Cohen-Grossberg神经网络稳定性分析

Stability analysis criterion for Cohen-Grossberg neural networks

为了研究具有逆Lipschitz激励函数的Cohen-Grossberg神经网络的稳定性,应用Brouwer拓扑度性质和线性矩阵不等式技术,探讨了Cohen-Grossberg神经网络的平衡点的存在性及唯一性。通过构造合适的Lyapunov函数和利用Lyapunov对角稳定性矩阵,给出了唯一平衡点全局指数稳定的充分条件。

The purpose of this study is to present a novel class of Cohen-Grossberg neural networks with inverse-Lipschitz neuron activation functions. By employing the Brouwer degree properties and linear matrix inequality techniques, the existence and uniqueness of equilibrium point for Cohen-Grossberg neural networks are investigated. With the construction of appropriate Lyapunov functions and the application of Lyapunov diagonally stable matrices; this study provides a sufficient condition which is used to check the global exponential stability of a unique equilibrium point.