Selected Publication:
SHR
Neuro
Cancer
Cardio
Lipid
Metab
Microb
Holzinger, A; Kieseberg, P; Mulller, H.
KANDINSKY Patterns: A Swiss-Knife for the Study of Explainable AI.
ERCIM NEWS. 2020; (120): 41-42.
Web of Science
- Leading authors Med Uni Graz
-
Holzinger Andreas
- Co-authors Med Uni Graz
-
Müller Heimo
- Altmetrics:
- Abstract:
- 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).