March 2021 - Comp-neuro - lists.cnsorg.org

Research Associate Position at Cardiff University Brain Research Imaging Centre

by Jiaxiang ZHANG

[Apologize for cross-posting] Dear all, We are seeking an enthusiastic early-career scientist for a research associate position at Cardiff University Brain Research Imaging Centre (CUBRIC). The successful candidate will join a collaborative and multidisciplinary research team to work on the neurocognitive mechanisms of human decision-making, integrating multimodal brain imaging (MEG, functional MRI and diffusion MRI) and computational modelling. The post holder will develop computational models that describe data from behavioural and brain imaging experiments, in particular to take a lead role in integrating large-scale computational simulations with imaging results from multiple modalities. The research aims to understand the computational and neurocognitive processes of human decision-making, and how decision deficits may arise due to brain injury or neurodegeneration. The research associate will also be expected to collaborate with other researchers in the team on imaging data analyses and data curation. You will have access to imaging facilities at CUBRIC and several multimodal imaging datasets. Cardiff University Brain Research Imaging Centre (CUBRIC) houses a unique combination of state-of-the-art facilities and world-leading expertise, with 4 human MRI systems (2 x Siemens Prisma, 1 x Siemens Connectom, 1 x Siemens 7T), MEG, EEG, TMS, tDCS, clinical research units and testing labs. Further details of CUBRIC can be found on our webpage (http://sites.cardiff.ac.uk/cubric) This is a full-time, fixed-term position until February 2023, available to start now. Remote working is possible if COVID-19 restrictions are in place. For informal enquiries, please contact Dr Jiaxiang Zhang ( zhangj73(a)cardiff.ac.uk) A formal application needs to be submitted via the link online ( https://www.jobs.ac.uk/job/CEQ831/research-associate) *Application deadline: April 6th, 2021.* *Essential Criteria* 1. A PhD degree in a relevant discipline (e.g., mathematics, computer science, engineering, physics or psychology) 2. Research experience or a strong interest in human decision-making 3. Strong experience in computational models of cognitive processes and/or macroscopic neural systems, including the use of neural mass models or neural field models 4. Experience of analysing brain imaging data in one or more modalities (e.g., diffusion MRI, BOLD functional MRI, MEG/EEG), using common software packages 5. Strong programming skills (e.g., Matlab, Python, C/C++ or R) 6. Experience with Unix/Linux environment for data analysis, including bash scripting and parallel computing on high-performance clusters 7. Proven ability to publish high-quality research in peer-reviewed academic journals 8. Knowledge of software development cycles and best programming practices, including coding standards, version control administration, debug and code sharing, with strong commitments to open science practices 9. Excellent written and verbal communication skills, evidenced by publications and/or conference presentations 10. Strong interpersonal skills, including proven ability to work cooperatively within a team while also being able to take the initiative *Desirable Criteria * 1. Experience of brain functional and structural connectivity analyses 2. Experience in statistical methods (e.g., GLM, mixed models, multivariate statistics, hierarchical models and Bayesian statistics) and/or machine learning methods 3. Experience in deep learning models of imaging processing --- Dr. Jiaxiang Zhang Cardiff University Brain Research Imaging Centre (CUBRIC) School of Psychology Cardiff University Maindy Road, Cardiff, CF24 4HQ https://ccbrain.org

March 25, 2021

INCF Assembly 2021: abstract submission closes March 31!

by Helena Ledmyr

Join us virtually for the 2021 INCF Assembly on April 19-27, with an exciting program <https://neuroinformatics.incf.org/2021/program> covering different aspects of FAIR neuroscience! Abstract submission <https://neuroinformatics.incf.org/abstract-submission> is open until March 31, and registration <https://neuroinformatics.incf.org/2021/registration> is now open . Members of INCF enjoy heavily discounted registration fees, which are already lowered due to the meeting being virtual this year. You can sign up for membership and see the other benefits here <https://www.incf.org/join-incf/individuals> - one year costs 20 USD for students and postdocs, and 50 USD for regular members. The INCF Assembly 2021 aims to provide the neuroscience community with approaches that can be used today to implement the FAIR principles in their research. It also aims to provide tool developers and infrastructure providers with an opportunity to interact with the user community and to interact with other practitioners to advance the field of neuroinformatics. The 2021 INCF Assembly will address topics around FAIR neuroscience such as: - FAIR approaches for neuroscience in general, neuroimaging, electrophysiology, and computational neuroscience - Electrophysiology and computational neuroscience - Data science - Showcase of tools and infrastructures - Open innovation and intellectual property - Information about ongoing work in INCF councils and committees - Funders and publishers roundtable - Workshops on developing standards and a roadmap for FAIR neuroscience The INCF Assembly is the only international meeting that focuses on providing researchers with hands-on training experiences and enabling interaction with software developers and infrastructure providers. We hope to see you online in April! ----------------------------- Helena Ledmyr, PhD *Director* *Development and Communications* International Neuroinformatics Coordinating Facility Secretariat Karolinska Institutet. Nobels väg 15A, SE-171 77 Stockholm. Sweden Email: helena.ledmyr(a)incf.org Phone: +46 8 524 870 35 incf.org neuroinformatics.incf.org

