Skip to content

A TensorFlow implementation of Canonical Correlation Analysis (CCA) loss with custom gradients.

Notifications You must be signed in to change notification settings

itsikad/cca-loss-TF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Canonical Correlation Analysis Loss

A TensorFlow implementation of CCA loss with custom gradients.

Link to original paper: https://ttic.uchicago.edu/~klivescu/papers/andrew_icml2013.pdf

Files

This project includes two files:

  1. cca_loss.py - An implementation of the loss and its gradients
  2. deep_cca_model.py - An example deep model using the cca_loss (currently a toy model)

TODO:

  1. Update deep_cca_model.py to an actual deep network

About

A TensorFlow implementation of Canonical Correlation Analysis (CCA) loss with custom gradients.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages