| Zugriffsnummer | 46409 |
| Dokumenttyp | Konferenzartikel |
| Peer Review | unbekannt |
| Sprache | Englisch |
| Titel | Ensemble learning for computational optical form measurement |
| Autor(in); Institution |
Hoffmann, Lara; 8.4, Mathematische Modellierung und Datenanalyse, PTB-Berlin; 4.2, Bild- und Wellenoptik, PTB-Braunschweig
Elster, Clemens; 8.4, Mathematische Modellierung und Datenanalyse, PTB-Berlin
Fortmeier, Ines; 4.2, Bild- und Wellenoptik, PTB-Braunschweig
|
| Quelle/Jahr | SMSI 2021 - Sensor and Measurement Science International:(2021), 318 - 319 |
| ISBN | 978-3-9819376-4-0 |
| DOI | |
| Verlag | Wunstorf: AMA Service GmbH |
| Konferenzangaben | SMSI 2021, Sensor and Measurement Sience International 2021, Virtual Conference, 03-06, May, 2021 |
| Freie Schlagworte | dynamic data ; deep learning ; uncertainty |
| Zusammenfassung | For the processing of dynamic data (e.g. vibrations) an exact knowledge of the temporal relations is necessary. In this topic we present Deep learning has become a powerful tool of data analysis with applications in such different areas as medical imaging, language processing or autonomous driving. Recently, deep learning techniques have also been applied to an inverse problem in optical form measurement. In a proof-of-principle study it was shown that an accurate solution of the inverse problem can be achieved by a deep neural network that is trained on a large data base. This work augments the developed method with a quantification of its uncertainty by considering an ensemble of networks. The approach is tested using virtual experiments with known ground truth. |
| Themenbereich der Metrologie | Mathematik und metrologische Informationstechnik |