Semantic Scholar Open Access 2011 1724 sitasi

Fast and accurate modeling of molecular atomization energies with machine learning.

Matthias Rupp Matthias Rupp Alexandre Tkatchenko Alexandre Tkatchenko Klaus-Robert Müller +3 lainnya

Lihat Sumber DOI

Abstrak

We introduce a machine learning model to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only. The problem of solving the molecular Schrödinger equation is mapped onto a nonlinear statistical regression problem of reduced complexity. Regression models are trained on and compared to atomization energies computed with hybrid density-functional theory. Cross validation over more than seven thousand organic molecules yields a mean absolute error of ∼10 kcal/mol. Applicability is demonstrated for the prediction of molecular atomization potential energy curves.

Topik & Kata Kunci

Physics Mathematics Medicine

Penulis (8)

Matthias Rupp

Alexandre Tkatchenko

Klaus-Robert Müller

O. V. Lilienfeld

Format Sitasi

APA MLA BibTeX

Rupp, M., Rupp, M., Tkatchenko, A., Tkatchenko, A., Müller, K., Müller, K. et al. (2011). Fast and accurate modeling of molecular atomization energies with machine learning.. https://doi.org/10.1103/PhysRevLett.108.058301

Akses Cepat

Lihat di Sumber doi.org/10.1103/PhysRevLett.108.058301

Informasi Jurnal

Tahun Terbit: 2011
Bahasa: en
Total Sitasi: 1724×
Sumber Database: Semantic Scholar
DOI: 10.1103/PhysRevLett.108.058301
Akses: Open Access ✓