A weak condition for global stability of delayed neural networks

The classical analysis of asymptotical and exponential stability of neural networks needs assumptions on the existence of a positive Lyapunov function V and on the strict negativity of the function dV=dt, which often come as a result of boundedness or uniformly almost periodicity of the activation f...

Full description

Bibliographic Details
Main Authors: Luo, R., Xu, Honglei, Wang, W., Sun, Jie, Xu, W.
Format: Journal Article
Published: American Institute of Mathematical Sciences (A I M S Press) 2016
Online Access:http://hdl.handle.net/20.500.11937/40445
_version_ 1848755873221967872
author Luo, R.
Xu, Honglei
Wang, W.
Sun, Jie
Xu, W.
author_facet Luo, R.
Xu, Honglei
Wang, W.
Sun, Jie
Xu, W.
author_sort Luo, R.
building Curtin Institutional Repository
collection Online Access
description The classical analysis of asymptotical and exponential stability of neural networks needs assumptions on the existence of a positive Lyapunov function V and on the strict negativity of the function dV=dt, which often come as a result of boundedness or uniformly almost periodicity of the activation functions. In this paper, we investigate the asymptotical stability problem of Hopfield neural networks with time delays under weaker conditions. By constructing a suitable Lyapunov function, sufficient conditions are derived to guarantee global asymptotical stability and exponential stability of the equilibrium of the system. These conditions do not require the strict negativity of dV=dt, nor do they require that the activation functions to be bounded or uniformly almost periodic.
first_indexed 2025-11-14T09:03:13Z
format Journal Article
id curtin-20.500.11937-40445
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:03:13Z
publishDate 2016
publisher American Institute of Mathematical Sciences (A I M S Press)
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-404452017-09-13T13:37:32Z A weak condition for global stability of delayed neural networks Luo, R. Xu, Honglei Wang, W. Sun, Jie Xu, W. The classical analysis of asymptotical and exponential stability of neural networks needs assumptions on the existence of a positive Lyapunov function V and on the strict negativity of the function dV=dt, which often come as a result of boundedness or uniformly almost periodicity of the activation functions. In this paper, we investigate the asymptotical stability problem of Hopfield neural networks with time delays under weaker conditions. By constructing a suitable Lyapunov function, sufficient conditions are derived to guarantee global asymptotical stability and exponential stability of the equilibrium of the system. These conditions do not require the strict negativity of dV=dt, nor do they require that the activation functions to be bounded or uniformly almost periodic. 2016 Journal Article http://hdl.handle.net/20.500.11937/40445 10.3934/jimo.2016.12.505 American Institute of Mathematical Sciences (A I M S Press) unknown
spellingShingle Luo, R.
Xu, Honglei
Wang, W.
Sun, Jie
Xu, W.
A weak condition for global stability of delayed neural networks
title A weak condition for global stability of delayed neural networks
title_full A weak condition for global stability of delayed neural networks
title_fullStr A weak condition for global stability of delayed neural networks
title_full_unstemmed A weak condition for global stability of delayed neural networks
title_short A weak condition for global stability of delayed neural networks
title_sort weak condition for global stability of delayed neural networks
url http://hdl.handle.net/20.500.11937/40445