中立联想记忆神经网络鲁棒稳定性新准则  

New criteria for robust stability of bidirectional associative memory neural networks of neutral-type

作　　者：冯伟[1,2] 吴海霞[1,2] 但松健[2] 

机构地区：[1]重庆大学自动化学院,重庆400044 [2]重庆第二师范学院数学与信息工程系,重庆400065

出　　处：《计算机应用研究》2015年第4期1048-1051,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61103211);重庆市博士后基金资助项目(XM201310);重庆市教委科技项目(KJ1401403;KJ1401405)

摘　　要：针对一类具有离散时滞和参数范数有界的不确定性中立联想记忆神经网络的全局渐近鲁棒稳定性问题进行了研究。通过应用范数理论和矩阵不等式分析方法,并构造合适的Lyapunov-Krasovskii泛函,推导出了与时滞无关的新稳定性判定准则,用于保证神经网络的平衡点是全局渐近鲁棒稳定的。该准则中包含的未知参数少、计算复杂度低,易于验证。仿真算例验证了新判定准则的有效性。By employing a suitable Lyapunov functional,matrix inequality method and using the norm-bounded method,this paper studied the problem of global asymptotic robust stability for the class of bidirectional associative memory neural network model of neutral-type with discrete time delays and norm-bounded uncertainties. And it derived new delay-independent stability criteria to guarantee the equilibrium point of this class of neural network was global asymptotically robust stable. The proposed results are easy to verify because of less unknown parameters and low computational complexity in these criteria. A numerical example demonstrates the effectiveness of the criteria presented.

关 键 词：中立联想记忆神经网络 鲁棒稳定性 离散时滞 范数有界 李雅普诺夫泛函 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]