含脉冲的时标神经网络的平衡解的存在唯一性（英文）  

Existence and uniqueness of equilibrium solution for impulsive neural networks on time scales

作　　者：杨逢建[1] 丁问司[2] 吴东庆[1] 张超龙[1] 陈新明[1] 

机构地区：[1]仲恺农业工程学院计算科学学院,广东广州510225 [2]华南理工大学机械与汽车工程学院,广东广州510641

出　　处：《仲恺农业工程学院学报》2014年第2期32-35,共4页Journal of Zhongkai University of Agriculture and Engineering

基　　金：Supported by National Natural Science Foundation of China(50775075)

摘　　要：讨论了一般性的具有脉冲和时滞的时标神经网络解的存在条件.利用非光滑分析和李雅普诺夫泛函,在不假定激励函数有界和可微的条件下,得到了这类神经网络存在唯一的平衡点的充分条件.作为特例,得到了具有脉冲和时滞的时标Hopfield神经网络、细胞神经网络、双向联想记忆神经网络等系统的平衡解的存在唯一性条件.The dynamics properties of general neural networks with delays and impulses on time scales was discussed .By means of nonsmooth analysis and Lipschitz functional , sufficient conditions were ob-tained for the existence and uniqueness of equilibrium solution without assuming the activation function to be bounded or differentiable .As special cases , the existence and uniqueness of equilibrium solution for Hopfield neural networks , delayed cellular neural networks and bidirectional associative memory networks with impulses on time scales were obtained .

关 键 词：脉冲神经网络 时标 粒度函数 同态映射 平衡解 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]