Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199869894> ?p ?o ?g. }
- W3199869894 endingPage "6670" @default.
- W3199869894 startingPage "6658" @default.
- W3199869894 abstract "Artificial neural networks (NNs) are one of the most frequently used machine learning approaches to construct interatomic potentials and enable efficient large-scale atomistic simulations with almost ab initio accuracy. However, the simultaneous training of NNs on energies and forces, which are a prerequisite for, e.g., molecular dynamics simulations, can be demanding. In this work, we present an improved NN architecture based on the previous GM-NN model [V. Zaverkin and J. Kastner, J. Chem. Theory Comput. 16, 5410-5421 (2020)], which shows an improved prediction accuracy and considerably reduced training times. Moreover, we extend the applicability of Gaussian moment-based interatomic potentials to periodic systems and demonstrate the overall excellent transferability and robustness of the respective models. The fast training by the improved methodology is a pre-requisite for training-heavy workflows such as active learning or learning-on-the-fly." @default.
- W3199869894 created "2021-09-27" @default.
- W3199869894 creator A5001083977 @default.
- W3199869894 creator A5036807127 @default.
- W3199869894 creator A5047160329 @default.
- W3199869894 creator A5056979833 @default.
- W3199869894 date "2021-09-29" @default.
- W3199869894 modified "2023-10-12" @default.
- W3199869894 title "Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments" @default.
- W3199869894 cites W1582774210 @default.
- W3199869894 cites W1677182931 @default.
- W3199869894 cites W1833887972 @default.
- W3199869894 cites W1975997599 @default.
- W3199869894 cites W1981368803 @default.
- W3199869894 cites W1988115241 @default.
- W3199869894 cites W1996248434 @default.
- W3199869894 cites W2002852143 @default.
- W3199869894 cites W2013266493 @default.
- W3199869894 cites W2022256605 @default.
- W3199869894 cites W2025444507 @default.
- W3199869894 cites W2028455000 @default.
- W3199869894 cites W2029413789 @default.
- W3199869894 cites W2057858097 @default.
- W3199869894 cites W2058370262 @default.
- W3199869894 cites W2061179540 @default.
- W3199869894 cites W2068972463 @default.
- W3199869894 cites W2070753604 @default.
- W3199869894 cites W2077822985 @default.
- W3199869894 cites W2080635178 @default.
- W3199869894 cites W2083415705 @default.
- W3199869894 cites W2104489082 @default.
- W3199869894 cites W2105616783 @default.
- W3199869894 cites W2114704115 @default.
- W3199869894 cites W2120145199 @default.
- W3199869894 cites W2130437470 @default.
- W3199869894 cites W2144062946 @default.
- W3199869894 cites W2144288821 @default.
- W3199869894 cites W2147421370 @default.
- W3199869894 cites W2197007850 @default.
- W3199869894 cites W2200589053 @default.
- W3199869894 cites W2333779612 @default.
- W3199869894 cites W2410722695 @default.
- W3199869894 cites W2527189750 @default.
- W3199869894 cites W2585152223 @default.
- W3199869894 cites W2601081289 @default.
- W3199869894 cites W2650911154 @default.
- W3199869894 cites W2742127985 @default.
- W3199869894 cites W2749006386 @default.
- W3199869894 cites W2768213699 @default.
- W3199869894 cites W2785813126 @default.
- W3199869894 cites W2891365537 @default.
- W3199869894 cites W2923693308 @default.
- W3199869894 cites W2935718355 @default.
- W3199869894 cites W2954088480 @default.
- W3199869894 cites W2959623824 @default.
- W3199869894 cites W2962834855 @default.
- W3199869894 cites W2963657244 @default.
- W3199869894 cites W2964268718 @default.
- W3199869894 cites W2968558338 @default.
- W3199869894 cites W2970217468 @default.
- W3199869894 cites W3003486042 @default.
- W3199869894 cites W3012230641 @default.
- W3199869894 cites W3043300003 @default.
- W3199869894 cites W3084233865 @default.
- W3199869894 cites W3098509317 @default.
- W3199869894 cites W3098862241 @default.
- W3199869894 cites W3099276598 @default.
- W3199869894 cites W3101643101 @default.
- W3199869894 cites W3101744125 @default.
- W3199869894 cites W3106310231 @default.
- W3199869894 cites W3128596184 @default.
- W3199869894 doi "https://doi.org/10.1021/acs.jctc.1c00527" @default.
- W3199869894 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34585927" @default.
- W3199869894 hasPublicationYear "2021" @default.
- W3199869894 type Work @default.
- W3199869894 sameAs 3199869894 @default.
- W3199869894 citedByCount "13" @default.
- W3199869894 countsByYear W31998698942021 @default.
- W3199869894 countsByYear W31998698942022 @default.
- W3199869894 countsByYear W31998698942023 @default.
- W3199869894 crossrefType "journal-article" @default.
- W3199869894 hasAuthorship W3199869894A5001083977 @default.
- W3199869894 hasAuthorship W3199869894A5036807127 @default.
- W3199869894 hasAuthorship W3199869894A5047160329 @default.
- W3199869894 hasAuthorship W3199869894A5056979833 @default.
- W3199869894 hasBestOaLocation W31998698942 @default.
- W3199869894 hasConcept C104317684 @default.
- W3199869894 hasConcept C111919701 @default.
- W3199869894 hasConcept C11413529 @default.
- W3199869894 hasConcept C119857082 @default.
- W3199869894 hasConcept C121332964 @default.
- W3199869894 hasConcept C121864883 @default.
- W3199869894 hasConcept C140331021 @default.
- W3199869894 hasConcept C147597530 @default.
- W3199869894 hasConcept C154945302 @default.
- W3199869894 hasConcept C163716315 @default.
- W3199869894 hasConcept C177212765 @default.
- W3199869894 hasConcept C179254644 @default.