Novel robust stability criteria for stochastic Hopfield neural networks with time delays

Rongni Yang; Huijun Gao; Peng Shi

doi:10.1109/TSMCB.2008.2006860

Novel robust stability criteria for stochastic Hopfield neural networks with time delays

Rongni Yang^*
, Huijun Gao
, Peng Shi

^*Corresponding author for this work

School of Astronautics

Harbin Institute of Technology
University of South Wales
Victoria University
University of South Australia

Research output: Contribution to journal › Article › peer-review

161 Scopus citations

Abstract

In this paper, the problem of asymptotic stability for stochastic Hopfield neural networks (HNNs) with time delays is investigated. New delay-dependent stability criteria are presented by constructing a novel Lyapunov-Krasovskii functional. Moreover, the results are further extended to the delayed stochastic HNNs with parameter uncertainties. The main idea is based on the delay partitioning technique, which differs greatly from most existing results and reduces conservatism. Numerical examples are provided to illustrate the effectiveness and less conservativeness of the developed techniques.

Original language	English
Pages (from-to)	467-474
Number of pages	8
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	39
Issue number	2
DOIs	https://doi.org/10.1109/TSMCB.2008.2006860
State	Published - 2009

Keywords

Hopfield neural networks (HNNs)
Lyapunov-Krasovskii functional
Robust stability
Stochastic systems
Time delay
Uncertainties

Access to Document

10.1109/TSMCB.2008.2006860

Cite this

@article{ff3d0660f134464a8ab038dbfeac2d25,

title = "Novel robust stability criteria for stochastic Hopfield neural networks with time delays",

abstract = "In this paper, the problem of asymptotic stability for stochastic Hopfield neural networks (HNNs) with time delays is investigated. New delay-dependent stability criteria are presented by constructing a novel Lyapunov-Krasovskii functional. Moreover, the results are further extended to the delayed stochastic HNNs with parameter uncertainties. The main idea is based on the delay partitioning technique, which differs greatly from most existing results and reduces conservatism. Numerical examples are provided to illustrate the effectiveness and less conservativeness of the developed techniques.",

keywords = "Hopfield neural networks (HNNs), Lyapunov-Krasovskii functional, Robust stability, Stochastic systems, Time delay, Uncertainties",

author = "Rongni Yang and Huijun Gao and Peng Shi",

year = "2009",

doi = "10.1109/TSMCB.2008.2006860",

language = "英语",

volume = "39",

pages = "467--474",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Novel robust stability criteria for stochastic Hopfield neural networks with time delays

AU - Yang, Rongni

AU - Gao, Huijun

AU - Shi, Peng

PY - 2009

Y1 - 2009

N2 - In this paper, the problem of asymptotic stability for stochastic Hopfield neural networks (HNNs) with time delays is investigated. New delay-dependent stability criteria are presented by constructing a novel Lyapunov-Krasovskii functional. Moreover, the results are further extended to the delayed stochastic HNNs with parameter uncertainties. The main idea is based on the delay partitioning technique, which differs greatly from most existing results and reduces conservatism. Numerical examples are provided to illustrate the effectiveness and less conservativeness of the developed techniques.

AB - In this paper, the problem of asymptotic stability for stochastic Hopfield neural networks (HNNs) with time delays is investigated. New delay-dependent stability criteria are presented by constructing a novel Lyapunov-Krasovskii functional. Moreover, the results are further extended to the delayed stochastic HNNs with parameter uncertainties. The main idea is based on the delay partitioning technique, which differs greatly from most existing results and reduces conservatism. Numerical examples are provided to illustrate the effectiveness and less conservativeness of the developed techniques.

KW - Hopfield neural networks (HNNs)

KW - Lyapunov-Krasovskii functional

KW - Robust stability

KW - Stochastic systems

KW - Time delay

KW - Uncertainties

UR - https://www.scopus.com/pages/publications/64049116250

U2 - 10.1109/TSMCB.2008.2006860

DO - 10.1109/TSMCB.2008.2006860

M3 - 文章

AN - SCOPUS:64049116250

SN - 1083-4419

VL - 39

SP - 467

EP - 474

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

IS - 2

ER -

Novel robust stability criteria for stochastic Hopfield neural networks with time delays

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this