Extrapolation validation (EV): a universal validation method for mitigating machine learning extrapolation risk
Digital Discovery · 2024 · 3 (5) · 1058-1067
DOI: 10.1039/d3dd00256j ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Discovery, 2024. Verfasst von Mengxian Yu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
A generic machine learning model validation method named extrapolation validation (EV) has been proposed, which evaluates the trustworthiness of model predictions to mitigate the extrapolation risk before the model transitions to applications.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yu, M., Zhou, Y., Wang, Q., & Yan, F. (2024). Extrapolation validation (EV): a universal validation method for mitigating machine learning extrapolation risk. Digital Discovery, 3(5), 1058-1067. https://doi.org/10.1039/d3dd00256j
Vancouver
Yu M, Zhou Y, Wang Q, Yan F. Extrapolation validation (EV): a universal validation method for mitigating machine learning extrapolation risk. Digital Discovery. 2024;3(5):1058-1067. doi:10.1039/d3dd00256j
BibTeX
@article{Yu2024,
author = {Yu, Mengxian and Zhou, Yin-Ning and Wang, Qiang and Yan, Fangyou},
title = {Extrapolation validation (EV): a universal validation method for mitigating machine learning extrapolation risk},
journal = {Digital Discovery},
year = {2024},
volume = {3},
number = {5},
pages = {1058--1067},
doi = {10.1039/d3dd00256j}
}
EUVIMED