Towards Robust Deep Neural Networks

We examine the relationship between the energy landscape of neural networks and their robustness to adversarial attacks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical evidence that networks corresponding to lower...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2018-10
Hauptverfasser:	Wang, Timothy E, Gu, Jack, Mehta, Dhagash, Zhao, Xiaojun, Bernal, Edgar A
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational chemistry Computer vision Machine learning Neural networks Organic chemistry Production methods Regularization Robustness (mathematics) Sensitivity Software
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!