Skip to content

Very concise example of integrated gradients (a method to reveal areas of attention in input images)

Notifications You must be signed in to change notification settings

JoHof/IntegratedGradientsTutorial

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 

Repository files navigation

Integrated Gradients Tutorial

Very concise toy example of integrated gradients (a method to reveal areas of attention of neural networks in input images)

Integrated Gradients were proposed by Sundararajan et al. in the paper:

Sundararajan, Mukund, Ankur Taly, and Qiqi Yan. "Axiomatic attribution for deep networks." In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 3319-3328. JMLR. org, 2017

https://arxiv.org/pdf/1703.01365.pdf

About

Very concise example of integrated gradients (a method to reveal areas of attention in input images)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published