March 25, 2021

Network Neuroscience Satellite at Networks2021 online conference - Call for contributions

by Daniele Marinazzo

The 2021 Network Neuroscience Satellite <https://netneurosci.github.io/networks2021satellite> of the Networks2021 <https://networks2021.net/> conference will happen online between June 28 and July 2, with the most likely dates being June 30/July 1 (TBC soon). *Background and Motivation:* Recent technological developments have enabled mapping and recording of neural systems with unprecedented coverage and detail. Increasingly, the brain’s structure and function are approached from the perspective of complexity and networks, with theoretical and empirical/computational studies that conceptualize the brain as a complex system, composed of elements and interactions that are dynamically and functionally integrated. Network science offers important conceptual tools, insights, and robust computational methods for dynamic network systems’ analyses. At the intersection of networks and brain science, the interdisciplinary field of Network Neuroscience is now addressing a broad range of both basic and applied scientific questions, regarding many aspects of brain architecture and function. This satellite will provide an opportunity for participants with diverse backgrounds to present cutting-edge research, discuss latest network findings and exchange ideas. *Invited speakers:* - Maurizio Corbetta (University of Padua, Italy) - Plamen Ch. Ivanov (Boston University, United States) - Mariangeles Serrano (University of Barcelona, Spain) - Carolyn Parkinson (University of California Los Angeles, United States) - Dimitri Van De Ville (EPFL and University of Geneva, Switzerland) *Organizing and program committee:* - Richard F. Betzel (Indiana University, United States) - Fabrizio De Vico Fallani (INRIA, France) - Katja Heuer (Max Planck Institute for Cognitive and Brain Sciences, Germany) - Daniele Marinazzo (Ghent University, Belgium) - Olaf Sporns (Indiana University, United States) - Roberto Toro (Pasteur Institute, France) - Emma Towlson (University of Calgary, Canada) - Robin Wilkins (University of North Carolina, United States) The satellite will include a number of* poster and oral presentations* contributed by submission. For the poster sessions we are working to provide a friendly, robust, and inclusive platform to maximize the quality of the interactions. If you would like to present your work, please, follow this link to <https://easychair.org/conferences/?conf=netneuro2021>Easychair <https://easychair.org/conferences/?conf=netneuro2021>, select the type of contribution and submit your abstract by *April 9th*. Abstracts should be in pdf format and no longer than 1 page (about 500 words). Please note that we have only a limited number of slots available for oral presentations, and encourage you to consider submitting your work as a poster. We will be holding a dedicated session for the posters. Oral presentations (“Contributed Talks”, 15 minutes) will be selected by the program committee. We welcome submissions from all areas of Network Neuroscience, to include (but not limited to): - Brain transcriptional and gene regulation networks; - Structural brain networks; - Functional brain networks; - Network theory, modeling and analysis; - Network communication and information flow; - Circuit dynamics; - Brain-behavior interactions; - Systems neuroscience; - Clinical applications. Please note that as per the rules of Networks2021, you may not deliver the same oral presentation in this satellite as at the main conference. Posters, however, may be presented at the satellite and at the main conference if appropriate. Communication of accepted submissions and invitations for oral “contributed talks” will be sent by *April 23rd*. The early deadline for registration at the Networks2021 conference is *May 1st*. Please don't forget to visit our webpage <https://netneurosci.github.io/networks2021satellite>, and add yourself with your interests and keywords to the brainweb <https://brain-web.github.io/community/>! -- Daniele Marinazzo Department of Data Analysis Faculty of Psychology and Educational Sciences, Ghent University Postal address: Henri Dunantlaan 2, B-9000 Ghent, Belgium Office address: Henri Dunantlaan 1, B-9000 Ghent, Belgium (directions in the link below) +32 (0) 9 264 6375 <http://www.da.ugent.be/>http://users.ugent.be/~dmarinaz/ Twitter @dan_marinazzo <https://twitter.com/dan_marinazzo> Directions to the office <https://soleway.ugent.be/routes/1250> http://helpdesk.ugent.be/e-maildisclaimer.php

