| 提高多层前向神经网络泛化能力的讨论 |
| |
| 引用本文： | 欧阳林群.提高多层前向神经网络泛化能力的讨论[J].南平师专学报,2007,26(2):60-63. |
| |
| 作者姓名： | 欧阳林群 |
| |
| 作者单位： | 武夷学院,电子工程系,福建,武夷山,354300 |
| |
| 摘 要： | 泛化能力是多层前向神经网络最重要的性能．泛化问题已成为目前神经网络领域的研究热点。本文从泛化理论现有提高神经网络泛化能力的方法等几个方面总结了当前神经网络结构优化与泛化能力研究的现状。神经网络泛化能力的提高可通过神经网络结构的优化和正则化等方法加以实现，并对提高网络泛化能力问题进行讨论。
|
| 关 键 词： | 神经网络 泛化能力 泛化方法 |
| 文章编号： | 1008-5963（2007）02-0060-04 |
| 修稿时间： | 2007-01-16 |
The Discussion on Improving Generalization Ability of a Feedforward Neural Network |
| |
| OUYANG Linqun.The Discussion on Improving Generalization Ability of a Feedforward Neural Network[J].Journal of Nanping Teachers College,2007,26(2):60-63. |
| |
| Authors: | OUYANG Linqun |
| |
| Institution: | Electronic Engineering Department of Wuyi University, Wuyishan, 354300 China |
| |
| Abstract: | Generalization ability is the most important performance of a feed-forward neural network, and the problem of generalization has been widely studied recently among the neural network community.this paper has surveyed the recent research work on neural network generalization ability and structural optimization in such respects as generalization theory and the prevailing methods for improving neural network generalization ability .It has pointed out that the generalization ability of neural network can be improved by using network optimization and regularization methods , the problem of improving neural network generalization ability is also analyzed. |
| |
| Keywords: | neural networks generalization ability generalization methods |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
