文件列表:

Autoencoder_Code\2006(深度学习经典)Reducing the dimensionality of data with neural networks_图文_百度文库.url (209, 2016-12-05)
Autoencoder_Code\backprop.m (5594, 2006-05-21)
Autoencoder_Code\backpropclassify.m (5474, 2006-06-20)
Autoencoder_Code\CG_CLASSIFY.m (1853, 2006-06-20)
Autoencoder_Code\CG_CLASSIFY_INIT.m (1136, 2006-06-20)
Autoencoder_Code\CG_MNIST.m (2727, 2006-06-20)
Autoencoder_Code\converter.m (3011, 2006-06-20)
Autoencoder_Code\makebatches.m (4169, 2006-06-20)
Autoencoder_Code\minimize.m (9180, 2014-10-23)
Autoencoder_Code\mnistclassify.m (1902, 2006-06-20)
Autoencoder_Code\mnistdeepauto.m (2199, 2006-06-20)
Autoencoder_Code\mnistdisp.m (1084, 2006-06-20)
Autoencoder_Code\rbm.m (3914, 2006-06-20)
Autoencoder_Code\rbmhidlinear.m (3964, 2006-06-20)
Autoencoder_Code\Reducing the Dimensionality of Data with Neural Networks：神经网络用于降维 - wishchin的专栏 - 博客频道 - CSDN.NET.url (124, 2016-12-05)
Autoencoder_Code\t10k-images-idx3-ubyte (7840016, 1998-01-26)
Autoencoder_Code\t10k-labels-idx1-ubyte (10008, 1998-01-26)
Autoencoder_Code\train-images-idx3-ubyte (47040016, 1996-11-18)
Autoencoder_Code\train-labels-idx1-ubyte (60008, 1996-11-18)
Autoencoder_Code\中文帮助.txt (2215, 2014-12-06)
Autoencoder_Code (0, 2016-12-09)

% Code provided by Ruslan Salakhutdinov and Geoff Hinton % % Permission is granted for anyone to copy, use, modify, or distribute this % program and accompanying programs and documents for any purpose, provided % this copyright notice is retained and prominently displayed, along with % a note saying that the original programs are available from our % web page. % The programs and documents are distributed without any warranty, express or % implied. As the programs were written for research purposes only, they have % not been tested to the degree that would be advisable in any important % application. All use of these programs is entirely at the user's own risk. How to make it work: 1. Create a separate directory and download all these files into the same directory 2. Download from http://yann.lecun.com/exdb/mnist the following 4 files: * train-images-idx3-ubyte.gz train-labels-idx1-ubyte.gz * t10k-images-idx3-ubyte.gz t10k-labels-idx1-ubyte.gz 3. Unzip these 4 files by executing: * gunzip train-images-idx3-ubyte.gz * gunzip train-labels-idx1-ubyte.gz * gunzip t10k-images-idx3-ubyte.gz * gunzip t10k-labels-idx1-ubyte.gz If unzipping with WinZip, make sure the file names have not been changed by Winzip. 4. Download Conjugate Gradient code minimize.m available at http://www.kyb.tuebingen.mpg.de/bs/people/carl/code/minimize/ 5. Download the following 13 files for training an autoencoder and a classification model: * mnistdeepauto.m Main file for training deep autoencoder * mnistclassify.m Main file for training classification model * converter.m Converts raw MNIST digits into matlab format * rbm.m Training RBM with binary hidden and visible units * rbmhidlinear.m Training RBM with Gaussian hidden and binary visible units * backprop.m Backpropagation for fine-tuning an autoencoder * backpropclassify.m Backpropagation for classification using "encoder" network * CG_MNIST.m Conjugate Gradient optimization for fine-tuning an autoencoder * CG_CLASSIFY_INIT.m Conjugate Gradient optimization for classification (training top-layer weights while holding low-level weights fixed) * CG_CLASSIFY.m Conjugate Gradient optimization for classification (training all weights) * makebatches.m Creates minibatches for RBM training * mnistdisp.m Displays progress during fine-tuning stage * README.txt 6. For training a deep autoencoder run mnistdeepauto.m in matlab. 7. For training a classification model run mnistclassify.m in matlab. 8. Make sure you have enough space to store the entire MNIST dataset on your disk. You can also set various parameters in the code, such as maximum number of epochs, learning rates, network architecture, etc.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：