| 广义BP算法及网络容错性和泛化能力的研究 |
| |
| 引用本文： | 董聪,刘西拉.广义BP算法及网络容错性和泛化能力的研究[J].控制与决策,1998,13(2):120-124. |
| |
| 作者姓名： | 董聪 刘西拉 |
| |
| 作者单位： | 清华大学土木工程系 |
| |
| 基金项目： | 国家自然科学基金，航空基金，CIMS基金，智能技术与系统国家重点实验室基金,攀登计划重大项目资助 |
| |
| 摘 要： | 给出广义ＢＰ算法及其网络学习的多种方式，常用的前向网络全并行权值修改方式是其中效率较低的一种，有许多更好的权值修改方式可以使用。网络的泛化能力依赖于网络的拓扑结构，对国际上为改进网络泛化能力而采用的几种修正学习算法的实际功能做了简要的评论。
|
| 关 键 词： | 广义BP算法，前向网络，网络拓扑，泛化能力 |
A Study on Generalized BP Algorithm of Neural Network and Its Fault Tolerance and Generalization Capability |
| |
| Dong Cong,Liu Xila.A Study on Generalized BP Algorithm of Neural Network and Its Fault Tolerance and Generalization Capability[J].Control and Decision,1998,13(2):120-124. |
| |
| Authors: | Dong Cong Liu Xila |
| |
| Affiliation: | Tsinghua University |
| |
| Abstract: | In this paper, a generalized BP algorithm is presented, and some new learning approaches which are more suitable to multilayer feedforward neural networks are suggested. Full parallel weight modification of multilayer feedforward network has been widely used by now, but its computing efficiency is lower, while many of other learning methods are better to be used. The generalized capability of feedforward nets is related to its topologic structure, a systematic review is made over those modified algorithms for improving the generalization capability of multilayer feedforward network. |
| |
| Keywords: | generalized BP algorithm multilayer feedforward network topologic structure generalization capability |
| 本文献已被 CNKI 维普 等数据库收录！ |
