Hoffmann, Lara and Fortmeier, Ines and Elster, Clemens (2021) Uncertainty quantification by ensemble learning for computational optical form measurements. Machine Learning: Science and Technology, 2 (3). 035030. ISSN 2632-2153
![[thumbnail of Hoffmann_2021_Mach._Learn.__Sci._Technol._2_035030.pdf]](http://journal.repositoryarticle.com/style/images/fileicons/text.png)
Hoffmann_2021_Mach._Learn.__Sci._Technol._2_035030.pdf - Published Version
Download (3MB)
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.
Item Type: | Article |
---|---|
Subjects: | South Asian Library > Multidisciplinary |
Depositing User: | Unnamed user with email support@southasianlibrary.com |
Date Deposited: | 04 Jul 2023 04:31 |
Last Modified: | 03 Jun 2024 12:44 |
URI: | http://journal.repositoryarticle.com/id/eprint/1271 |