在神经网络的应用过程中,经常遇到样本太多问题,采用模糊聚类分析,科学选取学习样本,使少量的学习样本本身包含全部样本的特性,很好地解决了由于样本多学习速度慢的问题,并提出了训练结果检验方法.此方法可以作为神经网络应用的一个拓展.

During the application of BP neural network, there is a question of how to deal with a great lot of the sample set. The fuzzy cluster analysis is used as the preprocessing to select the sample set which includes characteristic of all members, which can solve the problem of study speed, and the method of analyzing the result of training is developed. This process can be a necessary supplement of the application of BP neural network.