neural-network
所属分类：Windows编程
开发工具：Python
文件大小：1970KB
下载次数：49
上传日期：2016-02-27 12:09:12
上 传 者：
dylan_zju
说明： 深度学习python实现，并附有MNIST上的测试程序，准确率98 以上
(Deep learning learns low and high-level features large amounts of unlabeled data, improving classification on different, labeled, datasets. Deep learning can achieve an accuracy of 98 on the MNIST dataset.
)
文件列表:
neural-network (0, 2012-04-06)
neural-network\deep (0, 2012-04-06)
neural-network\deep\deep.py (5172, 2012-04-06)
neural-network\deep\display_network.py (21, 2012-04-06)
neural-network\deep\lazy_deep.py (4339, 2012-04-06)
neural-network\deep\neurolib.py (14, 2012-04-06)
neural-network\deep\numerical_gradient.py (24, 2012-04-06)
neural-network\deep\sample_images.py (19, 2012-04-06)
neural-network\deep\selftaught.py (27, 2012-04-06)
neural-network\deep\softmax.py (21, 2012-04-06)
neural-network\deep\sparse_autoencoder.py (24, 2012-04-06)
neural-network\display_network.py (2588, 2012-04-06)
neural-network\neurolib.py (1019, 2012-04-06)
neural-network\numerical_gradient.py (962, 2012-04-06)
neural-network\pca (0, 2012-04-06)
neural-network\pca\display_network.py (21, 2012-04-06)
neural-network\pca\pca.py (1728, 2012-04-06)
neural-network\pca\pca2d.py (1569, 2012-04-06)
neural-network\pca\pca_gen.py (2197, 2012-04-06)
neural-network\pca\sample_images.py (19, 2012-04-06)
neural-network\rae (0, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP (0, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code (0, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\classifyWithRAE.m (2678, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\computeCostAndGradRAE.m (6113, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\forwardPropRAE.m (4600, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\getAccuracy.m (262, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\getFeatures.m (1424, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\getW.m (2037, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\initializeParameters.m (947, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\RAECost.m (1291, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\read_rtPolarity.m (4417, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\soft_cost.m (735, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\trainTestRAE.m (3838, 2012-04-06)
neural-network\rae\codeDataMoviesEMNLP\code\tree2.m (5251, 2012-04-06)
neural-network\rae\codeNIPS2011 (0, 2012-04-06)
neural-network\rae\codeNIPS2011\cell2str.m (307, 2012-04-06)
neural-network\rae\codeNIPS2011\convertStanfordParserTrees.m (4865, 2012-04-06)
... ...
This is a rewrite of the tutorial about unsupervised feature learning and deep learning in Python using numpy and scipy.
Tutorial: http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
I use numpy for matrices, and scipy.optimize package for the L-BFGS minimization algorithm.
Deep learning learns low and high-level features from large amounts of unlabeled data, improving classification on different, labeled, datasets. Deep learning can achieve an accuracy of ***% on the MNIST dataset.
近期下载者：
相关文件：
收藏者：