self-taught-learning
所属分类：人工智能/神经网络/深度学习
开发工具：matlab
文件大小：9012KB
下载次数：149
上传日期：2015-09-28 09:35:55
上 传 者：
bingxueshawang
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 (0, 2015-09-22)
self-taught learning\display_network.m (2647, 2011-01-05)
self-taught learning\feedForwardAutoencoder.m (1322, 2015-09-13)
self-taught learning\initializeParameters.m (622, 2011-01-05)
self-taught learning\loadMNISTImages.m (811, 2011-04-28)
self-taught learning\loadMNISTLabels.m (516, 2011-04-26)
self-taught learning\mnist-train-images.idx3-ubyte (47040016, 1996-11-18)
self-taught learning\mnist-train-labels.idx1-ubyte (60008, 1996-11-18)
self-taught learning\softmaxCost.m (1252, 2015-07-26)
self-taught learning\softmaxPredict.asv (746, 2015-09-13)
self-taught learning\softmaxPredict.m (746, 2015-09-13)
self-taught learning\softmaxTrain.m (1891, 2011-05-11)
self-taught learning\sparseAutoencoderCost.m (4351, 2015-07-25)
self-taught learning\stlExercise.asv (5291, 2015-09-22)
self-taught learning\stlExercise.m (5302, 2015-09-22)
近期下载者：
相关文件：
收藏者：