Explainable Machine learning (ExML) seminar
Overview
In this seminar we will discuss different methodologies in Explainable Machine Learning, which is concerned with understanding what information a Machine Learning system learns and how it uses this information for decision making. We cover both seminal works as well as recent advancements in the field, including post-hoc explainability approaches and inherently interpretable model designs.
The seminar will consist of an introductory meeting with a lecture at the beginning of the semester introducing the field and distributing papers, and a two-day block course in the semester break covering paper presentations and discussions. Students are expected to read into their assigned paper, the related literature, prepare a talk as well as a paper summary with critical discussion.
Course Information
Semester: SS
Year: 2024
Requirements: The student has a solid understanding of Machine Learning and feels comfortable with Neural Networks (for example through lectures High Level Computer Vision, Neural Networks: Theory and Implementation, or Machine Learning).
Time and location:
Introductory lecture: 23.04.24 14:00 - 16:00 E1.4 room 024 (MPII lecture hall)
Block seminar: 06.08.24 & 07.08.24* 10:00 - 16:00 E1.4 room 021 (MPII seminar room)
*Please note the changed date due to a clash with the ML core lecture exam!
Essay is due on 12.07.24, 1pm (CEST)
Registration: Registration through the SIC seminar assignment system.
Registration through LSF is mandatory no later than 14.5.24!
Lecturer: Dr. Jonas Fischer, Prof. Dr. Bernt Schiele
Material
The introductory lecture slides, including student-paper assignments and paper links, can be found in our course Nextcloud.
For the basics of the field of Interpretability/Explainability, we recommend
Interpretable Machine Learning - A Guide for Making Black Box Models Explainable by Christoph Molnar
The book can be accessed for free online (external link), and as part of the Semesterapparat of the UdS Math and CS library.