| SLFM网络及其学习算法的改进 |
| |
| 引用本文： | 乐清洪,张庆丰,张锋铭,朱名铨.SLFM网络及其学习算法的改进[J].航空精密制造技术,2000,36(4):28-31. |
| |
| 作者姓名： | 乐清洪 张庆丰 张锋铭 朱名铨 |
| |
| 作者单位： | 西北工业大学飞行器制造工程系,西安,710072 |
| |
| 摘 要： | 介绍了一种新型的人工神经网络--有监督线性特征映射(SLFM)网络,它综合了BP网络的可监督性和SOM网络算法简单的优点,具有学习速度快、精度高、扩展能力较强的优点.文中讨论了SLFM网络的拓扑结构和学习机制,并对网络的学习算法进行了改进,对比实验表明,改进后的SLFM网络其性能得到了进一步的提高.
|
| 关 键 词： | 人工神经网络 拓扑结构 学习算法 |
| 文章编号： | 1003-5451(2000)04-0028-04 |
| 修稿时间： | 2000年1月3日 |
SLFM Network and Improved on Its Learning Algorithm |
| |
| Yue Qing hong,Zhang Qing feng Zhang Feng ming et al.SLFM Network and Improved on Its Learning Algorithm[J].Aviation Precision Manufacturing Technology,2000,36(4):28-31. |
| |
| Authors: | Yue Qing hong Zhang Qing feng Zhang Feng ming |
| |
| Abstract: | In this paper, a new type of artificial neural network, called supervised linear feature mapping (SLFM) network is presented, which integrates the advantages of BP in which learning is supervised and SOM network in which the algorithm adopted is simple, and features quick learning speed, high learning accuracy and good extension ability. Based on the discussion on the topology and learning algorithm of SLFM, the learning algorithm adopted is improved. Compared with the original, the improved SLFM has better properties. |
| |
| Keywords: | artificial neural network topology structure learning algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
