ICLR 2021 - Workshop on "How Can Findings About The Brain Improve AI Systems?"
Submission deadline: February 26, 2021
Workshop website: https://iclrbrain2ai.github.io/
Contact: brain2ai.2021@gmail.com
The brain comprises billions of neurons organized into an intricate network of highly specialized functional areas. This biological cognitive system can efficiently process vast amounts of multi-modal data to perceive and react to its ever-changing environment. Unlike current AI systems, it does not struggle with domain adaptation, few-shot learning, or commonsense reasoning.
Inspiration from neuroscience has benefited AI in the past: modern convolutional networks mimic the deep, nested information flow in visual cortex, and hippocampal replay of previous experiences has brought about experience replay in reinforcement learning. Recent work at the intersection of neuroscience and AI has made progress in directly integrating neuroscientific data with AI systems and has led to learned representations that are more robust to label corruptions, allow for better generalization in some language tasks, and provide new ways to interpret and evaluate what domain-relevant information is learned by deep neural networks. In this workshop, we aim to examine the extent to which insights about the brain can lead to better AI.
We will consider the following (non-exhaustive) list of topics for contribution:
Integration of neuroscientific data at different granularities (neural recordings, neuroimaging etc.) to train AI systems
Brain-inspired inductive biases and ML architectures for AI systems
Neuroscientific data as an evaluation metric for AI systems
Mechanistic insight into cognitive functions (vision, language, decision making, attention, etc.)
Limitations of current AI systems in tasks at which humans excel (compositionality, commonsense reasoning, continual learning, few-shot learning, causality, etc.)
Cross-modality and cross-species comparisons of neuroscientific data with respect to benefits to AI
Datasets that can facilitate the transfer of neuroscientific insight to AI
Submit at: https://cmt3.research.microsoft.com/BRAIN2AI2021/Submission/Index
The workshop will feature a diverse set of topics led by the following invited speakers and panelists (in alphabetical order):
Anima Anandkumar, California Institute of Technology
David Cox, Harvard University
Kenji Doya, Okinawa Institute of Science and Technology Graduate University
Allyson Ettinger, University of Chicago
Alona Fyshe, University of Alberta
Jack Gallant, University of California, Berkeley
Andrea Martin, Max Planck Institute for Psycholinguistics
Kimberly Statchenfeld, DeepMind
Josh Tenenbaum, MIT
Formatting Instructions: All submissions must be in PDF format. Submissions are limited to four content pages, including all figures and tables; additional pages containing only references are allowed. You must format your submission using the ICLR 2021 LaTeX style files. Submissions that meaningfully violate the ICLR style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review. All submissions should be anonymous. The review process is double-blind. We also welcome recently (within the last year) published papers that are within the scope of the workshop (without re-formatting). Already-published papers do not have to be anonymous. They are eligible for a spotlight session and will only have a very light review process.
Virtual format: The workshop will be geared towards more dynamic and interactive discussion focused on Q&A sessions. Accepted abstracts and papers will result in, at minimum, a pre-recorded spotlight talk. All presenters will be given live virtual “coffee break” rooms during all breaks in the conference schedule to engage in small group discussions with participants. Discussions around talks will be organized in live virtual “breakout” rooms with similar topics and themes so that workshop attendees and presenters can interact in a less formal, discussion-centric setting.
Important Dates:
Paper submission deadline: 11:59 PM EST, Feb 26, 2021
Author notification: 11:59 PM EST, Mar 26, 2021
Camera-ready papers due: 11:59 PM EST, Apr 15, 2021
Workshop: May 8, 2021