurity and networks. The student will have access to state-of-the-art machine learning servers equipped with A100 GPUs and connected to the Loughborough University high-speed network facilities. Opportunities for exchanges and short visits to world-leading AI laboratories within our extensive collaboration network will be encouraged. The collaborative environment ensures exposure to diverse perspectives and facilitates knowledge exchange. Interested candidates are invited to contact me for further information at a.soltoggio(a)lboro.ac.uk<mailto:a.soltoggio@lboro.ac.uk> Best regards, Andrea -- Dr. Andrea Soltoggio (he/him or they/them) Senior Lecturer (Associate Professor) in Artificial Intelligence Department of Computer Science, School of Science & Intelligent Automation Centre https://www.intelligent-automation.org.uk/about-us/centre-staff & Centre for Information Management https://www.lboro.ac.uk/departments/sbe/cim/ Haslegrave Building, N.2.03 Loughborough University LE11 3TU, UK Email: a.soltoggio(a)lboro.ac.uk<mailto:a.soltoggio@lboro.ac.uk> Web: http://www.lboro.ac.uk/departments/compsci/staff/dr-andrea-soltoggio.html

Jan. 8, 2024

Three fully funded PhD Studentships at Sussex AI

by Thomas Nowotny

Dear all, We have three fully-funded (internationals included) PhD studentships available within Sussex AI<https://www.sussex.ac.uk/research/centres/ai-research-group/#SussexAI>, starting in September 2024! This is a great opportunity for doctoral research in our interdisciplinary Centre of Excellence based at the University of Sussex<https://www.sussex.ac.uk/>, where we are the focal point for research in AI methods and applications. We encourage prospective students to submit innovative proposals that either: - Engage with theoretical challenges in Artificial Intelligence. - Develop new Artificial Intelligence methods that have the potential to enable novel applications. - Address complex problems requiring research at the intersection of traditional disciplinary boundaries. To find out more information, check out the full advert https://www.sussex.ac.uk/study/fees-funding/phd-funding/view/1686-Sussex-AI… Best regards, Thomas (co-director of Sussex AI) -- Prof. Thomas Nowotny Head of AI Research Group CCNR, Sussex Neuroscience Phone: +44-1273-678593 Engineering and Informatics, Fax: +44-1273-877873 University of Sussex, Falmer, Brighton BN1 9QJ sussex.ac.uk/informatics/tnowotny<http://sussex.ac.uk/informatics/tnowotny> <../../owa/redir.aspx?C=9e11bb0e527242938402b42d9b5498ea&URL=http%3a%2f%2fsussex.ac.uk%2finformatics%2ftnowotny>

Jan. 8, 2024

PhD & postdoc position in computational resilience research

by Janina Hesse

The Computational Resilience Research group at the LIR (Mainz, Germany) is hiring PhD students and PostDocs for theoretical projects. By advanced data analysis and the development of dynamical models, we unravel the complex processes that prevent or enable resilience. To that end, we work in close collaboration with our experimental colleagues, using extensive mouse and human data sets from molecular to behavioral. We strive for a diverse, supportive, and collaborative work atmosphere. The position offers excellent interdisciplinary training possibilities at the intersection of modelling, machine learning, and medicine, with ample opportunities for interactions within the Institute for Quantitative and Computational Biosciences (IQCB) of the Johannes Gutenberg-University Mainz. A typical background would be a Master's/PhD in the life sciences, physics, computer sciences, mathematics, or another quantitative field. For information on how to apply see https://lir-mainz.de/assets/lir_84_doctoral-candidate-or-postdoc_eng-170193… At the Leibniz Institute for Resilience Research (LIR) in Mainz, Germany, we study resilience - the maintenance or restoration of mental health during or following stressful life events or life circumstances. The LIR is the first center of its kind in Europe, and its main objectives are to understand resilience mechanisms from a neuroscientific point of view, to develop and provide appropriate interventions to strengthen resilience, as well as to promote resilience in living and working environments. Leibniz-Institut für Resilienzforschung (LIR) gGmbH Jun.-Prof. Dr. Janina Hesse Group leader Computational Resilience Research janina.hesse(a)lir-mainz.de Wallstraße 7 55122 Mainz https://www.lir-mainz.de   [Icon Description automatically generated with low confidence] Aufsichtsratsvorsitzender: Dr. Frank-Dieter Kuchta Geschaeftsfuehrer: Prof. Dr. Klaus Lieb, Prof. Dr. Beat Lutz (wissenschaftlich), Dr. Thorsten Mundi (kaufmaennisch). HRB 48032, Amtsgericht Mainz Diese E-Mail enthaelt vertrauliche und/oder rechtlich geschuetzte Informationen. Wenn Sie nicht der richtige Adressat sind oder diese E-Mail irrtuemlich erhalten haben, informieren Sie bitte sofort den Absender und loeschen Sie diese E-Mail. Das Kopieren sowie die Weitergabe dieser E-Mail und der darin enthaltenen Informationen ist nicht gestattet. This email may contain confidential and/or privileged information. If you are not the intended recipient (or have received this email in error) please notify the sender immediately and delete this e-mail. Any unauthorized copying, disclosure or distribution of the material in this email is strictly forbidden. Unsere Hinweise zum Datenschutz finden Sie hier: https://lir-mainz.de/datenschutz

