Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947179935> ?p ?o ?g. }
- W2947179935 endingPage "375" @default.
- W2947179935 startingPage "365" @default.
- W2947179935 abstract "This paper addresses the understanding and characterization of residual networks (ResNet), which are among the state-of-the-art deep learning architectures for a variety of supervised learning problems. We focus on the mapping component of ResNets, which map the embedding space toward a new unknown space where the prediction or classification can be stated according to linear criteria. We show that this mapping component can be regarded as the numerical implementation of continuous flows of diffeomorphisms governed by ordinary differential equations. In particular, ResNets with shared weights are fully characterized as numerical approximation of exponential diffeomorphic operators. We stress both theoretically and numerically the relevance of the enforcement of diffeomorphic properties and the importance of numerical issues to make consistent the continuous formulation and the discretized ResNet implementation. We further discuss the resulting theoretical and computational insights into ResNet architectures." @default.
- W2947179935 created "2019-06-07" @default.
- W2947179935 creator A5045707906 @default.
- W2947179935 creator A5046811680 @default.
- W2947179935 creator A5075497720 @default.
- W2947179935 date "2019-05-29" @default.
- W2947179935 modified "2023-10-18" @default.
- W2947179935 title "Residual Networks as Flows of Diffeomorphisms" @default.
- W2947179935 cites W1573041381 @default.
- W2947179935 cites W1579576867 @default.
- W2947179935 cites W1677182931 @default.
- W2947179935 cites W2082484987 @default.
- W2947179935 cites W2102099319 @default.
- W2947179935 cites W2115167851 @default.
- W2947179935 cites W2155298532 @default.
- W2947179935 cites W2158167845 @default.
- W2947179935 cites W2170167891 @default.
- W2947179935 cites W2194775991 @default.
- W2947179935 cites W2214802144 @default.
- W2947179935 cites W2242218935 @default.
- W2947179935 cites W2302255633 @default.
- W2947179935 cites W2549139847 @default.
- W2947179935 cites W2963359731 @default.
- W2947179935 cites W2974916071 @default.
- W2947179935 cites W3098011980 @default.
- W2947179935 cites W4244723818 @default.
- W2947179935 cites W4250309529 @default.
- W2947179935 cites W4295632409 @default.
- W2947179935 doi "https://doi.org/10.1007/s10851-019-00890-3" @default.
- W2947179935 hasPublicationYear "2019" @default.
- W2947179935 type Work @default.
- W2947179935 sameAs 2947179935 @default.
- W2947179935 citedByCount "27" @default.
- W2947179935 countsByYear W29471799352019 @default.
- W2947179935 countsByYear W29471799352020 @default.
- W2947179935 countsByYear W29471799352021 @default.
- W2947179935 countsByYear W29471799352022 @default.
- W2947179935 countsByYear W29471799352023 @default.
- W2947179935 crossrefType "journal-article" @default.
- W2947179935 hasAuthorship W2947179935A5045707906 @default.
- W2947179935 hasAuthorship W2947179935A5046811680 @default.
- W2947179935 hasAuthorship W2947179935A5075497720 @default.
- W2947179935 hasBestOaLocation W29471799352 @default.
- W2947179935 hasConcept C11413529 @default.
- W2947179935 hasConcept C120665830 @default.
- W2947179935 hasConcept C121332964 @default.
- W2947179935 hasConcept C126255220 @default.
- W2947179935 hasConcept C134306372 @default.
- W2947179935 hasConcept C154945302 @default.
- W2947179935 hasConcept C155512373 @default.
- W2947179935 hasConcept C168167062 @default.
- W2947179935 hasConcept C192209626 @default.
- W2947179935 hasConcept C28826006 @default.
- W2947179935 hasConcept C33923547 @default.
- W2947179935 hasConcept C41008148 @default.
- W2947179935 hasConcept C41608201 @default.
- W2947179935 hasConcept C47556283 @default.
- W2947179935 hasConcept C51544822 @default.
- W2947179935 hasConcept C73000952 @default.
- W2947179935 hasConcept C78045399 @default.
- W2947179935 hasConcept C80444323 @default.
- W2947179935 hasConcept C97355855 @default.
- W2947179935 hasConceptScore W2947179935C11413529 @default.
- W2947179935 hasConceptScore W2947179935C120665830 @default.
- W2947179935 hasConceptScore W2947179935C121332964 @default.
- W2947179935 hasConceptScore W2947179935C126255220 @default.
- W2947179935 hasConceptScore W2947179935C134306372 @default.
- W2947179935 hasConceptScore W2947179935C154945302 @default.
- W2947179935 hasConceptScore W2947179935C155512373 @default.
- W2947179935 hasConceptScore W2947179935C168167062 @default.
- W2947179935 hasConceptScore W2947179935C192209626 @default.
- W2947179935 hasConceptScore W2947179935C28826006 @default.
- W2947179935 hasConceptScore W2947179935C33923547 @default.
- W2947179935 hasConceptScore W2947179935C41008148 @default.
- W2947179935 hasConceptScore W2947179935C41608201 @default.
- W2947179935 hasConceptScore W2947179935C47556283 @default.
- W2947179935 hasConceptScore W2947179935C51544822 @default.
- W2947179935 hasConceptScore W2947179935C73000952 @default.
- W2947179935 hasConceptScore W2947179935C78045399 @default.
- W2947179935 hasConceptScore W2947179935C80444323 @default.
- W2947179935 hasConceptScore W2947179935C97355855 @default.
- W2947179935 hasFunder F4320320883 @default.
- W2947179935 hasFunder F4320321589 @default.
- W2947179935 hasIssue "3" @default.
- W2947179935 hasLocation W29471799351 @default.
- W2947179935 hasLocation W29471799352 @default.
- W2947179935 hasLocation W29471799353 @default.
- W2947179935 hasLocation W29471799354 @default.
- W2947179935 hasLocation W29471799355 @default.
- W2947179935 hasLocation W29471799356 @default.
- W2947179935 hasLocation W29471799357 @default.
- W2947179935 hasOpenAccess W2947179935 @default.
- W2947179935 hasPrimaryLocation W29471799351 @default.
- W2947179935 hasRelatedWork W1553476531 @default.
- W2947179935 hasRelatedWork W1967857696 @default.
- W2947179935 hasRelatedWork W2041896318 @default.
- W2947179935 hasRelatedWork W2315511445 @default.
- W2947179935 hasRelatedWork W2443207603 @default.