FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008669240> ?p ?o ?g. }

• W3008669240 endingPage "1301" @default.
• W3008669240 startingPage "1290" @default.
• W3008669240 abstract "In a departure from conventional chemical approaches, data-driven models of chemical reactions have recently been shown to be statistically successful using machine learning. These models, however, are largely black box in character and have not provided the kind of chemical insights that historically advanced the field of chemistry. To examine the knowledgebase of machine-learning models—what does the machine learn—this article deconstructs black-box machine-learning models of a diverse chemical reaction data set. Through experimentation with chemical representations and modeling techniques, the analysis provides insights into the nature of how statistical accuracy can arise, even when the model lacks informative physical principles. By peeling back the layers of these complicated models we arrive at a minimal, chemically intuitive model (and no machine learning involved). This model is based on systematic reaction-type classification and Evans–Polanyi relationships within reaction types which are easily visualized and interpreted. Through exploring this simple model, we gain deeper understanding of the data set and uncover a means for expert interactions to improve the model’s reliability." @default.
• W3008669240 created "2020-03-06" @default.
• W3008669240 creator A5009402523 @default.
• W3008669240 creator A5042777510 @default.
• W3008669240 creator A5051122318 @default.
• W3008669240 creator A5051918150 @default.
• W3008669240 creator A5060805106 @default.
• W3008669240 date "2020-02-24" @default.
• W3008669240 modified "2023-10-18" @default.
• W3008669240 title "What Does the Machine Learn? Knowledge Representations of Chemical Reactivity" @default.
• W3008669240 cites W1496317909 @default.
• W3008669240 cites W1531524766 @default.
• W3008669240 cites W1965269139 @default.
• W3008669240 cites W1965736404 @default.
• W3008669240 cites W1970983973 @default.
• W3008669240 cites W1975147762 @default.
• W3008669240 cites W1978536813 @default.
• W3008669240 cites W1988115241 @default.
• W3008669240 cites W1988636074 @default.
• W3008669240 cites W1992757684 @default.
• W3008669240 cites W1997974358 @default.
• W3008669240 cites W1998260904 @default.
• W3008669240 cites W1999859339 @default.
• W3008669240 cites W2000614400 @default.
• W3008669240 cites W2026265322 @default.
• W3008669240 cites W2027414105 @default.
• W3008669240 cites W2027611895 @default.
• W3008669240 cites W2047414823 @default.
• W3008669240 cites W2060586571 @default.
• W3008669240 cites W2066412916 @default.
• W3008669240 cites W2071922898 @default.
• W3008669240 cites W2151697120 @default.
• W3008669240 cites W2158177761 @default.
• W3008669240 cites W2164524421 @default.
• W3008669240 cites W2280192198 @default.
• W3008669240 cites W2281240662 @default.
• W3008669240 cites W2313127483 @default.
• W3008669240 cites W2324964582 @default.
• W3008669240 cites W2325959393 @default.
• W3008669240 cites W2341037910 @default.
• W3008669240 cites W2347129741 @default.
• W3008669240 cites W2410010784 @default.
• W3008669240 cites W2477622860 @default.
• W3008669240 cites W2527189750 @default.
• W3008669240 cites W2541404351 @default.
• W3008669240 cites W2551217916 @default.
• W3008669240 cites W2564876500 @default.
• W3008669240 cites W2565751006 @default.
• W3008669240 cites W2580919858 @default.
• W3008669240 cites W2586210924 @default.
• W3008669240 cites W2593855134 @default.
• W3008669240 cites W2606363443 @default.
• W3008669240 cites W2610707110 @default.
• W3008669240 cites W2612331475 @default.
• W3008669240 cites W2736643800 @default.
• W3008669240 cites W2747592475 @default.
• W3008669240 cites W2749580687 @default.
• W3008669240 cites W2753962198 @default.
• W3008669240 cites W2765349976 @default.
• W3008669240 cites W2769423117 @default.
• W3008669240 cites W2770447879 @default.
• W3008669240 cites W2775684663 @default.
• W3008669240 cites W2777416523 @default.
• W3008669240 cites W2785942661 @default.
• W3008669240 cites W2788266460 @default.
• W3008669240 cites W2800440295 @default.
• W3008669240 cites W2830440988 @default.
• W3008669240 cites W2896312952 @default.
• W3008669240 cites W2900743800 @default.
• W3008669240 cites W2906453878 @default.
• W3008669240 cites W2962884579 @default.
• W3008669240 cites W2965447776 @default.
• W3008669240 cites W3098269892 @default.
• W3008669240 cites W3100545487 @default.
• W3008669240 cites W3102659967 @default.
• W3008669240 cites W3102693939 @default.
• W3008669240 cites W3104508774 @default.
• W3008669240 cites W3104705366 @default.
• W3008669240 cites W4239510810 @default.
• W3008669240 doi "https://doi.org/10.1021/acs.jcim.9b00721" @default.
• W3008669240 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7166311" @default.
• W3008669240 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32091880" @default.
• W3008669240 hasPublicationYear "2020" @default.
• W3008669240 type Work @default.
• W3008669240 sameAs 3008669240 @default.
• W3008669240 citedByCount "19" @default.
• W3008669240 countsByYear W30086692402020 @default.
• W3008669240 countsByYear W30086692402021 @default.
• W3008669240 countsByYear W30086692402022 @default.
• W3008669240 countsByYear W30086692402023 @default.
• W3008669240 crossrefType "journal-article" @default.
• W3008669240 hasAuthorship W3008669240A5009402523 @default.
• W3008669240 hasAuthorship W3008669240A5042777510 @default.
• W3008669240 hasAuthorship W3008669240A5051122318 @default.
• W3008669240 hasAuthorship W3008669240A5051918150 @default.
• W3008669240 hasAuthorship W3008669240A5060805106 @default.
• W3008669240 hasBestOaLocation W30086692402 @default.
• W3008669240 hasConcept C105795698 @default.

• next