Here are the materials related to my session:
https://christophm.github.io/interpretable-ml-book/
https://originalstatic.aminer.cn/misc/pdf/Molnar-interpretable-machine-learning_compressed.pdf
- The following section: Interpretability, Interpretable Models, Model-Agnostic Methods (Feature Importance, Local Surrogate: LIME, Shapley Values), Example-Based Explanations (Counterfactual Explanations, Adversarial Examples, Prototypes and Criticisms)

The practical session will be based on this work
https://openreview.net/forum?id=WZixOzLrWF
Github: https://github.com/kdjoumessi/Test-Time-Explainability
