I am looking into the field of explainable AI. The idea is to provide justification for the decision/outputs of Machine Learning Algorithms.

I found some resources online such as: https://www.darpa.mil/program/explainable-artificial-intelligence from DARPA, and this paper https://arxiv.org/abs/1710.00794.

  • Can anyone suggest some good examples where Explainable AI was applied successfully ?
  • Main people in the field ? main research labs ?
  • A book ?

I would recommend a great book by Christoph Molnar: Interpretable Machine Learning - A Guide for Making Black Box Models Explainable.

It touches upon both Interpretable Models, e.g. Linear/Logistic Regression, Generalized Linear Models (GLMs), Generative Additive Models (GAMs), Decision Trees and Model-Agnostic Methods, e.g. LIME, SHAP.

Awesome Interpretable Machine Learning links to many interesting publications in the field.


Longer papers which I found when I recently started exploring this topic are:

For a more applied perspective and descriptions of concrete applications, you can start with this recent Science article introducing the topic to a general audience.

A good list of references can be found on the website of the IJCAI/ECAI 2018 Workshop on Explainable Artificial Intelligence and the Workshop on Human Interpretability in Machine Learning held at the same conference.

If you found more information elsewhere in the meantime, I'd be very interested to learn about it.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.