Quantum-chemical insights from deep tensor neural networks
Technische Universität Berlin · Korea University · +2 more institutions
Abstract
Abstract Learning from data has led to paradigm shifts in a multitude of disciplines, including web, text and image search, speech recognition, as well as bioinformatics. Can machine learning enable similar breakthroughs in understanding quantum many-body systems? Here we develop an efficient deep learning approach that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems. We unify concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate (1 kcal mol −1 ) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of…
Citation impact
- FWCI
- 65.27
- Percentile
- 100%
- References
- 57
Authors
5- KTKristof T. Schütt
Technische Universität Berlin
- FAFarhad Arbabzadah
Technische Universität Berlin
- SCStefan Chmiela
Technische Universität Berlin
- KMK. MüllerCorresponding
Korea University, Technische Universität Berlin
- ATAlexandre TkatchenkoCorresponding
University of Luxembourg, Fritz Haber Institute of the Max Planck Society
Topics & keywords
- Chemical space
- Observable
- Computer science
- Quantum
- Quantum chemical
- Tensor (intrinsic definition)
- Artificial neural network
- Molecule