Improved exponential convergence result for generalized neural networks including interval time-varying delayed signals

G. Rajchakit; R. Saravanakumar; Choon Ki Ahn; Hamid Reza Karimi

doi:10.1016/j.neunet.2016.10.009

Improved exponential convergence result for generalized neural networks including interval time-varying delayed signals

G. Rajchakit, R. Saravanakumar, Choon Ki Ahn, Hamid Reza Karimi

School of Electrical Engineering

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

34 Citations (Scopus)

Abstract

This article examines the exponential stability analysis problem of generalized neural networks (GNNs) including interval time-varying delayed states. A new improved exponential stability criterion is presented by establishing a proper Lyapunov–Krasovskii functional (LKF) and employing new analysis theory. The improved reciprocally convex combination (RCC) and weighted integral inequality (WII) techniques are utilized to obtain new sufficient conditions to ascertain the exponential stability result of such delayed GNNs. The superiority of the obtained results is clearly demonstrated by numerical examples.

Original language	English
Pages (from-to)	10-17
Number of pages	8
Journal	Neural Networks
Volume	86
DOIs	https://doi.org/10.1016/j.neunet.2016.10.009
Publication status	Published - 2017 Feb 1

Bibliographical note

Funding Information:
The work was supported in part by the Thailand Research Fund (TRF) Grant No. RSA5980019 , the Higher Education Commission and Faculty of Science, Maejo University, Thailand , and in part by the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning ( NRF-2014R1A1A1006101 ).

Publisher Copyright:
© 2016 Elsevier Ltd

Keywords

Generalized neural network
Stability analysis
Time-varying delay
Weighted integral inequality

ASJC Scopus subject areas

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/j.neunet.2016.10.009

Cite this

@article{d85190e33bc748e59509ef02fe09eab8,

title = "Improved exponential convergence result for generalized neural networks including interval time-varying delayed signals",

abstract = "This article examines the exponential stability analysis problem of generalized neural networks (GNNs) including interval time-varying delayed states. A new improved exponential stability criterion is presented by establishing a proper Lyapunov–Krasovskii functional (LKF) and employing new analysis theory. The improved reciprocally convex combination (RCC) and weighted integral inequality (WII) techniques are utilized to obtain new sufficient conditions to ascertain the exponential stability result of such delayed GNNs. The superiority of the obtained results is clearly demonstrated by numerical examples.",

keywords = "Generalized neural network, Stability analysis, Time-varying delay, Weighted integral inequality",

author = "G. Rajchakit and R. Saravanakumar and Ahn, {Choon Ki} and Karimi, {Hamid Reza}",

note = "Funding Information: The work was supported in part by the Thailand Research Fund (TRF) Grant No. RSA5980019 , the Higher Education Commission and Faculty of Science, Maejo University, Thailand , and in part by the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning ( NRF-2014R1A1A1006101 ). Publisher Copyright: {\textcopyright} 2016 Elsevier Ltd",

year = "2017",

month = feb,

day = "1",

doi = "10.1016/j.neunet.2016.10.009",

language = "English",

volume = "86",

pages = "10--17",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Improved exponential convergence result for generalized neural networks including interval time-varying delayed signals

AU - Rajchakit, G.

AU - Saravanakumar, R.

AU - Ahn, Choon Ki

AU - Karimi, Hamid Reza

N1 - Funding Information: The work was supported in part by the Thailand Research Fund (TRF) Grant No. RSA5980019 , the Higher Education Commission and Faculty of Science, Maejo University, Thailand , and in part by the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning ( NRF-2014R1A1A1006101 ). Publisher Copyright: © 2016 Elsevier Ltd

PY - 2017/2/1

Y1 - 2017/2/1

N2 - This article examines the exponential stability analysis problem of generalized neural networks (GNNs) including interval time-varying delayed states. A new improved exponential stability criterion is presented by establishing a proper Lyapunov–Krasovskii functional (LKF) and employing new analysis theory. The improved reciprocally convex combination (RCC) and weighted integral inequality (WII) techniques are utilized to obtain new sufficient conditions to ascertain the exponential stability result of such delayed GNNs. The superiority of the obtained results is clearly demonstrated by numerical examples.

AB - This article examines the exponential stability analysis problem of generalized neural networks (GNNs) including interval time-varying delayed states. A new improved exponential stability criterion is presented by establishing a proper Lyapunov–Krasovskii functional (LKF) and employing new analysis theory. The improved reciprocally convex combination (RCC) and weighted integral inequality (WII) techniques are utilized to obtain new sufficient conditions to ascertain the exponential stability result of such delayed GNNs. The superiority of the obtained results is clearly demonstrated by numerical examples.

KW - Generalized neural network

KW - Stability analysis

KW - Time-varying delay

KW - Weighted integral inequality

UR - http://www.scopus.com/inward/record.url?scp=85001948852&partnerID=8YFLogxK

U2 - 10.1016/j.neunet.2016.10.009

DO - 10.1016/j.neunet.2016.10.009

M3 - Article

C2 - 27923168

AN - SCOPUS:85001948852

SN - 0893-6080

VL - 86

SP - 10

EP - 17

JO - Neural Networks

JF - Neural Networks

ER -

Improved exponential convergence result for generalized neural networks including interval time-varying delayed signals

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this