DP Compress: A Model Compression Scheme for Generating Efficient Deep Potential Models

Machine-learning-based interatomic potential energy surface (PES) models are revolutionizing the field of molecular modeling. However, although much faster than electronic structure schemes, these models suffer from costly computations via deep neural networks to predict the energy and atomic forces...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of chemical theory and computation 2022-09, Vol.18 (9), p.5559-5567
Hauptverfasser:	Lu, Denghui, Jiang, Wanrun, Chen, Yixiao, Zhang, Linfeng, Jia, Weile, Wang, Han, Chen, Mohan
Format:	Artikel
Sprache:	eng
Schlagworte:	Aluminum Artificial neural networks Chemistry Condensed Matter, Interfaces, and Materials Copper Deep learning Electronic structure Machine learning Magnesium Molecular dynamics Physical properties Physics Potential energy
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!