March 25, 2021

Postdoc and research assistant positions in Florida. Sleep and memory spike dynamics

by Carmen Varela

Two positions (*one postdoc and one research assistant/post-bac*) in the laboratory of Dr. Carmen Varela (Psychology Department, Florida Atlantic University; https://www.varelalab.org/) to investigate the role of the thalamus in sleep-dependent memory consolidation. *Keywords*: behaving rodent extracellular electrophysiology, cell population dynamics, thalamic circuits, learning and memory, sleep consolidation, synaptic plasticity, mRNA translation. Start date flexible within 2021. *Project 1 (postdoc; 3 years with possibility of extension):* Cell population dynamics of spike activity in thalamic cells during learning and subsequent NREM sleep consolidation. *Project 2 (research assistant; 1-2 years with possibility of extension):* Synaptic changes evoked by thalamic activity during sleep-dependent memory consolidation. **** Requirements **** Interested candidates please send your curriculum and a brief description of your research interests to varelac(a)fau.edu We are looking for team-oriented candidates, ideally with prior experience with rodent behavior and electrophysiology. Candidates selected for an interview will be asked to provide contact information for up to three references. **** What you get **** · Work on exciting and impactful projects to understand the contribution of higher order thalamic cells to learning and memory. · Develop research skills using state-of-the-art systems, molecular and computational neuroscience techniques. · Mentorship, supportive lab environment, in a rapidly growing neuroscience campus. *Location**:* The Varela laboratory is located in FAU’s Jupiter campus, a rapidly growing neuroscience hub, which also hosts our partners the Max Planck Florida Institute for Neuroscience and Scripps Research Institute. Best, Carmen Varela, Ph.D. Assistant Professor Psychology Department Florida Atlantic University MC-19, room 106 Jupiter, FL 33458

March 22, 2021

Open Post-doctoral Position in Human Perceptual Neuroscience at NYU

by Hardstone, Richard

The Perception and Brain Dynamics Laboratory (PI: Biyu J. He, Ph.D.) at New York University is currently recruiting for a post-doctoral fellow to study neural mechanisms of human perception and the interaction between perceptual and cognitive systems. We are looking for a candidate with independent critical thinking, strong analytical and quantitative skills, and good interpersonal skills. We are especially interested in candidates with experience in using advanced neuroimaging data analyses to test theories in perceptual/cognitive neuroscience, and/or candidates with experience in large-scale computational modeling. Our laboratory is located on the medical campus of New York University in Manhattan, NY, and is affiliated with the Neuroscience Institute, Departments of Neurology, Neuroscience & Physiology, and Radiology. The position is expected to start in fall 2021. We provide competitive salary and benefits that adjust for cost of living in New York City. To apply, please send a CV, a cover letter, a statement of scientific and career goals, and names and contacts of three referees to Prof. Biyu Jade He (email: biyu.jade.he(a)gmail.com<mailto:biyu.jade.he@gmail.com>) with the subject line “post-doctoral application 2021”. ------------------------------------------------------------ This email message, including any attachments, is for the sole use of the intended recipient(s) and may contain information that is proprietary, confidential, and exempt from disclosure under applicable law. Any unauthorized review, use, disclosure, or distribution is prohibited. If you have received this email in error please notify the sender by return email and delete the original message. Please note, the recipient should check this email and any attachments for the presence of viruses. The organization accepts no liability for any damage caused by any virus transmitted by this email. =================================

