Perspective on Machine Learning in Quantum Chemistry
My perspective on the state-of-the-art of machine learning in quantum chemistry and outlook for future developments was published in J. Phys. Chem. Lett.
Apart for the JPCL Perspective video above, the brief overview of the Perspective in context of our research is also available as a presentation in a form of LiveSlides:
The following topics from our research are discussed about which you can read in the following brief blog posts:
- Improving semiempirical Hamiltonian with machine learning (semiempirical parameter learning)
- Δ-machine learning
- Structure-based sampling
- Nonadiabatic excited-state dynamics with kernel ridge regression and deep neural networks
- Data sets for developing and benchmarking machine learning methods
Numerical examples shown in Perspective were prepared using our software package MLatom for atomistic simulations with machine learning.
The Perspective is dedicated to my mentor and very good friend Walter Thiel, who unexpectedly passed away in 2019. During my post-doctoral stay with him, Walter supported me in my machine learning studies.
- Pavlo O. Dral, Quantum Chemistry in the Age of Machine Learning. J. Phys. Chem. Lett. 2020, 11, 2336–2347. DOI: 10.1021/acs.jpclett.9b03664.