UFLDL Tutorial

From Ufldl

(Difference between revisions)
Jump to: navigation, search
Line 71: Line 71:
[[Useful Links]]
[[Useful Links]]
-
 
'''Advanced Topics''':
'''Advanced Topics''':
 +
 +
'''Sparse Coding'''
 +
* [[Sparse Coding]]
 +
* [[Sparse Coding: Autoencoder Interpretation]]
 +
* [[Exercise:Sparse Coding]]
 +
 +
'''ICA Style Models'''
 +
* [[Independent Component Analysis]]
 +
* [[Topographic Independent Component Analysis]]
[[Convolutional training]]  
[[Convolutional training]]  
Line 82: Line 90:
[[Denoising Autoencoders]]
[[Denoising Autoencoders]]
-
 
-
[[Sparse Coding]]
 
-
 
-
[[Sparse Coding: Autoencoder Interpretation]]
 
[[K-means]]
[[K-means]]
Line 92: Line 96:
[[Slow Feature Analysis]]
[[Slow Feature Analysis]]
-
 
-
ICA Style Models:
 
-
* [[Independent Component Analysis]]
 
-
* [[Topographic Independent Component Analysis]]
 
[[Tiled Convolution Networks]]
[[Tiled Convolution Networks]]

Revision as of 06:52, 28 May 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


Softmax Regression


Self-Taught Learning and Unsupervised Feature Learning


Building Deep Networks for Classification


Linear Decoders with Autoencoders


Working with Large Images


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.


Miscellaneous:

MATLAB Modules

Data Preprocessing

Style Guide

Useful Links

Advanced Topics:

Sparse Coding

ICA Style Models

Convolutional training

Restricted Boltzmann Machines

Deep Belief Networks

Denoising Autoencoders

K-means

Spatial pyramids / Multiscale

Slow Feature Analysis

Tiled Convolution Networks


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

Personal tools