Novel stability criterion for DNNs via improved asymmetric LKF

This paper briefly proposes an improved asymmetric Lyapunov-Krasovskii functional to analyze the stability issue of delayed neural networks (DNNs). By utilizing linear matrix inequalities (LMIs) incorporating integral inequality and reciprocally convex combination techniques, a new stability criteri...

Full description

Saved in:
Bibliographic Details
Main Authors: Xianhao Zheng, Jun Wang, Kaibo Shi, Yiqian Tang, Jinde Cao
Format: Article
Language:English
Published: AIMS Press 2024-09-01
Series:Mathematical Modelling and Control
Subjects:
Online Access:https://www.aimspress.com/article/doi/10.3934/mmc.2024025
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590348101091328
author Xianhao Zheng
Jun Wang
Kaibo Shi
Yiqian Tang
Jinde Cao
author_facet Xianhao Zheng
Jun Wang
Kaibo Shi
Yiqian Tang
Jinde Cao
author_sort Xianhao Zheng
collection DOAJ
description This paper briefly proposes an improved asymmetric Lyapunov-Krasovskii functional to analyze the stability issue of delayed neural networks (DNNs). By utilizing linear matrix inequalities (LMIs) incorporating integral inequality and reciprocally convex combination techniques, a new stability criterion is formulated. Compared to existing methods, the newly developed stability criterion demonstrates less conservatism and complexity in analyzing neural networks. To explicate the potency and preeminence of the proposed stability criterion, a renowned numerical instance is showcased, serving as an illustrative embodiment.
format Article
id doaj-art-9e810fcc423e45a496bd71e74c3ffeb5
institution Kabale University
issn 2767-8946
language English
publishDate 2024-09-01
publisher AIMS Press
record_format Article
series Mathematical Modelling and Control
spelling doaj-art-9e810fcc423e45a496bd71e74c3ffeb52025-01-24T01:02:08ZengAIMS PressMathematical Modelling and Control2767-89462024-09-014330731510.3934/mmc.2024025Novel stability criterion for DNNs via improved asymmetric LKFXianhao Zheng0Jun Wang1Kaibo Shi2Yiqian Tang3Jinde Cao4Electronic Information Engineering Key Laboratory of Electronic Information of State Ethnic Affairs Commission, College of Electrical Engineering, Southwest Minzu University, Chengdu 610041, ChinaElectronic Information Engineering Key Laboratory of Electronic Information of State Ethnic Affairs Commission, College of Electrical Engineering, Southwest Minzu University, Chengdu 610041, ChinaSchool of Electronic Information and Electrical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Electronic Information and Electrical Engineering, Chengdu University, Chengdu 610106, ChinaSchool of Mathematics, Southeast University, Nanjing 210096, ChinaThis paper briefly proposes an improved asymmetric Lyapunov-Krasovskii functional to analyze the stability issue of delayed neural networks (DNNs). By utilizing linear matrix inequalities (LMIs) incorporating integral inequality and reciprocally convex combination techniques, a new stability criterion is formulated. Compared to existing methods, the newly developed stability criterion demonstrates less conservatism and complexity in analyzing neural networks. To explicate the potency and preeminence of the proposed stability criterion, a renowned numerical instance is showcased, serving as an illustrative embodiment.https://www.aimspress.com/article/doi/10.3934/mmc.2024025asymmetric lyapunov-krasovskii functionaldelayed neural networkintegral inequalitystability criterion
spellingShingle Xianhao Zheng
Jun Wang
Kaibo Shi
Yiqian Tang
Jinde Cao
Novel stability criterion for DNNs via improved asymmetric LKF
Mathematical Modelling and Control
asymmetric lyapunov-krasovskii functional
delayed neural network
integral inequality
stability criterion
title Novel stability criterion for DNNs via improved asymmetric LKF
title_full Novel stability criterion for DNNs via improved asymmetric LKF
title_fullStr Novel stability criterion for DNNs via improved asymmetric LKF
title_full_unstemmed Novel stability criterion for DNNs via improved asymmetric LKF
title_short Novel stability criterion for DNNs via improved asymmetric LKF
title_sort novel stability criterion for dnns via improved asymmetric lkf
topic asymmetric lyapunov-krasovskii functional
delayed neural network
integral inequality
stability criterion
url https://www.aimspress.com/article/doi/10.3934/mmc.2024025
work_keys_str_mv AT xianhaozheng novelstabilitycriterionfordnnsviaimprovedasymmetriclkf
AT junwang novelstabilitycriterionfordnnsviaimprovedasymmetriclkf
AT kaiboshi novelstabilitycriterionfordnnsviaimprovedasymmetriclkf
AT yiqiantang novelstabilitycriterionfordnnsviaimprovedasymmetriclkf
AT jindecao novelstabilitycriterionfordnnsviaimprovedasymmetriclkf