March 17, 2021

3x Positions in Reinforcement Learning & Comp Cogn Neuroscience for Healthcare

by Aldo Faisal

Dear All We are looking for machine learning, causal statistics and computational neuroscience minded people to join our rapidly growing team around developing Reinforcement Learning for medical interventions. Recruitment is on a rolling basis, but for administrative purposes we have a first cut-off end of this month. If you want to move beyond Atari games and work on intervention-based Machine Learning that will have impact on medial practice and eventually patient lives - do join us as we have received the unique opportunity to join us to work on the Machine Learning, Computational Cognitive Science and a rapidly growing team working on the hospital IT, regulatory and clinical side of our AI for Healthcare testbed for "Level 2 autonomous medical treatment”. Details below Kind regards Aldo — 3 x Postdoctoral Positions in Reinforcement Learning for Healthcare (AI Clinician) @ Imperial College Job Summary Research Associate salary: £40,858 - £48,340 per annum* Full-time, Fixed term to start ASAP for 2 years with the possibility for extension Our vision is to establish the computational foundations for an „AI clinician“, an AI system informed by millions of patient records that is using Reinforcement Learning (RL) to learn optimal treatment policies for critically ill patients (Komorowksi et Faisal, 2018, Nature Medicine; Gottesman et al, 2019, Nature Medicine). Prof Aldo Faisal, has been awarded a prestigious UKRI Turing AI Fellowship in Reinforcement Learning for Healthcare for which are recruiting up to 3 post-doctoral Research Associates. Our machine learning research goal is centred on developing what is needed as a theoretical foundation for taking our „AI clinician“ proof-of-principle all the way to clinical deployment, and expanding its capabilities and responsibilities. Our Research Associates doing fundamental work will be supported by a team of experienced Researchers and a program grant to take the AI Clinician through the regulatory and technical challenges of clinical deployment. The AI Clinician programme is grounded in the established foundations of clinical decision support systems, which will run as a bed-side recommender system watching over the patients state second-by-second and prompting specific clinical interventions to undertake as the patient state evolves. We are uniquely placed to take our machine learning developments into a meaningful clinical setting, as we have been awarded with generous funding by the UK’s Ministry of Health/NHS-X to setup a globally unique AI for Healthcare testbed for reinforcement learning interventions in 4 intensive care units across Central London. On the clinical side of the AI Clinician we are collaborating with world-leading intensive care clinicians (Anthony Gordon & Matthieu Komorowksi) also at Imperial College. Our project has the support of regulatory experts and specialised medical device units that support us in taking our entire research program all the way to clinical deployment in a live hospital environment. The overall research environment is corresponding to our ambition, the Departments where Aldo Faisal’s research group is based has been consistently ranked top 3 in the UK, and Imperial College has been consistently ranked in the top-10 universities world-wide. Imperial College boasts a world-leading ecosystem of AI for Healthcare research across the breadth of both AI and Medicine, and hosts among other things the pioneering UKRI Centre in AI for Healthcare (directed by Aldo Faisal), as well as the AI network, comprising over 200 faculty and 1000 Research Associates and PhD Students at Imperial that work in AI. Duties and responsibilities The aim of the project is the advancement of foundational Reinforcement Learning methods with the immediate application to clinical intervention and involves the unique opportunity to develop core machine learning theory and see it evaluated with clinical end-users as needed. We are therefore searching for our UKRI Turing AI research programme areas at the interface of: 1. Causal Inference & Reinforcement Learning Despite the parallels between optimal sequential decision making in Causal Inference (Dynamic Treatment Regimens) and continuous control in RL, there has only been some initial work linking these (Barenboim & Pearl, 2016; Johnson et al 2017; Gottesmann et Faisal…, 2019, Nature Med) and we are keen to synthesize these into a common theory. 2. Foundations of Reinforcement Learning Advancing RL methods to cope with partial observability, risk, sparseness or the size of vast data sets, (including Distributional RL & Fusing Off-policy & On-Policy learning; Off-Policy Learning in POMDPs; Neural ODEs for RL), e.g. see Li & Faisal, 2021, AAAI; 3. Explainable AI & Cognitive Neuroscience We believe that Explainability in AI requires us to develop empirical methods for measuring how well humans were explained and how much trust this explanation has caused, establishing a clear link to cognitive neuroscience. E.g. see Beyret, Shafti & Faisal, IROS 2019, Shafti et Faisal, IROS 2020. Location: London Salary: £40,858 to £48,340 per annum Hours: Full Time Contract Type: Fixed-Term/Contract Placed On: 2nd March 2021 Closes: 31st March 2021 Job Ref: ENG01585 How to apply For further details on this opportunity visit https://www.imperial.ac.uk/jobs/ <https://www.imperial.ac.uk/jobs/> and search using vacancy reference number ENG01585. Candidates should also attach: A full CV A short statement indicating what you see are interesting issues relating to the above post and why your expertise is relevant Informal enquiries regarding post please contact Aldo Faisal: aldo.faisal(a)imperial.ac.uk <mailto:aldo.faisal@imperial.ac.uk> For queries regarding the application process contact Jamie Perrins: j.perrins(a)imperial.ac.uk <mailto:j.perrins@imperial.ac.uk> Closing Date: 31st March 2021 (midnight) Apply <https://www.imperial.ac.uk/jobs/description/ENG01585/3-x-research-associate> — Aldo Faisal, PhD Professor of AI & Neurocscience UKRI Turing AI Fellow Director, UKRI Centre for Doctoral Training in AI for Healthcare Director, Behaviour Analytics Lab, Data Science Institute Dept. of Bioengineering & Dept. Of Computing Imperial College London SW7 2AZ London UK @FaisalLab www.FaisalLab.org aldo.faisal(a)imperial.ac.uk http://www3.imperial.ac.uk/people/a.faisal

