| 前馈神经网络泛化性能力的系统分析 |
| |
| 引用本文： | 江学军,唐焕文.前馈神经网络泛化性能力的系统分析[J].系统工程理论与实践,2000,20(8):36-40. |
| |
| 作者姓名： | 江学军 唐焕文 |
| |
| 作者单位： | (1)山东经济学院计划统计系;(2)大连理工大学管理科学与工程研究所 |
| |
| 摘 要： | 通过对多层前馈网络的运行机制的系统分析 ,指出影响前馈网络泛化能力的根本原因是训练网络用的样本 ,包括样本质量、样本数量和样本代表性三个方面 .针对复杂系统给出了一种提高前馈网络泛化能力的途径 ,并通过对仿真算例的计算验证了得出的结论 .
|
| 关 键 词： | 多层前馈神经网络 泛化能力 系统分析 |
| 修稿时间： | 1998-12-30 |
System Analysis for Generalization of MFNN |
| |
| JIANG Xue-jun,TANG Huan-wen.System Analysis for Generalization of MFNN[J].Systems Engineering —Theory & Practice,2000,20(8):36-40. |
| |
| Authors: | JIANG Xue-jun TANG Huan-wen |
| |
| Institution: | (1) Shandong Institute of Economic;(2) Dalian University of Technology |
| |
| Abstract: | By the system analysis for the operation mechanism of multilayer feedforward neural networks(MFNN),this paper points out that the basic reasons affecting the generalization capability of MFNN are quality, quantity and representation ability of the training samples. And we give a method to raise the generalization capability of the complex system. The conclusion has been proved by experimental results. |
| |
| Keywords: | MFNN generalization capability system analysis |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《系统工程理论与实践》浏览原始摘要信息 |
| 点击此处可从《系统工程理论与实践》下载免费的PDF全文 |
