Explainability of artificial intelligence (AI)

Duration: 01.07.2021 to 30.06.2025
Total funding volume: approx. 14 million euros
University funding volume: 8.2 million euros
Funded by: German Research Foundation (DFG)

How can humans understand decisions made by machines? What do algorithmic approaches tell us? How can artificial intelligence (AI) become comprehensible?

Technical explanations often require knowledge about how AI works and are difficult to understand. In the Collaborative Research Centre/Transregio Constructing Explainability, researchers are developing ways to involve users in the explanation process.

To this end, the interdisciplinary research team is investigating the principles, mechanisms and social practices of explaining and how these can be taken into account in the design of AI systems. The aim of the project is to make explanation processes understandable and to create comprehensible assistance systems.

A total of 21 project leaders and around 30 researchers from the fields of linguistics, psychology, media studies, sociology, economics and computer science at Bielefeld and Paderborn Universities are investigating the co-construction of explanations.

Project leader: Prof Dr Philipp Cimiano, Bielefeld University (deputy spokesperson)