Title (eng)

KANDINSKY Patterns: A Swiss-Knife for the Study of Explainable AI.

Author

Andreas Holzinger   Medical University Graz and Alberta Machine Intelligence Institute Edmonton, Canada

Peter Kieseberg   University of Applied Sciences, St.Poelten

Heimo Müller   Medical University Graz

Description (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).

Object languages

English

Date

2020-01

Rights

© All rights reserved