Skip to content
master
Switch branches/tags
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.

readme.md

Parametric t-SNE

Laurens Van Der Maaten's parametric implementation of t-SNE.

Laurens' original implementation is for Matlab, here we are running in Octave with oct2py in the notebook Parametric t-SNE (Original). This code can take hours to complete.

In the Parametric t-SNE (Keras) notebook there is an implementation of the same technique by reimplementing all functions in Python with numpy and Keras. The code runs significantly faster (on my machine, 20 minutes). There are also some work-in-progress experiments, like using the pairwise probabilty embedding to pre-train the weights of an autoencoder, which appears to converge to a lower reconstruction error than a vanilla autoencoder.

Setup

On OS X:

$ brew install octave
$ pip install -r requirements.txt
$ jupyter notebook

About

Running parametric t-SNE by Laurens Van Der Maaten with Octave and oct2py.

Resources

License

Releases

No releases published

Packages

No packages published