Pulina, Luca and Tacchella, Armando (2011) Checking safety of neural networks with SMT solvers: a comparative evaluation. In: AI*IA 2011: Proceedings of the 12th International conference on Artificial intelligence around man and beyond, 15-17 September 2011, Palermo, Italy. Berlin - Heidelberg, Springer. p. 127-138. ISBN 978-3-642-23953-3. Conference or Workshop Item.
Full text not available from this repository.
In this paper we evaluate state-of-the-art SMT solvers on encodings of verification problems involving Multi-Layer Perceptrons (MLPs), a widely used type of neural network. Verification is a key technology to foster adoption of MLPs in safety-related applications, where stringent requirements about performance and robustness must be ensured and demonstrated. While safety problems for MLPs can be attacked solving Boolean combinations of linear arithmetic constraints, the generated encodings are hard for current state-of-the-art SMT solvers, limiting our ability to verify MLPs in practice.
I documenti depositati in UnissResearch sono protetti dalle leggi che regolano il diritto d'autore
Repository Staff Only: item control page