摘要
将一类具有混合时滞随机神经网络均方渐近稳定的判据推广到不确定神经网络的鲁棒稳定性,所导出的判据都表示为线性矩阵不等式(LMI)的形式,可通过使用一些标准的数值方法求解.最后给出了一个简单的例子说明所提出的判定条件的有效性和可应用性.
A linear matrix inequality (LMI) approach is developed to derive the criteria for the asymptotic stability, which can be readily checked by using some standard numerical packages such as the Matlab LMI Toolbox and expressed in form of LMI. In this paper, the results are extended to uncertain stochastic neural networks with Markovian jumping parameters and mixed delays. Finally, a simple example is provided to demonstrate the effectiveness and applicability of the proposed testing criteria.
出处
《数学的实践与认识》
CSCD
北大核心
2014年第7期254-259,共6页
Mathematics in Practice and Theory
基金
宿迁高等师范学校科研基金(2013)
关键词
随机神经网络
不确定神经网络
混合时滞
鲁棒稳定性
线性矩阵不等式
stochastic neural networks
uncertain neural networks
mixed time delaysrobust stability
linear matrix inequality