• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

两类子网递归神经网络平衡点分析。

Analysis of Equilibria for a Class of Recurrent Neural Networks With Two Subnetworks.

出版信息

IEEE Trans Cybern. 2022 Jun;52(6):4701-4716. doi: 10.1109/TCYB.2020.3034249. Epub 2022 Jun 16.

DOI:10.1109/TCYB.2020.3034249
PMID:33296319
Abstract

This article is concerned with the problem of the number and dynamical properties of equilibria for a class of connected recurrent networks with two switching subnetworks. In this network model, parameters serve as switches that allow two subnetworks to be turned ON or OFF among different dynamic states. The two subnetworks are described by a nonlinear coupled equation with a complicated relation among network parameters. Thus, the number and dynamical properties of equilibria have been very hard to investigate. By using Sturm's theorem, together with the geometrical properties of the network equation, we give a complete analysis of equilibria, including the existence, number, and dynamical properties. Necessary and sufficient conditions for the existence and exact number of equilibria are established. Moreover, the dynamical property of each equilibrium point is discussed without prior assumption of their locations. Finally, simulation examples are given to illustrate the theoretical results in this article.

摘要

这篇文章关注的是一类具有两个切换子网的连通递归网络的平衡点的数量和动态特性的问题。在这个网络模型中,参数充当开关,可以在不同的动态状态之间打开或关闭两个子网。这两个子网由一个具有网络参数之间复杂关系的非线性耦合方程来描述。因此,平衡点的数量和动态特性很难研究。通过使用 Sturm 定理以及网络方程的几何性质,我们对平衡点进行了全面的分析,包括平衡点的存在性、数量和动态特性。建立了平衡点存在和确切数量的充分必要条件。此外,无需先验假设平衡点的位置,就可以讨论每个平衡点的动态特性。最后,给出了仿真示例来说明本文的理论结果。

相似文献

1
Analysis of Equilibria for a Class of Recurrent Neural Networks With Two Subnetworks.两类子网递归神经网络平衡点分析。
IEEE Trans Cybern. 2022 Jun;52(6):4701-4716. doi: 10.1109/TCYB.2020.3034249. Epub 2022 Jun 16.
2
Multistability of Switched Neural Networks With Piecewise Linear Activation Functions Under State-Dependent Switching.分段线性激活函数切换下的具有状态相关切换的切换神经网络的多稳定性。
IEEE Trans Neural Netw Learn Syst. 2019 Jul;30(7):2052-2066. doi: 10.1109/TNNLS.2018.2876711. Epub 2018 Nov 12.
3
Multistability of Switched Neural Networks With Gaussian Activation Functions Under State-Dependent Switching.具有状态相关切换的高斯激活函数的切换神经网络的多稳定性。
IEEE Trans Neural Netw Learn Syst. 2022 Nov;33(11):6569-6583. doi: 10.1109/TNNLS.2021.3082560. Epub 2022 Oct 27.
4
Multistability of switched neural networks with sigmoidal activation functions under state-dependent switching.具有状态相关切换的 Sigmoidal 激活函数的切换神经网络的多稳定性。
Neural Netw. 2020 Feb;122:239-252. doi: 10.1016/j.neunet.2019.10.012. Epub 2019 Nov 2.
5
Dynamical Behaviors of Multiple Equilibria in Competitive Neural Networks With Discontinuous Nonmonotonic Piecewise Linear Activation Functions.具有不连续非单调分段线性激活函数的竞争神经网络中的多重平衡点的动态行为。
IEEE Trans Cybern. 2016 Mar;46(3):679-93. doi: 10.1109/TCYB.2015.2413212. Epub 2015 Mar 26.
6
R+n-global stability of a Cohen-Grossberg neural network system with nonnegative equilibria.具有非负平衡点的Cohen-Grossberg神经网络系统的R + n全局稳定性。
Neural Netw. 2007 Aug;20(6):714-22. doi: 10.1016/j.neunet.2007.05.004. Epub 2007 May 31.
7
Exact coexistence and locally asymptotic stability of multiple equilibria for fractional-order delayed Hopfield neural networks with Gaussian activation function.分数阶时滞广义 Hopfield 神经网络的具有高斯激活函数的多个平衡点的精确共存和局部渐近稳定性。
Neural Netw. 2021 Oct;142:690-700. doi: 10.1016/j.neunet.2021.07.029. Epub 2021 Aug 5.
8
Multiple and Complete Stability of Recurrent Neural Networks With Sinusoidal Activation Function.具有正弦激活函数的递归神经网络的多重完全稳定性
IEEE Trans Neural Netw Learn Syst. 2021 Jan;32(1):229-240. doi: 10.1109/TNNLS.2020.2978267. Epub 2021 Jan 4.
9
Equilibria and their bifurcations in a recurrent neural network involving iterates of a transcendental function.一个涉及超越函数迭代的递归神经网络中的平衡及其分岔
IEEE Trans Neural Netw. 2008 May;19(5):782-94. doi: 10.1109/TNN.2007.912321.
10
Novel criteria for global robust stability of dynamical neural networks with multiple time delays.具有多个时滞的动力神经网络全局鲁棒稳定性的新准则。
Neural Netw. 2021 Oct;142:119-127. doi: 10.1016/j.neunet.2021.04.039. Epub 2021 May 7.