Extended Dissipative Analysis for Neural Networks With Time-Varying Delays

Author

Lee, Tong H. ; Myeong-Jin Park ; Park, Jae Hyo ; Oh-Min Kwon ; Sang-Moon Lee

Author_Institution

Dept. of Electr. Eng., Yeungnam Univ., Kyongsan, South Korea

Volume

25

Issue

10

fYear

2014

fDate

Oct. 2014

Firstpage

1936

Lastpage

1941

Abstract

In this brief, an extended dissipativity analysis was conducted for a neural network with time-varying delays. The concept of the extended dissipativity can be used to solve for the H_∞, L₂ - L_∞, passive, and dissipative performance by adjusting the weighting matrices in a new performance index. In addition, the activation function dividing method is modified by introducing a tuning parameter. Examples are provided to show the effectiveness and less conservatism of the proposed method.

Keywords

delays; matrix algebra; neural nets; time-varying systems; transfer functions; H∞ dissipative performance; H∞ passive performance; L∞ dissipative performance; L∞ passive performance; L2 dissipative performance; L2 passive performance; activation function dividing method; extended dissipative analysis; neural networks; time-varying delays; tuning parameter; weighting matrices; Biological neural networks; Delays; Linear matrix inequalities; Neurons; Stability criteria; Symmetric matrices; Dissipativity; neural networks; passivity; stability; stability.;

fLanguage

English

Journal_Title

Neural Networks and Learning Systems, IEEE Transactions on

Publisher

ieee

ISSN

2162-237X

Type

jour

DOI

10.1109/TNNLS.2013.2296514

Filename

6712166