Exploring model complexity in machine learned potentials for simulated properties

Exploring model complexity in machine learned potentials for simulated properties

Abstract Machine learning (ML) enables the development of interatomic potentials with the accuracy of first principles methods while retaining the speed and parallel efficiency of empirical potentials. While ML potentials traditionally use atom-centered descriptors as inputs, different...

Descripción completa

Detalles Bibliográficos
Autores principales: Rohskopf, A., Goff, J., Sema, D., Gordiz, K., Nguyen, N. C., Henry, A., Thompson, A. P., Wood, M. A.
Otros Autores: Massachusetts Institute of Technology. Department of Mechanical Engineering
Formato: Artículo
Lenguaje:English
Publicado: Springer International Publishing 2023
Acceso en línea:https://hdl.handle.net/1721.1/152387

Internet

https://hdl.handle.net/1721.1/152387

Ejemplares similares