Quantitative Relation Between Learning Ability and Generalization Ability of BP Neural Network

LI Zuo-yong; YI Yong-zhi

您当前的位置：

首页 >

文章列表页 >

Quantitative Relation Between Learning Ability and Generalization Ability of BP Neural Network

更新时间：2025-07-16

- Quantitative Relation Between Learning Ability and Generalization Ability of BP Neural Network
- Acta Electronica Sinica Vol. 31, Issue 9, Pages: 1341-1344(2003)
- 作者机构：
  
  成都信息工程学院,四川,成都,610041
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：2003
- 稿件说明：
移动端阅览
LI Zuo-yong, YI Yong-zhi. Quantitative Relation Between Learning Ability and Generalization Ability of BP Neural Network[J]. Acta Electronica Sinica, 2003, 31(9): 1341-1344.
DOI：

LI Zuo-yong, YI Yong-zhi. Quantitative Relation Between Learning Ability and Generalization Ability of BP Neural Network[J]. Acta Electronica Sinica, 2003, 31(9): 1341-1344. DOI：

摘要

分析BP网络过拟合时网络学习能力与泛化能力之间的内在联系

引入描述问题复杂性程度的复相关系数

建立了BP网络过拟合时

反映网络学习能力的训练样本集的训练相对误差与表征泛化能力的网络对检验样本集的测试相对误差之间满足的定量关系式.通过模拟若干不同类型函数的BP网络数值建模试验

确定了关系式中过拟合参数

的取值范围为0.007~0.07

指出BP网络应用于给定样本集的训练过程中

具有较佳泛化能力的停止训练方法.

Abstract

Based on the analysis of the internal relation between learning ability and generalization ability of the overfitting of BP neural network

by the introduction of mulit-correlative coefficient to manifest the complexity of the function

a quantitative uncertainty relation between the fitting relative error of training sample sets and the testing relative error of verifying sample sets

which describe the learning ability and the generalization ability of BP network

respectively

was revealed in the overfitting of BP neural network.Tests of numerical simulation for multi-kinds of different functions were carried out to determine the value distribution (0.007~0.07)of overfitting parameter

in the relation.Based on the quantitative relation

the training method for the improvement of generalization ability in the training process of sample sets using BP neu

ral network was given.

关键词

Keywords

references

Views

1057

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Student-Problem Association Based Heterogeneous Graph Knowledge Tracing Model

3D Depth Point Cloud Supervision and Confidence Correction for Face Spoofing Detection

Survey on Twin Support Vector Regression

Related Author

WANG Zhi-xiao

YUAN Guan

SI Yu-qing

YAN Qiu-yan

YUAN Guan

LIAO Guang-jun

WANG Yu-fei

LIU Bei-bei

Related Institution

School of Computer Science & Technology， China University of Mining and Technology

School of Electronic and Information Engineering， South China University of Technology

Department of Criminal Science and Technology， Guangdong Police College

Singapore International Joint Research Institute

School of Computer Science and Technology， China University of Mining and Technology

⁰