swMATH ID: 6592
Software Authors: Pulina, Luca; Tacchella, Armando
Description: NeVer: a tool for artificial neural networks verification The adoption of artificial neural networks (ANNs) in safety-related applications is often avoided because it is difficult to rule out possible misbehaviors with traditional analytical or probabilistic techniques. In this paper we present {sc NeVer}, our tool for checking safety of ANNs.{sc NeVer} encodes the problem of verifying safety of ANNs into the problem of satisfying corresponding Boolean combinations of linear arithmetic constraints. We describe the main verification algorithm and the structure of {sc NeVer}. We present also empirical results confirming the effectiveness of {sc NeVer} on realistic case studies.
Homepage: http://rd.springer.com/article/10.1007%2Fs10472-011-9243-0
Keywords: formal methods for adaptive systems; abstraction techniques; verification
Related Software: Matlab; OPQ; SHARK; CESAR; Roboop
Cited in: 2 Publications

Citations by Year