Students have obtained a comprehensive and practical understanding of how to combine visualization and artificial intelligence. On the one hand, they know how to leverage visualization to understand and explain the input, the inner workings, and the output of machine learning models. On the other hand, they know how to leverage machine learning to create effective visualizations, recommend suitable visualization types, or guide users towards potentially interesting patterns in complex datasets.
Skills
Knowledge
Interpret different models and understand what insights can be derived from them (k2)
Create elegant and informative data visualizations that help you understand models and communicate their results (k3, k6)
Apply a practical data visualization design workflow to take on any explainable AI and generative VIS challenge (k3, k6)
Evaluate and decide in which situations you need to use state-of-the-art data visualization systems and libraries in the context of AI (k5)
Fundamentals & Explaining Algorithms
Explaining Through Projections
Visual Analytics for Deep Learning
Overview of Explanation Techniques
Generative AI for visualization
Selected Recent Work & Case Studies
Criteria for evaluation
Written exam
Methods
Slides combined with case studies and in-class exercises
Language
English
Study material
Study material provided during the course
Changing subject?
No
Further information
In addition to the lecture, students can take an optional practical lab to learn how to combine AI methods with visualization theory.
The course was formerly known as Explainable AI.
Corresponding lecture
in collaboration with 993MLPEEAIU20: UE Explainable AI (1.5 ECTS) equivalent to 993MLPEEAIK19: KV Explainable AI (3 ECTS)
Earlier variants
They also cover the requirements of the curriculum (from - to) 993MLPEEAIV24: VL AI and Visualization (2024W-2025S) 993MLPEEAIV20: VL Explainable AI (2020W-2024S)
