research
∙
07/19/2022
Bounding generalization error with input compression: An empirical study with infinite-width networks
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) ...
share
research
∙
06/27/2022
Monitoring Shortcut Learning using Mutual Information
The failure of deep neural networks to generalize to out-of-distribution...
research
∙
05/06/2019
Batch Normalization is a Cause of Adversarial Vulnerability
Batch normalization (batch norm) is often used in an attempt to stabiliz...
research
∙
11/30/2018
Adversarial Examples as an Input-Fault Tolerance Problem
We analyze the adversarial examples problem in terms of a model's fault ...
research
∙
04/10/2018
Adversarial Training Versus Weight Decay
Performance-critical machine learning models should be robust to input p...
research
∙
02/13/2018
Predicting Adversarial Examples with High Confidence
It has been suggested that adversarial examples cause deep learning mode...
research
∙
11/01/2017