Code repository for deep learning interpretability project.
Neural Networks are widely considered to be "BlackBox" Models and the interpretability of Deep Learning Models are still an area of active research . In order to better understand the interpretability, my peers and I performed some experiments leveraging existing statistical methods.
We conduct experiments on MNIST Dataset and for purpose of interpretability we are working on CNN model .
Some techniques explored :-
-
Conformal Predictions
-
Integrated Gradients
-
SHAP
We will perform further experiments to get a better understanding than what we have acheived