Title (en)
KANDINSKY Patterns: A Swiss-Knife for the Study of Explainable AI.
Language
English
Description (en)
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).
Author of the digital object
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)
Licence Selected
Type of publication
Article
Name of Publication (en)
ERCIM News
Number
120
From Page
41
To Page
42
Publication Date
2020-01
University of Applied Sciences St. Pölten | Campus-Platz 1 | A-3100 St. Pölten | T +43/2742/313 228-234