Cargando…

Uncertainty quantification for predictions of atomistic neural networks

The value of uncertainty quantification on predictions for trained neural networks (NNs) on quantum chemical reference data is quantitatively explored. For this, the architecture of the PhysNet NN was suitably modified and the resulting model (PhysNet-DER) was evaluated with different metrics to qua...

Descripción completa

Detalles Bibliográficos
Autores principales: Vazquez-Salazar, Luis Itza, Boittier, Eric D., Meuwly, Markus
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society of Chemistry 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9667919/
https://www.ncbi.nlm.nih.gov/pubmed/36425481
http://dx.doi.org/10.1039/d2sc04056e

Ejemplares similares