• STABILITY ANALYSIS FOR RECURRENT NEURAL NETWORKS WITH TIME-VARYING DELAYS
Abstract
In this paper global asymptotic stability analysis of static recurrent neural networks with time-varying delay is studied by the LMI approach. Firstly, a novel Lyapunov functional is introduced, which involves the integral terms of the neuron state. Furthermore, a new technique is applied when estimating the upper bound of the derivative of the Lyapunov functional. Based on this, some less conservative criteria are obtained for the concerned static neural networks.Throughout this paper, and denote the n-dimension Euclidean space and set of all real matrices, respectively. A real symmetric matrix P 0 ( 0) denotes P being a positive definite matrix. I is used to denote an identity matrix with proper dimensions. Matrices, if not explicitly stated, are assumed to have compatible dimensions. The symmetric term in a symmetric matrix are denoted by .
Keywords
Full Text:
PDFThis work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
© 2010-2022 International Journal of Mathematical Archive (IJMA) Copyright Agreement & Authorship Responsibility |