Silicon potentials investigated using density functional theory fitted neural networks
E Sanville, A Bholoa, R Smith… - Journal of Physics …, 2008 - iopscience.iop.org
Journal of Physics: Condensed Matter, 2008•iopscience.iop.org
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.
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.
Abstract
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.
iopscience.iop.org
以上显示的是最相近的搜索结果。 查看全部搜索结果