March 16, 2021

Full-time Research Assistant posion on funded project investigating the neural basis of conscious vision -- Brascamp lab

by Brascamp, Jan

Our lab is seeking to hire a Research Assistant for a funded project investigating the neural basis of conscious vision. The successful candidate will play a pivotal role in many aspects of the study including recruiting and scheduling participants, collecting behavioral and neuroimaging data, and organizing and analyzing study data. In addition, this position will involve general lab management, including maintaining ethical protocols, and there will be opportunity to contribute to other ongoing projects in the lab. The research assistant will also have the opportunity to prepare scientific results for publication and presentation, and there will be ample opportunity to learn methods in functional neuroimaging, visual psychophysics, and eye tracking/pupillometry. Accordingly, this position should be viewed as a stepping stone toward gaining entry into graduate or professional school. The ideal candidate should be highly motivated, organized, and capable of working independently, have strong organizational and interpersonal skills, and hold a Bachelor’s or Master’s degree in psychology, neuroscience, or related discipline. Individuals interested in the psychology and neuroscience of visual perception are especially encouraged to apply. Minimum qualifications include a Bachelor’s degree in psychology, neuroscience, or related field, and previous (undergraduate or post-undergraduate) experience in human subjects research. Experience with vision research is highly desirable. Working knowledge of Microsoft Office (Word, Excel, Powerpoint) is essential. Experience using a programming language (Python, Matlab) is desired, but not necessary. Preference will be given to those who can commit to two years of service. The start date is flexible. Interested applicants should e-mail Dr. Jan Brascamp at brascamp(a)msu.edu and include all required application materials: 1) 1-2 page letter of interest, including interests and long-term career goals/plans. 2) CV 3) Transcript (unofficial or official) 4) Contact information (phone and email address) for three individuals who can provide a reference Applications will be reviewed starting immediately and continue until the position is filled. Any questions about the position may be directed to Dr. Jan Brascamp at brascamp(a)msu.edu

March 16, 2021

Scientific Liaison Officer position at Jülich Supercomputing Centre, Germany

by Abigail Morrison

Dear Colleagues, We have a position open for a Scientific Liaison Officer for EBRAINS at the Jülich Supercomputing Centre, Jülich Research Centre, Germany. We are looking for candidates with excellent communication skills, a strong scientific background and computing skills to both promote EBRAINS in the neuroscience community, and drive development activities within the Human Brain Project to ensure the requirements of the community are being met. For a full description and details of how to apply, please see the announcement on our website: https://www.fz-juelich.de/SharedDocs/Stellenangebote/_common/dna/2021-103-E… Closing date: 30 March 2021 All the best, Abigail Morrison -- Prof. Dr. Abigail Morrison IAS-6 / INM-6 / SimLab Neuroscience Jülich Research Center & Computer Science 3 - Software Engineering RWTH Aachen http://www.fz-juelich.de/inm/inm-6 http://www.fz-juelich.de/ias/jsc/slns http://www.se-rwth.de Office: +49 2461 61-9805 Fax # : +49 2461 61-9460 Pronouns: she/her ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ Forschungszentrum Juelich GmbH 52425 Juelich Sitz der Gesellschaft: Juelich Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498 Vorsitzender des Aufsichtsrats: MinDir Volker Rieke Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender), Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------

