Research on Adaptive Dynamic Fuzzy Neural Network #br#
Algorithms with Gauss Activation Function and Eigenvalue #br#
Decomposition Pruning Technologies

HE Zhengfeng; ZHANG Defeng; SUN Yamin

您当前的位置：

首页 >

文章列表页 >

Research on Adaptive Dynamic Fuzzy Neural Network #br# Algorithms with Gauss Activation Function and Eigenvalue #br# Decomposition Pruning Technologies

更新时间：2023-12-11

- Research on Adaptive Dynamic Fuzzy Neural Network #br# Algorithms with Gauss Activation Function and Eigenvalue #br# Decomposition Pruning Technologies
- Acta Scientiarum Naturalium Universitatis SunYatseni Vol. 52, Issue 1, Pages: 34-39(2013)
- 作者机构：
  
  1. 佛山科学技术学院理学院,广东,佛山,528000
  2. 佛山科学技术学院计算机系,广东,佛山,528000
  3. 南京理工大学计算机科学与技术学院,江苏,南京,210094
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2013，
  
  Published Online：25 January 2013，
扫描看全文
HE Zhengfeng, ZHANG Defeng, SUN Yamin. Research on Adaptive Dynamic Fuzzy Neural Network #br# Algorithms with Gauss Activation Function and Eigenvalue #br# Decomposition Pruning Technologies. [J]. Acta Scientiarum Naturalium Universitatis SunYatseni 52(1):34-39(2013)
DOI：

HE Zhengfeng, ZHANG Defeng, SUN Yamin. Research on Adaptive Dynamic Fuzzy Neural Network #br# Algorithms with Gauss Activation Function and Eigenvalue #br# Decomposition Pruning Technologies. [J]. Acta Scientiarum Naturalium Universitatis SunYatseni 52(1):34-39(2013) DOI：

摘要

提出了一种D-FNN的新算法。其算法的最主要特点是：D-FNN选择高斯函数作为网络的激活函数和模糊系统的隶属函数，该算法不仅具有强大的全局映射泛化能力，而且在细化局部方面也有效；使用特征值分解修剪技术使得网络结构不会持续增长，可获得更为紧凑的DFNN结构，避免了过拟合现象。最后通过对Hermite多项式逼近能力来验证所提方案的有效性。仿真结果表明使用特征值分解修剪技术和高斯激活函数的D-FNN具有良好的性能。

Abstract

A new algorithm，which uses D-FNN Gauss function as a network activation function and fuzzy membership function

is proposed. The algorithm obtains strong global mapping generalization ability and effectiveness in local refinement

and adopts eigenvalue decomposition pruning technology to enables more compact D-FNN structure to avoid the phenomenon of over fitting. Finally

the algorithm is confirmed through the Hermite polynomial approximation to approach ability of validity. The simulation results show that the eigenvalue decomposition of pruning techniques and Gauss activation function of D-FNN has good performance.

关键词

动态模糊神经网络模糊规则修剪技术特征值分解

Keywords

dynamic fuzzy neural network(D-FNN)fuzzy rulepruning technologyeigenvalue decomposition(ED)

references

Views

373

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dynamic Fuzzy Neural Network Method Research of the Glide Window and Pruning Technology

Research on Online Self-Organizational Learning GD-FNN Algorithm by Grading

Research Based on D-FNN Algorithm on the Nonlinear Dynamic System Identification

The Rule Criteria and Pruning Strategy Based on D-FNN Algorithm Research

Related Author

马

莉

张德丰

马子龙

ZUO Jun

ZHOU Ling

SUN Yamin

YANG Wenyin

Related Institution

Department of Computer Science,Foshan University



Department of Electrical Engineering, Harbin Institute of Technology

School of Electronic and Information Engineering, Foshan University

Postal code：510275
Tel：020-84112585，84113223 Email：xuebaozr@mail.sysu.edu.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