吴恩达深度学习课程记录

it is possible to use both L2 regularization and dropout

np.sum

没有指明维度，那么np.sum计算的是整个矩阵的和

L2_regularization_cost

### START CODE HERE ### (approx. 1 line)
    L2_regularization_cost = np.sum((np.sum(np.square(W1)),np.sum(np.square(W2)),np.sum(np.square(W3))))*lambd/(2*m)

L2_regularization_cost 适合于希望超参数少的情况，现在只需要调lambd
如果lambd太大的话，分类就会太“平滑”，导致高偏差.