Multistability of neural networks with discontinuous activation function

被引：58

作者：

Huang, Gan ^{[1
]}

Cao, Jinde ^{[1
]}

机构：

[1] Southeast Univ, Dept Math, Nanjing 210096, Peoples R China

来源：

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION | 2008年 / 13卷 / 10期

基金：

中国国家自然科学基金;

关键词：

neural networks; multilevel function; activation function; multistability;

D O I：

10.1016/j.cnsns.2007.07.005

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

In this paper, the multistability is studied for two-dimensional neural networks with multilevel activation functions. And it is showed that the system has n(2) isolated equilibrium points which are locally exponentially stable, where the activation function has n segments. Furthermore, evoked by periodic external input, n(2) periodic orbits which are locally exponentially attractive, can be found. And these results are extended to k-neuron networks, which is really enlarge the capacity of the associative memories. Examples and simulation results are used to illustrate the theory. (c) 2007 Elsevier B.V. All rights reserved.

引用

页码：2279 / 2289

页数：11

共 50 条

[31] Periodic Function as Activation Function for Neural Networks [J].

Xu, Ding ;

Guan, Yue ;

Cai, Ping-ping .

INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE: TECHNIQUES AND APPLICATIONS, AITA 2016, 2016, :179-183

[32] Multistability of Recurrent Neural Networks With Nonmonotonic Activation Functions and Mixed Time Delays [J].

Liu, Peng ;

Zeng, Zhigang ;

Wang, Jun .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2016, 46 (04) :512-523

[33] Multistability analysis of state-dependent switched Hopfield neural networks with the Gaussian-wavelet-type activation function [J].

Liu, Yang ;

Wang, Zhen ;

Huang, Xia .

MATHEMATICS AND COMPUTERS IN SIMULATION, 2022, 196 :232-250

[34] Enhancement of neural networks with an alternative activation function tanhLU [J].

Shen, Shui-Long ;

Zhang, Ning ;

Zhou, Annan ;

Yin, Zhen-Yu .

EXPERT SYSTEMS WITH APPLICATIONS, 2022, 199

[35] Robust Multistability and Multiperiodicity of Neural Networks with Time Delays [J].

Wang, Lili .

ADVANCES IN NEURAL NETWORKS - ISNN 2015, 2015, 9377 :146-153

[36] Multistability of Fuzzy Neural Networks With a General Class of Activation Functions and State-Dependent Switching Rules [J].

Ou, Shiqin ;

Guo, Zhenyuan ;

Wang, Jun .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2023, 31 (02) :645-659

[37] Multistability and convergence in delayed neural networks [J].

Cheng, Chang-Yuan ;

Lin, Kuang-Hui ;

Shih, Chih-Wen .

PHYSICA D-NONLINEAR PHENOMENA, 2007, 225 (01) :61-74

[38] The multistability of delayed competitive neural networks with piecewise non-monotonic activation functions [J].

Zhang, Yan ;

Qiao, Yuanhua ;

Duan, Lijuan ;

Miao, Jun .

MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2022, 45 (16) :10295-10311

[39] Multistability of Second-Order Competitive Neural Networks With Nondecreasing Saturated Activation Functions [J].

Nie, Xiaobing ;

Cao, Jinde .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2011, 22 (11) :1694-1708

[40] Multistability and instability of delayed competitive neural networks with nondecreasing piecewise linear activation functions [J].

Nie, Xiaobing ;

Cao, Jinde ;

Fei, Shumin .

NEUROCOMPUTING, 2013, 119 :281-291

← 1 2 3 4 5 →