Conference: NSF-NIH Joint Workshop on Foundational AI in Biology

点击翻译按钮获取中文摘要

Methods and new techniques in artificial intelligence (AI) are rapidly beingdeveloped, extended, and applied to challenging problems in biology. At thesame time, as new experimental methods, new data collection efforts, andgreater understanding are developed in biology, the class and scope of problemsthat are amendable to AI approaches is growing. Extreme interest and rapidprogress in AI has also made the AI research landscape diverse and complex,with a number of related, competing, and overlapping technologies andapproaches being advanced. This rich ecosystem is a boon to research andinnovation, but it also makes identifying threads and pressing problems morechallenging. Thus, there is a need to survey the current frontier of theinterface between AI methodology and biology and to chart future directions andchallenges. We propose a 2-day, online workshop to address that need. Thisworkshop will host invited talks by researchers working on foundational AImethods in biology. New directions and connections between emerging AImethodologies and problems in biology and health will be identified,synthesized, highlighted, and formalized. The workshop will catalyze discussionand help set the agenda for future research in this area, helping to launch newdirections and solidify promising ones.The workshop will consist of approximately 13 talks and 4 discussion sessionsover two days. Speakers will be selected based on their prior work andexperience with developing new foundational AI methodology that answersbiological questions. Speakers will be asked to focus on one or more of thefollowing foundational AI themes as related to biology and human health: (1)Fairness and Social Effects of AI; (2) Federated Learning; (3) Generative DeepLearning Models; (4) Scalability of AI; (5) Privacy and Security in AI; (6)Method Optimization and Automated Algorithm Design; (7) Explainable AI andCausality; (8) Active Learning and Automated Science; (9) Transfer Learning;and (10) Incorporation of Prior Knowledge in AI. Though the workshop cannothope to deeply cover all these foundational aspects, we aim to cover as many aspossible. Speakers will connect these foundational computational techniques toproblems in biology in areas such as genomics, structural biology, drugdevelopment, systems biology, biomedical imaging, neuroscience, and diseaseforecasting. With permission of the speaker, the talks will be recorded anddistributed over the internet, and participants will be invited to contributeto a publication that surveys the identified themes, directions, andchallenges.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.