Skip to content

georgeiswang/Sparse-Autoencoder-Tensorflow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Sparse Autoencoder

The code is a tensorlow version implementation of Sparse Autoencoder. A detail explaination of Sparse Autoencoder can be found from Andrew Ng's Tutorial.

Why use Sparse Autoencoder?

The main purspose for sparse-autoencoder is to encode the averaged word vectors in one query such that the encoded vector will share the similar properties as word2vec training (i.e. similar queries will have shorter distance in Euclidean space).

About

Tensorflow codes for training sparse autoencoder

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages