Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310359596> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4310359596 abstract "Abstract Descriptor generation methods using latent representations of Encoder-Decoder (ED) models with SMILES as input is useful because of continuity of descriptor and restorability to structure. However, it is not clear how the structure is recognized in the learning progress of ED model. In this work, we created ED models of various learning progress and investigated the relationship between structural information and the learning progress. We showed that compound substructures were learned early in ED models by monitoring the accuracy of downstream tasks and input-output substructure similarity using substructure-based descriptor, which suggests that existing evaluation methods based on the accuracy of downstream tasks may not be sensitive enough to evaluate the performance of ED models few with SMILES as descriptor generation methods. On the other hand, we showed that structure restoration was time consuming, and in particular, insufficient learning led to estimation of a larger structure than the actual one. It can be inferred that determining the end point of the structure is a difficult task for the model. To the best of our knowledge, this is the first study to link the learning progress of SMILES by ED model to chemical structures for a wide range of chemicals." @default.
- W4310359596 created "2022-12-09" @default.
- W4310359596 creator A5002472002 @default.
- W4310359596 creator A5061014418 @default.
- W4310359596 creator A5079497729 @default.
- W4310359596 date "2022-11-29" @default.
- W4310359596 modified "2023-10-17" @default.
- W4310359596 title "Investigation of chemical structure recognition by encoder-decoder models in learning progress" @default.
- W4310359596 cites W1757990252 @default.
- W4310359596 cites W1988037271 @default.
- W4310359596 cites W2016589492 @default.
- W4310359596 cites W2039183761 @default.
- W4310359596 cites W2121604817 @default.
- W4310359596 cites W2177317049 @default.
- W4310359596 cites W2200017991 @default.
- W4310359596 cites W2323328911 @default.
- W4310359596 cites W2765224015 @default.
- W4310359596 cites W2777416523 @default.
- W4310359596 cites W2805002767 @default.
- W4310359596 cites W2901476322 @default.
- W4310359596 cites W2984339599 @default.
- W4310359596 cites W2991736596 @default.
- W4310359596 cites W2999309192 @default.
- W4310359596 cites W3023204497 @default.
- W4310359596 cites W3085821739 @default.
- W4310359596 cites W3098269892 @default.
- W4310359596 cites W3100358278 @default.
- W4310359596 cites W3107551345 @default.
- W4310359596 cites W3147675882 @default.
- W4310359596 cites W3194368700 @default.
- W4310359596 cites W3214740101 @default.
- W4310359596 cites W4221062742 @default.
- W4310359596 cites W4226159083 @default.
- W4310359596 cites W4283586469 @default.
- W4310359596 doi "https://doi.org/10.21203/rs.3.rs-2300113/v1" @default.
- W4310359596 hasPublicationYear "2022" @default.
- W4310359596 type Work @default.
- W4310359596 citedByCount "0" @default.
- W4310359596 crossrefType "posted-content" @default.
- W4310359596 hasAuthorship W4310359596A5002472002 @default.
- W4310359596 hasAuthorship W4310359596A5061014418 @default.
- W4310359596 hasAuthorship W4310359596A5079497729 @default.
- W4310359596 hasBestOaLocation W43103595961 @default.
- W4310359596 hasConcept C103278499 @default.
- W4310359596 hasConcept C111919701 @default.
- W4310359596 hasConcept C115961682 @default.
- W4310359596 hasConcept C118505674 @default.
- W4310359596 hasConcept C119857082 @default.
- W4310359596 hasConcept C127413603 @default.
- W4310359596 hasConcept C153180895 @default.
- W4310359596 hasConcept C154945302 @default.
- W4310359596 hasConcept C201995342 @default.
- W4310359596 hasConcept C21547014 @default.
- W4310359596 hasConcept C2776207758 @default.
- W4310359596 hasConcept C2780451532 @default.
- W4310359596 hasConcept C41008148 @default.
- W4310359596 hasConcept C66938386 @default.
- W4310359596 hasConcept C99679407 @default.
- W4310359596 hasConceptScore W4310359596C103278499 @default.
- W4310359596 hasConceptScore W4310359596C111919701 @default.
- W4310359596 hasConceptScore W4310359596C115961682 @default.
- W4310359596 hasConceptScore W4310359596C118505674 @default.
- W4310359596 hasConceptScore W4310359596C119857082 @default.
- W4310359596 hasConceptScore W4310359596C127413603 @default.
- W4310359596 hasConceptScore W4310359596C153180895 @default.
- W4310359596 hasConceptScore W4310359596C154945302 @default.
- W4310359596 hasConceptScore W4310359596C201995342 @default.
- W4310359596 hasConceptScore W4310359596C21547014 @default.
- W4310359596 hasConceptScore W4310359596C2776207758 @default.
- W4310359596 hasConceptScore W4310359596C2780451532 @default.
- W4310359596 hasConceptScore W4310359596C41008148 @default.
- W4310359596 hasConceptScore W4310359596C66938386 @default.
- W4310359596 hasConceptScore W4310359596C99679407 @default.
- W4310359596 hasLocation W43103595961 @default.
- W4310359596 hasLocation W43103595962 @default.
- W4310359596 hasOpenAccess W4310359596 @default.
- W4310359596 hasPrimaryLocation W43103595961 @default.
- W4310359596 hasRelatedWork W2015538044 @default.
- W4310359596 hasRelatedWork W2385621972 @default.
- W4310359596 hasRelatedWork W2900794075 @default.
- W4310359596 hasRelatedWork W2961085424 @default.
- W4310359596 hasRelatedWork W3183633970 @default.
- W4310359596 hasRelatedWork W3208309985 @default.
- W4310359596 hasRelatedWork W4289653936 @default.
- W4310359596 hasRelatedWork W4306674287 @default.
- W4310359596 hasRelatedWork W2164844972 @default.
- W4310359596 hasRelatedWork W4224009465 @default.
- W4310359596 isParatext "false" @default.
- W4310359596 isRetracted "false" @default.
- W4310359596 workType "article" @default.