Stability Analysis of Quaternion-Valued Neutral Neural Networks with Generalized Activation Functions

被引：3
|
作者：
Wu, Yanqiu [1 ]
Tu, Zhengwen [1 ]
Dai, Nina [2 ]
Wang, Liangwei [1 ]
Hu, Ning [3 ]
Peng, Tao [1 ]
机构：
[1] Chongqing Three Gorges Univ, Sch Math & Stat, Wanzhou 404100, Peoples R China
[2] Chongqing Three Gorges Univ, Sch Elect & Informat Engn, Wanzhou 404100, Peoples R China
[3] Chongqing Three Gorges Univ, Expt & Practice Ctr, Wanzhou 404100, Peoples R China
来源：
COGNITIVE COMPUTATION | 2024年 / 16卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Quaternion-valued neutral neural networks (QVNNNs); Stability; Wirtinger-based inequality; Reciprocally convex inequality; Neutral delay; GLOBAL EXPONENTIAL STABILITY; TIME-VARYING DELAYS; SYNCHRONIZATION; DISCRETE; CRITERIA;
D O I：
10.1007/s12559-023-10212-w
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Stability is a central issue in the study of dynamical systems, and quaternion-valued neural networks (QVNNs) perform well in handling the problem involving high-dimension date. The paper is dedicated to investigating the stability problem of QVNNs with neutral delay. In order to accurately estimate the derivative of Lyapunov functional, both reciprocally convex inequality and Wirtinger-based inequality are extended to the quaternion domain. And the direct quaternion method is used to analyze the quaternion-valued neutral neural networks (QVNNNs). Based on the generalized inequalities, the existence, uniqueness, and global stability criteria for QVNNS with several freedom matrices are derived. Concision and compact stability criteria of QVNNNs are established in the form of quaternion-valued LMIs, and the correctness of the theoretical results was verified through a numerical example.
引用
收藏
页码：392 / 403
页数：12
相关论文
共 50 条
  • [1] Stability Analysis of Quaternion-Valued Neutral Neural Networks with Generalized Activation Functions
    Yanqiu Wu
    Zhengwen Tu
    Nina Dai
    Liangwei Wang
    Ning Hu
    Tao Peng
    Cognitive Computation, 2024, 16 : 392 - 403
  • [2] Multistability analysis of quaternion-valued neural networks with cosine activation functions *
    Yu, Siyi
    Li, Hua
    Chen, Xiaofeng
    Lin, Dongyuan
    APPLIED MATHEMATICS AND COMPUTATION, 2023, 445
  • [3] Lagrange stability of memristive quaternion-valued neural networks with neutral items
    Tu, Zhengwen
    Wang, Dandan
    Yang, Xinsong
    Cao, Jinde
    NEUROCOMPUTING, 2020, 399 (399) : 380 - 389
  • [4] Generalized exponential stability of neutral stochastic quaternion-valued neural networks with variable coefficients and infinite delay
    Ruan, Dehao
    Lu, Yao
    SYSTEMS & CONTROL LETTERS, 2024, 191
  • [5] Stability criteria of quaternion-valued neutral-type delayed neural networks
    Song, Qiankun
    Long, Luyu
    Zhao, Zhenjiang
    Liu, Yurong
    Alsaadi, Fuad E.
    NEUROCOMPUTING, 2020, 412 : 287 - 294
  • [6] Lagrange stability of quaternion-valued memristive neural networks
    Huang, Qun
    Ma, Nan
    Tu, Zhengwen
    MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2024, 47 (18) : 14796 - 14806
  • [7] Stability of Quaternion-Valued Neural Networks with Mixed Delays
    Jingwen Zhu
    Jitao Sun
    Neural Processing Letters, 2019, 49 : 819 - 833
  • [8] Stability Analysis of Quaternion-Valued Neural Networks: Decomposition and Direct Approaches
    Liu, Yang
    Zhang, Dandan
    Lou, Jungang
    Lu, Jianquan
    Cao, Jinde
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (09) : 4201 - 4211
  • [9] Stability of Quaternion-Valued Neural Networks with Mixed Delays
    Zhu, Jingwen
    Sun, Jitao
    NEURAL PROCESSING LETTERS, 2019, 49 (02) : 819 - 833
  • [10] Multistability analysis of delayed quaternion-valued neural networks with nonmonotonic piecewise nonlinear activation functions
    Tan, Manchun
    Liu, Yunfeng
    Xu, Desheng
    APPLIED MATHEMATICS AND COMPUTATION, 2019, 341 : 229 - 255
12345