Open AccessUncertainty quantification by ensemble learning for computational optical form measurements
Author(s) -
Lara Hoffmann,
Ines Fortmeier,
Clemens Elster
Publication year - 2021
Publication title -
machine learning: science and technology
Language(s) - English
Resource type - Journals
ISSN - 2632-2153
DOI - 10.1088/2632-2153/ac0495
Subject(s) - computer science , uncertainty quantification , ensemble learning , artificial intelligence , inverse problem , machine learning , context (archaeology) , reliability (semiconductor) , deep learning , trustworthiness , field (mathematics) , scope (computer science) , mathematics , mathematical analysis , power (physics) , physics , computer security , quantum mechanics , paleontology , pure mathematics , biology , programming language
Uncertainty quantification by ensemble learning is explored in terms of an application known from the field of computational optical form measurements. The application requires solving a large-scale, nonlinear inverse problem. Ensemble learning is used to extend the scope of a recently developed deep learning approach for this problem in order to provide an uncertainty quantification of the solution to the inverse problem predicted by the deep learning method. By systematically inserting out-of-distribution errors as well as noisy data, the reliability of the developed uncertainty quantification is explored. Results are encouraging and the proposed application exemplifies the ability of ensemble methods to make trustworthy predictions on the basis of high-dimensional data in a real-world context.