Week 7: Explainable artificial intelligence (XAI)

Main reference

Molnar 8.1, 8.5, 9.2-9.6

What you will learn this week

  • Global explainability
  • Local explainability
    • LIME
    • Counterfactuals
    • Anchors
    • Shapley values

Lecture slides

Tutorial instructions

Instructions:

Assignments