稀疏自编码器和分类器实现结合 self-taught-learning

代码说明：

  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。(Independent Learning the encoder and the sparse classifiers achieve the combination. First through sparse coding since no label was handwritten 5-9 training obtain the optimal parameters, and then through the front propagation, get the training and test sets of features, a label by 0-4 trained softmax model train set, then enter the test set to the classification model to classify.)

文件列表：

self-taught learning
....................\display_network.m,2647,2011-01-05
....................\feedForwardAutoencoder.m,1322,2015-09-13
....................\initializeParameters.m,622,2011-01-05
....................\loadMNISTImages.m,811,2011-04-28
....................\loadMNISTLabels.m,516,2011-04-26
....................\mnist-train-images.idx3-ubyte,47040016,1996-11-18
....................\mnist-train-labels.idx1-ubyte,60008,1996-11-18
....................\softmaxCost.m,1252,2015-07-26
....................\softmaxPredict.asv,746,2015-09-13
....................\softmaxPredict.m,746,2015-09-13
....................\softmaxTrain.m,1891,2011-05-11
....................\sparseAutoencoderCost.m,4351,2015-07-25
....................\stlExercise.asv,5291,2015-09-22
....................\stlExercise.m,5302,2015-09-22