eXplainable AI (XAI)

1. Definitions, Intrinsic & Model-Agnostic XAI Methods
2. PI (Permutation Feature Importance)
3. SHAP (Shapley Additive exPlanations)
4. LIME (Local Interpretable Model Agnostic Explanation)

Loading the player...

Βασίλης Μάγκλαρης - maglaris@netmode.ntua.gr

Σχολή Ηλεκτρολόγων Μηχ. & Μηχ. Υπολογιστών Ε.Μ.Π.

Slides