| Zugriffsnummer | 49548 |
| Dokumenttyp | Buchartikel |
| Peer Review | unbekannt |
| Sprache | Englisch |
| Titel | GUM-compliant uncertainty propagation for deep neural networks |
| Autor(in); Institution |
Jung, Barbara; PSt, Präsidialer Stab, PTB-Braunschweig; 9.4, Metrologie für die digitale Transformation, PTB-Berlin
|
| Quelle/Jahr | Advanced Mathematical and Computational Tools in Metrology and Testing XIII: 13 (2025), 204 - 213 |
| Schriftenreihe | Series on Advances in Mathematics for Applied Sciences: 94 |
| Herausgeber(in) |
Pavese, Franco; Istituto Nazionale di Ricerca Metrologica (INRIM), Torino, ITALY
Bošnjaković, Alen; Institute of Metrology of Bosnia and Herzegovina, BOSNIA and HERZEGOVINA
Eichstädt, Sascha; 9.4, Metrologie für die digitale Transformation, PTB-Berlin
Forbes, Alistair B; National Physical Laboratory, UK
Sousa, João Alves; Instituto Português da Qualidade, PORTUGAL
|
| ISBN | 978-981-98-0066-7 (print) ; 978-981-98-0068-1 (online) |
| DOI | |
| Verlag | New Jersey: World Scientific |
| Freie Schlagworte | measurement uncertainty ; uncertainty propagation ; neural networks ; software |
| Zusammenfassung | Advances in algorithms and computing capacities continue to increase the popularity of neural networks. In particular, their use in safety-critical applications (e.g. aviation, transport, telecommunications) poses new challenges with regard to the consideration of uncertainties in their input data. If these consist of sensor measurements, metrology provides a standard reference for dealing with such uncertainties in the internationally harmonised and recognised “Guide to the expression of uncertainty in measurements” (GUM). In this work, a solid mathematical foundation is established for applying the principles of the GUM to simple neural networks, so-called multilayer perceptrons. FAIR –Findable, Accessible, Interoperable and Reusable –software is made available to enable emergent research. |
Zitierung
Ludwig, B., Eichstädt, S., & Jung, B. (2025). GUM-compliant uncertainty propagation for deep neural networks. In F. Pavese, A. Bošnjaković, S. Eichstädt, A. B. Forbes, & J. A. Sousa (Eds.), Advanced Mathematical and Computational Tools in Metrology and Testing XIII (pp. 204–213). New Jersey: World Scientific. https://doi.org/10.1142/9789819800674_0018