Silicon potentials investigated using density functional theory fitted neural networks
By Edward Sanville, A. Bholoa, R. Smith, S. Kenny. 2008
38 citations recorded by the source corpus.
We present a method for fitting neural networks to geometric and energetic data sets. We then apply this method by fitting a neural network to a set of data generated using the local density approximation for systems composed entirely of silicon. In order to generate atomic potential energy data, we use the Bader analysis scheme to partition the total system energy among the constituent atoms. We then demonstrate the transferability of the neural network potential by fitting to various bulk, surface, and cluster systems.
Subfields: Atomic and Molecular Physics, and Optics, Materials Chemistry, Structural Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Atomic and Molecular Physics, and Optics
- Yuri Mishin
- Rohit Batra
- Rampi Ramprasad
- James R. Kermode
- Gábor Csányi
- G. P. P. Pun
- Noam Bernstein
- A. P. Bart'ok
In Materials Chemistry
- Yuri Mishin
- Rohit Batra
- Gábor Csányi
- James R. Kermode
- Noam Bernstein
- Rampi Ramprasad
- A. P. Bart'ok
- Alexander V. Shapeev
In Structural Biology
Citations in the corpus
- Machine Learning a General-Purpose Interatomic Potential for Silicon (2018, background): “Modeling the short-range interactions with artificial neural networks (NNs) really took off about a decade ago [35], starting with the bulk phases of silicon [36,37], with many more to follow: describing some silicon defects [38], the graphite-diamond transition [39], bulk zinc oxide [40], copper wi”
- Physically informed artificial neural networks for atomistic modeling of materials (2018, methodology): “[34] E.”