Jan. 8, 2024

Retraction of a fraudulent publication

by Michael Biehl

Dear All. It is my pleasure to announce that a fraudulent and blatantly plagiarized publication from July 2023, (allegedly) about the training of layered neural networks in time-dependent envrionments, has been retracted by the Editorial Office of *MDPI Applied Sciences*, at last. The retraction process took very long and communication was quite unpleasant. *Please see * *https://www.mdpi.com/2076-3417/14/2/476* <https://www.mdpi.com/2076-3417/14/2/476> *for details and links to the plagiarized original pieces of work. * Note that the term "overlap" in the retraction notice is way too polite in view of the brazen "cut-and-paste" approach of the "authors". They literally copy/pasted essentially all figures and equations from other sources. The text consists of non-sensical gibberish and contains no original results whatsoever. Four referees apparently failed to note the gobbledygook and recognize the plagiarism. Best wishes, Michael Biehl -- --------------------------------------------------- Prof. Dr. Michael Biehl Bernoulli Institute for Mathematics, Computer Science & Artificial Intelligence P.O. Box 407, 9700 AK Groningen, NL https://www.cs.rug.nl/~biehl m.biehl(a)rug.nl

Jan. 8, 2024

Modellers Workshop for the Brain Dynamics Toolbox

by Stewart Heitmann

Enrolments are now open for the Modellers Workshop for the Brain Dynamics Toolbox. This is an online course for researchers who wish to build custom dynamical models using the Brain Dynamics Toolbox. The course focuses on practical programming techniques for the major classes of differential equations (ordinary, partial, delay, stochastic) that arise in computational neuroscience. Example code is provided in all cases. Upon completion, students will be able to turn custom differential equations into working simulations. Study time is 8 hours. Course Website https://bdtoolbox.teachable.com/p/modellers-workshop Toolbox Website https://bdtoolbox.org Important Dates Enrolments close 31st Jan 2024. Disclaimer The information contained in this communication from the sender is confidential. It is intended solely for use by the recipient and others authorized to receive it. If you are not the recipient, you are hereby notified that any disclosure, copying, distribution or taking action in relation of the contents of this information is strictly prohibited and may be unlawful. This email has been scanned for viruses and malware, and may have been automatically archived by Mimecast Ltd, an innovator in Software as a Service (SaaS) for business. Providing a safer and more useful place for your human generated data. Specializing in; Security, archiving and compliance. To find out more visit the Mimecast website.

Jan. 7, 2024

From Animals to Animats: 17th International Conference on the Simulation of Adaptive Behavior (SAB 2024) - Conference Announcement and Call For Papers

