Title: Passivity analysis of neural networks with discrete and distributed delays

Authors: JianXi Yang, QianKun Song, JianTing Zhou

Addresses: Computer and Information School, Chongqing Jiaotong University, Chongqing 400074, China. ' Department of Mathematics, Chongqing Jiaotong University, Chongqing 400074, China. ' College of Civil Engineering and Architecture, Chongqing Jiaotong University, Chongqing 400074, China

Abstract: In this paper, the passivity problem is investigated for a class of neural networks with discrete and distributed delays as well as generalised activation functions. By constructing proper Lyapunov-Krasovskii functional and employing a combination of the free-weighting matrix method and inequality technique, a new delay-dependent criterion for the passivity of the addressed neural networks is established in terms of Linear Matrix Inequalities (LMIs), which can be checked numerically using the effective LMI toolbox in MATLAB. Two examples are given to show the effectiveness and less conservatism of the proposed criterion. It is noteworthy that the traditional assumptions on the differentiability of the time-varying delays and the boundedness of its derivative are removed.

Keywords: passivity; neural networks; discrete delays; distributed delays; linear matrix inequalities; LMIs; time-varying delays.

DOI: 10.1504/IJSCC.2010.035418

International Journal of Systems, Control and Communications, 2010 Vol.2 No.4, pp.379 - 390

Published online: 30 Sep 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article