随机延迟细胞神经网络的几乎必然指数稳定性

Almost sure exponential stability of stochastic delayed cellular neural networks

依据细胞神经网络的输出函数的饱和线性特征,将状态空间分解成子区域来研究一类延时细胞神经网络在噪声环境下的几乎必然指数稳定性。当细胞神经网络模型的扰动项满足Lipschitz条件时,得到一些几乎必然指数稳定的代数标准。所有结果只需计算网络的平衡点与矩阵的特征值。

In view of the character of saturation of output functions of the cellular neural networks, the method decomposing the state to sub - regions is adopted to study almost sure exponential stability on a class delayed cellular neural networks which are in the noised environment. When perturbed terms in the model of the neural network satisfy Lipschitz condition, some algebraic criteria of almost sure exponential stability are obtained. All results need only to compute equilibrium of networks and eigenvalues of matrices.