Year: 2018
Communications in Computational Physics, Vol. 23 (2018), Iss. 3 : pp. 629–639
Abstract
We present a simple, yet general, deep neural network representation of the potential energy surface for atomic and molecular systems. It is "first-principle" based, in the sense that no ad hoc approximations or empirical fitting functions are required. When tested on a wide variety of examples, it reproduces the original model within chemical accuracy. This brings us one step closer to carrying out molecular simulations with quantum mechanics accuracy at empirical potential computational cost.
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/cicp.OA-2017-0213
Communications in Computational Physics, Vol. 23 (2018), Iss. 3 : pp. 629–639
Published online: 2018-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 11
Keywords: Potential energy surface deep learning molecular simulation.