摘要
结合作者研制的BP神经网络生成器,对BP网络结构和训练参数选取进行了详细的讨论,在克服传统BP网络缺陷方面进行了有益的探索。
The paper mainly discusses BP neural network structure and choice of sample trainning parameter, which is based on neural netwrok generator. On the research being done on this study. We make a successful study for overcoming the disadvantages of nenral network.
