[1]贾丽会 张修如.BP算法分析与改进[J].计算机技术与发展,2006,(10):101-103.
 JIA Li-hui,ZHANG Xiu-ru.Analysis and Improvements of BP Algorithm[J].,2006,(10):101-103.
点击复制

BP算法分析与改进()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2006年10期
页码:
101-103
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Analysis and Improvements of BP Algorithm
文章编号:
1673-629X(2006)10-0101-03
作者:
贾丽会 张修如
中南大学信息科学与工程学院
Author(s):
JIA Li-huiZHANG Xiu-ru
College of Information Science & Engineering, Central South University
关键词:
BP算法收敛速度局部极小点遗传算法模拟退火算法
Keywords:
BP algorithm convergence rate local minimum genetic algorithm simulated annealing
分类号:
TP183
文献标志码:
A
摘要:
在人工神经网络中,BP神经网络是一种应用广泛的多层前馈神经网络。分析了BP算法的基本原理,指出了BP算法具有收敛速度慢、易陷入局部极小点等缺陷以及这些缺陷产生的根源。针对这些缺陷,通过在标准BP算法中引入变步长法、加动量项法、遗传算法、模拟退火算法等几种方法来优化BP算法。实验结果表明,这些方法有效地提高了BP算法的收敛性,避免陷入局部最小点
Abstract:
Back - propagation neural network is an extensively applied multi - layer feedforward neural network in artificial neural network. Basic principle of BP algorithm is analyzed firstly. Then some defects such as slow convergence rate and getting into local minimum in BP algorithm are pointed out, and the mot of the defects is presented. Finally, in view of these limitations, several methods such as genetic algorithm and simulated annealing algorithm etc. are led to optimize BP algorithm. Experiment results show that these methods increase efficiently the convergence performance of BP algorithm and avoid local minimum

相似文献/References:

[1]薛俊 陈行 陶军.一种基于神经网络的入侵检测技术[J].计算机技术与发展,2009,(08):148.
 XUE Jun,CHEN Hang,TAO Jun.Technology of Intrusion Detection Based on Neural Network[J].,2009,(10):148.
[2]蔡秋茹 罗烨 柳益君 叶飞跃.企业资信的BP神经网络评估模型研究[J].计算机技术与发展,2009,(10):117.
 CAI Qiu-ru,LUO Ye,LIU Yi-jun,et al.Research on BP Neural Network Model for Corporation Credit Rating[J].,2009,(10):117.
[3]王晓敏 刘希玉 戴芬.BP神经网络预测算法的改进及应用[J].计算机技术与发展,2009,(11):64.
 WANG Xiao-min,LIU Xi-yu,DAI Fen.Improvement and Application of BP Neural Network Forecasting Algorithm[J].,2009,(10):64.
[4]曾万里 危韧勇 陈红玲.基于改进PSO算法的BP神经网络的应用研究[J].计算机技术与发展,2008,(04):49.
 ZENG Wan-li,WEI Ren-yong,CHEN Hong-ling.Research and Application of BP Neural Network Based on Improved PSO Algorithm[J].,2008,(10):49.
[5]丁晓贵 刘桂江.基于PIDNN的污水处理系统参数辨识研究[J].计算机技术与发展,2008,(05):200.
 DING Xiao-gui,LIU Gui-jiang.Study on Identification Parameters of Wastewater Treatment System Based on PIDNN[J].,2008,(10):200.
[6]张充 史青宣 苗秀芬 杨芳 田学东.基于BP神经网络的手写体数字识别[J].计算机技术与发展,2008,(06):128.
 ZHANG Chong,SHI Qing-xuan,MIAO Xiu-fen,et al.Handwritten Numeral Recognition Based on BP Neural Network[J].,2008,(10):128.
[7]郭彦伟 王洪国 王鑫 于惠.一种基于并行策略的BP改进算法[J].计算机技术与发展,2008,(10):110.
 GUO Yan-wei,WANG Hong-guo,WANG Xin,et al.An Improved BP Algorithm Based on Parallel[J].,2008,(10):110.
[8]马恋 何锫.基于神经网络的数据压缩研究[J].计算机技术与发展,2007,(02):12.
 MA Lian,HE Pei.Research on NN- Based Data Compression[J].,2007,(10):12.
[9]夏敏 刘宏申.基于小波描述子和神经网络的形状识别[J].计算机技术与发展,2007,(03):106.
 XIA Min,LIU Hong-shen.The Shape Recognition System Based on Wavelet Descriptors and Neural Networks[J].,2007,(10):106.
[10]王辉.基于结构简化的BP网络的多类形状识别[J].计算机技术与发展,2006,(07):13.
 WANG Hui.An Algorithm Research on BP Based on Structure Simplification[J].,2006,(10):13.
[11]李志俊 程家兴 金奎 饶玉佳.基于样本期望训练数的BP神经网络改进研究[J].计算机技术与发展,2009,(05):103.
 LI Zhi-jun,CHENG Jia-xing,JIN Kui,et al.BP Algorithm Improvement Based on Sample Expected Training Number[J].,2009,(10):103.

备注/Memo

备注/Memo:
贾丽会(1976-),女,湖北钟祥人,硕士研究生,讲师,研究方向为图形图像处理技术、信号处理,模式识别;张修如,副教授,研究方向为信息系统、GIS、图形图像处理技术、模式识别
更新日期/Last Update: 1900-01-01