Some novel approaches on state estimation of delayed neural networks

Some novel approaches on state estimation of delayed neural networks
复制标题

延迟神经网络状态估计的一些新方法

DOI:
10.1016/j.ins.2016.08.064
复制
发表时间:
2016-12
影响因子:
8.1
通讯作者:
Zhong, Shouming
Zhong, Shouming
中科院分区:
计算机科学1区
文献类型:
--
作者:
Liu, Xinzhi;Tang, Yuanyan;Zhu, Hong;Zhong, Shouming

文献摘要

参考文献

被引文献

相似文献

本文研究了一类具有时变延迟的神经网络(NN)的状态估计问题。构造了一种新颖的 Lyapunov-Krasovskii 泛函 (LKF),其中使用三重积分项并采用二次延迟划分方法 (SDPA)。与现有的延迟划分方法相比,所提出的方法可以利用更多关于时间延迟间隔的信息。通过充分利用改进的 Wirtinger 积分不等式 (MWII),导出了改进的延迟相关稳定性准则,保证了延迟神经网络 (DNN) 期望状态估计器的存在。根据线性矩阵不等式(LMI)的解,获得更好的估计器增益矩阵。此外,通过引入一些可调参数,提出了一种新的激活函数划分方法。三个数值例子和仿真证明了所提出方法的有效性和优点。
This paper studies the issue of state estimation for a class of neural networks (NNs) with time-varying delay. A novel Lyapunov-Krasovskii functional (LKF) is constructed, where triple integral terms are used and a secondary delay-partition approach (SDPA) is employed. Compared with the existing delay-partition approaches, the proposed approach can exploit more information on the time-delay intervals. By taking full advantage of a modified Wirtinger’s integral inequality (MWII), improved delay-dependent stability criteria are derived, which guarantee the existence of desired state estimator for delayed neural networks (DNNs). A better estimator gain matrix is obtained in terms of the solution of linear matrix inequalities (LMIs). In addition, a new activation function dividing method is developed by bringing in some adjustable parameters. Three numerical examples with simulations are presented to demonstrate the effectiveness and merits of the proposed methods.
DOI: 10.1007/s11071-012-0499-7
发表时间: 2012-06
期刊: Nonlinear Dynamics
影响因子: 5.6
作者:
Zhengguang Wu;Ju H. Park;H. Su;J. Chu
通讯作者: Zhengguang Wu;Ju H. Park;H. Su;J. Chu
DOI: 10.1016/j.ins.2016.02.004
发表时间: 2016-06
期刊: Inf. Sci.
影响因子: --
作者:
C. Ahn;P. Shi;R. Agarwal;Jing Xu
通讯作者: C. Ahn;P. Shi;R. Agarwal;Jing Xu
DOI: 10.1109/tnn.2008.2000206
发表时间: 2008-08-01
影响因子: --
作者:
Huang, He;Feng, Gang;Cao, Jinde
通讯作者: Cao, Jinde
使用延迟分解方法的时变延迟神经网络的新延迟相关稳定性准则
DOI: 10.1109/tnnls.2013.2285564
发表时间: 2014-07-01
影响因子: 10.4
作者:
Ge, Chao;Hua, Changchun;Guan, Xinping
通讯作者: Guan, Xinping
DOI: 10.1016/j.neucom.2013.09.020
发表时间: 2014-04
期刊: Neurocomputing
影响因子: 6
作者:
S. Lakshmanan;K. Mathiyalagan;Ju H. Park;R. Sakthivel;Fathalla A. Rihan
通讯作者: S. Lakshmanan;K. Mathiyalagan;Ju H. Park;R. Sakthivel;Fathalla A. Rihan