by Jeffrey L Krichmar

Happy New Year! On September 9-12, 2024, UC Irvine will be hosting this year’s From Animals to Animats: 17th International Conference on the Simulation of Adaptive Behavior (SAB 2024). The Simulation of Adaptive Behavior (SAB) interdisciplinary conference brings together researchers in artificial intelligence, artificial life, computer science, cybernetics, ethology, evolutionary biology, neuroscience, robotics, and many other fields, to further our understanding of the behaviors and underlying mechanisms that allow natural animals and artificial agents to adapt and survive in complex, dynamic and uncertain environments. Animats denote the connection between animals and synthetic agents. The conference focuses on models and experiments designed to help characterize and compare various organizational principles and architectures underlying adaptive behavior in real animals and in animats. SAB 2024 solicits contributions dealing with any aspect of adaptive behavior. We especially invite submissions from researchers who connect biology and natural behavior to synthetic agents. Conference papers are peer-reviewed and accepted papers will be published in “From Animals to Animats 17. SAB 2024.” Lecture Notes in Artificial Intelligence, Springer Nature. We have a great lineup of confirmed speakers: Oliver Brock – Technische Universitat Berlin Lola Canamero – CY Cergy Paris University Kris Carlson – BrainChip Jeff Clune – The University of British Columbia Jens Krause – Leibniz Institute of Freshwater Ecology and Inland Fisheries Maja Mataric – University of Southern California Praveen Pilly – Intelligent Systems Laboratory at HRL Laboratories Jun Tani – Okinawa Institute of Science and Technology Janet Wiles – University of Queensland More conference information is available at: https://sites.uci.edu/sab2024/ Venue -------- CalIT2 Auditorium University of California, Irvine Irvine, CA 92697 USA CALL FOR PAPERS - SAB 2024 (April 1, 2024 Deadline) ————————————————————— More details can be found at: https://sab2024.socsci.uci.edu/call-for-papers Important Dates ---------------------- April 1, 2024: Deadline for paper submission April 15, 2024: Deadline for Workshop and tutorial proposals June15, 2024: Notice of acceptance June 30, 2024: Camera-ready papers September 9-12: Conference dates Hope to see you in September! Jeff Krichmar Department of Cognitive Sciences 2328 Social & Behavioral Sciences Gateway University of California, Irvine Irvine, CA 92697-5100 jkrichma(a)uci.edu http://www.socsci.uci.edu/~jkrichma https://sites.uci.edu/sab2024/

Jan. 7, 2024

PhD and postdoc position at Jülich Research Center

by Sacha van Albada

PhD and postdoc position in large-scale brain modeling and simulation at Jülich Research Center PhD and postdoc opportunities with a focus on the simulation of large-scale biological neural networks are available in the Theoretical Neuroanatomy group at Jülich Research Center, Germany (https://www.fz-juelich.de/en/inm/inm-6/forschung/theoretical-neuroanatomy) The projects will advance a research program that centers on the full-scale simulation of thalamocortical networks using the simulator NEST. The postdoc position is available in the context of the Henriette Herz Scouting Program of the Humboldt Foundation, and will be offered to a female candidate. The program is particularly aimed at candidates from countries underrepresented in the Humboldt Foundation. We will jointly define a research project and the selected candidate will receive a Humboldt Research Fellowship (https://www.humboldt-foundation.de/en/apply/sponsorship-programmes/humboldt…) The position is available for 24 months for postdocs up to 4 years after the PhD defense and for 18 months for experienced researchers 4-12 years after the PhD defense. The PhD defense should not be more than 12 years ago, and candidates should not have previous or existing links to Germany in terms of study, research stays, or citizenship. Due consideration will be given to any gaps in the CV due to family care or other personal circumstances. The PhD position is open to candidates regardless of gender. The candidate should have a background in physics, mathematics, computer science, biology (or specifically neuroscience), or engineering. Excellent quantitative and analytical skills are highly valued. We offer a structured program guiding doctoral researchers through the PhD work and plenty of opportunities for local and international collaboration. The researchers will be embedded in a vibrant research institute (https://<https://www.csn.fz-juelich.de/>www.csn.fz-juelich.de<https://www.csn.fz-juelich.de/>). Links also exist to the University of Cologne, so that candidates can gain teaching/tutoring experience. To apply, please send a motivation letter, CV, and university transcripts and certificates to s.van.albada(a)fz-juelich.de<mailto:s.van.albada@fz-juelich.de> and to our scientific coordinator Martina Reske (m.reske(a)fz-juelich.de<mailto:m.reske@fz-juelich.de>). -- Prof. Sacha Jennifer van Albada Institute of Neuroscience and Medicine (INM-6) Tel. +49 2461 61-96808 Computational and Systems Neuroscience & Fax +49 2461 61-9460 Institute for Advanced Simulation (IAS-6) Theoretical Neuroscience & JARA-Institut Brain Structure-Function Relationships (INM-10) Jülich Research Centre Jülich, Germany Computational Neuroanatomy Tel. +49-221-470-3829 Institute of Zoology Fax +49-221-470-4889 University of Cologne Cologne, Germany ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Jülich GmbH 52425 Jülich Sitz der Gesellschaft: Jülich Eingetragen im Handelsregister des Amtsgerichts Düren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Stefan Müller Geschäftsführung: Prof. Dr. Astrid Lambrecht (Vorsitzende), Karsten Beneke (stellv. Vorsitzender), Dr. Ir. Pieter Jansens ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------

