Solid harmonic wavelet scattering for predictions of molecule properties
| Autor: | Stéphane Mallat, Louis Thiry, Georgios Exarchakis, Michael Eickenberg, Matthew J. Hirn |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Chemical Physics (physics.chem-ph)
FOS: Computer and information sciences Physics Computer Science - Machine Learning Multilinear map 010304 chemical physics Scattering FOS: Physical sciences General Physics and Astronomy Machine Learning (stat.ML) Harmonic (mathematics) 01 natural sciences Machine Learning (cs.LG) Computational Engineering Finance and Science (cs.CE) Wavelet Statistics - Machine Learning Physics - Chemical Physics 0103 physical sciences Molecule Density functional theory Statistical physics Physical and Theoretical Chemistry Invariant (mathematics) Computer Science - Computational Engineering Finance and Science 010306 general physics |
| Zdroj: | The Journal of chemical physics. 148(24) |
| ISSN: | 1089-7690 |
| Popis: | We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory. 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. Multi-linear 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. Comment: Keywords: wavelets, electronic structure calculations, solid harmonics, invariants, multilinear regression |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|