Abstract
Trustworthy deep learning
Stanley Osher
University of California, Los Angeles (UCLA)
In this work we discuss trustworthy deep learning, which includes
1. Robust deep learning, 2. Accurate deep learning, 3. Efficient deep learning and 4. Private deep learning,
with theoretical guarantees, usually based on ideas borrowed from differential equations.
(joint work with Bao Wang and others)
1. Robust deep learning, 2. Accurate deep learning, 3. Efficient deep learning and 4. Private deep learning,
with theoretical guarantees, usually based on ideas borrowed from differential equations.
(joint work with Bao Wang and others)