Publikationsrepositorium - Helmholtz-Zentrum Dresden-Rossendorf
1 PublikationUncertainty quantification in machine learning applications
Schmerler, S.; Starke, S.; Steinbach, P.; M. K. Siddiqui, Q.; Fiedler, L.; Cangi, A.; Kulkarni, S. H.
Abstract
We strive to popularize the usage of uncertainty quantification methods in machine learning through publications and application in various projects covering diverse fields from regression and classification to instance segmentation. In addition, we employ domain shift detection techniques to tackle population-level out-of-distribution scenarios. In all cases, the goal is to assess model prediction validity given unseen test data.
Keywords: machine learning; uncertainty
-
Poster
Helmholtz AI Evaluation 2022, 05.-07.10.2022, München, Germany
Downloads
Permalink: https://www.hzdr.de/publications/Publ-35454