This two-day course introduces the basics of Explainable AI (XAI) and serves as a foundation for further self-guided learning. It combines theory with hands-on exercises, with opportunities for discussion with the instructors.
This 2-half-day course provides an introduction to the topic of Explainable AI (XAI). This fundamental knowledge is to be used as a starting point for self-guided learning during and beyond the course time.
All course days cover alternating sequences of theoretical input and hands-on exercises, which are discussed with the instructors during the course.
The goal of the course is to help participants understand how XAI methods can help uncover biases in the data or provide interesting insights. After a general introduction to XAI, the course goes deeper into state-of-the-art model agnostic as well as model-specific interpretation techniques. The practical hands-on sessions will help to learn about strengths and weaknesses of these standard methods used in the field.
Learning goals
Day 1: Introduction to XAI and XAI for Random Forest
- General introduction to eXplainable AI
- Theory and practical application of the model-agnostic methods Permutation Feature Importance, SHAP and LIME to Random Forest models
- Theory and practical application of the model-specific method FGC to Random Forest models
- Comparison of different XAI methods for Random Forest models
Day 2: XAI for CNNs
- Short introduction to Convolutional Neural Networks (CNNs)
- Theory and practical application of the model-agnostic methods SHAP and LIME to CNN models
- Theory and practical application of the model-specific method Grad-CAM to CNN models for image data
- Comparison of different XAI methods for CNN models
Course date
Register now: May 6–7, 2025
For more information on how to register, please follow the link on the course date.
Prerequisites
Basic knowledge of Python (as taught in the courses “First steps in Python“ and “Data processing with Pandas & Data visualization with Matplotlib”). Basic understanding of ML / DL models (as taught in the courses “Machine Learning 1” or “Introduction to Machine Learning” and “Introduction to deep Learning”) (Random Forest, CNNs, Transformers).
Target group
This course is open to researchers of all career stages, or anyone interested in learning about the subject.
This course is free of charge.
