Work

Solid harmonic wavelet scattering for predictions of molecule properties

Year: 2018

Type: article

Abstract: We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory (DFT). Using Gaussian-type orbital functions, we create surrogate electronic densities of the molecule from which we compute invariant "solid harmonic scattering coefficients" that account for different types of interactions at different scales. Multilinear regressions of various physical properties of molecules are computed from these invariant coefficients. Numerical experiments show that these regressions have near state-of-the-art performance, even with relatively few training examples. Predictions over small sets of scattering coefficients can reach a DFT precision while being interpretable.

Source: The Journal of Chemical Physics

DOI: 10.1063/1.5023798

Authors: Michael Eickenberg, Georgios Exarchakis, Matthew Hirn, Stéphane Mallat, Louis Thiry

Institutions: Université Paris Sciences et Lettres, École Normale Supérieure - PSL, Michigan State University, Collège de France

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: green

Funders: Alfred P. Sloan Foundation, Directorate for Mathematical and Physical Sciences, Defense Advanced Research Projects Agency, FP7 Ideas: European Research Council

Awards: G283102380, G3463625024, Invariant Representations for High-Dimensional Signal Classifications, G8608703288