Matches in SemOpenAlex for { <https://semopenalex.org/work/W2318118870> ?p ?o ?g. }
- W2318118870 endingPage "4638" @default.
- W2318118870 startingPage "4629" @default.
- W2318118870 abstract "The classical interchange (permutation) of atoms of similar identity does not have an effect on the overall potential energy. In this study, we present feed-forward neural network structures that provide permutation symmetry to the potential energy surfaces of molecules. The new feed-forward neural network structures are employed to fit the potential energy surfaces for two illustrative molecules, which are H2O and ClOOCl. Modifications are made to describe the symmetric interchange (permutation) of atoms of similar identity (or mathematically, the permutation of symmetric input parameters). The combined-function-derivative approximation algorithm (J. Chem. Phys. 2009, 130, 134101) is also implemented to fit the neural-network potential energy surfaces accurately. The combination of our symmetric neural networks and the function-derivative fitting effectively produces PES fits using fewer numbers of training data points. For H2O, only 282 configurations are employed as the training set; the testing root-mean-squared and mean-absolute energy errors are respectively reported as 0.0103 eV (0.236 kcal/mol) and 0.0078 eV (0.179 kcal/mol). In the ClOOCl case, 1693 configurations are required to construct the training set; the root-mean-squared and mean-absolute energy errors for the ClOOCl testing set are 0.0409 eV (0.943 kcal/mol) and 0.0269 eV (0.620 kcal/mol), respectively. Overall, we find good agreements between ab initio and NN prediction in term of energy and gradient errors, and conclude that the new feed-forward neural-network models advantageously describe the molecules with excellent accuracy." @default.
- W2318118870 created "2016-06-24" @default.
- W2318118870 creator A5038017332 @default.
- W2318118870 creator A5075655440 @default.
- W2318118870 date "2012-05-02" @default.
- W2318118870 modified "2023-09-26" @default.
- W2318118870 title "Modified Feed-Forward Neural Network Structures and Combined-Function-Derivative Approximations Incorporating Exchange Symmetry for Potential Energy Surface Fitting" @default.
- W2318118870 cites W1498436455 @default.
- W2318118870 cites W1727290854 @default.
- W2318118870 cites W1965807998 @default.
- W2318118870 cites W1966820249 @default.
- W2318118870 cites W1966939946 @default.
- W2318118870 cites W1967108496 @default.
- W2318118870 cites W1971275758 @default.
- W2318118870 cites W1971920777 @default.
- W2318118870 cites W1975708211 @default.
- W2318118870 cites W1979319235 @default.
- W2318118870 cites W1993569557 @default.
- W2318118870 cites W2000363633 @default.
- W2318118870 cites W2000407885 @default.
- W2318118870 cites W2000957843 @default.
- W2318118870 cites W2002248394 @default.
- W2318118870 cites W2013001431 @default.
- W2318118870 cites W2014415452 @default.
- W2318118870 cites W2015027094 @default.
- W2318118870 cites W2018518989 @default.
- W2318118870 cites W2019427580 @default.
- W2318118870 cites W2022101332 @default.
- W2318118870 cites W2025444507 @default.
- W2318118870 cites W2030280844 @default.
- W2318118870 cites W2036500885 @default.
- W2318118870 cites W2042640655 @default.
- W2318118870 cites W2043076340 @default.
- W2318118870 cites W2044940178 @default.
- W2318118870 cites W2046149728 @default.
- W2318118870 cites W2048522468 @default.
- W2318118870 cites W2053117030 @default.
- W2318118870 cites W2058370262 @default.
- W2318118870 cites W2061179540 @default.
- W2318118870 cites W2063007245 @default.
- W2318118870 cites W2082369519 @default.
- W2318118870 cites W2083956694 @default.
- W2318118870 cites W2087404659 @default.
- W2318118870 cites W2095085454 @default.
- W2318118870 cites W2100030276 @default.
- W2318118870 cites W2115033122 @default.
- W2318118870 cites W2127644822 @default.
- W2318118870 cites W2128084896 @default.
- W2318118870 cites W2130437470 @default.
- W2318118870 cites W2332718840 @default.
- W2318118870 cites W2952363531 @default.
- W2318118870 doi "https://doi.org/10.1021/jp3020386" @default.
- W2318118870 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/22548349" @default.
- W2318118870 hasPublicationYear "2012" @default.
- W2318118870 type Work @default.
- W2318118870 sameAs 2318118870 @default.
- W2318118870 citedByCount "27" @default.
- W2318118870 countsByYear W23181188702012 @default.
- W2318118870 countsByYear W23181188702013 @default.
- W2318118870 countsByYear W23181188702014 @default.
- W2318118870 countsByYear W23181188702015 @default.
- W2318118870 countsByYear W23181188702016 @default.
- W2318118870 countsByYear W23181188702017 @default.
- W2318118870 countsByYear W23181188702018 @default.
- W2318118870 countsByYear W23181188702019 @default.
- W2318118870 countsByYear W23181188702020 @default.
- W2318118870 countsByYear W23181188702021 @default.
- W2318118870 countsByYear W23181188702022 @default.
- W2318118870 crossrefType "journal-article" @default.
- W2318118870 hasAuthorship W2318118870A5038017332 @default.
- W2318118870 hasAuthorship W2318118870A5075655440 @default.
- W2318118870 hasConcept C105795698 @default.
- W2318118870 hasConcept C106159729 @default.
- W2318118870 hasConcept C111771559 @default.
- W2318118870 hasConcept C11413529 @default.
- W2318118870 hasConcept C121332964 @default.
- W2318118870 hasConcept C121864883 @default.
- W2318118870 hasConcept C125277925 @default.
- W2318118870 hasConcept C134306372 @default.
- W2318118870 hasConcept C139945424 @default.
- W2318118870 hasConcept C14036430 @default.
- W2318118870 hasConcept C147597530 @default.
- W2318118870 hasConcept C154945302 @default.
- W2318118870 hasConcept C162324750 @default.
- W2318118870 hasConcept C178790620 @default.
- W2318118870 hasConcept C184779094 @default.
- W2318118870 hasConcept C185592680 @default.
- W2318118870 hasConcept C186370098 @default.
- W2318118870 hasConcept C21308566 @default.
- W2318118870 hasConcept C24890656 @default.
- W2318118870 hasConcept C2524010 @default.
- W2318118870 hasConcept C2779886137 @default.
- W2318118870 hasConcept C2781442258 @default.
- W2318118870 hasConcept C33257320 @default.
- W2318118870 hasConcept C33923547 @default.
- W2318118870 hasConcept C41008148 @default.
- W2318118870 hasConcept C50644808 @default.
- W2318118870 hasConcept C62520636 @default.