| BP网络学习参数模糊自适应算法的实现 |
| |
| 引用本文： | 冯天瑾,陈哲,顾方方.BP网络学习参数模糊自适应算法的实现[J].中国海洋大学学报(自然科学版),2000,30(1):137-141. |
| |
| 作者姓名： | 冯天瑾 陈哲 顾方方 |
| |
| 作者单位： | 青岛海洋大学电子工程系,青岛,266003 |
| |
| 基金项目： | 国家自然科学基金课题!( 6 96 75 0 0 5 )资助 |
| |
| 摘 要： | 前馈神经网络BP算法的改进方案中，对网络训练(学习)过程中学习率和惯性系数进行模糊自适应调节，以提高收敛速度，是一项很有效的措施。文中具体分析了如何根据设计者的先验知识确定模糊规则和隶属函数，并以三比特异或函数(或称奇偶分类)的实现为例，验证了这种算法的改进、加速了BP网络的学习过程。
|
| 关 键 词： | 前馈神经网络 BP算法 学习率 惯性系数 模糊控制规则表 隶属度函数 |
| 文章编号： | 1001-1862(2000)01-0137-05 |
| 修稿时间： | 1998-09-01 |
A Fuzzy Adaptive Algorithm for Learning Parameters of BP Networks |
| |
| Feng Tianjin,Chen Zhe,Gu Fangfang.A Fuzzy Adaptive Algorithm for Learning Parameters of BP Networks[J].Periodical of Ocean University of China,2000,30(1):137-141. |
| |
| Authors: | Feng Tianjin Chen Zhe Gu Fangfang |
| |
| Abstract: | In the improved approaches of BP algorithm for feedforward neural networks, it is very effective for accelerating training that the learning rate and the momentum coefficient are updated by the fuzzy logic controller during the learning process. This article analyzes how to choose the fuzzy control rule table and the membership function by using a priori knowledge about the process. We also apply the improved algorithm to the experiment of 3-bit XOR problem, the results show that the convergence rate is much higher than the classical BP algorithm. |
| |
| Keywords: | feedforward neural network BP algorithm learning rate momentum coefficient fuzzy control rule table membership function |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
