Skip to content

matthewclso/ConvTransformer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

ConvTransformer

This architecture combines the popular Transformer network with the proven convolution kernel. We investigate how this can improve performance and training speed in the application of Neural Machine Translation.

You can read more about the theory in documentation.pdf

About

Transformers with convolutional attention heads

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published