Jan. 4, 2024

Applications open for Okinawa/OIST Computational Neuroscience Course 2024 (OCNC 2024)

by Erik De Schutter

OKINAWA/OIST COMPUTATIONAL NEUROSCIENCE COURSE 2024 Methods, Neurons, Networks and Behaviors June 17 to July 4, 2024 Okinawa Institute of Science and Technology Graduate University, Japan https://groups.oist.jp/ocnc The aim of the Okinawa/OIST Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn the latest advances in neuroscience, and for those with experimental backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, held from June 17th through July 4th, 2024 at an oceanfront seminar house of the Okinawa Institute of Science and Technology Graduate University. Applications are through the course web page (https://groups.oist.jp/ocnc) only; January 1 - January 31, 2024. Applicants will receive confirmation of acceptance end of March. Like in preceding years, the 19th OCNC will be a comprehensive three-week course covering single neurons, networks, and behaviors with ample time for student projects. The first week will focus exclusively on methods with hands-on tutorials during the afternoons, while the second and third weeks will have lectures by international and local experts. The course has a strong hands-on component based on student proposed modeling or data analysis projects, which are further refined with the help of a dedicated tutor. Applicants are required to propose their project at the time of application. There is no tuition fee. The sponsor will provide lodging and meals during the course. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet each other and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. Lecturers: Erik De Schutter (OIST) Kenji Doya (OIST) Tomoki Fukai (OIST) Izumi Fukunaga (OIST) N. Alex Cayco Gajic (École Normale Supérieure, Paris, France) Yukiko Goda (OIST) Arvind Kumar (KTH, Stockholm, Sweden) Bernd Kuhn (OIST) Matthew Larkum (Humboldt University, Berlin, Germany) Hakwan Lau (RIKEN CBS, Tokyo, Japan) Sukbin Lim (NYU Shangai, China) Gerald Pao (OIST) Thomas Parr (Oxford University, UK) Sam Reiter (OIST) Kazumasa Tanaka (OIST)

