XAI demonstrator

Teaching the use of Explainable Artificial Intelligence in a practical way

Increasingly, artificial intelligence (AI) is supporting decision-making in companies and for private individuals. However, automated decisions by algorithms will be viewed critically - even when the algorithms demonstrably lead to better results than human decision-makers. The reason: in many cases, the complexity of intelligent systems means that algorithmic decisions are made through a "black box" from a human perspective and can no longer be traced and validated. The research field of Explainable Artificial Intelligence (XAI) addresses this point and aims to generate automated explanations that are comprehensible to humans, which make the decisions made by AI systems in individual cases comprehensible and understandable to the user (see also: www.erklaerbare-ki.de). But what does XAI do in the first place and how can it help create a basis for appropriate trust towards the AI system?

The goal of the XAI demonstrator, which was developed at the University of Ulm, is to answer these questions by means of practical use cases in order to familiarize both students and the general public with the still rather unknown research field of Explainable Artificial Intelligence. The project was funded by the Péter Horváth Foundation.

Sponsor: Péter Horváth Foundation

Project period: June 2020 - January 2021

Further links

To the XAI demonstrator: https://www.erklaerbare-ki.de/xai-demonstrator

To the technical documentation: https://xai-demonstrator.github.io/xai-demonstrator

To the Github repository: https://github.com/XAI-Demonstrator/xai-demonstrator


The XAI demonstrator makes methods and concepts of XAI accessible to the general public by means of easily understandable application examples (use cases). In two use cases, users can themselves enlist the help of an AI system whose recommendations and decisions are explained live by an XAI.

In this way, the XAI demonstrator makes it possible to see the functioning of various XAI algorithms in action and thus to get to know the basic principle and application possibilities of XAI in a practical and understandable way. The XAI demonstrator will be used as a demonstration object for teaching, for imparting knowledge about XAI in companies and administration, and for addressing a broad public. Furthermore, the demonstrator is used scientifically to collect user feedback, to test new XAI approaches and, in particular, to evaluate their effect on the user.