Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043300003> ?p ?o ?g. }
- W3043300003 endingPage "5421" @default.
- W3043300003 startingPage "5410" @default.
- W3043300003 abstract "Machine learning techniques allow a direct mapping of atomic positions and nuclear charges to the potential energy surface with almost ab-initio accuracy and the computational efficiency of empirical potentials. In this work we propose a machine learning method for constructing high-dimensional potential energy surfaces based on feed-forward neural networks. As input to the neural network we propose an extendable invariant local molecular descriptor constructed from geometric moments. Their formulation via pairwise distance vectors and tensor contractions allows a very efficient implementation on graphical processing units (GPUs). The atomic species is encoded in the molecular descriptor, which allows the restriction to one neural network for the training of all atomic species in the data set. We demonstrate that the accuracy of the developed approach in representing both chemical and configurational spaces is comparable to the one of several established machine learning models. Due to its high accuracy and efficiency, the proposed machine-learned potentials can be used for any further tasks, for example the optimization of molecular geometries, the calculation of rate constants or molecular dynamics." @default.
- W3043300003 created "2020-07-23" @default.
- W3043300003 creator A5047160329 @default.
- W3043300003 creator A5056979833 @default.
- W3043300003 date "2020-07-16" @default.
- W3043300003 modified "2023-10-17" @default.
- W3043300003 title "Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials" @default.
- W3043300003 cites W1564335142 @default.
- W3043300003 cites W1975997599 @default.
- W3043300003 cites W1981368803 @default.
- W3043300003 cites W1988115241 @default.
- W3043300003 cites W1988485815 @default.
- W3043300003 cites W2025444507 @default.
- W3043300003 cites W2029413789 @default.
- W3043300003 cites W2058370262 @default.
- W3043300003 cites W2067011309 @default.
- W3043300003 cites W2080635178 @default.
- W3043300003 cites W2083415705 @default.
- W3043300003 cites W2092157292 @default.
- W3043300003 cites W2096747776 @default.
- W3043300003 cites W2104489082 @default.
- W3043300003 cites W2105616783 @default.
- W3043300003 cites W2110798204 @default.
- W3043300003 cites W2114704115 @default.
- W3043300003 cites W2144062946 @default.
- W3043300003 cites W2145454068 @default.
- W3043300003 cites W2146801543 @default.
- W3043300003 cites W2151752974 @default.
- W3043300003 cites W2197007850 @default.
- W3043300003 cites W2285269575 @default.
- W3043300003 cites W2410722695 @default.
- W3043300003 cites W2527189750 @default.
- W3043300003 cites W2546239211 @default.
- W3043300003 cites W2585152223 @default.
- W3043300003 cites W2601081289 @default.
- W3043300003 cites W2605801743 @default.
- W3043300003 cites W2650911154 @default.
- W3043300003 cites W2768213699 @default.
- W3043300003 cites W2778051509 @default.
- W3043300003 cites W2790176708 @default.
- W3043300003 cites W2891365537 @default.
- W3043300003 cites W2911997094 @default.
- W3043300003 cites W2923693308 @default.
- W3043300003 cites W2935718355 @default.
- W3043300003 cites W2968558338 @default.
- W3043300003 cites W3099276598 @default.
- W3043300003 cites W3101643101 @default.
- W3043300003 cites W3106310231 @default.
- W3043300003 cites W3187163767 @default.
- W3043300003 cites W358380361 @default.
- W3043300003 doi "https://doi.org/10.1021/acs.jctc.0c00347" @default.
- W3043300003 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32672968" @default.
- W3043300003 hasPublicationYear "2020" @default.
- W3043300003 type Work @default.
- W3043300003 sameAs 3043300003 @default.
- W3043300003 citedByCount "48" @default.
- W3043300003 countsByYear W30433000032020 @default.
- W3043300003 countsByYear W30433000032021 @default.
- W3043300003 countsByYear W30433000032022 @default.
- W3043300003 countsByYear W30433000032023 @default.
- W3043300003 crossrefType "journal-article" @default.
- W3043300003 hasAuthorship W3043300003A5047160329 @default.
- W3043300003 hasAuthorship W3043300003A5056979833 @default.
- W3043300003 hasBestOaLocation W30433000032 @default.
- W3043300003 hasConcept C119857082 @default.
- W3043300003 hasConcept C121332964 @default.
- W3043300003 hasConcept C147597530 @default.
- W3043300003 hasConcept C154945302 @default.
- W3043300003 hasConcept C155281189 @default.
- W3043300003 hasConcept C163716315 @default.
- W3043300003 hasConcept C184898388 @default.
- W3043300003 hasConcept C185592680 @default.
- W3043300003 hasConcept C190470478 @default.
- W3043300003 hasConcept C202444582 @default.
- W3043300003 hasConcept C33923547 @default.
- W3043300003 hasConcept C41008148 @default.
- W3043300003 hasConcept C48044578 @default.
- W3043300003 hasConcept C50644808 @default.
- W3043300003 hasConcept C62520636 @default.
- W3043300003 hasConcept C77088390 @default.
- W3043300003 hasConceptScore W3043300003C119857082 @default.
- W3043300003 hasConceptScore W3043300003C121332964 @default.
- W3043300003 hasConceptScore W3043300003C147597530 @default.
- W3043300003 hasConceptScore W3043300003C154945302 @default.
- W3043300003 hasConceptScore W3043300003C155281189 @default.
- W3043300003 hasConceptScore W3043300003C163716315 @default.
- W3043300003 hasConceptScore W3043300003C184898388 @default.
- W3043300003 hasConceptScore W3043300003C185592680 @default.
- W3043300003 hasConceptScore W3043300003C190470478 @default.
- W3043300003 hasConceptScore W3043300003C202444582 @default.
- W3043300003 hasConceptScore W3043300003C33923547 @default.
- W3043300003 hasConceptScore W3043300003C41008148 @default.
- W3043300003 hasConceptScore W3043300003C48044578 @default.
- W3043300003 hasConceptScore W3043300003C50644808 @default.
- W3043300003 hasConceptScore W3043300003C62520636 @default.
- W3043300003 hasConceptScore W3043300003C77088390 @default.
- W3043300003 hasFunder F4320320879 @default.
- W3043300003 hasFunder F4320322572 @default.