Palestras e Seminários



virtual/à distância

Palestrante: Trevor Darrell

Responsável: Fernando Santos Osório (Este endereço de email está sendo protegido de spambots. Você precisa do JavaScript ativado para vê-lo.)

The Perspectives in AI Seminar of the C4AI

Supervising with boolean class labels all future scenarios a machine learning application may encounter is understood to be infeasible, leading to renewed interest in adaptive and self-supervised methods. Yet several popular “unsupervised” methods implicitly presume knowledge of target domain invariances. I’ll present three new methods that do not require hand-selecting augmentation strategies and learn without supervision: multi-task contrastive learning, automatic selection of augmentation policies, and entropy-based adaptation at test time without access to source labels or data. As time permits I’ll also outline recent work on advisable learning, which leverages explanations at training time to make limited supervision even more effective. Fully unsupervised and advisable learning can work together to dramatically reduce the level of supervision required for real-world tasks.
Prof. Darrell is on the faculty of the CS and EE Divisions of the EECS Department at UC Berkeley. He founded and co-leads Berkeley’s Berkeley Artificial Intelligence Research (BAIR) lab, the Berkeley DeepDrive (BDD) Industrial Consortia, and the recently launched BAIR Commons program in partnership with Facebook, Google, Microsoft, Amazon, and other partners. He also is Faculty Director of the PATH research center at UC Berkeley, and previously led the Vision group at the UC-affiliated International Computer Science Institute in Berkeley. Prior to that, Prof. Darrell was on the faculty of the MIT EECS department from 1999-2008, where he directed the Vision Interface Group. He was a member of the research staff at Interval Research Corporation from 1996-1999, and received the S.M., and PhD. degrees from MIT in 1992 and 1996, respectively. He obtained the B.S.E. degree from the University of Pennsylvania in 1988.
#C4AI #artificiaintelligence #PerspectivesInAISeminar


© 2021 Instituto de Ciências Matemáticas e de Computação