Multistability analysis of quaternion-valued neural networks with cosine activation functions *

被引：9
|
作者：
Yu, Siyi [1 ]
Li, Hua [1 ]
Chen, Xiaofeng [1 ]
Lin, Dongyuan [2 ]
机构：
[1] Chongqing Jiaotong Univ, Dept Math, Chongqing 400074, Peoples R China
[2] Southwest Univ, Coll Elect & Informat Engn, Chongqing 400715, Peoples R China
来源：
APPLIED MATHEMATICS AND COMPUTATION | 2023年 / 445卷
基金：
中国国家自然科学基金;
关键词：
Multistability; Quaternion-valued neural networks; Attraction basins; Cosine activation function; ASSOCIATIVE MEMORY; COMPLETE STABILITY;
D O I：
10.1016/j.amc.2023.127849
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
It is significant to design a system with high storage capacity for associative memory and pattern recognition. To address this issue, this paper first proposes a quaternion-valued neural network (QVNN) model with multiple equilibrium points in which the cosine function is used as the activation function of QVNN. Then, based on the Brouwer fixed point theorem and the geometric properties of the activation function, sufficient conditions for QVNN to have unique equilibrium points, finite equilibrium points, and countable infinite equilibrium points are obtained, respectively. Furthermore, sufficient conditions for the exponential stability of equilibrium points are derived, and the attraction basins of the stable equilibrium points are given. Finally, two numerical examples are given to confirm the validity of the proposed theoretical results.
引用
收藏
页数：16
相关论文
共 50 条
  • [11] Robust stability analysis of quaternion-valued neural networks via LMI approach
    Chen, Xiaofeng
    Li, Lianjie
    Li, Zhongshan
    ADVANCES IN DIFFERENCE EQUATIONS, 2018,
  • [12] Impulsive disturbance on stability analysis of delayed quaternion-valued neural networks
    Wang, Huamin
    Wei, Guoliang
    Wen, Shiping
    Huang, Tingwen
    APPLIED MATHEMATICS AND COMPUTATION, 2021, 390 (390)
  • [13] Coexistence of locally multistable equilibrium points for "-neuron delayed quaternion-valued neural networks with continuous piecewise nonlinear activation functions
    Chouhan, Shiv Shankar
    Das, Subir
    Chen, Xiaofeng
    NEUROCOMPUTING, 2024, 594
  • [14] Robust stability analysis of quaternion-valued neural networks with time delays and parameter uncertainties
    Chen, Xiaofeng
    Li, Zhongshan
    Song, Qiankun
    Hu, Jin
    Tan, Yuanshun
    NEURAL NETWORKS, 2017, 91 : 55 - 65
  • [15] Robust stability analysis of quaternion-valued neural networks via LMI approach
    Xiaofeng Chen
    Lianjie Li
    Zhongshan Li
    Advances in Difference Equations, 2018
  • [16] Scaled Conjugate Gradient Learning for Quaternion-Valued Neural Networks
    Popa, Calin-Adrian
    NEURAL INFORMATION PROCESSING, ICONIP 2016, PT III, 2016, 9949 : 243 - 252
  • [17] Enhanced Gradient Descent Algorithms for Quaternion-Valued Neural Networks
    Popa, Calin-Adrian
    SOFT COMPUTING APPLICATIONS, SOFA 2016, VOL 2, 2018, 634 : 45 - 53
  • [18] Quaternion-valued recurrent projection neural networks on unit quaternions
    Valle, Marcos Eduardo
    Lobo, Rodolfo Anibal
    THEORETICAL COMPUTER SCIENCE, 2020, 843 : 136 - 152
  • [19] Exponential Stability Analysis of Mixed Delayed Quaternion-Valued Neural Networks Via Decomposed Approach
    Wang, Huamin
    Tan, Jie
    Wen, Shiping
    IEEE ACCESS, 2020, 8 : 91501 - 91509
  • [20] Antiperiodic solutions to delayed inertial quaternion-valued neural networks
    Xu, Changjin
    Li, Peiluan
    Liao, Maoxin
    Liu, Zixin
    Xiao, Qimei
    MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2020, 43 (12) : 7326 - 7344
12345