A new approach to potential fitting using neural networks

A methodology is presented for developing transferable empirical potential functions without following the usual procedure of postulating a functional form. Instead, a neural network (NN) is employed to learn the functional relationships of potential energy surfaces from the local geometric arrangem...

Full description

Saved in:
Bibliographic Details
Main Authors: Ajeevsing Bholoa, Steven Kenny, Roger Smith
Format: Default Article
Published: 2007
Subjects:
Geochemistry not elsewhere classified
Other mathematical sciences not elsewhere classified
Neural network
Tight-binding
Empirical potentials
Geochemistry
Mathematical Sciences not elsewhere classified
Online Access:https://hdl.handle.net/2134/2434
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items