https://phaidra.ustp.at/o:4336 KANDINSKY Patterns: A Swiss-Knife for the Study of Explainable AI. Holzinger, Andreas Andreas Holzinger Medical University Graz and Alberta Machine Intelligence Institute Edmonton, Canada Kieseberg, Peter Peter Kieseberg University of Applied Sciences, St.Poelten Müller, Heimo Heimo Müller Medical University Graz text eng Kandinsky Patterns are mathematically describable, simple, self-contained, hence controllable test datasets for the development, validation and training of explainability in artificial intelligence (AI) and machine learning (ML). All rights reserved ERCIM News(120), 41-42 (2020-01) ERCIM News 120 41 42 754.01 kB 2020-01