摘要
在人工神经网络的使用中,BP神经网络是使用比较多的网络结构,简要介绍了BP网络的基本结构和BP算法,分析BP网络存在的缺陷,介绍了两种改进BP网络泛化能力的方法,并通过例子分析了两种方法的适用性。
In the application of artificial neural network, BP network is more often used than others. In this paper, the basic structure and algorithm of the BP network are briefly introduced and its disadvantages discussed. Accordingly, two methods to improve the generalization ability of BP network are presented, and through an example, their applicability is analyzed.
出处
《石家庄铁道学院学报》
2005年第3期94-96,103,共4页
Journal of Shijiazhuang Railway Institute
关键词
BP神经网络
泛化能力
过拟合
BP neural network
the generalization ability
over fit
作者简介
黄琳，女，1979年出生，助教。
