Deep Canonical Correlation Analysis with Python
MIT License
I'm currently adapting the code from https://github.com/VahidooX/DeepCCA.
This is an implementation of Deep Canonical Correlation Analysis in Python.
DCCA is a non-linear version of CCA which uses neural networks as the mapping functions instead of linear transformers. DCCA is originally proposed in the following paper:
Galen Andrew, Raman Arora, Jeff Bilmes, Karen Livescu, "Deep Canonical Correlation Analysis.", ICML, 2013.
It uses the Keras library with the Tensorflow backend.
The following are the differences between this implementation and the original paper: