1 code implementation • 7 Dec 2019 • Adam Noack, Isaac Ahern, Dejing Dou, Boyang Li
We demonstrate that training the networks to have interpretable gradients improves their robustness to adversarial perturbations.
no code implementations • ICLR 2020 • Isaac Ahern, Adam Noack, Luis Guzman-Nateras, Dejing Dou, Boyang Li, Jun Huan
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently.