Hold me tight! Influence of discriminative features on deep network
boundaries
release_ikusamygzrevhfaoya5hiyh7km
by
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen
Moosavi-Dezfooli, Pascal Frossard
2020
Abstract
Important insights towards the explainability of neural networks and their
properties reside in the formation of their decision boundaries. In this work,
we borrow tools from the field of adversarial robustness and propose a new
framework that permits to relate the features of the dataset with the distance
of data samples to the decision boundary along specific directions. We
demonstrate that the inductive bias of deep learning has the tendency to
generate classification functions that are invariant along non-discriminative
directions of the dataset. More surprisingly, we further show that training on
small perturbations of the data samples are sufficient to completely change the
decision boundary. This is actually the characteristic exploited by the
so-called adversarial training to produce robust classifiers. Our general
framework can be used to reveal the effect of specific dataset features on the
macroscopic properties of deep models and to develop a better understanding of
the successes and limitations of deep learning.
In text/plain
format
Archived Files and Locations
application/pdf 4.4 MB
file_6hy4clsdcfcvbkxyf6nl35hvoq
|
arxiv.org (repository) web.archive.org (webarchive) |
2002.06349v1
access all versions, variants, and formats of this works (eg, pre-prints)