Jan. 3, 2024

ICDL Confirmed Speakers – paper deadline Jan 8, poster deadline March 1

by nagai.yukie＠mail.u-tokyo.ac.jp

Dear colleagues, Join us in Austin May 20-23 2024 for the IEEE International Conference on Development and Learning (ICDL). ICDL is an intimate and unique meeting gathering researchers interested in development from the perspective of ecological psychology, robotics, and computation. We have confirmed an amazing list of speakers for the event - including a keynote by Jitendra Malik, the research director for Facebook AI - as well as 20 of the most important thinkers in this space. Our goal is to encourage deep conversations through carefully curated single-track symposia, including: Curiosity-Driven Learning and Predictive Models Yukie Nagai - The University of Tokyo, Japan Elizabeth Bonawitz - Harvard University, USA Gert Westermann - Lancaster University, UK Michael Goldstein - Cornell University, USA Language Development in Humans and Machines Xavier Hinaut - Inria & Bordeaux University, France Casey Lew-Williams - Princeton University, USA Daniel Messinger - University of Miami, USA Catherine Laing - University of York, UK Developmental Machine Learning and Everyday Inputs Karen Adolph - New York University, USA Linda Smith - Indiana University, USA Jochen Triesch - Frankfurt Institute for Advanced Studies, Germany Marvin Lavechin - Ecole Normale Supérieure, France Egocentric vision and attention John Franchak - University of California, Riverside, USA Kristen Grauman - The University of Texas at Austin, USA Mary Hayhoe - The University of Texas at Austin, USA Jim Rehg - University of Illinois Urbana-Champaign, USA Body Representation and Sensorimotor Organization Daniela Corbetta - The University of Tennessee, USA Matej Hoffmann - Czech Technical University in Prague, Czech Republic Hoshinori Kanazawa - The University of Tokyo, Japan Peter Marshall - Temple University, USA Website: https://la.utexas.edu/users/dil/ICDL_Austin_2024/ Deadline for full paper submissions extended: December 15, 2023, January 8, 2024 Deadline for 1-page poster abstracts and journal track poster submissions: March 1, 2024 Full papers and other submissions are invited on a range of topics including but not limited to: • Embodied learning and development in biological systems and robots • Developmental stages and sensitive periods • Emergence of verbal and nonverbal communication • Curiosity, intrinsic motivations, exploration, play and active learning • Architectures for lifelong learning • Emergence of body and affordance perception • Learning control of body movement • Emotional development and the role of emotion in learning • Prediction, planning, and problem solving • The relationship between evolution and development • Epistemological foundations and philosophical issues • Robotic and computational models of human and animal development • Developmentally-inspired machine learning • Human-robot interaction in developmental contexts • Applications of machine learning to human and animal development Submissions may take the form of full (6-page) papers, 1-page poster abstracts, journal track posters, and workshops or tutorials. Please see below for details on each submission type. Decisions regarding acceptance will be based on technical quality, novelty, and expected interest to the conference’s interdisciplinary audience. In addition to talks and posters originating from these submissions, the conference will feature a keynote speaker as well as several invited symposia showcasing recent research on a set of themes, with different disciplines and perspectives featured, to prompt lively and productive discussion at the conference. Submission types: Full six-page paper submissions Papers of at most 6 pages in IEEE double column format will undergo peer-review, and accepted and presented submissions will be included in the conference proceedings published by IEEE Xplore. Up to two extra pages are acceptable for a publication fee of $100 per page. Accepted papers will be invited for presentation either in oral or poster format Please make use of the template provided at https://www.ieee.org/conferences/publishing/templates.html 1-page poster abstracts To encourage discussion of late-breaking results or for work that is not sufficiently mature for a full paper, we will accept 1-page abstracts. These submissions will not be included in the conference proceedings. Accepted abstracts will be presented during the poster session. Journal-track posters Journal track poster submissions must be about a journal paper that has been published recently (no earlier than December 2022), on a topic relevant to ICDL. Best regards, Yukie Nagai, on behalf of the organizing committees — Yukie Nagai, Ph.D. Project Professor, The University of Tokyo nagai.yukie(a)mail.u-tokyo.ac.jp | https://developmental-robotics.jp CREST Cognitive Feelings: https://cognitive-feeling.jp CREST Cognitive Mirroring: https://cognitive-mirroring.org

Jan. 3, 2024

CfP Social Interaction for Human and Virtual Agents

by Treur, J. (Jan)

SIHVA 2024: Computational Modeling of Social Interaction for Human and Virtual Agents Special Session at the 16th Asian Conference on Intelligent Information and Database Systems (ACIIDS 2024) 15-18 April 2024, Ras Al Khaimah, UAE Website: https://aciids.pwr.edu.pl/2024/session.php?acronym=SIHVA Organizers Sophie C.F. Hendrikse University of Amsterdam, Psychological Methods Group E-mail: s.c.f.hendrikse(a)uva.nl<mailto:s.c.f.hendrikse@uva.nl> Jan Treur Vrije Universiteit Amsterdam, Social AI Group E-mail: j.treur(a)vu.nl<mailto:j.treur@vu.nl> Objectives From a Computer Science or AI perspective, social interaction for human or virtual agents might simply be modeled like exchange of information. However, as many researchers involved in this area know, in a realistic context there is much more to it than that. Some examples of quite relevant aspects are how information about the other agent is represented and interpreted, how the interaction behaviour is context-sensitive and has flexibility in responses, and can be adaptive over time, for example, like in bonding. Research on all of such and other relevant aspects can be addressed in this track. Topics Some of the specific topics covered are (but the scope is not limited to these): * Multimodal interaction * Representing and learning about the other agent, self-other distinction * Social contagion and mirroring * Emergence of similarity during social interaction: homophily, synchrony * Adaptivity of interaction behaviour over shorter and longer time periods * Interpersonal regulation of emotions between agents * Joint-decision making * Collaborative learning * Artificial social systems * Social affective computing * Socially intelligent agents and multi-agent systems Important dates Paper submission: January 5, 2024 (2nd extension) Notification of acceptance: February 28, 2024 Camera-ready papers: March 15, 2024 Registration & payment: March 15, 2024 Conference date: April 15-18, 2024

Dec. 29, 2023