混合时滞随机神经网络全局渐近同步  

Synchronization in an array of coupled stochastic neural networks with mixed delays

作　　者：黄优良[1] 

机构地区：[1]韶关学院数学系,广东韶关512005

出　　处：《安徽大学学报（自然科学版）》2009年第4期18-25,共8页Journal of Anhui University(Natural Science Edition)

摘　　要：研究了一类具混合时滞神经网络耦合大系统的同步问题.应用矩阵的Kronecker积与线性矩阵不等式,得到耦合大系统同步的一些充分性判据,所得到的结果易于通过Matlab线性矩阵不等式工具箱(LMI)进行检验,所讨论的神经网络具有参数的不确定性、分布时滞、随机扰动以及非线性耦合等,而且弱化了相关文献中激励函数为严格Lipshitz或Sigma型的假定,使所得结果更为精细.The synchronization problem of an array of stochastic delayed neural networks was investigated. By exploiting Kronecker product and linear matrix inequality, some sufficient conditions, under which the array of stochastic delayed neural networks could achieve global asymptotical synchronization in the mean square, were derived. Noted that the LMIs could be easily and effectively solved by using the Matlab LMI toolbox. Here the considered neural networks were quite general, which contained parameter uncertainties, distributed time-delay, stochastic disturbance and nonlinear coupling. The assumption on activation functions was relaxed without assuming to be of Lipschitz type or Sigma type. The sufficient conditions were obtained for the array of stochastic delayed neural networks to be robustly globally asymptotically synchronized in the mean square.

关 键 词：神经网络 同步 时变时滞 分布时滞 LYAPUNOV方法 随机扰动 

分 类 号：O416.2[理学—理论物理]