Delay-slope-dependent stability results of recurrent neural networks

Tao Li; Wei Xing Zheng; Chong Lin

doi:10.1109/TNN.2011.2169425

Delay-slope-dependent stability results of recurrent neural networks

Tao Li, Wei Xing Zheng, Chong Lin

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

112 Citations (Scopus)

Abstract

By using the fact that the neuron activation functions are sector bounded and nondecreasing, this brief presents a new method, named the delay-slope-dependent method, for stability analysis of a class of recurrent neural networks with time-varying delays. This method includes more information on the slope of neuron activation functions and fewer matrix variables in the constructed Lyapunov-Krasovskii functional. Then some improved delay-dependent stability criteria with less computational burden and conservatism are obtained. Numerical examples are given to illustrate the effectiveness and the benefits of the proposed method.

Original language	English
Article number	1
Pages (from-to)	2138-2143
Number of pages	6
Journal	IEEE transactions on neural networks
Volume	22
Issue number	12
DOIs	https://doi.org/10.1109/TNN.2011.2169425
Publication status	Published - 2011

Keywords

Lyapunov functions
neural networks (computer science)

Access to Document

10.1109/TNN.2011.2169425

Cite this

@article{e2728c9611f54ee2a7400dddd33596c1,

title = "Delay-slope-dependent stability results of recurrent neural networks",

abstract = "By using the fact that the neuron activation functions are sector bounded and nondecreasing, this brief presents a new method, named the delay-slope-dependent method, for stability analysis of a class of recurrent neural networks with time-varying delays. This method includes more information on the slope of neuron activation functions and fewer matrix variables in the constructed Lyapunov-Krasovskii functional. Then some improved delay-dependent stability criteria with less computational burden and conservatism are obtained. Numerical examples are given to illustrate the effectiveness and the benefits of the proposed method.",

keywords = "Lyapunov functions, neural networks (computer science)",

author = "Tao Li and Zheng, {Wei Xing} and Chong Lin",

year = "2011",

doi = "10.1109/TNN.2011.2169425",

language = "English",

volume = "22",

pages = "2138--2143",

journal = "IEEE transactions on neural networks",

issn = "1045-9227",

publisher = "IEEE Press",

number = "12",

}

TY - JOUR

T1 - Delay-slope-dependent stability results of recurrent neural networks

AU - Li, Tao

AU - Zheng, Wei Xing

AU - Lin, Chong

PY - 2011

Y1 - 2011

N2 - By using the fact that the neuron activation functions are sector bounded and nondecreasing, this brief presents a new method, named the delay-slope-dependent method, for stability analysis of a class of recurrent neural networks with time-varying delays. This method includes more information on the slope of neuron activation functions and fewer matrix variables in the constructed Lyapunov-Krasovskii functional. Then some improved delay-dependent stability criteria with less computational burden and conservatism are obtained. Numerical examples are given to illustrate the effectiveness and the benefits of the proposed method.

AB - By using the fact that the neuron activation functions are sector bounded and nondecreasing, this brief presents a new method, named the delay-slope-dependent method, for stability analysis of a class of recurrent neural networks with time-varying delays. This method includes more information on the slope of neuron activation functions and fewer matrix variables in the constructed Lyapunov-Krasovskii functional. Then some improved delay-dependent stability criteria with less computational burden and conservatism are obtained. Numerical examples are given to illustrate the effectiveness and the benefits of the proposed method.

KW - Lyapunov functions

KW - neural networks (computer science)

UR - http://handle.uws.edu.au:8081/1959.7/526348

U2 - 10.1109/TNN.2011.2169425

DO - 10.1109/TNN.2011.2169425

M3 - Article

SN - 1045-9227

VL - 22

SP - 2138

EP - 2143

JO - IEEE transactions on neural networks

JF - IEEE transactions on neural networks

IS - 12

M1 - 1

ER -

Delay-slope-dependent stability results of recurrent neural networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this