Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS

Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS

Deep learning models that leverage large datasets are often the state of the art for modelling molecular properties. When the datasets are smaller (

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Digital discovery 2023-06, Vol.2 (3), p.759-774
Hauptverfasser: Tom, Gary, Hickman, Riley J, Zinzuwadia, Aniket, Mohajeri, Afshan, Sanchez-Lengeling, Benjamin, Aspuru-Guzik, Alán
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Deep learning models that leverage large datasets are often the state of the art for modelling molecular properties. When the datasets are smaller (
ISSN:2635-098X
2635-098X
DOI:10.1039/d2dd00146b