EU Horizon 2020
Horizon 2020
HomeNewsResearch ThemesPeopleKey Prior PublicationsPublications
[Kwi22] Marta Kwiatkowska. Robustness Guarantees for Bayesian Neural Networks. In Proc. 19th International Conference on Quantitative Evaluation of SysTems (QEST 2022). 2022. [pdf] [bib]
Downloads:  pdf pdf (305 KB)  bib bib
Abstract. Bayesian neural networks (BNNs), a family of neural networks with a probability distribution placed on their weights, have the advantage of being able to reason about uncertainty in their predictions as well as data. Their deployment in safety-critical applications demands rigorous robustness guarantees. This paper summarises recent progress in developing algorithmic methods to ensure certifiable safety and robustness guarantees for BNNs, with the view to support design automation for systems incorporating BNN components.