MATLAB Modules

From Ufldl

(Difference between revisions)
Jump to: navigation, search
(Initial commit)
(Filled in file contents)
Line 1: Line 1:
== MATLAB Modules ==
== MATLAB Modules ==
-
'''[[Exercise:Sparse_Autoencoder|Sparse autoencoder]]''
+
'''[[Exercise:Sparse_Autoencoder|Sparse autoencoder]]'''
[http://ufldl.stanford.edu/wiki/resources/sparseae_exercise.zip sparseae_exercise.zip]
[http://ufldl.stanford.edu/wiki/resources/sparseae_exercise.zip sparseae_exercise.zip]
 +
* checkNumericalGradient.m - Makes sure that computeNumericalGradient is implmeented correctly
 +
* computeNumericalGradient.m - Computes numerical gradient of a function (to be filled in)
 +
* display_network.m - Visualizes images or filters for autoencoders as a grid
 +
* initializeParameters.m - Initializes parameters for sparse autoencoder randomly
 +
* sampleIMAGES.m - Samples 8x8 patches from an image matrix (to be filled in)
 +
* sparseAutoencoderCost.m - Calculates cost and gradient of cost function of sparse autoencoder
 +
* train.m - Framework for training and testing sparse autoencoder
'''[[Exercise:Vectorization|Vectorization]]'''
'''[[Exercise:Vectorization|Vectorization]]'''
[http://ufldl.stanford.edu/wiki/resources/mnistHelper.zip mnistHelper.zip]
[http://ufldl.stanford.edu/wiki/resources/mnistHelper.zip mnistHelper.zip]
-
 
+
* loadMNISTImages.m - Returns a matrix containing raw MNIST images
 +
* loadMNISTLabels.m - Returns a matrix containing MNIST labels
'''[[Exercise:PCA_and_Whitening|PCA and Whitening]]'''
'''[[Exercise:PCA_and_Whitening|PCA and Whitening]]'''
[http://ufldl.stanford.edu/wiki/resources/pca_exercise.zip pca_exercise.zip]
[http://ufldl.stanford.edu/wiki/resources/pca_exercise.zip pca_exercise.zip]
 +
* display_network.m - Visualizes images or filters for autoencoders as a grid
 +
* pca_gen.m - Framework for whitening exercise
 +
* sampleIMAGESRAW.m - Returns 8x8 raw unwhitened patches
'''[[Exercise:Softmax_Regression|Softmax Regression]]'''
'''[[Exercise:Softmax_Regression|Softmax Regression]]'''
[http://ufldl.stanford.edu/wiki/resources/softmax_exercise.zip softmax_exercise.zip]
[http://ufldl.stanford.edu/wiki/resources/softmax_exercise.zip softmax_exercise.zip]
 +
 +
* checkNumericalGradient.m - Makes sure that computeNumericalGradient is implmeented correctly
 +
* display_network.m - Visualizes images or filters for autoencoders as a grid
 +
* loadMNISTImages.m - Returns a matrix containing raw MNIST images
 +
* loadMNISTLabels.m - Returns a matrix containing MNIST labels
 +
* softmaxCost.m - Computes cost and gradient of cost function of softmax
 +
* softmaxTrain.m - Trains a softmax model with the given parameters
 +
* train.m - Framework for this exercise

Revision as of 18:43, 28 April 2011

MATLAB Modules

Sparse autoencoder

sparseae_exercise.zip

  • checkNumericalGradient.m - Makes sure that computeNumericalGradient is implmeented correctly
  • computeNumericalGradient.m - Computes numerical gradient of a function (to be filled in)
  • display_network.m - Visualizes images or filters for autoencoders as a grid
  • initializeParameters.m - Initializes parameters for sparse autoencoder randomly
  • sampleIMAGES.m - Samples 8x8 patches from an image matrix (to be filled in)
  • sparseAutoencoderCost.m - Calculates cost and gradient of cost function of sparse autoencoder
  • train.m - Framework for training and testing sparse autoencoder

Vectorization

mnistHelper.zip

  • loadMNISTImages.m - Returns a matrix containing raw MNIST images
  • loadMNISTLabels.m - Returns a matrix containing MNIST labels

PCA and Whitening

pca_exercise.zip

  • display_network.m - Visualizes images or filters for autoencoders as a grid
  • pca_gen.m - Framework for whitening exercise
  • sampleIMAGESRAW.m - Returns 8x8 raw unwhitened patches

Softmax Regression

softmax_exercise.zip

  • checkNumericalGradient.m - Makes sure that computeNumericalGradient is implmeented correctly
  • display_network.m - Visualizes images or filters for autoencoders as a grid
  • loadMNISTImages.m - Returns a matrix containing raw MNIST images
  • loadMNISTLabels.m - Returns a matrix containing MNIST labels
  • softmaxCost.m - Computes cost and gradient of cost function of softmax
  • softmaxTrain.m - Trains a softmax model with the given parameters
  • train.m - Framework for this exercise
Personal tools