Výsledky vyhledávání

Report

Understanding defects in amorphous silicon with million-atom simulations and machine learning

Autor: Morrow, Joe D., Ugwumadu, Chinonso, Drabold, David A., Elliott, Stephen R., Goodwin, Andrew L., Deringer, Volker L.

The structure of amorphous silicon is widely thought of as a fourfold-connected random network, and yet it is defective atoms, with fewer or more than four bonds, that make it particularly interesting. Despite many attempts to explain such "dangling-

Externí odkaz: http://arxiv.org/abs/2308.16868

Zobrazit plný text záznamu

Report

Robustness of Local Predictions in Atomistic Machine Learning Models

Autor: Chong, Sanggyu, Grasselli, Federico, Mahmoud, Chiheb Ben, Morrow, Joe D., Deringer, Volker L., Ceriotti, Michele

Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-dri

Externí odkaz: http://arxiv.org/abs/2306.15638

Zobrazit plný text záznamu

Report

How to validate machine-learned interatomic potentials

Autor: Morrow, Joe D., Gardner, John L. A., Deringer, Volker L.

Publikováno v: J. Chem. Phys. 158, 121501 (2023)

Machine learning (ML) approaches enable large-scale atomistic simulations with near-quantum-mechanical accuracy. With the growing availability of these methods there arises a need for careful validation, particularly for physically agnostic models -

Externí odkaz: http://arxiv.org/abs/2211.12484

Zobrazit plný text záznamu

Report

Indirect Learning of Interatomic Potentials for Accelerated Materials Simulations

Autor: Morrow, Joe D., Deringer, Volker L.

Publikováno v: J. Chem. Phys. 157, 104105 (2022)

Machine learning (ML) based interatomic potentials are emerging tools for materials simulations but require a trade-off between accuracy and speed. Here we show how one can use one ML potential model to train another: we use an existing, accurate, bu

Externí odkaz: http://arxiv.org/abs/2111.11120

Zobrazit plný text záznamu