Improved Neural-Network Optimization Algorithms for Classification of Imbalanced-Exemplar Patterns

Li Guanglin

您当前的位置：

首页 >

文章列表页 >

Improved Neural-Network Optimization Algorithms for Classification of Imbalanced-Exemplar Patterns

更新时间：2025-12-08

- Improved Neural-Network Optimization Algorithms for Classification of Imbalanced-Exemplar Patterns
- Acta Electronica Sinica Issue 1, Pages: 122-125(1998)
- 作者机构：
  
  1.   山东工业大学自动化系!济南
  2.   250061
  3.   浙江大学生命科学与医学工程学系!杭州
  4.   310027
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：1998
- 稿件说明：
移动端阅览
[1]李光林,吕维雪.神经网络识别非平衡样本模式的网络优化方法[J].电子学报,1998(01):122-125.

Li Guanglin. Improved Neural-Network Optimization Algorithms for Classification of Imbalanced-Exemplar Patterns[J]. Acta Electronica Sinica, 1998, (1): 122-125.
[1]李光林,吕维雪.神经网络识别非平衡样本模式的网络优化方法[J].电子学报,1998(01):122-125. DOI：

Li Guanglin. Improved Neural-Network Optimization Algorithms for Classification of Imbalanced-Exemplar Patterns[J]. Acta Electronica Sinica, 1998, (1): 122-125. DOI：

摘要

本文基于多目标代化的思想，分析了用神经网络实现非平衡样本模式识别与分类时，网络优化过程中基本BP算法收敛速度低的原因，给出了两种相应的改进算法，并利用这两种算法研究了两例非平衡样本模式的分类问题．研究结果表明：改进的算法有效地提高了网络优化的收敛速度。

Abstract

Based on the ideas of the multiobjechve optindzation

the pape analyzes the cause that convergence-rate of the standard BP（Back-Propagation） algorithm is low in the optindzaion of netal network which is used for classilication of imbalanced-exemplar patterns. We present the improved optindzation algorithms. Using the algorithms

we have been able to accelerate the rate of learning for two kinds of dsanced-exemplarpattem classification problems. The results indicate that the impmved algorithms can efficiently increase the convereence-rate of neural network optimizahon.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Method of Pattern Recognition Based on Associative Matrix

Research of Cognition Simulation Based Multi-Information Fusion System

The Theoretical Analysis and Application of the Multi-Layered Feed-forward Neural Network for Pattern Recognition

A Pattern Classification System Based on Neural Tree

Image Classification Network of Background Perception Mechanism

Related Author

ZHOU Jing-zhou

WANG Ji-cheng

瞿东晖

张立明

王继成

YUAN Heng

RAN Chao

ZHANG Sheng-chong

Related Institution

Faculty of Information Engineering,Shenzhen University

Faculty of Information Engineering Shenzhen University Shenzhen Guangdong China

Dept.of Computer Science and Engineering,Tongji University

Dept.of Computer Science and EngineeringTongji UniversityShanghai 200092China

Dept.of Electronic Engineering,Fudan University,Shanghai 2000433

⁰