FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136772266> ?p ?o ?g. }

• W3136772266 abstract "The training set of atomic configurations is key to the performance of any Machine Learning Force Field (MLFF) and, as such, the training set selection determines the applicability of the MLFF model for predictive molecular simulations. However, most atomistic reference datasets are inhomogeneously distributed across configurational space (CS), thus choosing the training set randomly or according to the probability distribution of the data leads to models whose accuracy is mainly defined by the most common close-to-equilibrium configurations in the reference data. In this work, we combine unsupervised and supervised ML methods to bypass the inherent bias of the data for common configurations, effectively widening the applicability range of MLFF to the fullest capabilities of the dataset. To achieve this goal, we first cluster the CS into subregions similar in terms of geometry and energetics. We iteratively test a given MLFF performance on each subregion and fill the training set of the model with the representatives of the most inaccurate parts of the CS. The proposed approach has been applied to a set of small organic molecules and alanine tetrapeptide, demonstrating an up to two-fold decrease in the root mean squared errors for force predictions of these molecules. This result holds for both kernel-based methods (sGDML and GAP/SOAP models) and deep neural networks (SchNet model). For the latter, the developed approach simultaneously improves both energy and forces, bypassing the compromise to be made when employing mixed energy/force loss functions." @default.
• W3136772266 created "2021-03-29" @default.
• W3136772266 creator A5002697621 @default.
• W3136772266 creator A5026929463 @default.
• W3136772266 creator A5069777955 @default.
• W3136772266 creator A5087321869 @default.
• W3136772266 date "2021-03-22" @default.
• W3136772266 modified "2023-10-18" @default.
• W3136772266 title "Improving molecular force fields across configurational space by combining supervised and unsupervised machine learning" @default.
• W3136772266 cites W1031578623 @default.
• W3136772266 cites W1531674615 @default.
• W3136772266 cites W1865667476 @default.
• W3136772266 cites W1978183953 @default.
• W3136772266 cites W1981368803 @default.
• W3136772266 cites W2016381774 @default.
• W3136772266 cites W2020072134 @default.
• W3136772266 cites W2029413789 @default.
• W3136772266 cites W2037672122 @default.
• W3136772266 cites W2039425860 @default.
• W3136772266 cites W2059282894 @default.
• W3136772266 cites W2128873947 @default.
• W3136772266 cites W2148424525 @default.
• W3136772266 cites W2150981663 @default.
• W3136772266 cites W2265661434 @default.
• W3136772266 cites W2527189750 @default.
• W3136772266 cites W2547447472 @default.
• W3136772266 cites W2585152223 @default.
• W3136772266 cites W2620687153 @default.
• W3136772266 cites W2725390203 @default.
• W3136772266 cites W2767510182 @default.
• W3136772266 cites W2781673954 @default.
• W3136772266 cites W2785434749 @default.
• W3136772266 cites W2785813126 @default.
• W3136772266 cites W2791773856 @default.
• W3136772266 cites W2886120629 @default.
• W3136772266 cites W2892113269 @default.
• W3136772266 cites W2897116080 @default.
• W3136772266 cites W2916789848 @default.
• W3136772266 cites W2962713877 @default.
• W3136772266 cites W2999213643 @default.
• W3136772266 cites W3016546928 @default.
• W3136772266 cites W3088965305 @default.
• W3136772266 cites W3093686881 @default.
• W3136772266 cites W3098321015 @default.
• W3136772266 cites W3099423575 @default.
• W3136772266 cites W3100603243 @default.
• W3136772266 cites W3102449990 @default.
• W3136772266 cites W3102994515 @default.
• W3136772266 cites W3103799425 @default.
• W3136772266 cites W3106310231 @default.
• W3136772266 cites W3133931590 @default.
• W3136772266 cites W3155501465 @default.
• W3136772266 doi "https://doi.org/10.1063/5.0035530" @default.
• W3136772266 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33810678" @default.
• W3136772266 hasPublicationYear "2021" @default.
• W3136772266 type Work @default.
• W3136772266 sameAs 3136772266 @default.
• W3136772266 citedByCount "17" @default.
• W3136772266 countsByYear W31367722662021 @default.
• W3136772266 countsByYear W31367722662022 @default.
• W3136772266 countsByYear W31367722662023 @default.
• W3136772266 crossrefType "journal-article" @default.
• W3136772266 hasAuthorship W3136772266A5002697621 @default.
• W3136772266 hasAuthorship W3136772266A5026929463 @default.
• W3136772266 hasAuthorship W3136772266A5069777955 @default.
• W3136772266 hasAuthorship W3136772266A5087321869 @default.
• W3136772266 hasBestOaLocation W31367722662 @default.
• W3136772266 hasConcept C10803110 @default.
• W3136772266 hasConcept C11413529 @default.
• W3136772266 hasConcept C114614502 @default.
• W3136772266 hasConcept C119857082 @default.
• W3136772266 hasConcept C154945302 @default.
• W3136772266 hasConcept C177264268 @default.
• W3136772266 hasConcept C199360897 @default.
• W3136772266 hasConcept C202444582 @default.
• W3136772266 hasConcept C33923547 @default.
• W3136772266 hasConcept C41008148 @default.
• W3136772266 hasConcept C50644808 @default.
• W3136772266 hasConcept C74193536 @default.
• W3136772266 hasConcept C8038995 @default.
• W3136772266 hasConcept C9652623 @default.
• W3136772266 hasConceptScore W3136772266C10803110 @default.
• W3136772266 hasConceptScore W3136772266C11413529 @default.
• W3136772266 hasConceptScore W3136772266C114614502 @default.
• W3136772266 hasConceptScore W3136772266C119857082 @default.
• W3136772266 hasConceptScore W3136772266C154945302 @default.
• W3136772266 hasConceptScore W3136772266C177264268 @default.
• W3136772266 hasConceptScore W3136772266C199360897 @default.
• W3136772266 hasConceptScore W3136772266C202444582 @default.
• W3136772266 hasConceptScore W3136772266C33923547 @default.
• W3136772266 hasConceptScore W3136772266C41008148 @default.
• W3136772266 hasConceptScore W3136772266C50644808 @default.
• W3136772266 hasConceptScore W3136772266C74193536 @default.
• W3136772266 hasConceptScore W3136772266C8038995 @default.
• W3136772266 hasConceptScore W3136772266C9652623 @default.
• W3136772266 hasFunder F4320321038 @default.
• W3136772266 hasFunder F4320338335 @default.
• W3136772266 hasIssue "12" @default.
• W3136772266 hasLocation W31367722661 @default.
• W3136772266 hasLocation W31367722662 @default.

• next