Stability Analysis of Delayed Recurrent Neural Networks Based on a Flexible Terminal Inequality

被引：2
|
作者：
Yu, Shuhang [1 ]
Zhang, Huaguang [2 ,3 ]
Yan, Yuqing [1 ]
Tian, Yufeng [4 ]
机构：
[1] Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110004, Liaoning, Peoples R China
[2] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110004, Liaoning, Peoples R China
[3] Northeastern Univ, Sch Informat Sci & Engn, Shenyang 110004, Liaoning, Peoples R China
[4] Chongqing Univ, Coll Automat, Chongqing 400044, Peoples R China
来源：
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS | 2024年 / 71卷 / 01期
关键词：
Time-varying delay; flexible terminal-based reciprocally convex inequality; recurrent neural networks; stability analysis; GLOBAL ASYMPTOTIC STABILITY; TIME-VARYING DELAYS; FUZZY-SYSTEMS;
D O I：
10.1109/TCSII.2023.3298959
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
The stability issue of recurrent neural networks (RNNs) with time-varying delay is studied in this brief. By adding a set of flexible terminals, a flexible terminal-based reciprocally convex inequality (FTRCI) relying on one adjustable parameter Q is suggested. Different from the existing estimation techniques, FTRCI employs more slack matrices and utilize more delay information. A novel stability criterion based on linear matrix inequalities (LMIs) is developed using FTRCI. The recently developed stability criterion is demonstrated through the use of a numerical example.
引用
收藏
页码：316 / 320
页数：5
相关论文
共 50 条
  • [1] Stability analysis for delayed cellular neural networks based on linear matrix inequality approach
    Liao, XF
    Wong, KW
    Yang, SZ
    INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2004, 14 (09): : 3377 - 3384
  • [2] Improved exponential stability analysis for delayed recurrent neural networks
    Mahmoud, Magdi S.
    Xia, Yuanqing
    JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2011, 348 (02): : 201 - 211
  • [3] Analysis of global asymptotic stability of delayed recurrent neural networks
    Li, Guanjun
    Xu, Jin
    DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES A-MATHEMATICAL ANALYSIS, 2006, 13 : 306 - 309
  • [4] Further analysis on stability of delayed neural networks via inequality technique
    Jiayu Wang
    Journal of Inequalities and Applications, 2011
  • [5] Further analysis on stability of delayed neural networks via inequality technique
    Wang, Jiayu
    JOURNAL OF INEQUALITIES AND APPLICATIONS, 2011,
  • [6] Stability Analysis of Recurrent Neural Networks With Time-Varying Delay by Flexible Terminal Interpolation Method
    Wang, Zhanshan
    Tian, Yufeng
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (02) : 2887 - 2893
  • [7] Stability analysis of delayed neural networks via a new integral inequality
    Yang, Bin
    Wang, Juan
    Wang, Jun
    NEURAL NETWORKS, 2017, 88 : 49 - 57
  • [8] Stability Analysis for Delayed Recurrent Neural Networks Based on Delay-decomposition Approach
    Xing, Guangxia
    Gao, Yanbo
    PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, : 1861 - 1866
  • [9] Stability Analysis of Delayed Neural Networks via Composite-Matrix-Based Integral Inequality
    Shi, Yupeng
    Ye, Dayong
    MATHEMATICS, 2023, 11 (11)
  • [10] Stability analysis of delayed neural networks via compound-parameter -based integral inequality
    Xue, Wenlong
    Jin, Zhenghong
    Tian, Yufeng
    AIMS MATHEMATICS, 2024, 9 (07): : 19345 - 19360
12345