Quantum-chemical insights from deep tensor neural networks
Machine learning is an increasingly popular approach to analyse data and make predictions. Here the authors develop a ‘deep learning’ framework for quantitative predictions and qualitative understanding of quantum-mechanical observables of chemical systems, beyond properties trivially contained in t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2017-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/ncomms13890 |
| _version_ | 1830287740401352704 |
|---|---|
| author | Kristof T. Schütt Farhad Arbabzadah Stefan Chmiela Klaus R. Müller Alexandre Tkatchenko |
| author_facet | Kristof T. Schütt Farhad Arbabzadah Stefan Chmiela Klaus R. Müller Alexandre Tkatchenko |
| author_sort | Kristof T. Schütt |
| collection | DOAJ |
| description | Machine learning is an increasingly popular approach to analyse data and make predictions. Here the authors develop a ‘deep learning’ framework for quantitative predictions and qualitative understanding of quantum-mechanical observables of chemical systems, beyond properties trivially contained in the training data. |
| first_indexed | 2024-12-19T04:23:02Z |
| format | Article |
| id | doaj.art-459cc75532c24b7085302dabbc24454d |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-12-19T04:23:02Z |
| publishDate | 2017-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-459cc75532c24b7085302dabbc24454d2022-12-21T20:36:06ZengNature PortfolioNature Communications2041-17232017-01-01811810.1038/ncomms13890Quantum-chemical insights from deep tensor neural networksKristof T. Schütt0Farhad Arbabzadah1Stefan Chmiela2Klaus R. Müller3Alexandre Tkatchenko4Machine Learning Group, Technische Universität BerlinMachine Learning Group, Technische Universität BerlinMachine Learning Group, Technische Universität BerlinMachine Learning Group, Technische Universität BerlinTheory Department, Fritz-Haber-Institut der Max-Planck-GesellschaftMachine learning is an increasingly popular approach to analyse data and make predictions. Here the authors develop a ‘deep learning’ framework for quantitative predictions and qualitative understanding of quantum-mechanical observables of chemical systems, beyond properties trivially contained in the training data.https://doi.org/10.1038/ncomms13890 |
| spellingShingle | Kristof T. Schütt Farhad Arbabzadah Stefan Chmiela Klaus R. Müller Alexandre Tkatchenko Quantum-chemical insights from deep tensor neural networks Nature Communications |
| title | Quantum-chemical insights from deep tensor neural networks |
| title_full | Quantum-chemical insights from deep tensor neural networks |
| title_fullStr | Quantum-chemical insights from deep tensor neural networks |
| title_full_unstemmed | Quantum-chemical insights from deep tensor neural networks |
| title_short | Quantum-chemical insights from deep tensor neural networks |
| title_sort | quantum chemical insights from deep tensor neural networks |
| url | https://doi.org/10.1038/ncomms13890 |
| work_keys_str_mv | AT kristoftschutt quantumchemicalinsightsfromdeeptensorneuralnetworks AT farhadarbabzadah quantumchemicalinsightsfromdeeptensorneuralnetworks AT stefanchmiela quantumchemicalinsightsfromdeeptensorneuralnetworks AT klausrmuller quantumchemicalinsightsfromdeeptensorneuralnetworks AT alexandretkatchenko quantumchemicalinsightsfromdeeptensorneuralnetworks |