Harvard Medical AI: Alex Tamkin presents Domain-Agnostic Self-Supervised Learning

A talk hosted by the Rajpurkar Lab at Harvard which works on developing medical AI. These talks cover recent papers or topics in core AI / medical AI in a format targeted to those interested in the cutting edge of AI and its applications in medicine. In this session, expert guest Alex Tamkin presents his work on domain-agnostic self supervised learning. Alex is a fourth-year PhD student in Computer Science at Stanford, advised by Noah Goodman and part of the Stanford ML and NLP Groups. His research focuses on understanding, building, and controlling self-supervised models, especially in domain-general or multimodal settings. Tamkin, A., Liu, V., Lu, R., Fein, D., Schultz, C. and Goodman, N., 2021, June. DABS: a Domain-Agnostic Benchmark for Self-Supervised Learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1). Full Paper: Rajpurkar Lab Website: