Skip to content

Check the influence of weight initialization on CNNs

Notifications You must be signed in to change notification settings

jcbgamboa/CNN_pretrain

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CNN_pretrain

CNNs have produced great results. But a problem they have is that they require too much data. Could there be ways to initialize their weights such that this requirement is loosed? This code checks some ideas, for example: can we initialize the CNN using the weights of the CAE (as it was already proposed in the original CAE article)? Do we actually get better results if we do that? And what about Greedy layer-wise pre- training? But how to adapt it to the convolutional nature of CNNs?

[still under construction........]

About

Check the influence of weight initialization on CNNs

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published