research
∙
11/16/2022
Improving Interpretability via Regularization of Neural Activation Sensitivity
State-of-the-art deep neural networks (DNNs) are highly effective at tac...
share
research
∙
09/23/2020
Adversarial robustness via stochastic regularization of neural activation sensitivity
Recent works have shown that the input domain of any machine learning cl...
research
∙
09/08/2019
