UFLDL Tutorial

From Ufldl

Jump to: navigation, search
(Boldfaced the topic headings.)
Line 4: Line 4:
sections II, III, IV (up to Logistic Regression) first.  
sections II, III, IV (up to Logistic Regression) first.  
-
Sparse Autoencoder
+
 
 +
'''Sparse Autoencoder'''
* [[Neural Networks]]
* [[Neural Networks]]
* [[Backpropagation Algorithm]]
* [[Backpropagation Algorithm]]
Line 18: Line 19:
'''Note''': The sections above this line are stable.  The sections below are still under construction, and may change without notice.  Feel free to browse around however, and feedback/suggestions are welcome.  
'''Note''': The sections above this line are stable.  The sections below are still under construction, and may change without notice.  Feel free to browse around however, and feedback/suggestions are welcome.  
-
Vectorized implementation
+
'''Vectorized implementation'''
* [[Vectorization]]
* [[Vectorization]]
* [[Logistic Regression Vectorization Example]]
* [[Logistic Regression Vectorization Example]]
Line 25: Line 26:
-
Preprocessing: PCA and Whitening
+
'''Preprocessing: PCA and Whitening'''
* [[PCA]]
* [[PCA]]
* [[Whitening]]
* [[Whitening]]
Line 33: Line 34:
-
Softmax Regression
+
'''Softmax Regression'''
* [[Softmax Regression]]
* [[Softmax Regression]]
* [[Exercise:Softmax Regression]]
* [[Exercise:Softmax Regression]]
-
Self-Taught Learning and Unsupervised Feature Learning  
+
'''Self-Taught Learning and Unsupervised Feature Learning'''
* [[Self-Taught Learning]]
* [[Self-Taught Learning]]
* [[Exercise:Self-Taught Learning]]
* [[Exercise:Self-Taught Learning]]
-
Building Deep Networks for Classification
+
'''Building Deep Networks for Classification'''
* [[Deep Networks: Overview]]
* [[Deep Networks: Overview]]
* [[Stacked Autoencoders]]
* [[Stacked Autoencoders]]
Line 50: Line 51:
-
Working with Large Images
+
'''Working with Large Images'''
* [[Feature extraction using convolution]]
* [[Feature extraction using convolution]]
* [[Pooling]]
* [[Pooling]]

Revision as of 20:46, 22 April 2011

Personal tools