A highlight by Jan Jensen about the Δ-ML approach proposed by us  was the most viewed highlight in Computational Chemistry Highlights in 2015. This marks a pleasant ending of the last-year research on improving accuracy of computationally less demanding methods for computational chemistry. The Δ-ML approach along with the automatic parametrization technique (APT)  corrects faults of both lower level quantum mechanics (QM) and ML approaches by combining them in hybrid QM/ML techniques. The highlighted technique uses ML to correct errors of quantum chemical calculations after they were performed, while APT uses ML to improve quantum chemical method before running calculations with it.
1. Pavlo O. Dral, O. Anatole von Lilienfeld, Walter Thiel, Machine Learning of Parameters for Accurate Semiempirical Quantum Chemical Calculations. J. Chem. Theory Comput. 2015, 11, 2120–2125. DOI: 10.1021/acs.jctc.5b00141.
2. Raghunathan Ramakrishnan, Pavlo O. Dral, Matthias Rupp, O. Anatole von Lilienfeld, Big Data meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. J. Chem. Theory Comput. 2015, ASAP. DOI: 10.1021/acs.jctc.5b00099.