| 多层感知器的一种快速网络训练法及其应用 |
| |
| 引用本文： | 宋宜斌. 多层感知器的一种快速网络训练法及其应用[J]. 控制与决策, 2000, 15(1): 125-127 |
| |
| 作者姓名： | 宋宜斌 |
| |
| 作者单位： | 烟台大学计算机科学与工程系,264005 |
| |
| 基金项目： | 山东省教委科研基金项目!（J98F04） |
| |
| 摘 要： | 从多层感知器原理分析出发，提出一种自适应学习速率因子方法，用于对多层感知器中ＢＰ算法的改进，并将改进算法用于ＸＯＲ问题的学习及某分类器实例样本的学习。仿真结果表明，改进的ＢＰ算法可显著加速网络训练速度，学习过程具有较好的收敛性和较强的鲁棒性。
|
| 关 键 词： | 多层感知器 BP算法 网络训练法 神经网络 |
| 修稿时间： | 1998-08-31 |
Quick Training Method for Multi-layer Perception and Its Application |
| |
| Song Yibin. Quick Training Method for Multi-layer Perception and Its Application[J]. Control and Decision, 2000, 15(1): 125-127 |
| |
| Authors: | Song Yibin |
| |
| Affiliation: | Yantai University |
| |
| Abstract: | Based on the mechanism of multi-layer perception (MLP), a method with adaptive learning rate factors for the improvement of BP algorithm is presented. The improved algorithm is applied to the learning process of the XOR question and some classifier. The simulation results show the presented quick training algorithm can speed up the learning process of MLP, and improve the learning properties on convergence and robust performance. |
| |
| Keywords: | multi-layer perception BP algorithm adaptive learning rate factor |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《控制与决策》浏览原始摘要信息 |
|
点击此处可从《控制与决策》下载全文 |
