Evaluating Scalable Uncertainty Estimation Methods for Deep Learning-Based Molecular Property Prediction

Advances in deep neural network (DNN)-based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolutional neural networks (GCNNs) reporting state-of-the-art performance for this task. However, some challenges...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of chemical information and modeling 2020-06, Vol.60 (6), p.2697-2717
Hauptverfasser:	Scalia, Gabriele, Grambow, Colin A, Pernici, Barbara, Li, Yi-Pei, Green, William H
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Bayesian analysis Datasets Deep learning Domains Error reduction Model accuracy Molecular properties Neural networks Statistical inference Uncertainty
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!