posted on 2014-07-30, 14:07authored byE. Sanville, Ajeevsing Bholoa, Roger Smith, Steven KennySteven Kenny
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.
History
School
Science
Department
Mathematical Sciences
Published in
JOURNAL OF PHYSICS-CONDENSED MATTER
Volume
20
Issue
28
Pages
? - ? (10)
Citation
SANVILLE, E. ... et al, 2008. Silicon potentials investigated using density functional theory fitted neural networks. Journal of Physics: Condensed Matter, 20 (28), 285219.