PhD Proposal: Robustness and Understandability of Deep Models
Amin Ghiasi
Abstract
|
|
Bio
Amin Ghiasi is a Ph.D. student working under the supervision of Prof. Tom Goldstein. His research is focused on deep learning models, their weaknesses (such as adversarial examples), ways to improve the robustness, and ways to understand them (such as deep visualization and model inversion).
This talk is organized by Tom Hurst