Trustworthy Deep Learning
Offered By: Institute for Pure & Applied Mathematics (IPAM) via YouTube
Course Description
Overview
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.
Syllabus
Intro
ResNet
Fineman
ResNets
Differential Privacy
Deep Noiser
Taught by
Institute for Pure & Applied Mathematics (IPAM)
Related Courses
Scientific ComputingUniversity of Washington via Coursera Differential Equations in Action
Udacity Initiation à la théorie des distributions
École Polytechnique via Coursera Everything is the Same: Modeling Engineered Systems
Northwestern University via Coursera Analyse numérique pour ingénieurs
École Polytechnique Fédérale de Lausanne via Coursera