Establishing Transparency in Artificial Intelligence Systems

International Conference on Transdisciplinary AI (TransAI), pp. 116–121

Abstract

Many of the artificial intelligence systems used nowadays have a very high level of accuracy but fail to explain their decisions. This is critical, especially in sensitive areas such as medicine and the health area at large but also for applications of the law, finance etc., where explanations for certain decisions are needed and are often same useful and valuable as the decision itself. The paper presents a review of four different methods for creating transparency in AI systems. It also suggests a list of criteria under which circumstances one should use which methods.

Authors 3

1. Lars Quakulinski Aachen Informatik 5

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Informatik 5,Aachen,Germany

   Informatik 5, RWTH Aachen University, Aachen, Germany

2. Adamantios Koumpis Aachen Institute for Biomedical Informatics Informatik 5

   RWTH Aachen University · University of Cologne

   Affiliation as printed

   University of Cologne,Informatik 5, RWTH Aachen, Institute for Biomedical Informatics,Cologne,Germany

   Informatik 5, RWTH Aachen, Institute for Biomedical Informatics, University of Cologne, Cologne, Germany

3. Oya Beyan

   University of Cologne · Fraunhofer Institute for Applied Information Technology

   Affiliation as printed

   University of Cologne,Fraunhofer Institute for Applied Information Technology (FIT),Institute for Biomedical Informatics,Cologne,Germany

   Institute for Biomedical Informatics, Fraunhofer Institute for Applied Information Technology (FIT), University of Cologne, Cologne, Germany