Skip to content

Construction and analysis of interpretable deep learning models

License

Notifications You must be signed in to change notification settings

mayukhsen13/Merck_Challenge_DL_Interpretability

Repository files navigation

Merck Co-Op Spring 2024

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 :-

  1. Conformal Predictions

  2. Integrated Gradients

  3. SHAP

    We will perform further experiments to get a better understanding than what we have acheived

About

Construction and analysis of interpretable deep learning models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published