FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044299712> ?p ?o ?g. }

• W3044299712 endingPage "6648" @default.
• W3044299712 startingPage "6640" @default.
• W3044299712 abstract "Multireference (MR) diagnostics are common tools for identifying strongly correlated electronic structure that makes single-reference (SR) methods (e.g., density functional theory or DFT) insufficient for accurate property prediction. However, MR diagnostics typically require computationally demanding correlated wave function theory (WFT) calculations, and diagnostics often disagree or fail to predict MR effects on properties. To overcome these challenges, we introduce a semi-supervised machine learning (ML) approach with virtual adversarial training (VAT) of an MR classifier using 15 WFT and DFT MR diagnostics as inputs. In semi-supervised learning, only the most extreme SR or MR points are labeled, and the remaining point labels are learned. The resulting VAT model outperforms the alternatives, as quantified by the distinct property distributions of SR- and MR-classified molecules. To reduce the cost of generating inputs to the VAT model, we leverage the VAT model's robustness to noisy inputs by replacing WFT MR diagnostics with regression predictions in an MR decision engine workflow that preserves excellent performance. We demonstrate the transferability of our approach to larger molecules and those with distinct chemical composition from the training set. This MR decision engine demonstrates promise as a low-cost, high-accuracy approach to the automatic detection of strong correlation for predictive high-throughput screening." @default.
• W3044299712 created "2020-07-29" @default.
• W3044299712 creator A5029457626 @default.
• W3044299712 creator A5038652876 @default.
• W3044299712 creator A5050671822 @default.
• W3044299712 creator A5064662152 @default.
• W3044299712 date "2020-07-21" @default.
• W3044299712 modified "2023-10-12" @default.
• W3044299712 title "Semi-supervised Machine Learning Enables the Robust Detection of Multireference Character at Low Cost" @default.
• W3044299712 cites W1479807131 @default.
• W3044299712 cites W1978627835 @default.
• W3044299712 cites W1990151518 @default.
• W3044299712 cites W2000798385 @default.
• W3044299712 cites W2015197254 @default.
• W3044299712 cites W2044940178 @default.
• W3044299712 cites W2045210181 @default.
• W3044299712 cites W2047389634 @default.
• W3044299712 cites W2050453167 @default.
• W3044299712 cites W2050858126 @default.
• W3044299712 cites W2057521586 @default.
• W3044299712 cites W2058363175 @default.
• W3044299712 cites W2067718414 @default.
• W3044299712 cites W2074616700 @default.
• W3044299712 cites W2074974429 @default.
• W3044299712 cites W2077653456 @default.
• W3044299712 cites W2080635178 @default.
• W3044299712 cites W2099796414 @default.
• W3044299712 cites W2100716186 @default.
• W3044299712 cites W2104489082 @default.
• W3044299712 cites W2107254944 @default.
• W3044299712 cites W2110791536 @default.
• W3044299712 cites W2123306226 @default.
• W3044299712 cites W2130074818 @default.
• W3044299712 cites W2133824255 @default.
• W3044299712 cites W2134329894 @default.
• W3044299712 cites W2154115947 @default.
• W3044299712 cites W2165131446 @default.
• W3044299712 cites W2169678694 @default.
• W3044299712 cites W2169886593 @default.
• W3044299712 cites W2189149359 @default.
• W3044299712 cites W2263840126 @default.
• W3044299712 cites W2316351572 @default.
• W3044299712 cites W2334172904 @default.
• W3044299712 cites W2337496963 @default.
• W3044299712 cites W2412387777 @default.
• W3044299712 cites W2464725281 @default.
• W3044299712 cites W2464735106 @default.
• W3044299712 cites W2474258807 @default.
• W3044299712 cites W2478294658 @default.
• W3044299712 cites W2484276062 @default.
• W3044299712 cites W2604906708 @default.
• W3044299712 cites W2613386458 @default.
• W3044299712 cites W2614641477 @default.
• W3044299712 cites W2739439285 @default.
• W3044299712 cites W2749580687 @default.
• W3044299712 cites W2776911035 @default.
• W3044299712 cites W2786308452 @default.
• W3044299712 cites W2788873578 @default.
• W3044299712 cites W2794704841 @default.
• W3044299712 cites W2800168263 @default.
• W3044299712 cites W2805401872 @default.
• W3044299712 cites W2806843381 @default.
• W3044299712 cites W2888391702 @default.
• W3044299712 cites W2892439819 @default.
• W3044299712 cites W2898972408 @default.
• W3044299712 cites W2921706278 @default.
• W3044299712 cites W2924564326 @default.
• W3044299712 cites W2949625893 @default.
• W3044299712 cites W2962933122 @default.
• W3044299712 cites W2964015639 @default.
• W3044299712 cites W2964159205 @default.
• W3044299712 cites W3009413739 @default.
• W3044299712 cites W3011816976 @default.
• W3044299712 cites W3012320417 @default.
• W3044299712 cites W3034944909 @default.
• W3044299712 cites W3101465336 @default.
• W3044299712 cites W3104577764 @default.
• W3044299712 cites W4234508324 @default.
• W3044299712 cites W4241228400 @default.
• W3044299712 cites W4246701721 @default.
• W3044299712 cites W4256336708 @default.
• W3044299712 doi "https://doi.org/10.1021/acs.jpclett.0c02018" @default.
• W3044299712 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32692570" @default.
• W3044299712 hasPublicationYear "2020" @default.
• W3044299712 type Work @default.
• W3044299712 sameAs 3044299712 @default.
• W3044299712 citedByCount "25" @default.
• W3044299712 countsByYear W30442997122020 @default.
• W3044299712 countsByYear W30442997122021 @default.
• W3044299712 countsByYear W30442997122022 @default.
• W3044299712 countsByYear W30442997122023 @default.
• W3044299712 crossrefType "journal-article" @default.
• W3044299712 hasAuthorship W3044299712A5029457626 @default.
• W3044299712 hasAuthorship W3044299712A5038652876 @default.
• W3044299712 hasAuthorship W3044299712A5050671822 @default.
• W3044299712 hasAuthorship W3044299712A5064662152 @default.
• W3044299712 hasBestOaLocation W30442997122 @default.
• W3044299712 hasConcept C104317684 @default.

• next