Global robust exponential stability for interval delayed neural networks with possibly unbounded activation functions

Sitian Qin; Dejun Fan; Ming Yan; Qinghe Liu

doi:10.1007/s11063-013-9309-6

Global robust exponential stability for interval delayed neural networks with possibly unbounded activation functions

Sitian Qin
, Dejun Fan^*
, Ming Yan
, Qinghe Liu

^*Corresponding author for this work

Harbin Institute of Technology Weihai
Automotive Engineering College

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

5 Scopus citations

Abstract

In this paper, we mainly study the global robust exponential stability of the neural networks with possibly unbounded activation functions. Based on the topological degree theory and Lyapunov functional method, we provide some new sufficient conditions for the global robust exponential stability. Under these conditions, we prove existence, uniqueness and global robust exponential stability of equilibrium point. In the end, some examples are provided to demonstrate the validity of the theoretical results.

Original language	English
Pages (from-to)	35-50
Number of pages	16
Journal	Neural Processing Letters
Volume	40
Issue number	1
DOIs	https://doi.org/10.1007/s11063-013-9309-6
State	Published - Aug 2014
Externally published	Yes

Keywords

Delayed neural networks with possibly unbounded activation
Global robust exponential stability
Topological degree theory

Access to Document

10.1007/s11063-013-9309-6

Cite this

@article{1c92b745e6044e41b0d6cf34f1ee616a,

title = "Global robust exponential stability for interval delayed neural networks with possibly unbounded activation functions",

abstract = "In this paper, we mainly study the global robust exponential stability of the neural networks with possibly unbounded activation functions. Based on the topological degree theory and Lyapunov functional method, we provide some new sufficient conditions for the global robust exponential stability. Under these conditions, we prove existence, uniqueness and global robust exponential stability of equilibrium point. In the end, some examples are provided to demonstrate the validity of the theoretical results.",

keywords = "Delayed neural networks with possibly unbounded activation, Global robust exponential stability, Topological degree theory",

author = "Sitian Qin and Dejun Fan and Ming Yan and Qinghe Liu",

year = "2014",

month = aug,

doi = "10.1007/s11063-013-9309-6",

language = "英语",

volume = "40",

pages = "35--50",

journal = "Neural Processing Letters",

issn = "1370-4621",

publisher = "Springer Netherlands",

number = "1",

}

TY - JOUR

T1 - Global robust exponential stability for interval delayed neural networks with possibly unbounded activation functions

AU - Qin, Sitian

AU - Fan, Dejun

AU - Yan, Ming

AU - Liu, Qinghe

PY - 2014/8

Y1 - 2014/8

N2 - In this paper, we mainly study the global robust exponential stability of the neural networks with possibly unbounded activation functions. Based on the topological degree theory and Lyapunov functional method, we provide some new sufficient conditions for the global robust exponential stability. Under these conditions, we prove existence, uniqueness and global robust exponential stability of equilibrium point. In the end, some examples are provided to demonstrate the validity of the theoretical results.

AB - In this paper, we mainly study the global robust exponential stability of the neural networks with possibly unbounded activation functions. Based on the topological degree theory and Lyapunov functional method, we provide some new sufficient conditions for the global robust exponential stability. Under these conditions, we prove existence, uniqueness and global robust exponential stability of equilibrium point. In the end, some examples are provided to demonstrate the validity of the theoretical results.

KW - Delayed neural networks with possibly unbounded activation

KW - Global robust exponential stability

KW - Topological degree theory

UR - https://www.scopus.com/pages/publications/84903782823

U2 - 10.1007/s11063-013-9309-6

DO - 10.1007/s11063-013-9309-6

M3 - 文章

AN - SCOPUS:84903782823

SN - 1370-4621

VL - 40

SP - 35

EP - 50

JO - Neural Processing Letters

JF - Neural Processing Letters

IS - 1

ER -

Global robust exponential stability for interval delayed neural networks with possibly unbounded activation functions

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this