Stability analysis of delayed neural networks via compound-parameter-based integral inequality

This paper revisits the issue of stability analysis of neural networks subjected to time-varying delays. A novel approach, termed a compound-matrix-based integral inequality (CPBII), which accounts for delay derivatives using two adjustable parameters, is introduced. By appropriately adjusting these...

Full description

Bibliographic Details
Main Authors: Xue, Wenlong, Jin, Zhenghong, Tian, Yufeng
Other Authors: School of Electrical and Electronic Engineering
Format: Journal Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/179899
_version_ 1824454805114847232
author Xue, Wenlong
Jin, Zhenghong
Tian, Yufeng
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Xue, Wenlong
Jin, Zhenghong
Tian, Yufeng
author_sort Xue, Wenlong
collection NTU
description This paper revisits the issue of stability analysis of neural networks subjected to time-varying delays. A novel approach, termed a compound-matrix-based integral inequality (CPBII), which accounts for delay derivatives using two adjustable parameters, is introduced. By appropriately adjusting these parameters, the CPBII efficiently incorporates coupling information along with delay derivatives within integral inequalities. By using CPBII, a novel stability criterion is established for neural networks with time-varying delays. The effectiveness of this approach is demonstrated through a numerical illustration.
first_indexed 2025-02-19T03:28:09Z
format Journal Article
id ntu-10356/179899
institution Nanyang Technological University
language English
last_indexed 2025-02-19T03:28:09Z
publishDate 2024
record_format dspace
spelling ntu-10356/1798992024-09-06T15:40:23Z Stability analysis of delayed neural networks via compound-parameter-based integral inequality Xue, Wenlong Jin, Zhenghong Tian, Yufeng School of Electrical and Electronic Engineering Mathematical Sciences Neural networks Time-varying delay This paper revisits the issue of stability analysis of neural networks subjected to time-varying delays. A novel approach, termed a compound-matrix-based integral inequality (CPBII), which accounts for delay derivatives using two adjustable parameters, is introduced. By appropriately adjusting these parameters, the CPBII efficiently incorporates coupling information along with delay derivatives within integral inequalities. By using CPBII, a novel stability criterion is established for neural networks with time-varying delays. The effectiveness of this approach is demonstrated through a numerical illustration. Published version 2024-09-02T04:10:26Z 2024-09-02T04:10:26Z 2024 Journal Article Xue, W., Jin, Z. & Tian, Y. (2024). Stability analysis of delayed neural networks via compound-parameter-based integral inequality. AIMS Mathematics, 9(7), 19345-19360. https://dx.doi.org/10.3934/math.2024942 2473-6988 https://hdl.handle.net/10356/179899 10.3934/math.2024942 2-s2.0-85195632738 7 9 19345 19360 en AIMS Mathematics © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0). application/pdf
spellingShingle Mathematical Sciences
Neural networks
Time-varying delay
Xue, Wenlong
Jin, Zhenghong
Tian, Yufeng
Stability analysis of delayed neural networks via compound-parameter-based integral inequality
title Stability analysis of delayed neural networks via compound-parameter-based integral inequality
title_full Stability analysis of delayed neural networks via compound-parameter-based integral inequality
title_fullStr Stability analysis of delayed neural networks via compound-parameter-based integral inequality
title_full_unstemmed Stability analysis of delayed neural networks via compound-parameter-based integral inequality
title_short Stability analysis of delayed neural networks via compound-parameter-based integral inequality
title_sort stability analysis of delayed neural networks via compound parameter based integral inequality
topic Mathematical Sciences
Neural networks
Time-varying delay
url https://hdl.handle.net/10356/179899
work_keys_str_mv AT xuewenlong stabilityanalysisofdelayedneuralnetworksviacompoundparameterbasedintegralinequality
AT jinzhenghong stabilityanalysisofdelayedneuralnetworksviacompoundparameterbasedintegralinequality
AT tianyufeng stabilityanalysisofdelayedneuralnetworksviacompoundparameterbasedintegralinequality