Author： Balasubramaniam P. Nagamani G. Rakkiyappan R.
Publisher： Springer Publishing Company
ISSN： 1370-4621
Source： Neural Processing Letters, Vol.32, Iss.2, 2010-10, pp. : 109-130
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
This paper is concerned with delay-dependent passivity analysis for delayed neural networks (DNNs) of neutral type. We first discuss the passivity conditions for DNNs without uncertainties and then extend this result to the case of interval uncertainties. By partitioning the delay intervals into multiple equidistant subintervals, some appropriate Lyapunov-Krasovskii functionals (LKFs) are constructed on these intervals. Considering these new LKFs and using free-weighting matrix approach, several new passivity criteria are proposed in terms of linear matrix inequalities, which are dependent on the size of the time delay. Finally, five numerical examples are given to illustrate the effectiveness and less conservatism of the developed techniques.
Related content
Access to resources
Recommend
