Skip to content

Implements TCAV (a model interpretation technique) using TensorFlow and discusses the method's strengths and weaknesses

Notifications You must be signed in to change notification settings

stevenbischoff/TCAV-Implementation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

TCAV-Implementation

TCAV (Testing with Concept Activation Vectors) is a well-known tool for interpreting deep learning models first proposed by Kim et. al: https://arxiv.org/abs/1711.11279. This project implements a TCAV class in XOR_TCAV.ipynb and uses it to gain a greater understanding of the capabilities and limitations of TCAV as a model interpretation tool.

The graphs folder contains scripts that create the Graphviz visualizations found in XOR_TCAV.ipynb.

About

Implements TCAV (a model interpretation technique) using TensorFlow and discusses the method's strengths and weaknesses

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published