titoli, abstracts, parole chiave >>>
NeVer: a tool for artificial neural networks verification

Pulina, Luca and Tacchella, Armando (2011) NeVer: a tool for artificial neural networks verification. Annals of Mathematics and Artificial Intelligence, Vol. 62 (3-4), p. 403-425. eISSN 1573-7470. Article.

Full text not available from this repository.

DOI: 10.1007/s10472-011-9243-0

Abstract

The adoption of Artificial Neural Networks (ANNs) in safety-related applications is often avoided because it is difficult to rule out possiblemisbehaviors with traditional analytical or probabilistic techniques. In this paper we present NeVer, our tool for checking safety of ANNs. 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 NeVer. We present also empirical results confirming the effectiveness of NeVer on realistic case studies.

Item Type:Article
ID Code:7104
Status:Published
Refereed:Yes
Uncontrolled Keywords:Formal methods for adaptive systems, abstraction techniques, algorithms and tools for verification
Subjects:Area 09 - Ingegneria industriale e dell'informazione > ING-INF/05 Sistemi di elaborazione delle informazioni
Divisions:001 Università di Sassari > 01 Dipartimenti > Economia, istituzioni e società
Publisher:Springer
eISSN:1573-7470
Copyright Holders:© Springer Science + Business Media B.V. 2012
Additional Information:From the issue entitled "Special Issue: Experimental evaluation of algorithms for solving problems with combinatorial explosion"
Deposited On:14 Feb 2012 10:23

I documenti depositati in UnissResearch sono protetti dalle leggi che regolano il diritto d'autore

Repository Staff Only: item control page