Skip to content

Library providing attribution methods for Keras models. Supports Tensorflow and Theano backends.

License

Notifications You must be signed in to change notification settings

cmu-transparency/lib-attribution

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

93 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

lib-attribution

NOTE: this is an outdated and unmaintained repository! For an up-to-date, maintained implementation of this work, please use the TruLens libray.

The code in this repositoy is provided as-is, and may not be functional. It is intened simply to accompany the paper, "Influence-directed Explanations for Convolutional Neural Networks" (arXiv).

If using the techniques implemented in this repository (or if using the TruLens repository), please use the following citation:

@INPROCEEDINGS{
  leino18influence,
  author={Klas Leino and Shayak Sen and Anupam Datta and Matt Fredrikson and Linyi Li},
  booktitle={2018 IEEE International Test Conference (ITC)},
  title={Influence-Directed Explanations for Deep Convolutional Networks},
  year={2018},
}

About

Library providing attribution methods for Keras models. Supports Tensorflow and Theano backends.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages