通过引入更加广泛的一类Lyapunov-Krasovskii泛函,并利用线性矩阵不等式分析技巧,得到了关于可变时滞广义神经网络模型平衡位置全局指数稳定的最新判据,并且判别条件中不限制连接权矩阵符号.该结果精炼和推广了一些已有的结果,并且更少保守,在实践上易于程序实现,方便使用.
[1] 李学明, 廖晓峰, 周尚波. 基于LMI方法的时滞细胞神经网络稳定性分析 [J]. 计算机学报 2004.doi:10.3321/j.issn:0254-4164.2004.03.014
[2] Joy M. Results concerning the absolute stability of delayed neural networks. [J]. Neural Networks: The Official Journal of the International Neural Network Society 2000, 6(6).
[3] Jinde Cao. A set of stability criteria for delayed cellular neural networks [J]. IEEE Transactions on Circuits and Systems.I.Fundamental Theory and Applications 2001, 4(4).
[4] Cao J, Wang J. Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays. [J]. Neural Networks: The Official Journal of the International Neural Network Society 2004, 3(3).
[5] Senan S., Arik S.. New results for exponential stability of delayed cellular neural networks [J]. IEEE Transactions on Circuits and Systems, II. Express briefs 2005, 3(3).
[6] Cao JD.. Global asymptotic stability of delayed bi-directional associative memory neural networks [J]. Applied mathematics and computation 2003, 2/3(2/3).
