Synthetic pre-training for neural-network interatomic potentials

Machine learning (ML) based interatomic potentials have transformed the field of atomistic materials modelling. However, ML potentials depend critically on the quality and quantity of quantum-mechanical reference data with which they are trained, and therefore developing datasets and training pipeli...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	John L A Gardner, Kathryn T Baker, Volker L Deringer
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	IOP Publishing 2024-01-01
Σειρά:	Machine Learning: Science and Technology
Θέματα:	machine learning neural networks synthetic data atomistic simulations molecular dynamics
Διαθέσιμο Online:	https://doi.org/10.1088/2632-2153/ad1626
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!