UFLDL Tutorial

From Ufldl

(Difference between revisions)
Jump to: navigation, search
Line 14: Line 14:
* [[Exercise:Sparse Autoencoder]]
* [[Exercise:Sparse Autoencoder]]
-
 
-
 
-
----
 
-
'''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'''
Line 32: Line 28:
* [[Exercise:PCA in 2D]]
* [[Exercise:PCA in 2D]]
* [[Exercise:PCA and Whitening]]
* [[Exercise:PCA and Whitening]]
 +
 +
----
 +
'''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.

Revision as of 20:10, 29 April 2011

Description: This tutorial will teach you the main ideas of Unsupervised Feature Learning and Deep Learning. By working through it, you will also get to implement several feature learning/deep learning algorithms, get to see them work for yourself, and learn how to apply/adapt these ideas to new problems.

This tutorial assumes a basic knowledge of machine learning (specifically, familiarity with the ideas of supervised learning, logistic regression, gradient descent). If you are not familiar with these ideas, we suggest you go to this Machine Learning course and complete sections II, III, IV (up to Logistic Regression) first.


Sparse Autoencoder


Vectorized implementation


Preprocessing: PCA and Whitening


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.


Softmax Regression


Self-Taught Learning and Unsupervised Feature Learning


Building Deep Networks for Classification


Working with Large Images


Miscellaneous:

MATLAB Modules

Data Preprocessing

Style Guide

Advanced Topics:

Restricted Boltzmann Machines

Deep Belief Networks

Denoising Autoencoders

Sparse Coding

K-means

Spatial pyramids / Multiscale

Slow Feature Analysis

ICA Style Models:

Tiled Convolution Networks


Material contributed by: Andrew Ng, Jiquan Ngiam, Chuan Yu Foo, Yifan Mai, Caroline Suen

Personal tools