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
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
  • [41] Existence and Exponential Stability of Solutions for Quaternion-Valued Delayed Hopfield Neural Networks by ξ-Norms
    Wang, Huamin
    Wen, Shiping
    IEEE ACCESS, 2019, 7 : 184509 - 184517
  • [42] Synchronization criteria for neutral-type quaternion-valued neural networks with mixed delays
    Li, Shuang
    Wang, Xiao-mei
    Qin, Hong-ying
    Zhong, Shou-ming
    AIMS MATHEMATICS, 2021, 6 (08): : 8044 - 8063
  • [43] Adaptive synchronization of quaternion-valued neural networks with reaction-diffusion and fractional order
    Zhang, Weiwei
    Zhao, Hongyong
    Sha, Chunlin
    NONLINEAR ANALYSIS-MODELLING AND CONTROL, 2024, 29 (05): : 958 - 982
  • [44] Stability and Synchronization of Delayed Quaternion-Valued Neural Networks under Multi-Disturbances
    Yang, Jibin
    Xu, Xiaohui
    Xu, Quan
    Yang, Haolin
    Yu, Mengge
    MATHEMATICS, 2024, 12 (06)
  • [45] Global μ-stability of quaternion-valued neural networks with mixed time-varying delays
    You, Xingxing
    Song, Qiankun
    Liang, Jing
    Liu, Yurong
    Alsaadi, Fuad E.
    NEUROCOMPUTING, 2018, 290 : 12 - 25
  • [46] Bipartite secure synchronization criteria for coupled quaternion-valued neural networks with signed graph
    Li, Ning
    Cao, Jinde
    Wang, Fei
    NEURAL NETWORKS, 2024, 180
  • [47] Direct approach on projective synchronization of inertial quaternion-valued neural networks with proportional delays
    Assali, El Abed
    COMPUTATIONAL & APPLIED MATHEMATICS, 2024, 43 (08)
  • [48] On Multistability of Competitive Neural Networks with Discontinuous Activation Functions
    Nie, Xiaobing
    Zheng, Wei Xing
    2014 4TH AUSTRALIAN CONTROL CONFERENCE (AUCC), 2014, : 245 - 250
  • [49] Mittag-Leffler stability analysis of multiple equilibrium points in impulsive fractional-order quaternion-valued neural networks
    Udhayakumar, K.
    Rakkiyappan, R.
    Cao, Jin-de
    Tan, Xue-gang
    FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2020, 21 (02) : 234 - 246
  • [50] Multistability of complex-valued recurrent neural networks with real-imaginary-type activation functions
    Huang, Yujiao
    Zhang, Huaguang
    Wang, Zhanshan
    APPLIED MATHEMATICS AND COMPUTATION, 2014, 229 : 187 - 200