Logo der Physikalisch-Technischen Bundesanstalt

Uncertainty Quantification by Ensemble Learning for Computational Optical Form Measurements

04.06.2021

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.


Authors:

Lara Hoffmann; 8.4 Data Analysis and Measurement Uncertainty & 4.2 Imaging and Wave Optics
Ines Fortmeier; 4.2 Imaging and Wave Optics
Clemens Elster; 8.4 Data Analysis and Measurement Uncertainty

For further information:

Hoffmann et al 2021 Mach. Learn.: Sci. Technol. doi.org/10.1088/2632-2153/ac0495