Seminar CS 717: Understanding Explainable AI Methods (HWS 2026)

This seminar will cover classical attribution methods in Explainable AI, including techniques such as saliency maps, feature importance, and gradient-based explanations.
It will focus on how these methods help interpret and analyze the decision-making process of machine learning models.

In this seminar, you will

• Read, understand, and explore scientific literature
• Summarize a current research topic in a concise report (10 single-column pages + references)
• Give two presentations about your topic (3 minutes flash presentation, 15 minutes detailed presentation)
• Moderate a scientific discussion about the topic of one of your fellow students
• Review a (draft of a) report of a fellow student

• This seminar is organized by Prof. Dr.-Ing. Margret Keuper
• Prerequisites:  Background in Machine Learning
• Maximum number of participants is 6 Bachelor's students

Seminar Schedule is provided here : Schedule (PDF, 189 kB)