Skip to content

Experiments with Direct Feedback Alignment and comparison to Backpropagation.

License

Notifications You must be signed in to change notification settings

chscheller/DirectFeedbackAlignment

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Direct Feedback Alignment

Experiments with Direct Feedback Alignment (https://arxiv.org/abs/1609.01596) and comparison to Backpropagation.

Contents

Small DNN framework with:

  • conv-, fully-connected-, dropout- and max-pool-layers
  • implementation of backward pass with dfa and backpropagation
  • customizable loss-function and optimizers (e.g. gd, momentum)

Reproducible experiments and comparisons

Installation

python setup.py

About

Experiments with Direct Feedback Alignment and comparison to Backpropagation.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages