Cargando…

Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures

Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model’s uncertainty is evaluated using point-prediction metrics, such as the negative log-likelihood (NLL), expec...

Descripción completa

Detalles Bibliográficos
Autores principales: Kompa, Benjamin, Snoek, Jasper, Beam, Andrew L.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8700765/
https://www.ncbi.nlm.nih.gov/pubmed/34945914
http://dx.doi.org/10.3390/e23121608

Ejemplares similares