March 16, 2021

Funded PhD position in modelling biological neuro-muscular control in dynamic locomotion with a link to biorobotics (Biomechanics / Biomedical Engineering / (Bio-)physics)

by Compsens

FUNDED PHD POSITION IN MODELLING BIOLOGICAL NEURO-MUSCULAR CONTROL IN DYNAMIC LOCOMOTION WITH A LINK TO BIOROBOTICS (BIOMECHANICS / BIOMEDICAL ENGINEERING / (BIO-)PHYSICS) We are currently seeking a highly motivated PHD STUDENT (F/M/D) WE OFFER a FUNDED RESEARCHER POSITION FOR 36 MONTHS in our project „Neuro-muscular contraction in dynamic locomotion“. The project has a strong focus on basic research investigating the function of biological muscles in locomotion and how to transfer important characteristics to novel bio-inspired robotic systems. You will be part of an interdisciplinary multi-center research group with muscle physiology and biorobotics researchers in a team of at least three PhD students. Your contribution will be focused on modelling and simulation of neuro-muscular control. Your contract should start in the first half of 2021. Salary will be based on previous experience. ABOUT US You will become a member of the group /Multi-Level Modeling in Motor Control and Rehabilitation Robotics/ at the Hertie Institute for Clinical Brain Research (HIH) in Tübingen. The project is in collaboration with the /Dynamic Locomotion Group/ at Max-Planck-Institute for Intelligent Systems and the /Department of Motion and Exercise Science /at the University of Stuttgart. Our joint research environment offers an excellent research infrastructure and outstanding graduate schools fostering the development of your career. REQUIREMENTS, CORE SKILLS The ideal candidate should have * A background in BIOMEDICAL ENGINEERING, (BIO-)PHYSICS, COMPUTATIONAL NEUROSCIENCE, or closely related * a Masters (or equivalent) degree from a recognized university. Near completion can be considered; * Prior knowledge in multi body dynamics modeling, dynamical systems, system identification, learning, or optimization, is a plus; * Proficient programming experience in Matlab, Python, or similar * Prior experience with neuro-muscular or musculo-skeletal modeling is a plus; * Excellent grades and analytical skills; * Proficient oral and written English skills; * Outstanding candidates with different backgrounds are encouraged to apply To apply The position is will remain open until filled. Applications sent before March 21st will be prioritised. Please send a Cover letter, CV, and transcript of records, along with contact details of two researchers or teachers who would be willing to write a letter of reference (we will contact them directly) to: DANIEL.HAEUFLE(a)UNI-TUEBINGEN.DE HTTPS://WWW.HIH-TUEBINGEN.DE/EN/MOCOM/ I AM LOOKING FORWARD TO YOUR APPLICATION! DANIEL HäUFLE

March 16, 2021

Sponsored competition announcement: the Multi-Agent Behavior Challenge

by Ann Kennedy

We are excited to announce the Multi-Agent Behavior (MABe) Challenge, a competition to build improved tools for the detection of multi-agent behaviors in neuroscience data! What: A machine learning competition to build supervised behavior classification tools, hosted on AIcrowd. When: The Challenge runs from March 8 2021 - April 30 2021 Where: https://www.aicrowd.com/challenges/multi-agent-behavior-representation-mode… Why: To understand the brain, we must understand how it controls behavior. The study of that behavior has classically relied on manual annotation of large volumes of videos. Automating the behavior annotation process would allow researchers to increase the speed, volume, and objectivity of their experiments, and to investigate new behaviors they otherwise would not have time to study. What's in it for me: the three challenge tasks share a $9000 prize pool sponsored by Northwestern University and Amazon SageMarker. The first 50 submissions to exceed any task baseline by at least 5% will receive $200 in Amazon SageMaker credits (max 2/team). Top performing teams will also be invited to present their work at the Multi-Agent Behavior Workshop at CVPR 2021 in June (workshop details coming soon). The challenge consists of three tasks: 1) develop methods to classify human-defined behaviors from tracked pose trajectories in a large dataset of videos of socially interacting mice, 2) fine-tune classifications to different annotator styles, and 3) learn to recognize new behaviors of interest from limited training examples. Relevant techniques include supervised learning, many-to-one time series modeling, style transfer/transfer learning, few-shot learning, domain-sensitive data augmentation, and unsupervised feature learning/clustering. Organized by Ann Kennedy (Northwestern University), Jennifer J. Sun (Caltech), Yisong Yue (Caltech), and Pietro Perona (Caltech), with data contributed by Tomomi Karigo and other members of the David Anderson lab (Caltech). Happy classifying!

March 15, 2021