ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Multistability of Switched Neural Networks With Gaussian Activation Functions Under State-Dependent Switching

Guo, Zhenyuan; Ou, Shiqin; Wang, Jun*hunan univ
IEEE Transactions on Neural Networks and Learning Systems2022-11DOI: 10.1109/TNNLS.2021.3082560
14被引7阅读
引用收藏
分享

摘要

This article presents theoretical results on the multistability of switched neural networks with Gaussian activation functions under state-dependent switching. It is shown herein that the number and location of the equilibrium points of the switched neural networks can be characterized by making use of the geometrical properties of Gaussian functions and local linearization based on the Brouwer fixed-point theorem. Four sets of sufficient conditions are derived to ascertain the existence of 7(p1)5(p2)3(p3) equilibrium points, and 4(p1)3(p2)2(p3) of them are locally stable, wherein p(1), p(2), and p(3) are nonnegative integers satisfying 0 <= p(1) + p(2) + p(3) <= n and n is the number of neurons. It implies that there exist up to 7(n) equilibria, and up to 4(n) of them are locally stable when p(1) = n. It also implies that properly selecting p(1), p(2), and p(3) can engender a desirable number of stable equilibria. Two numerical examples are elaborated to substantiate the theoretical results.

学科与关键词

关键词
Gaussian activation functionmultistabilitystate-dependent switchingswitched neural network
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Neural Networks and Learning Systems
发表日期
2022-11
卷期
第 33 卷, 第 11 期
页码
6569-6583
DOI
10.1109/TNNLS.2021.3082560
语言
ENGLISH
期刊等级
1区
成果收录
SCIE
资助标注
Research Grants Council, Hong Kong [11208517, 11202318, 11202019]; National Natural Science Foundation of China [61573003, 61673330]; Natural Science Foundation of Hunan [2019JJ40022]; Postgraduate Scientific Research Innovation Project of Hunan Province [CX20200420]

作者

  • G

    Guo, Zhenyuan (第一作者)

    hunan univ

  • O

    Ou, Shiqin

    hunan univ

查看全部 3 位作者收起作者
  • W

    Wang, Jun (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417