时滞耦合随机神经网络全局指数同步  

Exponential synchronization in an array of coupled delayed stochastic neural networks

作　　者：黄优良[1] 邱华[2] 房少梅[2] 

机构地区：[1]韶关学院数学系,广东韶关512005 [2]华南农业大学应用数学系,广东广州510642

出　　处：《福州大学学报（自然科学版）》2010年第1期48-53,共6页Journal of Fuzhou University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(10576013;10871075)

摘　　要：应用矩阵的Kronecker积、线性矩阵不等式及随机微分方程等有关工具,研究了一类具离散时滞与分布时滞的随机神经网络耦合大系统的均方全局指数同步问题.综合考虑了参数的不确定性、分布时滞、随机扰动、非线性耦合等的影响,并弱化了相关文献中激励函数为严格Lipshtz或Sigma型的假定,得到该耦合大系统均方全局指数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.By exploiting Kronecker product,linear matrix inequality and stochastic differential equation theory,the exponential synchronization problem of an array of coupled stochastic delayed neural networks is investigated.The considered neural networks are quite general,which contain parameter uncertainties,distributed time-delay,stochastic disturbance and nonlinear coupling.And the assumption on activation functions is relaxed without assuming to be of Lipschitz type or Sigma type.Some sufficient conditions,under which the array of stochastic delayed neural networks can achieve global exponential synchronization in the mean square,are derived.The obtained sufficient conditions can be easily and effectively solved by using the Matlab LMI toolbox.

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

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]