Room 206 (2nd floor, badged access)
18 janvier 2019 - 14h00
When neural networks meet dependability
par Chi-Hong Cheng de Fortiss
Abstract: Neural networks are instrumental in developing automated driving components such as perception or intention prediction. The safety-critical aspect of such a domain makes dependability of neural networks a central concern. In this talk, I highlight our initial steps towards engineering dependable neural networks by considering approaches such as testing, constraint solving and runtime verification.