# UFLDL Tutorial

### From Ufldl

(Difference between revisions)

Line 23: | Line 23: | ||

* [[Exercise:PCA in 2D]] | * [[Exercise:PCA in 2D]] | ||

* [[Exercise:PCA and Whitening]] | * [[Exercise:PCA and Whitening]] | ||

+ | |||

Self-Taught Learning and Unsupervised Feature Learning | Self-Taught Learning and Unsupervised Feature Learning | ||

Line 28: | Line 29: | ||

* [[Self-Taught Learning]] | * [[Self-Taught Learning]] | ||

* [[Image Classification]] (talk about how to extract features from a large image) | * [[Image Classification]] (talk about how to extract features from a large image) | ||

+ | * [[Exercise:Self-Taught Learning]] | ||

+ | |||

+ | |||

+ | Building Deep Networks for Classification | ||

* [[Softmax Regression]] | * [[Softmax Regression]] | ||

* [[Exercise:Softmax Regression]] | * [[Exercise:Softmax Regression]] | ||

- | + | ||

Fine-tuning | Fine-tuning |

## Revision as of 00:53, 19 April 2011

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

Vectorized implementation

- Vectorization
- Logistic Regression Vectorization Example
- Neural Network Vectorization
- Using the MNIST Dataset
- Exercise:Vectorization

Preprocessing: PCA and Whitening

Self-Taught Learning and Unsupervised Feature Learning

- Unsupervised Feature Learning
- Self-Taught Learning
- Image Classification (talk about how to extract features from a large image)
- Exercise:Self-Taught Learning

Building Deep Networks for Classification

Fine-tuning
- Exercise: Experiment with and without pre-training

Stacked Autoencoders

Fine-tuning Stacked AEs

Convolutional models (1 layer)

Pooling

Multiple layers of convolution and pooling

**Advanced Topics**:

RBM

DBN

K-means

Spatial pyramids??

SFA

ICA/TICA/TCNN