A delay-dependent approach to passivity analysis for uncertain neural networks with time-varying Delayd

Chien-Yu Lu; Hsun Heng Tsai; Te Jen Su; Jason Sheng Hong Tsai; Chin-Wen Liao

doi:10.1007/s11063-008-9072-2

A delay-dependent approach to passivity analysis for uncertain neural networks with time-varying Delayd

Chien-Yu Lu, Hsun Heng Tsai, Te Jen Su, Jason Sheng Hong Tsai, Chin-Wen Liao

Department of Industrial Education and Technology

Research output: Contribution to journal › Article

46 Citations (Scopus)

Abstract

This paper deals with the problem of passivity analysis for neural networks with time-varying delay, which is subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. Delay-dependent passivity condition is proposed by using the free-weighting matrix approach. These passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness of the proposed criteria.

Original language	English
Pages (from-to)	237-246
Number of pages	10
Journal	Neural Processing Letters
Volume	27
Issue number	3
DOIs	https://doi.org/10.1007/s11063-008-9072-2
Publication status	Published - 2008 Jun 1

All Science Journal Classification (ASJC) codes

Software
Neuroscience(all)
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1007/s11063-008-9072-2

Fingerprint Dive into the research topics of 'A delay-dependent approach to passivity analysis for uncertain neural networks with time-varying Delayd'. Together they form a unique fingerprint.

Cite this

@article{f6fdec2a140e4a5580fd56c45d1e10fd,

title = "A delay-dependent approach to passivity analysis for uncertain neural networks with time-varying Delayd",

abstract = "This paper deals with the problem of passivity analysis for neural networks with time-varying delay, which is subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. Delay-dependent passivity condition is proposed by using the free-weighting matrix approach. These passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness of the proposed criteria.",

author = "Chien-Yu Lu and Tsai, {Hsun Heng} and Su, {Te Jen} and Tsai, {Jason Sheng Hong} and Chin-Wen Liao",

year = "2008",

month = jun,

day = "1",

doi = "10.1007/s11063-008-9072-2",

language = "English",

volume = "27",

pages = "237--246",

journal = "Neural Processing Letters",

issn = "1370-4621",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - A delay-dependent approach to passivity analysis for uncertain neural networks with time-varying Delayd

AU - Lu, Chien-Yu

AU - Tsai, Hsun Heng

AU - Su, Te Jen

AU - Tsai, Jason Sheng Hong

AU - Liao, Chin-Wen

PY - 2008/6/1

Y1 - 2008/6/1

N2 - This paper deals with the problem of passivity analysis for neural networks with time-varying delay, which is subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. Delay-dependent passivity condition is proposed by using the free-weighting matrix approach. These passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness of the proposed criteria.

AB - This paper deals with the problem of passivity analysis for neural networks with time-varying delay, which is subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. Delay-dependent passivity condition is proposed by using the free-weighting matrix approach. These passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness of the proposed criteria.

UR - http://www.scopus.com/inward/record.url?scp=42449161839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42449161839&partnerID=8YFLogxK

U2 - 10.1007/s11063-008-9072-2

DO - 10.1007/s11063-008-9072-2

M3 - Article

AN - SCOPUS:42449161839

VL - 27

SP - 237

EP - 246

JO - Neural Processing Letters

JF - Neural Processing Letters

SN - 1370-4621

IS - 3

ER -