2019
DOI: 10.1039/c8cp06919k
|View full text |Cite|
|
Sign up to set email alerts
|

A critical comparison of neural network potentials for molecular reaction dynamics with exact permutation symmetry

Abstract: Several symmetry strategies have been compared in fitting full dimensional accurate potentials for reactive systems based on a neural network approach.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
64
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 50 publications
(64 citation statements)
references
References 68 publications
0
64
0
Order By: Relevance
“…Several comparative studies of these methods have recently appeared. [10][11][12][13] These methods all have in common that they do not rely on a model for representing potentials, e.g., Lennard-Jones, LEPS, exp/6, force-fields, etc. In this sense they are all non-parametric in the language of machine-learning (ML).…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations
“…Several comparative studies of these methods have recently appeared. [10][11][12][13] These methods all have in common that they do not rely on a model for representing potentials, e.g., Lennard-Jones, LEPS, exp/6, force-fields, etc. In this sense they are all non-parametric in the language of machine-learning (ML).…”
Section: Introductionmentioning
confidence: 99%
“…The above ML methods have been employed over the past 10 or so years to develop high-dimensional PESs for reactive systems. 8,9,12,13,[20][21][22][23] Some time ago Fu et al reported a PIP PES for the 7-atom O( 3 P)+C 2 H 4 reaction (which included spin-orbit coupling to the singlet PES). This PES was used in quasiclassical trajectory calculations which yielded excellent agreement with experiment for the branching ratio of numerous products.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Atomistic force fields continue to be developed [1][2][3][4][5][6][7][8][9][10] given their growing use and impact in biological and materials science. Extensive comparisons [11][12][13][14] between, traditional force fields can offer guidance in this development, as well as comparisons [15,16] between machine-learnt potentials. Within this grand scheme of force field development, the modeling of dispersion [17] energy has received special attention over the last decade and more.…”
Section: Introductionmentioning
confidence: 99%
“…Refs. [42][43][44]. While different flavours exist, they usually comprise sets of both radial and angular symmetry functions (SFs).…”
Section: Histograms Of (Weighted) Atom-centred Symmetry Functionsmentioning
confidence: 99%