• 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

时滞合作神经网络的极限环二分性与多稳定性。

Limit set dichotomy and multistability for a class of cooperative neural networks with delays.

出版信息

IEEE Trans Neural Netw Learn Syst. 2012 Sep;23(9):1473-85. doi: 10.1109/TNNLS.2012.2205703.

DOI:10.1109/TNNLS.2012.2205703
PMID:24807930
Abstract

Recent papers have pointed out the interest to study convergence in the presence of multiple equilibrium points (EPs) (multistability) for neural networks (NNs) with nonsymmetric cooperative (nonnegative) interconnections and neuron activations modeled by piecewise linear (PL) functions. One basic difficulty is that the semiflows generated by such NNs are monotone but, due to the horizontal segments in the PL functions, are not eventually strongly monotone (ESM). This notwithstanding, it has been shown that there are subclasses of irreducible interconnection matrices for which the semiflows, although they are not ESM, enjoy convergence properties similar to those of ESM semiflows. The results obtained so far concern the case of cooperative NNs without delays. The goal of this paper is to extend some of the existing results to the relevant case of NNs with delays. More specifically, this paper considers a class of NNs with PL neuron activations, concentrated delays, and a nonsymmetric cooperative interconnection matrix A and delay interconnection matrix A(τ). The main result is that when A+A(τ) satisfies a full interconnection condition, then the generated semiflows, which are monotone but not ESM, satisfy a limit set dichotomy analogous to that valid for ESM semiflows. It follows that there is an open and dense set of initial conditions, in the state space of continuous functions on a compact interval, for which the solutions converge toward an EP. The result holds in the general case where the NNs possess multiple EPs, i.e., is a result on multistability, and is valid for any constant value of the delays.

摘要

最近的一些论文指出,研究具有非对称合作(非负)连接和分段线性(PL)函数建模的神经元激活的神经网络(NN)在存在多个平衡点(EP)(多稳定性)时的收敛性很有意义。一个基本的困难是,由这样的 NN 产生的半流是单调的,但由于 PL 函数中的水平段,它们不是最终强单调的(ESM)。尽管如此,已经表明存在不可约连接矩阵的子类,对于这些半流,尽管它们不是 ESM,但它们具有类似于 ESM 半流的收敛性质。迄今为止获得的结果涉及没有延迟的合作 NN 的情况。本文的目标是将一些现有结果扩展到具有延迟的相关 NN 情况。更具体地说,本文考虑了一类具有 PL 神经元激活、集中延迟和非对称合作连接矩阵 A 和延迟连接矩阵 A(τ)的 NN。主要结果是,当 A+A(τ)满足全连接条件时,生成的半流是单调的但不是 ESM 的,满足类似于 ESM 半流的极限集二分法。因此,在紧区间上连续函数的状态空间中,存在一个初始条件的开集和稠密集,使得解收敛到 EP。该结果在 NN 具有多个 EP 的一般情况下有效,即多稳定性的结果,并且对于延迟的任何常数值都是有效的。

相似文献

1
Limit set dichotomy and multistability for a class of cooperative neural networks with delays.时滞合作神经网络的极限环二分性与多稳定性。
IEEE Trans Neural Netw Learn Syst. 2012 Sep;23(9):1473-85. doi: 10.1109/TNNLS.2012.2205703.
2
Multistability of two kinds of recurrent neural networks with activation functions symmetrical about the origin on the phase plane.具有原点对称激活函数的两种递归神经网络在相平面上的多稳定性。
IEEE Trans Neural Netw Learn Syst. 2013 Nov;24(11):1749-62. doi: 10.1109/TNNLS.2013.2262638.
3
Multistability of neural networks with time-varying delays and concave-convex characteristics.时变时滞和凹凸特性神经网络的多稳定性。
IEEE Trans Neural Netw Learn Syst. 2012 Feb;23(2):293-305. doi: 10.1109/TNNLS.2011.2179311.
4
New Conditions for Global Asymptotic Stability of Memristor Neural Networks.新的条件下全局渐近稳定的忆阻神经网络。
IEEE Trans Neural Netw Learn Syst. 2018 May;29(5):1822-1834. doi: 10.1109/TNNLS.2017.2688404. Epub 2017 Apr 12.
5
Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain.具有无限增益的时滞神经网络的全局指数稳定性和有限时间内的全局收敛性。
IEEE Trans Neural Netw. 2005 Nov;16(6):1449-63. doi: 10.1109/tnn.2005.852862.
6
A recurrent neural network for solving bilevel linear programming problem.用于求解双层线性规划问题的递归神经网络。
IEEE Trans Neural Netw Learn Syst. 2014 Apr;25(4):824-30. doi: 10.1109/TNNLS.2013.2280905.
7
Stability and synchronization of discrete-time neural networks with switching parameters and time-varying delays.离散时间切换参数时滞神经网络的稳定性与同步。
IEEE Trans Neural Netw Learn Syst. 2013 Dec;24(12):1957-72. doi: 10.1109/TNNLS.2013.2271046.
8
Convergence of nonautonomous Cohen-Grossberg-type neural networks with variable delays.具有可变时滞的非自治Cohen-Grossberg型神经网络的收敛性
IEEE Trans Neural Netw. 2008 Jan;19(1):140-7. doi: 10.1109/TNN.2007.903154.
9
Multistability of second-order competitive neural networks with nondecreasing saturated activation functions.具有非递减饱和激活函数的二阶竞争神经网络的多重稳定性
IEEE Trans Neural Netw. 2011 Nov;22(11):1694-708. doi: 10.1109/TNN.2011.2164934. Epub 2011 Sep 6.
10
Robust exponential stability of uncertain stochastic neural networks with distributed delays and reaction-diffusions.具有分布时滞和反应扩散的不确定随机神经网络的鲁棒指数稳定性。
IEEE Trans Neural Netw Learn Syst. 2012 Sep;23(9):1407-16. doi: 10.1109/TNNLS.2012.2203360.

引用本文的文献

1
Exponential synchronization of memristive Cohen-Grossberg neural networks with mixed delays.具有混合时滞的忆阻 Cohen-Grossberg 神经网络的指数同步。
Cogn Neurodyn. 2014 Jun;8(3):239-49. doi: 10.1007/s11571-013-9277-6. Epub 2014 Jan 4.