A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules

@article{Cheng2019AUD,
  title={A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules},
  author={Lixue Cheng and Matthew Welborn and T. Miller},
  journal={The Journal of chemical physics},
  year={2019},
  volume={150 13},
  pages={
          131103
        }
}
We address the degree to which machine learning (ML) can be used to accurately and transferably predict post-Hartree-Fock correlation energies. Refined strategies for feature design and selection are presented, and the molecular-orbital-based machine learning (MOB-ML) method is applied to several test systems. Strikingly, for the second-order Møller-Plessett perturbation theory, coupled cluster with singles and doubles (CCSD), and CCSD with perturbative triples levels of theory, it is shown… Expand
30 Citations
Machine learning accurate exchange and correlation functionals of the electronic density
  • 11
  • PDF
Hierarchical machine learning of potential energy surfaces.
  • 6
...
1
2
3
...

References

SHOWING 1-10 OF 74 REFERENCES
Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis.
  • 59
  • PDF
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach.
  • 200
  • PDF
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.
  • 325
  • PDF
Accurate molecular polarizabilities with coupled cluster theory and machine learning
  • 43
  • PDF
Quantum-chemical insights from deep tensor neural networks
  • 523
  • PDF
...
1
2
3
4
5
...