Explainable machine learning (2022, 3rd lecture): Global model-agnostic methods

Lecture series 'Explainable machine learning' (University of Bonn, winter term 2022)

Topics covered:
- What are global model-agnostic methods and why are they useful?
- Attribution methods and feature importance
- Partial dependence plots
- Permutation feature importance
- Variance feature importance
- Prototypes and criticism
- Maximum mean discrepancy and witness function

Lecturer: Ribana Roscher
Winter term 2022, University of Bonn