中文说明：
自主学习把稀疏自编码器和分类器实现结合。先通过稀疏自编码对无标签的5-9的手写体进行训练得到最优参数，然后通过前向传播，得到训练集和测试集的特征，通过0-4有标签训练集训练出softmax模型，然后输入测试集到分类模型实现分类。
English Description：
Autonomous Learning combines sparse self coder with classifier. Firstly, the unlabeled 5-9 handwriting is trained by sparse self coding to obtain the optimal parameters, and then the characteristics of the training set and test set are obtained by forward propagation. The softmax model is trained by 0-4 labeled training set, and then the test set is input into the classification model to realize classification