Explainable Machine Learning
Erklärbares Maschinelles Lernen
6 CPWinterEN
Prerequisites
Mandatory, as written
Knowledge of the content of module • 11881: Foundations of Data Mining or • 12351: Grundlagen des Data Mining
Recommended, as written
Basic knowledge of programming and machine learning
Contents
The most significant disadvantage of machine learning and deep learning algorithms today: the interpretability of models. To trust predictions of real-life applications of AI it is important to understand how (Explainability) and why (Interpretability) a prediction is made. • Key Concepts of Interpretability and Explainability Challenges • Fundamentals of Feature Importance and Impact • Global and Local Model-Agnostic Explainability Methods • Anchor and Counterfactual Explanations • Visualizing Convolutional Neural Networks • Interpretation Methods for multivariate Forecasting and Sensitivity Analysis • Tuning for Explainability
Learning outcomes
Students understand the interpretability and explainability of machine learning systems. They master methods of interpretability and can optimise systems for interpretability. They are able to implement interpretability and explainability mechanisms for machine learning systems.
Assessment
Prerequisite: • Successful completion of exercises and presentation of results in course Final module examination: • Written examination, 120 min.
Literature (5)
- Script and presentations are available for download in Moodle at the beginning of the semester and on an ongoing basis. Problems for exercises and instructions for lab experiments can be downloaded.
- Serg Masis, Interpretable Machine Learning with Python: Learn to build interpretable high-performance models with hands-on real-world examples, Packt 2021
- Ajay Thampi, Interpretable Ai: Building Explainable Machine Learning Systems, Manning 2022
- Christoph Molnar, Interpretable Machine Learning: A Guide For Making Black Box Models Explainable, 2022
- Uday Kamath; John Liu, Explainable Artificial Intelligence: An Introductionto Interpretable Machine Learning, Springer 2021
Remarks
• Study programme Informatik M.Sc.: Compulsory elective module in complex „Angewandte und Technische Informatik" (level 400) • Study programme Artificial Intelligence M.Sc.: Compulsory elective module in complex „Learning and Reasoning“ • Study programme Künstliche Intelligenz Technologie M.Sc.: Compulsory elective module in complex „Software-basierte Systeme“ • Study programme Cyber Security M.Sc.: Compulsory elective module in complex „Computer Science" • Study programme Medizininformatik B.Sc.: Compulsory elective module in complex „Informatik"
Source: BTU's module description · retrieved 29 Sep 2026Original