Skip to content

A Deep CCA program written by a plain numpy and scipy library

Notifications You must be signed in to change notification settings

search-opensource-space/Deep_CCA

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DCCA: Deep Canonical Correlation Analysis

An implementation of Deep Canonical Correlation Analysis (DCCA or Deep CCA) in Python with plain library like numpy and scipy need installed.

DCCA is a method to learn com-plex nonlinear transformations of two views of data such that the resulting representations are highly linearly correlated.

DCCA is originally proposed in the paper: Andrew G, Arora R, Bilmes J, et al. Deep canonical correlation analysis[C]//International Conference on Machine Learning. 2013: 1247-1255.

Many followers use this idea for many fields like following paper for matching images and text:

Yan F, Mikolajczyk K. Deep correlation for matching images and text[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3441-3450.

Wang W, Arora R, Livescu K, et al. On deep multi-view representation learning[C]//International Conference on Machine Learning. 2015: 1083-1092.

Zhang X, Jin C, Zhang Y, et al. Image Tag Recommendation via Deep Cross-Modal Correlation Mining[M]//Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Springer, Cham, 2016: 437-449.

About

A Deep CCA program written by a plain numpy and scipy library

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%