首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种用于快速分类问题的神经网络学习算法
引用本文:迟彦惠,齐欢,胡伟湘.一种用于快速分类问题的神经网络学习算法[J].华中科技大学学报(自然科学版),1999,27(6):90-92.
作者姓名:迟彦惠  齐欢  胡伟湘
作者单位:华中理工大学数学系
摘    要:对传统的BP算法进行了改进,提出了基于二阶导数的BP算法,大大减少了样本训练的迭代次数,从而提高了网络运算速度.对异或问题和蜢虫分类问题的计算,取得了满意的效果.

关 键 词:神经网络  快速分类  BP算法  梯度法  判别分析
修稿时间:1998-06-09.

A Learning Algorithm Applied to Fasting Classification in Neural Networks
Chi Yanhui,Qi Huan,Hu Weixiang.A Learning Algorithm Applied to Fasting Classification in Neural Networks[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,1999,27(6):90-92.
Authors:Chi Yanhui  Qi Huan  Hu Weixiang
Abstract:A new BP algorithm with introduction of second derivative is proposed to improve the conventional BP algorithm. The iteration of training samples is reduced. The computation rate of the algorithm in the networks is raised. The algorithm is applied to discussing XOR problem and the classification of midges.
Keywords:neural network  fasting classification  BP algorithm  gradient method  differentiate analysis
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号