Uncertainty quantification by ensemble learning for computational optical form measurements

Abstract 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 deve...

Full description

Saved in:
Bibliographic Details
Published in:Machine learning: science and technology 2021-09, Vol.2 (3), p.35030
Main Authors: Hoffmann, Lara, Fortmeier, Ines, Elster, Clemens
Format: Article
Language:English
Subjects:
computational optical form measurement
deep learning
ensemble methods
uncertainty quantification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract 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.
ISSN:2632-2153
2632-2153
DOI:10.1088/2632-2153/ac0495