NeVer 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 Standard Articles 1 Publication describing the Software, including 1 Publication in zbMATH Year NeVer: a tool for artificial neural networks verification. Zbl 1251.68143Pulina, Luca; Tacchella, Armando 2011 Cited by 5 Authors 1 Delgado Martínez, Guillermo 1 Manrique, Daniel 1 Pulina, Luca 1 Rolanía, Dolores Barrios 1 Tacchella, Armando Cited in 1 Serial 2 Annals of Mathematics and Artificial Intelligence Cited in 2 Fields 2 Computer science (68-XX) 1 Special functions (33-XX) Citations by Year