期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2018
卷号：2233&2234
页码：561-565
出版社：Newswood and International Association of Engineers
摘要：New results on passivity criteria for a class of neural
networks with interval and distributed time-varying delays,
as well as generalized activation function, is investigated. Based
on refined Jensen’s inequalities, improved Lyapunov-Krasovskii
functional (LKF) with double integrals, triple integrals, and
quadruple integrals, all of them are picked up in terms of linear
matrix inequalities (LMIs) which can be checked numerically
using the effective LMIs toolbox in MATLAB. Additionally, the
effectiveness of approach considered in this paper is illustrated
by numerical examples which is less conservative than the
previous results.
关键词：passivity analysis; neural networks; linear
matrix inequality; discrete and distributed time;varying delays
