Mean-square exponentially input-to-state stability of stochastic Cohen–Grossberg neural networks with time-varying delays

Autor:	Lingying Teng, Weisong Zhou, Daoyi Xu
Rok vydání:	2015
Předmět:	Mean square Artificial neural network Exponential growth Artificial Intelligence Control theory Cognitive Neuroscience State (functional analysis) Stability (probability) Differential inequalities Computer Science Applications Mathematics Exponential function
Zdroj:	Neurocomputing. 153:54-61
ISSN:	0925-2312
DOI:	10.1016/j.neucom.2014.11.052
Popis:	In this paper, a class of stochastic Cohen–Grossberg neural networks with time-varying delays is considered. By utilizing Razumikhin technique and constructing new Halanay differential inequalities, some sufficient conditions ensuring the mean-square exponential input-to-state stability of the networks are obtained. Two numerical examples are given to illustrate the efficiency of the derived results.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::72f1ab8c5f6a1834ab1a27dc426a4ea4 https://doi.org/10.1016/j.neucom.2014.11.052 Zobrazit plný text záznamu Full Text from ScienceDirect