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

Author:

Guidotti Dario1ORCID,Pandolfo Laura1ORCID,Pulina Luca1ORCID

Affiliation:

1. Department of Humanities and Social Sciences (DUMAS), University of Sassari, via Roma 151, 07100 Sassari, Italy

Abstract

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.

Funder

H2020 ECSEL JU

Publisher

MDPI AG

Subject

Information Systems

Reference56 articles.

1. RNN-SURV: A Deep Recurrent Model for Survival Analysis;Giunchiglia;Proceedings of the Artificial Neural Networks and Machine Learning—ICANN 2018—27th International Conference on Artificial Neural Networks,2018

2. A survey of deep neural network architectures and their applications;Liu;Neurocomputing,2017

3. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI;Arrieta;Inf. Fusion,2020

4. Visual interpretability for deep learning: A survey;Zhang;Frontiers Inf. Technol. Electron. Eng.,2018

5. Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications;Samek;Proc. IEEE,2021

Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. NeVer2: learning and verification of neural networks;Soft Computing;2024-07-31

2. Verifying Autoencoders for Anomaly Detection in Predictive Maintenance;Lecture Notes in Computer Science;2024

3. Formal Verification of Neural Networks: A “Step Zero” Approach for Vehicle Detection;Lecture Notes in Computer Science;2024

4. Verifying Neural Networks with Non-Linear SMT Solvers: a Short Status Report;2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI);2023-11-06

5. Detection of Component Degradation: A Study on Autoencoder-Based Approaches;2023 IEEE 19th International Conference on e-Science (e-Science);2023-10-09

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3