| 一个改进的BP神经网络自适应学习算法 |
| |
| 引用本文： | 陈昭炯.一个改进的BP神经网络自适应学习算法[J].福州大学学报(自然科学版),1998(4):19-21. |
| |
| 作者姓名： | 陈昭炯 |
| |
| 作者单位： | 福州大学计算机科学与技术系 |
| |
| 摘 要： | 提出了一个改进的自适应变步长ＢＰ网络学习算法，对多个布尔学习问题以及Ｆｉｓｈｅｒ收集的一个植物分类问题进行计算．结果表明，该算法不仅有相当快的收敛速度，而且在避免学习过程陷入局部极小方面也取得较好结果．
|
| 关 键 词： | 神经网络 搜索方法 学习算法 最优化 |
An Improved Adaptive Learning Algorithm for BP Neural Network |
| |
| Chen Zhaojiong.An Improved Adaptive Learning Algorithm for BP Neural Network[J].Journal of Fuzhou University(Natural Science Edition),1998(4):19-21. |
| |
| Authors: | Chen Zhaojiong |
| |
| Institution: | Chen Zhaojiong (Department of Computer Science and Technology, Fuzhou University,Fuzhou, 350002) |
| |
| Abstract: | On the basis of the work (6), we present an improved adaptive BP learning algorithm with variable stepsizes in which the nonmonotone line search technique from unconstrained optimization is employed. The algorithm has been tested on several Boolean learning problems as well as a well-known plant classification problem due to Fisher, and the results suggest that the algrithm not only converges in a quite fast way, but also avoids stagnation problem to some extent. |
| |
| Keywords: | neural network search method learning algorithm optimization |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《福州大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《福州大学学报(自然科学版)》下载免费的PDF全文 |
