Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971304966> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2971304966 endingPage "5000" @default.
- W2971304966 startingPage "4990" @default.
- W2971304966 abstract "Many measurement modalities arise from well-understood physical processes and result in information-rich but difficult-to-interpret data. Much of this data still requires laborious human interpretation. This is the case in nuclear magnetic resonance (NMR) spectroscopy, where the observed spectrum of a molecule provides a distinguishing fingerprint of its bond structure. Here we solve the resulting inverse problem: given a molecular formula and a spectrum, can we infer the chemical structure? We show for a wide variety of molecules we can quickly compute the correct molecular structure, and can detect with reasonable certainty when our method cannot. We treat this as a problem of graph-structured prediction, where armed with per-vertex information on a subset of the vertices, we infer the edges and edge types. We frame the problem as a Markov decision process (MDP) and incrementally construct molecules one bond at a time, training a deep neural network via imitation learning, where we learn to imitate a subisomorphic oracle which knows which remaining bonds are correct. Our method is fast, accurate, and is the first among recent chemical-graph generation approaches to exploit per-vertex information and generate graphs with vertex constraints. Our method points the way towards automation of molecular structure identification and potentially active learning for spectroscopy." @default.
- W2971304966 created "2019-09-05" @default.
- W2971304966 creator A5002781291 @default.
- W2971304966 date "2019-12-08" @default.
- W2971304966 modified "2023-09-24" @default.
- W2971304966 title "Deep imitation learning for molecular inverse problems" @default.
- W2971304966 cites W1778307852 @default.
- W2971304966 cites W1975147762 @default.
- W2971304966 cites W2053701172 @default.
- W2971304966 cites W2081546452 @default.
- W2971304966 cites W2082773457 @default.
- W2971304966 cites W2094914511 @default.
- W2971304966 cites W2097474301 @default.
- W2971304966 cites W2118103795 @default.
- W2971304966 cites W2155084314 @default.
- W2971304966 cites W2158349948 @default.
- W2971304966 cites W2552808051 @default.
- W2971304966 cites W2604652211 @default.
- W2971304966 cites W2745473362 @default.
- W2971304966 cites W2786103815 @default.
- W2971304966 cites W2962957031 @default.
- W2971304966 cites W2964108670 @default.
- W2971304966 cites W2964245012 @default.
- W2971304966 hasPublicationYear "2019" @default.
- W2971304966 type Work @default.
- W2971304966 sameAs 2971304966 @default.
- W2971304966 citedByCount "2" @default.
- W2971304966 countsByYear W29713049662019 @default.
- W2971304966 countsByYear W29713049662020 @default.
- W2971304966 crossrefType "proceedings-article" @default.
- W2971304966 hasAuthorship W2971304966A5002781291 @default.
- W2971304966 hasConcept C11413529 @default.
- W2971304966 hasConcept C115903868 @default.
- W2971304966 hasConcept C119857082 @default.
- W2971304966 hasConcept C132525143 @default.
- W2971304966 hasConcept C154945302 @default.
- W2971304966 hasConcept C41008148 @default.
- W2971304966 hasConcept C55166926 @default.
- W2971304966 hasConcept C80444323 @default.
- W2971304966 hasConcept C80899671 @default.
- W2971304966 hasConceptScore W2971304966C11413529 @default.
- W2971304966 hasConceptScore W2971304966C115903868 @default.
- W2971304966 hasConceptScore W2971304966C119857082 @default.
- W2971304966 hasConceptScore W2971304966C132525143 @default.
- W2971304966 hasConceptScore W2971304966C154945302 @default.
- W2971304966 hasConceptScore W2971304966C41008148 @default.
- W2971304966 hasConceptScore W2971304966C55166926 @default.
- W2971304966 hasConceptScore W2971304966C80444323 @default.
- W2971304966 hasConceptScore W2971304966C80899671 @default.
- W2971304966 hasLocation W29713049661 @default.
- W2971304966 hasOpenAccess W2971304966 @default.
- W2971304966 hasPrimaryLocation W29713049661 @default.
- W2971304966 hasRelatedWork W1580552115 @default.
- W2971304966 hasRelatedWork W1973597120 @default.
- W2971304966 hasRelatedWork W2185431605 @default.
- W2971304966 hasRelatedWork W2295295596 @default.
- W2971304966 hasRelatedWork W2336019627 @default.
- W2971304966 hasRelatedWork W2735163028 @default.
- W2971304966 hasRelatedWork W2768121184 @default.
- W2971304966 hasRelatedWork W2785253517 @default.
- W2971304966 hasRelatedWork W2785761199 @default.
- W2971304966 hasRelatedWork W2794727009 @default.
- W2971304966 hasRelatedWork W2891814056 @default.
- W2971304966 hasRelatedWork W2924720492 @default.
- W2971304966 hasRelatedWork W2943937285 @default.
- W2971304966 hasRelatedWork W2951046113 @default.
- W2971304966 hasRelatedWork W3005033386 @default.
- W2971304966 hasRelatedWork W3080862861 @default.
- W2971304966 hasRelatedWork W3093384451 @default.
- W2971304966 hasRelatedWork W3213694594 @default.
- W2971304966 hasRelatedWork W1940064195 @default.
- W2971304966 hasRelatedWork W2611508703 @default.
- W2971304966 hasVolume "32" @default.
- W2971304966 isParatext "false" @default.
- W2971304966 isRetracted "false" @default.
- W2971304966 magId "2971304966" @default.
- W2971304966 workType "article" @default.