LIPIcs.CONCUR.2019.1.pdf
- Filesize: 1.36 MB
- 5 pages
Computing systems are becoming ever more complex, increasingly often incorporating deep learning components. Since deep learning is unstable with respect to adversarial perturbations, there is a need for rigorous software development methodologies that encompass machine learning. This paper describes progress with developing automated verification techniques for deep neural networks to ensure safety and robustness of their decisions with respect to input perturbations. This includes novel algorithms based on feature-guided search, games, global optimisation and Bayesian methods.
Feedback for Dagstuhl Publishing