# UFLDL Tutorial

### From Ufldl

(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

**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**

- Neural Networks
- Backpropagation Algorithm
- Gradient checking and advanced optimization
- Autoencoders and Sparsity
- Visualizing a Trained Autoencoder
- Sparse Autoencoder Notation Summary
- 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**

- Vectorization
- Logistic Regression Vectorization Example
- Neural Network Vectorization
- Exercise:Vectorization

**Preprocessing: PCA and Whitening**

**Softmax Regression**

**Self-Taught Learning and Unsupervised Feature Learning**

**Building Deep Networks for Classification**

- Deep Networks: Overview
- Stacked Autoencoders
- Fine-tuning Stacked AEs
- Exercise: Implement deep networks for digit classification

**Working with Large Images**

**Advanced Topics**:

ICA Style Models: