文件名称:self-taught-learning
介绍说明－－下载内容来自于网络，使用问题请自行百度
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.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
self-taught learning/
self-taught learning/display_network.m
self-taught learning/feedForwardAutoencoder.m
self-taught learning/initializeParameters.m
self-taught learning/loadMNISTImages.m
self-taught learning/loadMNISTLabels.m
self-taught learning/mnist-train-images.idx3-ubyte
self-taught learning/mnist-train-labels.idx1-ubyte
self-taught learning/softmaxCost.m
self-taught learning/softmaxPredict.asv
self-taught learning/softmaxPredict.m
self-taught learning/softmaxTrain.m
self-taught learning/sparseAutoencoderCost.m
self-taught learning/stlExercise.asv
self-taught learning/stlExercise.m
self-taught learning/display_network.m
self-taught learning/feedForwardAutoencoder.m
self-taught learning/initializeParameters.m
self-taught learning/loadMNISTImages.m
self-taught learning/loadMNISTLabels.m
self-taught learning/mnist-train-images.idx3-ubyte
self-taught learning/mnist-train-labels.idx1-ubyte
self-taught learning/softmaxCost.m
self-taught learning/softmaxPredict.asv
self-taught learning/softmaxPredict.m
self-taught learning/softmaxTrain.m
self-taught learning/sparseAutoencoderCost.m
self-taught learning/stlExercise.asv
self-taught learning/stlExercise.m
本网站为编程资源及源代码搜集、介绍的搜索网站，版权归原作者所有！ 粤ICP备11031372号
1999-2046 搜珍网 All Rights Reserved.