Soft-Competition Learning Algorithms of the Radial Basis Function Neural Networks

ZHANG Zhi-hua; ZHENG Nan-ning; SHI Gang

您当前的位置：

首页 >

文章列表页 >

Soft-Competition Learning Algorithms of the Radial Basis Function Neural Networks

更新时间：2025-07-16

- Soft-Competition Learning Algorithms of the Radial Basis Function Neural Networks
- Acta Electronica Sinica Vol. 30, Issue 1, Pages: 132-135(2002)
- 作者机构：
  
  西安交通大学人工智能与机器人研究所,陕西,西安,710049
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183
- Published：2002
- 稿件说明：
移动端阅览
ZHANG Zhi-hua, ZHENG Nan-ning, SHI Gang. Soft-Competition Learning Algorithms of the Radial Basis Function Neural Networks[J]. Acta Electronica Sinica, 2002, 30(1): 132-135.
DOI：

ZHANG Zhi-hua, ZHENG Nan-ning, SHI Gang. Soft-Competition Learning Algorithms of the Radial Basis Function Neural Networks[J]. Acta Electronica Sinica, 2002, 30(1): 132-135. DOI：

摘要

本文构造了径向基函数(RBF)神经网络的一类软竞争学习算法(SCLA).该算法的主要思想是首先在高斯基函数中心向量的训练过程中引入了隶属度函数

对每个输入样本

所有中心向量根据该样本属于其代表的类的隶属度值的大小进行自适应地调整;第二

把隶属度函数的模糊因子的倒数与模拟退火算法中的温度等同起来

在迭代过程中采用递增的方式来调整它.SCLA是RBF网络基于

均值方法训练中心向量的学习算法的软竞争格式

它可以克服后者对初始值敏感和死节点的问题.仿真实验论证了SCLA是有效的.

Abstract

In this paper

the soft-competition learning algorithms (SCLA) of RBF neural networks are designed.The main ideas of the algorithms are:firstly

membership functions are introduced into the training procedure of the center vectors of the Gaussian basis functions

and for each input sample

all center vectors are self-adaptively adjusted according to the values of the membership functions

in what degree the sample belongs to the classes that the center vectors represent;secondly

the reciprocal of the fuzzy factor of membership function are considered as the temperature of the simulated annealing algorithm

and increasingly adjusting method is used to the fuzzy factor during the learning procedure.SCLA are soft-competition schemes of the learning algorithms

in which the center vectors are trained based on the

-means algorithm

and can reme

dy the problems of the dead-node and the sensitivity to initial weight vectors that the latter algorithms have.The simulation results show that SCLA are efficient.

关键词

Keywords

references

Views

1512

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Task-Guided Radial Basis Function Network for Mitosis Detection in Breast Histopathology Images

A Salp Swarm Algorithm Based on Stepped Tent Chaos and Simulated Annealing

Build Kd-Tree for Virtual Scenes in a Fast and Optimal Way

3D Reconstruction of Human Face Based on Shape Match Morphing Model

Hybrid Artificial Fish Swarm Optimization Algorithm Based on Mutation Operator and Simulated Annealing

Related Author

CAI Yu

TANG Qi-ling

LIU Zi-yi

DONG Chao-yi

WANG Qi-lai

QI Yong-sheng

CHEN Xiao-yan

ZHOU Peng

Related Institution

Department of Medical Engineering， Affiliated Yantai Yuhuangding Hospital of Qingdao University

School of Biomedical Engineering， South-Central Minzu University

Inner Mongolia Electromechanical Control Laboratory

Inner Mongolia University of Technology

State Key Laboratory for Novel Software Technology, Nanjing University

⁰