通过对字符特征的分析，确定输入层，隐含层，输出层单元数目。

Through the analysis of character features, confirm the input layer, hidden layer and the License of output layer units.

youdao

将各生育阶段的耗水量作为输入，将作物单产作为输出，构建了具有1个隐含单元层的BP神经网络结构。

With the relative water consumption of each growing stage as input and relative crop yield output, a BP artificial neural network structure containing a single hidden layer is established.

youdao

将已经通过工程手段计算出结果的数据以输入单元、隐含层和输出单元的形式代入系统进行神经网络训练，不同的屈服准则对应训练出不同的网络系统。

Take known data to the system to train the networks. According to different strength criterions, the different networks were trained. After that, the networks with new data were checked up.

youdao