State estimation of recurrent neural networks with two Markovian jumping parameters and mixed delays

被引:0
|
作者
Ren Jiaojiao [1 ]
Zhu Hong [1 ]
Zhong Shouming [2 ]
Zeng Yong [1 ]
Zhang Yuping [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Automat Engn, Chengdu 611731, Sichuan, Peoples R China
[2] Univ Elect Sci & Technol China, Sch Math Sci, Chengdu 611731, Sichuan, Peoples R China
关键词
Recurrent neural networks; State estimation; Markovian jumping parameters; Matrix decomposition; DISTRIBUTED DELAYS; STABILITY ANALYSIS; DISCRETE; DESIGN;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper examines the problem of state estimation of recurrent neural networks with two Markovian jumping parameters and mixed delays. Based on the method of matrix decomposition and the technique of inequalities, several sufficient criteria are established in terms of linear matrix inequalities (LMIs). Compared with the existing results, the obtained conditions are more effective due to constructing a newly augmented Lyapunov-Krasovskii functional, which makes full use of the cross terms information. Numerical simulations are given to illustrate the effectiveness and advantage of the proposed method.
引用
收藏
页码:1577 / 1582
页数:6
相关论文
共 50 条