Main content

CS 656 — Explainable Artificial Intelligence
(dt. Explainable Artificial Intelligence)

Level, degree of commitment Specialization module, depends on importing study program
Forms of teaching and learning,
workload		 Lecture (2 SWS), recitation class (2 SWS),
180 hours (60 h attendance, 120 h private study)
Credit points,
formal requirements		 6 CP
Course requirement(s): Successful completion of at least 50 percent of the points from the weekly exercises as well as at least 2 presentations of the tasks.
Examination type: Oral examination (individual examination) or written examination or written assignment
Language,
Grading		 English,
The grading is done with 0 to 15 points according to the examination regulations for the degree program M.Sc. Data Science.
Origin M.Sc. Data Science
Duration,
frequency		 One semester,
each summer semester
Person in charge of the module's outline Prof. Dr. Christin Seifert

Contents

Translation is missing, sorry. German original:

Definitions and taxonomy of eXplainable AI (XAI), selected explanation methods including feature importance, concept-based explanations, counterfactuals, intrinsically interpretable models, and understanding large-language models (LLMs). Explanation as conversation, and human factors in XAI. Evaluation of explanations. Prospects on responsible AI (fairness, robustness, and accountability).


Qualification Goals

Translation is missing, sorry. German original:

Die Studierenden

  • sind in der Lage, die Kernkonzepte von Erklärungen zu beschreiben und verschiedene Erklärungstechniken zu identifizieren,
  • können entscheiden, wann Erklärungen verwendet werden sollen und die geeigneten Methoden auswählen,
  • können Erklärungstechniken auf eine Vielzahl von Aufgaben des maschinellen Lernens bei unterschiedlichen Datentypen anwenden,
  • können Erklärungen bewerten.

Prerequisites

None. Knowledge of machine learning, especially neural networks and backpropagation, as well as programming in Python is recommended.


Applicability

The module can be attended at FB12 in study program(s)

  • B.Sc. Data Science
  • M.Sc. Data Science
  • M.Sc. Computer Science

When studying M.Sc. Data Science, this module can be attended in the study area Free Compulsory Elective Modules.

The module can also be used in other study programs (export module).


Recommended Reading

  • Will be announced in the course.



Please note:

This page describes a module according to the latest valid module guide in Winter semester 2025/26. Most rules valid for a module are not covered by the examination regulations and can therefore be updated on a semesterly basis. The following versions are available in the online module guide:

  • Winter 2016/17 (no corresponding element)
  • Summer 2018 (no corresponding element)
  • Winter 2018/19 (no corresponding element)
  • Winter 2019/20 (no corresponding element)
  • Winter 2020/21 (no corresponding element)
  • Summer 2021 (no corresponding element)
  • Winter 2021/22 (no corresponding element)
  • Winter 2022/23 (no corresponding element)
  • Winter 2023/24 (no corresponding element)
  • Winter 2025/26

The module guide contains all modules, independent of the current event offer. Please compare the current course catalogue in Marvin.

The information in this online module guide was created automatically. Legally binding is only the information in the examination regulations (Prüfungsordnung). If you notice any discrepancies or errors, we would be grateful for any advice.