FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224927704> ?p ?o ?g. }

• W4224927704 endingPage "12836" @default.
• W4224927704 startingPage "12827" @default.
• W4224927704 abstract "There has been increasing attention in using machine learning technologies, such as neural networks (NNs) and Gaussian process regression (GPR), to model multi-dimensional potential energy surfaces (PESs). A PES constructed using NNs features high accuracy and generalization capability, but a single NN cannot actively select training points as GPR does, resulting in expensive ab initio calculations as the molecular complexity increases. However, a PES constructed using GPR has a slow speed of evaluation and it is difficult to accurately describe a fast-changing potential. Herein, an efficient scheme for representing globally accurate reactive PESs with complex topography based on as few points as possible by incorporating active data selection of GPR into NN fitting is proposed. The validity of this strategy is tested using the BeH2+ system, and only 1270 points are automatically sampled. The generalization performance and speed of evaluation of the generated PES are much better than those of the GPR PES constructed using the same dataset. Moreover, an accurate NN PES is fitted by 12 122 points as a benchmark for comparison to further test the global accuracy of the PES obtained using this scheme, and the corresponding results present extremely consistent topography characteristics and calculated Be+(2S) + H2 reaction probabilities." @default.
• W4224927704 created "2022-04-28" @default.
• W4224927704 creator A5003077885 @default.
• W4224927704 creator A5047555174 @default.
• W4224927704 creator A5080760534 @default.
• W4224927704 date "2022-01-01" @default.
• W4224927704 modified "2023-09-23" @default.
• W4224927704 title "Representing globally accurate reactive potential energy surfaces with complex topography by combining Gaussian process regression and neural networks" @default.
• W4224927704 cites W1498436455 @default.
• W4224927704 cites W1964882117 @default.
• W4224927704 cites W1976809448 @default.
• W4224927704 cites W1993077801 @default.
• W4224927704 cites W1998860313 @default.
• W4224927704 cites W1999182500 @default.
• W4224927704 cites W2002087089 @default.
• W4224927704 cites W2003320348 @default.
• W4224927704 cites W2003501378 @default.
• W4224927704 cites W2021891874 @default.
• W4224927704 cites W2030280844 @default.
• W4224927704 cites W2032222091 @default.
• W4224927704 cites W2032436962 @default.
• W4224927704 cites W2034393847 @default.
• W4224927704 cites W2055526416 @default.
• W4224927704 cites W2055783031 @default.
• W4224927704 cites W2058370262 @default.
• W4224927704 cites W2059167945 @default.
• W4224927704 cites W2068473123 @default.
• W4224927704 cites W2135556320 @default.
• W4224927704 cites W2155482699 @default.
• W4224927704 cites W2164711568 @default.
• W4224927704 cites W2411133788 @default.
• W4224927704 cites W2424831523 @default.
• W4224927704 cites W2508146432 @default.
• W4224927704 cites W2511310272 @default.
• W4224927704 cites W2547447472 @default.
• W4224927704 cites W2595516356 @default.
• W4224927704 cites W2606373774 @default.
• W4224927704 cites W2644930549 @default.
• W4224927704 cites W2775447200 @default.
• W4224927704 cites W2775573246 @default.
• W4224927704 cites W2778051509 @default.
• W4224927704 cites W2786791309 @default.
• W4224927704 cites W2792351009 @default.
• W4224927704 cites W2805705780 @default.
• W4224927704 cites W2808095267 @default.
• W4224927704 cites W2809512457 @default.
• W4224927704 cites W2894384446 @default.
• W4224927704 cites W2897192959 @default.
• W4224927704 cites W2900144772 @default.
• W4224927704 cites W2911351655 @default.
• W4224927704 cites W2950674591 @default.
• W4224927704 cites W2955097063 @default.
• W4224927704 cites W2966808730 @default.
• W4224927704 cites W2998882720 @default.
• W4224927704 cites W2999166443 @default.
• W4224927704 cites W3001801734 @default.
• W4224927704 cites W3012292119 @default.
• W4224927704 cites W3016216085 @default.
• W4224927704 cites W3030664746 @default.
• W4224927704 cites W3033461492 @default.
• W4224927704 cites W3080921728 @default.
• W4224927704 cites W3086356742 @default.
• W4224927704 cites W3090555547 @default.
• W4224927704 cites W3099773359 @default.
• W4224927704 cites W3100571530 @default.
• W4224927704 cites W3100603243 @default.
• W4224927704 cites W3101568640 @default.
• W4224927704 cites W3103345637 @default.
• W4224927704 cites W3111349202 @default.
• W4224927704 cites W3132909951 @default.
• W4224927704 cites W3133762917 @default.
• W4224927704 cites W3158781419 @default.
• W4224927704 cites W3189164715 @default.
• W4224927704 cites W4236747715 @default.
• W4224927704 cites W4247680473 @default.
• W4224927704 cites W4376489813 @default.
• W4224927704 doi "https://doi.org/10.1039/d2cp00719c" @default.
• W4224927704 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35470359" @default.
• W4224927704 hasPublicationYear "2022" @default.
• W4224927704 type Work @default.
• W4224927704 citedByCount "3" @default.
• W4224927704 countsByYear W42249277042022 @default.
• W4224927704 countsByYear W42249277042023 @default.
• W4224927704 crossrefType "journal-article" @default.
• W4224927704 hasAuthorship W4224927704A5003077885 @default.
• W4224927704 hasAuthorship W4224927704A5047555174 @default.
• W4224927704 hasAuthorship W4224927704A5080760534 @default.
• W4224927704 hasConcept C105795698 @default.
• W4224927704 hasConcept C111919701 @default.
• W4224927704 hasConcept C11413529 @default.
• W4224927704 hasConcept C119857082 @default.
• W4224927704 hasConcept C121332964 @default.
• W4224927704 hasConcept C127313418 @default.
• W4224927704 hasConcept C13280743 @default.
• W4224927704 hasConcept C134306372 @default.
• W4224927704 hasConcept C147597530 @default.
• W4224927704 hasConcept C154945302 @default.
• W4224927704 hasConcept C163716315 @default.

• next