将Iris数据集分为2组，每组各75个样本，每组中每种花各有25个样本。其中一组作为以上程序的训练样本，另外一组作为检验样本。为了方便训练，将3类花分别编号为1，2，3 。

　　使用这些数据训练一个4输入（分别对应4个特征），3输出（分别对应该样本属于某一品种的可能性大小）的前向网络。-The Iris data set is divided into two groups each of 75 samples in each group have 25 samples in each flower. One set of sample programs as more training, another group as the test samples. To facilitate training, the three types of flowers were numbered 1,2,3. Training before using these data a 4-input (respectively 4 features), 3 outputs (respectively the possibility should belong to a variety of sample size) to the network.