Noise-to-state practical stability and stabilization of random neural networks

Ticao Jiao; Guangdeng Zong; C. K. Ahn

doi:10.1007/s11071-020-05628-0

Noise-to-state practical stability and stabilization of random neural networks

Ticao Jiao^*
, Guangdeng Zong
, C. K. Ahn

^*Corresponding author for this work

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

22 Citations (Scopus)

Abstract

This paper is devoted to studying noise-to-state practical stability and stabilization problems for random neural networks in the presence of general disturbances. It is proved that the existence and uniqueness of solutions is ensured if the noise intensity function is locally Lipschitz. Using random Lyapunov theory and the existence of practical Lyapunov functions, criteria are established for noise-to-state practical stability in mean of random neural networks. Some easily checkable and computable conditions are provided based on the structure characterization of the neural networks. Numerical examples are given to demonstrate the effectiveness of the developed methods.

Original language	English
Pages (from-to)	2469-2481
Number of pages	13
Journal	Nonlinear Dynamics
Volume	100
Issue number	3
DOIs	https://doi.org/10.1007/s11071-020-05628-0
Publication status	Published - 2020 May 1

Bibliographical note

Funding Information:
This work is supported by National Natural Science Foundation of China (61703249), (61773235), (61673197), (61703132) and (51707110), a Project funded by China Postdoctoral Science Foundation (2019M652351) and Taishan Scholar Project of Shandong Province (TSQN20161033) .

Publisher Copyright:
© 2020, Springer Nature B.V.

Keywords

Noise-to-state practical stability
Practical Lyapunov function
Random neural networks

ASJC Scopus subject areas

Control and Systems Engineering
Aerospace Engineering
Ocean Engineering
Mechanical Engineering
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1007/s11071-020-05628-0

Cite this

@article{bf1ac8fe25a44559b3889a8d92e5ab94,

title = "Noise-to-state practical stability and stabilization of random neural networks",

abstract = "This paper is devoted to studying noise-to-state practical stability and stabilization problems for random neural networks in the presence of general disturbances. It is proved that the existence and uniqueness of solutions is ensured if the noise intensity function is locally Lipschitz. Using random Lyapunov theory and the existence of practical Lyapunov functions, criteria are established for noise-to-state practical stability in mean of random neural networks. Some easily checkable and computable conditions are provided based on the structure characterization of the neural networks. Numerical examples are given to demonstrate the effectiveness of the developed methods.",

keywords = "Noise-to-state practical stability, Practical Lyapunov function, Random neural networks",

author = "Ticao Jiao and Guangdeng Zong and Ahn, \{C. K.\}",

note = "Funding Information: This work is supported by National Natural Science Foundation of China (61703249), (61773235), (61673197), (61703132) and (51707110), a Project funded by China Postdoctoral Science Foundation (2019M652351) and Taishan Scholar Project of Shandong Province (TSQN20161033) . Publisher Copyright: {\textcopyright} 2020, Springer Nature B.V.",

year = "2020",

month = may,

day = "1",

doi = "10.1007/s11071-020-05628-0",

language = "English",

volume = "100",

pages = "2469--2481",

journal = "Nonlinear Dynamics",

issn = "0924-090X",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - Noise-to-state practical stability and stabilization of random neural networks

AU - Jiao, Ticao

AU - Zong, Guangdeng

AU - Ahn, C. K.

N1 - Funding Information: This work is supported by National Natural Science Foundation of China (61703249), (61773235), (61673197), (61703132) and (51707110), a Project funded by China Postdoctoral Science Foundation (2019M652351) and Taishan Scholar Project of Shandong Province (TSQN20161033) . Publisher Copyright: © 2020, Springer Nature B.V.

PY - 2020/5/1

Y1 - 2020/5/1

N2 - This paper is devoted to studying noise-to-state practical stability and stabilization problems for random neural networks in the presence of general disturbances. It is proved that the existence and uniqueness of solutions is ensured if the noise intensity function is locally Lipschitz. Using random Lyapunov theory and the existence of practical Lyapunov functions, criteria are established for noise-to-state practical stability in mean of random neural networks. Some easily checkable and computable conditions are provided based on the structure characterization of the neural networks. Numerical examples are given to demonstrate the effectiveness of the developed methods.

AB - This paper is devoted to studying noise-to-state practical stability and stabilization problems for random neural networks in the presence of general disturbances. It is proved that the existence and uniqueness of solutions is ensured if the noise intensity function is locally Lipschitz. Using random Lyapunov theory and the existence of practical Lyapunov functions, criteria are established for noise-to-state practical stability in mean of random neural networks. Some easily checkable and computable conditions are provided based on the structure characterization of the neural networks. Numerical examples are given to demonstrate the effectiveness of the developed methods.

KW - Noise-to-state practical stability

KW - Practical Lyapunov function

KW - Random neural networks

UR - https://www.scopus.com/pages/publications/85084137562

U2 - 10.1007/s11071-020-05628-0

DO - 10.1007/s11071-020-05628-0

M3 - Article

AN - SCOPUS:85084137562

SN - 0924-090X

VL - 100

SP - 2469

EP - 2481

JO - Nonlinear Dynamics

JF - Nonlinear Dynamics

IS - 3

ER -

Noise-to-state practical stability and stabilization of random neural networks

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this