Overview Statistic: PDF-Downloads (blue) and Frontdoor-Views (gray)
The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 2 of 20
Back to Result List

Advances in Verification of ReLU Neural Networks

  • We consider the problem of verifying linear properties of neural networks. Despite their success in many classification and prediction tasks, neural networks may return unexpected results for certain inputs. This is highly problematic with respect to the application of neural networks for safety-critical tasks, e.g. in autonomous driving. We provide an overview of algorithmic approaches that aim to provide formal guarantees on the behavior of neural networks. Moreover, we present new theoretical results with respect to the approximation of ReLU neural networks. On the other hand, we implement a solver for verification of ReLU neural networks which combines mixed integer programming (MIP) with specialized branching and approximation techniques. To evaluate its performance, we conduct an extensive computational study. For that we use test instances based on the ACAS Xu System and the MNIST handwritten digit data set. Our solver is publicly available and able to solve the verification problem for instances which do not have independent bounds for each input neuron.
Metadaten
Author:Ansgar Rössig, Milena PetkovicORCiD
Document Type:Article
Parent Title (English):Journal of Global Optimization
Publisher:Springer
Granting Institution:Freie Universität Berlin
Year of first publication:2020
Preprint:urn:nbn:de:0297-zib-74174
DOI:https://doi.org/10.1007/s10898-020-00949-1
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.