Stability analysis of neural-network interconnected systems

Jiing Dong Hwang; Feng Hsiag Hsiao

doi:10.1109/TNN.2002.806643

Stability analysis of neural-network interconnected systems

Jiing Dong Hwang^*
, Feng Hsiag Hsiao

^*Corresponding author for this work

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

22 Scopus citations

Abstract

This paper is concerned with the stability problem of a neural-network (NN) interconnected system which consists of a set of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Subsequently, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of NN interconnected systems. Finally, a numerical example with simulations is given to demonstrate the results.

Original language	English
Pages (from-to)	201-208
Number of pages	8
Journal	IEEE Transactions on Neural Networks
Volume	14
Issue number	1
DOIs	https://doi.org/10.1109/TNN.2002.806643
State	Published - 01 2003
Externally published	Yes

Keywords

Interconnected systems
Linear difference inclusion (LDI)
Neural networks (NNs)

Access to Document

10.1109/TNN.2002.806643

Cite this

@article{868b1c75545348b09a2d612394d79f9d,

title = "Stability analysis of neural-network interconnected systems",

abstract = "This paper is concerned with the stability problem of a neural-network (NN) interconnected system which consists of a set of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Subsequently, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of NN interconnected systems. Finally, a numerical example with simulations is given to demonstrate the results.",

keywords = "Interconnected systems, Linear difference inclusion (LDI), Neural networks (NNs)",

author = "Hwang, \{Jiing Dong\} and Hsiao, \{Feng Hsiag\}",

year = "2003",

month = jan,

doi = "10.1109/TNN.2002.806643",

language = "英语",

volume = "14",

pages = "201--208",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

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

number = "1",

}

TY - JOUR

T1 - Stability analysis of neural-network interconnected systems

AU - Hwang, Jiing Dong

AU - Hsiao, Feng Hsiag

PY - 2003/1

Y1 - 2003/1

N2 - This paper is concerned with the stability problem of a neural-network (NN) interconnected system which consists of a set of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Subsequently, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of NN interconnected systems. Finally, a numerical example with simulations is given to demonstrate the results.

AB - This paper is concerned with the stability problem of a neural-network (NN) interconnected system which consists of a set of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Subsequently, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of NN interconnected systems. Finally, a numerical example with simulations is given to demonstrate the results.

KW - Interconnected systems

KW - Linear difference inclusion (LDI)

KW - Neural networks (NNs)

UR - https://www.scopus.com/pages/publications/0037277808

U2 - 10.1109/TNN.2002.806643

DO - 10.1109/TNN.2002.806643

M3 - 文章

AN - SCOPUS:0037277808

SN - 1045-9227

VL - 14

SP - 201

EP - 208

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 1

ER -

Stability analysis of neural-network interconnected systems

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this