Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A Survey on the Explainability of Supervised Machine Learning

: Burkart, Nadia; Huber, Marco F.


The journal of artificial intelligence research : JAIR 70 (2021), pp.245-317
ISSN: 1076-9757
ISSN: 1943-5037
Journal Article
Fraunhofer IOSB ()
Fraunhofer IPA ()
machine learning; knowledge discovery; neural networks; rule learning; Künstliche Intelligenz; maschinelles Lernen; neuronales Netz; Explainable Artificial Intelligence (XAI)

Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or finance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.