Lecturer for Introduction to Explainable Machine Learning

This course gives an introduction to explainable and interpretable methods and approaches in machine learning. We discuss prominent concepts in explainable machine learning, analyze and compare their potential and shortcomings, and apply them to example problems.

The covered topics include but are not limited to:

• the role of explanations in machine learning (ML)
• definitions and terminology in explainable ML
• inherent versus post-hoc explainability
• prototypes in classification
• heat maps and saliency-based approaches
• global post-hoc explanations via surrogate models
• additive feature attribution methods
• local interpretable model-agnostic explanations
• explanations via Shapley values
• advanced methods from recent literature
• plausability, faithfulness, comprehensibility and consistency of explanations.