Lecturer: Marc Streit, Christian Steinparz, Andreas Hinterreiter
Contact: xai-course(at)jku.at 

Objectives

What’s the role of visualization in the age of machine learning? In the algorithm-focused world, visualizations can help understand and explain the input, the inner workings, and the output of machine learning models. In the human-focused world, machine learning can help with tasks such as creating effective visualizations, recommending suitable visualization types, or guiding users toward potentially interesting patterns in large and complex datasets. In this course, we will cover both worlds.

Subject

• Introduction and Course Overview
• Fundamentals & Explaining Algorithms
• Explaining Through Projections
• Visual Analytics for Deep Learning
• Overview of Explanation Techniques
• Selected Recent Work & Case Studies

Criteria for Evaluation

Lecture: Written exam (oral exam in exceptional cases).
Lab: Individual and group assignments.

Methods

Lecture: Slides combined with case studies and in-class exercises.
Lab: Tutorials on various technologies and techniques; presentation and discussion of assignments.

Study Material

Study material will be provided during the course.

Further Information

The lecture can be combined with an optional practical lab.