东南大学学报（英文版）2006，Vol.22Issue(2)：286-293,8.
时滞反馈神经网络模型的周期解的存在性和全局稳定性
Exponential stability and existence of periodic solutions for a class of recurrent neural networks with delays
戴志娟1
作者信息
- 1. 南京大学数学系,南京,210093;扬州教育学院数学系,扬州,225002
- 折叠
摘要
Abstract
Both the global exponential stability and the existence of periodic solutions for a class of recurrent neural networks with continuously distributed delays (RNNs) are studied. By employing the inequality a m∏k=1 bqkk ≤ 1/r m∑k=1 qk brk + 1/r a r(a ≥ 0, bk ≥ 0, qk ＞ 0, with m∑k=1 qk = r - 1 and r ≥ 1), constructing suitable Lyapunov functions and applying the homeomorphism theory, a family of simple and new sufficient conditions are given ensuring the global exponential stability and the existence of periodic solutions of RNNs. The results extend and improve the results of earlier publications.关键词
反馈神经网络/全局稳定性/周期解/时滞/同构/Lyapunov函数Key words
recurrent neural network/global exponential stability/periodic solution/delay/homeomorphism/Lyapunov function分类
数理科学引用本文复制引用
戴志娟..时滞反馈神经网络模型的周期解的存在性和全局稳定性[J].东南大学学报（英文版）,2006,22(2):286-293,8.
