A scale training algorithm of BP neural network is used, and sample reorganization method is proposed. Its advantage is the fast training speed and good feature extraction ability.
作者使用比例训练的BP算法，提出对训练模式进行样本重组的方法，其特点是训练速度快、特征抽取能力强。
Based on expatiated the basic structure model and some general improved algorithms of BP neural network, this paper brings forward a new self-organization learning algorithm.
介绍了BP网络的基本结构模型与常见改进算法，在此基础上提出了一种新型的结构自组织BP网络算法。
Training a multilayer neural net by BP algorithm is slow and it is difficult to choose the number of hidden units and layers in advance.
使用BP算法训练多层网络的速度很慢而且事先难于确定隐节点和隐层的适当数目。
应用推荐