Global asymptotic stability and global exponential stability of continuous-time recurrent neural networks
Global asymptotic stability and global exponential stability of continuous-time recurrent neural networks
复制标题
DOI：
10.1109/tac.2002.1000277
复制
发表时间：
2002-08
期刊：
影响因子：
--
通讯作者：
Sanqing Hu;Jun Wang
中科院分区：
文献类型：
--
作者：
Sanqing Hu;Jun Wang
本文提出了具有 Lipschitz 连续和单调非递减激活函数的一类通用连续时间循环神经网络的全局渐近稳定性 (GAS) 和全局指数稳定性 (GES) 的新结果。我们首先给出神经网络 GAS 的三个充分条件。这些可测试的充分条件不同于现有条件并对其进行了改进。然后，我们将现有的 GAS 结果扩展到 GES 结果，并将现有的 GES 结果扩展到具有较少限制的连接权重矩阵和/或部分 Lipschitz 激活函数的更一般情况。
This paper presents new results on global asymptotic stability (GAS) and global exponential stability (GES) of a general class of continuous-time recurrent neural networks with Lipschitz continuous and monotone nondecreasing activation functions. We first give three sufficient conditions for the GAS of neural networks. These testable sufficient conditions differ from and improve upon existing ones. We then extend an existing GAS result to GES one and also extend the existing GES results to more general cases with less restrictive connection weight matrices and/or partially Lipschitz activation functions.