采用动量梯度下降算法训练BP网络。在本源码中，训练样本定如下：p=[-1 -2 3 1 -1 1 5 -3] 目标矢量为t=[-1 -1 1 1]-Gradient descent algorithm using momentum BP network training. In this source, the training sample set as follows: p = [-1-2 3 1 -1 1 5-3]　target vector for t = [-1-1 1 1]