Learning pair potentials using differentiable simulations
<jats:p> Learning pair interactions from experimental or simulation data is of great interest for molecular simulations. We propose a general stochastic method for learning pair interactions from data using differentiable simulations (DiffSim). DiffSim defines a loss function based on structur...
Main Authors: | Wang, Wujie, Wu, Zhenghao, Dietschreit, Johannes CB, Gómez-Bombarelli, Rafael |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Materials Science and Engineering |
Format: | Article |
Language: | English |
Published: |
AIP Publishing
2023
|
Online Access: | https://hdl.handle.net/1721.1/150447 |
Similar Items
-
From free-energy profiles to activation free energies
by: Dietschreit, Johannes CB, et al.
Published: (2022) -
Active learning and neural network potentials accelerate molecular screening of ether-based solvate ionic liquids
by: Wang, Wujie, et al.
Published: (2020) -
Coarse-graining auto-encoders for molecular dynamics
by: Wang, Wujie, et al.
Published: (2020) -
Differentiable Multiscale Molecular Simulations
by: Wang, Wujie
Published: (2023) -
Active learning accelerates ab initio molecular dynamics on reactive energy surfaces
by: Ang, Shi Jun, et al.
Published: (2022)