Machine learning for quantum mechanics in a nutshell

343 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Quantum machine learning (2016, neutral): “In addition, machine learning was employed in a variety of related ﬁelds, e.g. the discovery of the Higgs Boson [10], molecular energy prediction trained using databases of known energy spectra [11] and gravitational wave detection [12].”
Machine-learned potentials for next-generation matter simulations (2021, methodology): “One widely used group of regression models for ML potentials are kernel-based methods 47,65,66 , in particular Gaussian processes (GPs; see Fig.”
Machine Learning and Materials Informatics: Recent Applications and Prospects (2017, background): “A variety of ﬁngerprinting schemes as well as learning schemes that lead up to force ﬁelds have been recently reviewed [9,82,88].”
Machine Learning Force Fields: Construction, Validation, and Outlook (2016, methodology): “10,32,33 Finally, in order to evaluate the performance of a developed force ﬁ eld, three error metrics  mean absolute error (MAE), maximum absolute error (MAX), and the standard deviation (in particular 2 σ )  were chosen.”
Machine learning for heterogeneous catalyst design and discovery (2018, methodology): “Using PCA, major trends in the dataset regarding the impact of the support, temperature, solvent, and metal for the hydrogenation of 5-ethoxymethylfurfural were found; for example, SiO 2 -supported catalysts typically have much lower activity than Al 2 O 3 -supported catalysts and higher conversions”