一类具分布时滞神经网络的全局指数稳定性

本文讨论了一类具分布时滞神经网络的稳定性.利用广义Dahlquist数和广义Halanay不等式,我们得到了该神经网络平衡点存在、唯一且全局指数稳定的充分条件.此外,我们的方法还估计出了神经网络指数收敛到平衡点的速度.由于我们的方法去除了关于激活函数的有界性、可微性和单调性的常用假设,因此我们的结果是某些现有结果的推广和改进.

Global Exponential Stability of a Class of Neural Networks with Distributed Delays

The paper investigates stability of a class of neural networks with distributed delays.By generalized Dahlquist constant and generalized Halanay inequality,we derive a sufficient condition for existence,uniqueness and global exponential stability of the equilibrium point of the neural networks.Moreover,our method presents the exponential convergence rate of the neural networks to stable equilibrium point.Our results generalize and improve some existing ones because our method abandons the typical assumptions on boundedness,differentiability and monotonicity of activation functions.