UFLDL Tutorial

From Ufldl

(Difference between revisions)
Jump to: navigation, search
Line 23: Line 23:
* [[Exercise:PCA in 2D]]
* [[Exercise:PCA in 2D]]
* [[Exercise:PCA and Whitening]]
* [[Exercise:PCA and Whitening]]
 +
 +
 +
Softmax Regression
 +
* [[Softmax Regression]]
 +
* [[Exercise:Softmax Regression]]
Self-Taught Learning and Unsupervised Feature Learning  
Self-Taught Learning and Unsupervised Feature Learning  
-
* [[Unsupervised Feature Learning]]
 
* [[Self-Taught Learning]]
* [[Self-Taught Learning]]
-
* [[Image Classification]]  (talk about how to extract features from a large image)
 
* [[Exercise:Self-Taught Learning]]
* [[Exercise:Self-Taught Learning]]
Building Deep Networks for Classification
Building Deep Networks for Classification
-
* [[Softmax Regression]]
+
* [[Stacked Autoencoders]]
-
* [[Exercise:Softmax Regression]]
+
* [[Fine-tuning Stacked AEs]]
 +
* [[Exercise: Implement deep networks for digit classification]]
-
Fine-tuning
+
Working with Large Images
-
- Exercise: Experiment with and without pre-training
+
* Feature extraction using convolution 
 +
* Pooling
 +
* Multiple layers of convolution and pooling
-
Stacked Autoencoders
+
'''Advanced Topics''':
-
Fine-tuning Stacked AEs
+
[[Restricted Boltzmann Machines]]
-
Convolutional models (1 layer)
+
[[Deep Belief Networks]]
-
Pooling
+
[[Sparse Coding]]
-
Multiple layers of convolution and pooling
+
[[K-means]]
-
'''Advanced Topics''':
+
[[Spatial pyramids / Multiscale]]
-
 
+
-
RBM
+
-
 
+
-
DBN
+
-
 
+
-
[[Sparse Coding]]
+
-
K-means
+
[[Slow Feature Analysis]]
-
Spatial pyramids??
+
ICA Style Models:
 +
* [[Independent Component Analysis]]
 +
* [[Topographic Independent Component Analysis]]
-
SFA
 
-
ICA/TICA/TCNN
+
[[Tiled Convolution Networks]]

Revision as of 00:57, 19 April 2011

Sparse Autoencoder


Vectorized implementation


Preprocessing: PCA and Whitening


Softmax Regression


Self-Taught Learning and Unsupervised Feature Learning


Building Deep Networks for Classification


Working with Large Images

  • Feature extraction using convolution
  • Pooling
  • Multiple layers of convolution and pooling

Advanced Topics:

Restricted Boltzmann Machines

Deep Belief Networks

Sparse Coding

K-means

Spatial pyramids / Multiscale

Slow Feature Analysis

ICA Style Models:


Tiled Convolution Networks

Personal tools