Multistability of complex-valued neural networks with discontinuous activation functions

被引：82
|
作者：
Liang, Jinling [1 ]
Gong, Weiqiang [1 ]
Huang, Tingwen [2 ]
机构：
[1] Southeast Univ, Dept Math, Nanjing 210096, Jiangsu, Peoples R China
[2] Texas A&M Univ, Sci Program, Doha, Qatar
来源：
NEURAL NETWORKS | 2016年 / 84卷
基金：
中国国家自然科学基金;
关键词：
Complex-valued neural networks; Multistability; Discontinuous function; Attraction basin; TIME-VARYING DELAYS; MULTIPLE MU-STABILITY; ASSOCIATIVE MEMORY; GLOBAL STABILITY; LOCAL STABILITY; ALGORITHM; RELAXATION; EQUILIBRIA; DYNAMICS; MODEL;
D O I：
10.1016/j.neunet.2016.08.008
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, based on the geometrical properties of the discontinuous activation functions and the Brouwer's fixed point theory, the multistability issue is tackled for the complex-valued neural networks with discontinuous activation functions and time-varying delays. To address the network with discontinuous functions, Filippov solution of the system is defined. Through rigorous analysis, several sufficient criteria are obtained to assure the existence of 25(n) equilibrium points. Among them, 9(n) points are locally stable and 16(n) - 9(n) equilibrium points are unstable. Furthermore, to enlarge the attraction basins of the 9(n) equilibrium points, some mild conditions are imposed. Finally, one numerical example is provided to illustrate the effectiveness of the obtained results. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码：125 / 142
页数：18
相关论文
共 50 条
  • [1] Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginarytype activation functions
    黄玉娇
    胡海根
    Chinese Physics B, 2015, 24 (12) : 275 - 283
  • [2] Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions
    Huang Yu-Jiao
    Hu Hai-Gen
    CHINESE PHYSICS B, 2015, 24 (12)
  • [3] Multistability of delayed complex-valued competitive neural networks with discontinuous non-monotonic piecewise nonlinear activation functions
    Xu, Desheng
    Tan, Manchun
    COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION, 2018, 62 : 352 - 377
  • [4] Multistability analysis of complex-valued recurrent neural networks with sine and cosine activation functions
    Yang, Liu
    Gong, Weiqiang
    Li, Qiang
    Sun, Fanrong
    Xing, Mali
    NEUROCOMPUTING, 2024, 577
  • [5] Dynamical Behavior of Complex-Valued Hopfield Neural Networks with Discontinuous Activation Functions
    Zengyun Wang
    Zhenyuan Guo
    Lihong Huang
    Xinzhi Liu
    Neural Processing Letters, 2017, 45 : 1039 - 1061
  • [6] Dynamical Behavior of Complex-Valued Hopfield Neural Networks with Discontinuous Activation Functions
    Wang, Zengyun
    Guo, Zhenyuan
    Huang, Lihong
    Liu, Xinzhi
    NEURAL PROCESSING LETTERS, 2017, 45 (03) : 1039 - 1061
  • [7] 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
  • [8] Global exponential stability of delayed complex-valued neural networks with discontinuous activation functions
    Hu, Jin
    Tan, Haidong
    Zeng, Chunna
    NEUROCOMPUTING, 2020, 416 : 1 - 11
  • [9] Complex-Valued Neural Networks With Nonparametric Activation Functions
    Scardapane, Simone
    Van Vaerenbergh, Steven
    Hussain, Amir
    Uncini, Aurelio
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2020, 4 (02): : 140 - 150
  • [10] Multistability of complex-valued neural networks with distributed delays
    Gong, Weiqiang
    Liang, Jinling
    Zhang, Congjun
    NEURAL COMPUTING & APPLICATIONS, 2017, 28 : S1 - S14
12345