Trustworthy Deep Learning

Explore trustworthy deep learning in this 32-minute conference talk by Stanley Osher from the University of California, Los Angeles. Delve into four key aspects: robust, accurate, efficient, and private deep learning, supported by theoretical guarantees derived from differential equations. Learn about IntroResNet, FinemanResNets, Differential Privacy, and Deep Noiser as part of the Deep Learning and Medical Applications 2020 series presented at the Institute for Pure and Applied Mathematics, UCLA.