Skip to content

A PyTorch implementation of Correlation Recurrent Units

License

Notifications You must be signed in to change notification settings

simsunghyun/CRU

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Correlation Recurrent Units

This is a PyTorch implementation of the Correlation Recurrent Units (CRU) in "CRU: A Novel Neural Architecture for Improving the Predictive Performance of Time-Series Data" (Sunghyun Sim, Dohee Kim, Hyerim Bae, arxiv, 2022).

The CRU is a new layer specialized in predicting time series data and consists of the following figure. image

To learn more about CRU, you could read "https://arxiv.org/abs/2211.16653"

Releases

No releases published

Packages

No packages published

Languages