版权说明 操作指南
首页 > 成果 > 详情

Finite-time multistability of a multidirectional associative memory neural network with multiple fractionalorders based on a generalized Gronwall inequality

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Zhiguang Liu;Xiangyu Xu;Tiejun Zhou*
通讯作者:
Tiejun Zhou
作者机构:
College of Mathematics and Statistics, Hengyang Normal University, Hengyang, China
College of Information and Intelligence Science, Hunan Agricultural University, Changsha, China
Hunan Province Key Laboratory of Intelligent Agriculture Equipment, Changsha, China
[Liu Z.] College of Mathematics and Statistics, Hengyang Normal University, Hunan, Hengyang, 421008, China<&wdkj&>College of Information and Intelligence Science, Hunan Agricultural University, Hunan, Changsha, 410128, China
[Xiangyu Xu] College of Information and Intelligence Science, Hunan Agricultural University, Hunan, Changsha, 410128, China
通讯机构:
[Tiejun Zhou] C
College of Information and Intelligence Science, Hunan Agricultural University, Changsha, China<&wdkj&>Hunan Province Key Laboratory of Intelligent Agriculture Equipment, Changsha, China
语种:
英文
关键词:
Associative processing;Associative storage;Chemical activation;Fixed point arithmetic;Laplace transforms;Memory architecture;Activation functions;Associative memory neural networks;Finite-time;Finite-time multistability;Fractional order;Gaussian wavelets;Generalized gronwall inequalities;Multidirectional associative memory neural network;Multiple fractional order;Multistability;Neural networks
期刊:
Neural Computing and Applications
ISSN:
0941-0643
年:
2024
卷:
36
期:
22
页码:
13527-13549
基金类别:
This work was supported by the Hunan Provincial Natural Science Foundations [Grant numbers 2021JJ30309 and 2023JJ50090].
机构署名:
本校为第一机构
院系归属:
数学与统计学院
摘要:
This paper addressed the finite-time multistability of a Caputo fractionalorder multidirectional associative memory neural network (FMAMNN) with multiple orders, where the fractionalorders are not limited to 0 to 1. There are three main findings. Firstly, by using Brouwer fixed point theorem, the existence conditions of multiple equilibria of FMAMNN with Gaussian-wavelet-type activation functions were obtained, and the number of equilibria is (2+s2)l, where the exponent l is determined by the number of neurons, and s is the number of segments i...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com