On Data Augmentation and Adversarial Risk: An Empirical Analysis

no code implementations • 6 Jul 2020 • Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard A. Moser, Gerhard Widmer

Data augmentation techniques have become standard practice in deep learning, as it has been shown to greatly improve the generalisation abilities of models.

Adversarial Attack Data Augmentation

ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy

1 code implementation • 20 May 2020 • Natalia Shepeleva, Werner Zellinger, Michal Lewandowski, Bernhard Moser

We propose a new metric space of ReLU activation codes equipped with a truncated Hamming distance which establishes an isometry between its elements and polyhedral bodies in the input space which have recently been shown to be strongly related to safety, robustness, and confidence.