Medizinische Universität Graz Austria/Österreich - Forschungsportal - Medical University of Graz
Gewählte Publikation:
SHR Neuro Krebs Kardio Lipid Stoffw Microb
Muller, H; Holzinger, A.
Kandinsky Patterns
ARTIF INTELL. 2021; 300: 103546
Doi: 10.1016/j.artint.2021.103546
[OPEN ACCESS]
Web of Science
FullText
FullText_MUG
- Führende Autor*innen der Med Uni Graz
- Müller Heimo
- Co-Autor*innen der Med Uni Graz
- Holzinger Andreas
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- Kandinsky Figures and Kandinsky Patterns are mathematically describable, simple, self-contained hence controllable synthetic test data sets for the development, validation and training of visual tasks and explainability in artificial intelligence (AI). Whilst Kandinsky Patterns have these computationally manageable properties, they are at the same time easily distinguishable by human observers. Consequently, controlled patterns can be described by both humans and computers. We define a Kandinsky Pattern as a set of Kandinsky Figures, where for each figure an "infallible authority" defines that the figure belongs to the Kandinsky Pattern. With this simple principle we build training and validation data sets for testing explainability, interpretability and context learning. In this paper we describe the basic idea and some underlying principles of Kandinsky Patterns. We provide a Github repository and invite the international AI research community to a challenge to experiment with our Kandinsky Patterns. The goal is to help expand and advance the field of AI, and in particular to contribute to the increasingly important field of explainable AI. (C) 2021 The Authors. Published by Elsevier B.V.
- Find related publications in this database (Keywords)
- Explainable Al
- Explainability
- Synthetic test data
- Ground truth