New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks
In this paper, we solve the mean-square exponential input-to-state stability problem for a class of stochastic delayed recurrent neural networks with time-varying coefficients. With the aid of stochastic analysis theory and a Lyapunov-Krasovskii functional, we derive a novel criterion that ensures t...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2018-01-01
|
Series: | Systems Science & Control Engineering |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/21642583.2018.1544512 |
id |
doaj-10aaf0d26e924d578810d3877fed6f41 |
---|---|
record_format |
Article |
spelling |
doaj-10aaf0d26e924d578810d3877fed6f412020-11-25T01:35:48ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832018-01-016150150910.1080/21642583.2018.15445121544512New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networksWentao Wang0Shuhua Gong1Wei Chen2Shanghai University of Engineering ScienceJiaxing UniversityShanghai Lixin University of Accounting and FinanceIn this paper, we solve the mean-square exponential input-to-state stability problem for a class of stochastic delayed recurrent neural networks with time-varying coefficients. With the aid of stochastic analysis theory and a Lyapunov-Krasovskii functional, we derive a novel criterion that ensures the given system is mean-square exponentially input-to-state stable. Furthermore, the new criterion generalizes and improves some known results. Finally, two examples and their numerical simulations are provided to demonstrate the theoretical results.http://dx.doi.org/10.1080/21642583.2018.1544512Stochastic delayed recurrent neural networksinput-to-state stabilityItô's formulaLyapunov-Krasovskii functional |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wentao Wang Shuhua Gong Wei Chen |
spellingShingle |
Wentao Wang Shuhua Gong Wei Chen New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks Systems Science & Control Engineering Stochastic delayed recurrent neural networks input-to-state stability Itô's formula Lyapunov-Krasovskii functional |
author_facet |
Wentao Wang Shuhua Gong Wei Chen |
author_sort |
Wentao Wang |
title |
New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks |
title_short |
New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks |
title_full |
New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks |
title_fullStr |
New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks |
title_full_unstemmed |
New result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks |
title_sort |
new result on the mean-square exponential input-to-state stability of stochastic delayed recurrent neural networks |
publisher |
Taylor & Francis Group |
series |
Systems Science & Control Engineering |
issn |
2164-2583 |
publishDate |
2018-01-01 |
description |
In this paper, we solve the mean-square exponential input-to-state stability problem for a class of stochastic delayed recurrent neural networks with time-varying coefficients. With the aid of stochastic analysis theory and a Lyapunov-Krasovskii functional, we derive a novel criterion that ensures the given system is mean-square exponentially input-to-state stable. Furthermore, the new criterion generalizes and improves some known results. Finally, two examples and their numerical simulations are provided to demonstrate the theoretical results. |
topic |
Stochastic delayed recurrent neural networks input-to-state stability Itô's formula Lyapunov-Krasovskii functional |
url |
http://dx.doi.org/10.1080/21642583.2018.1544512 |
work_keys_str_mv |
AT wentaowang newresultonthemeansquareexponentialinputtostatestabilityofstochasticdelayedrecurrentneuralnetworks AT shuhuagong newresultonthemeansquareexponentialinputtostatestabilityofstochasticdelayedrecurrentneuralnetworks AT weichen newresultonthemeansquareexponentialinputtostatestabilityofstochasticdelayedrecurrentneuralnetworks |
_version_ |
1725066218447044608 |