Leveraging Satisfiability Modulo Theory Solvers for Verification of Neural Networks in Predictive Maintenance Applications

Autor:	Dario Guidotti, Laura Pandolfo, Luca Pulina
Jazyk:	angličtina
Rok vydání:	2023
Předmět:	neural networks predictive maintenance trustworthy AI formal verification Information technology T58.5-58.64
Zdroj:	Information, Vol 14, Iss 7, p 397 (2023)
Druh dokumentu:	article
ISSN:	2078-2489
DOI:	10.3390/info14070397
Popis:	Interest in machine learning and neural networks has increased significantly in recent years. However, their applications are limited in safety-critical domains due to the lack of formal guarantees on their reliability and behavior. This paper shows recent advances in satisfiability modulo theory solvers used in the context of the verification of neural networks with piece-wise linear and transcendental activation functions. An experimental analysis is conducted using neural networks trained on a real-world predictive maintenance dataset. This study contributes to the research on enhancing the safety and reliability of neural networks through formal verification, enabling their deployment in safety-critical domains.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/74c45f2ce2d9472fae8d8ab8d17ad8d7 Zobrazit plný text záznamu View record in DOAJ Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.