forked from fcchou/sparse_autoencoder
-
Notifications
You must be signed in to change notification settings - Fork 0
Neural-network-based sparse autoencoder
License
Sandy4321/sparse_autoencoder
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
This is an exercise on implementing a sparse autoencoder. The excerise comes from Prof. Andrew Ng from the following website: http://ufldl.stanford.edu/wiki/index.php/Exercise:Sparse_Autoencoder The description and tutorial of the excerise can be also found in the PDF files in this folder. Note that I am implementing it in Python instead of MATLAB. The basic algorithm is the same. The code requires numpy and scipy. matplotlib is needed for visualization. Example: ====Gradient checking==== python gradient_test.py ====Training and visualize hidden units==== python visualize.py Example output figure are given (gradient_check.png and hidden_units.png). You may also play with the parameters in the code to see the difference on the results. The main codes are in sparse_autoencoder.py. Here the SparseAutoencoder class is designed to be quite general, so you may use it for other types of data.
About
Neural-network-based sparse autoencoder
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 100.0%