| BP网络改进模型的性能对比研究 |
| |
| 引用本文： | 李朝峰,屈颖歌,夏德深,邹海. BP网络改进模型的性能对比研究[J]. 计算机工程与应用, 2003, 39(19): 120-121,132 |
| |
| 作者姓名： | 李朝峰 屈颖歌 夏德深 邹海 |
| |
| 作者单位： | 1. 南京理工大学计算机系603-2教研室,南京,210094
2. 中国矿业大学信息学院,徐州,221008 |
| |
| 基金项目： | 南京理工大学博士后基金项目资助 |
| |
| 摘 要： | 文章通过实例对BP网络的几种代表性改进模型进行了性能对比研究。分析了BP网络基于标准梯度下降法和基于数值优化方法的算法改进和训练策略改进获得的代表性模型的优缺点,并结合遥感图像分类实例,对其收敛速度和分类效果进行了对比分析,其结果可为BP网络模型的选择和改进提供一些思路和借鉴。
|
| 关 键 词： | BP网络 梯度下降法 数值优化 训练策略 性能对比 |
| 文章编号： | 1002-8331-(2003)19-0120-02 |
Comparative Study on Improved Models of BP Networks |
| |
| Li Chaofeng Qu Yingge Xia Deshen Zou Hai. Comparative Study on Improved Models of BP Networks[J]. Computer Engineering and Applications, 2003, 39(19): 120-121,132 |
| |
| Authors: | Li Chaofeng Qu Yingge Xia Deshen Zou Hai |
| |
| Affiliation: | Li Chaofeng 1 Qu Yingge 1 Xia Deshen 1 Zou Hai 21 |
| |
| Abstract: | A comparative study on some typical improved models of BP networks is proposed.The advantages and disadvantages of two improved methods,one of improved algorithm based on standard Gradient descent and numerical optimization,and another of improved training strategy,are analyzed.At last taking remote sensing image classification as samples,comparative study on convergent velocity and classified effect is done.The study can be used for the reference in selecting learning algorithm and improved high performance algorithms of BP networks. |
| |
| Keywords: | BP networks Gradient descent algorithm Numerical optimization Training strategy Comparative study |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
