Interpretable Machine Learning

Overview

Semester Winter (except WS 24/25)
ECTS 5
Level Master

Description

Language

The course will be held in English.

The learning objectives include the students acquiring both the theoretical and practical basics of interpretable machine learning (iML). For this purpose, they should internalize the mathematical basics as well as be able to implement, execute and evaluate iML approaches. In a final project, the students will independently apply the learned concepts to a new problem.

Recommended pre-requisites

  • Artificial Intelligence
  • Machine Learning
  • Deep Learning

Lecturer

Prof. Dr. rer. nat. Marius Lindauer
Adresse
Welfengarten 1
30167 Hannover
Gebäude
Raum
Prof. Dr. rer. nat. Marius Lindauer
Adresse
Welfengarten 1
30167 Hannover
Gebäude
Raum

Topics

  • GAMs and Rule-based Approaches
  • Feature Effects
  • Local Explanations
  • Shapley Values for Explainability
  • Instance-wise Feature Selection
  • Gradient-based Feature Attribution
  • Actionable Explanation and Resources
  • Evaluating Interpretability and Utility

Literature

The full list of literature can be found on the StudentIP course page. Recommended books to accompany the lecture are:

  • Interpretable ML Book by Molnar.
  • Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K., & Müller, K. R. (Eds.). (2019). Explainable AI: interpreting, explaining and visualizing deep learning (Vol. 11700). Springer Nature., ISO 690.