摘要
使用不等式技巧和非负矩阵性质 ,讨论了含可变时延的大规模通有神经网络动力系统的渐近行为 ,建立了估计该系统平衡态吸引域的方法 .当时延有界时 ,给出了平衡态的指数吸引域及指数收敛速度估计 .所得结论可用于含时延的大规模通有神经网络动力系统的容错性能评价以及综合过程 .
Asymptotic behavior is discussed for large-scale general neural networks with time-varying delays by employing the inequality techniques and the properties of nonnegative matrices. Some estimation results are obtained about the attraction domain of equilibrium states and sufficient conditions for asympotic stability of large-scale general neural networks with time-varying delays. Moreover, the exponential attraction domain and the exponential convergent rate of equilibrium states for large-scale general neural networks with time-varying delays are estimated when delays are bounded. These results can be used for evaluation of error-correction capability and synthesis procedure of the networks.
出处
《西安交通大学学报》
EI
CAS
CSCD
北大核心
2001年第10期1089-1092,共4页
Journal of Xi'an Jiaotong University
基金
国家自然科学基金资助项目 (199710 6 6 )
四川省教育厅重点资助项目
