Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034670733> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W3034670733 abstract "Machine learning models often suffer from the problem of over-fitting. Many data augmentation methods have been proposed to tackle such a problem, and one of them is called mixup. Mixup is a recently proposed regularization procedure, which linearly interpolates a random pair of training examples. This regularization method works very well experimentally, but its theoretical guarantee is not adequately discussed. In this study, we aim to discover why mixup works well from the aspect of the statistical learning theory. In addition, we reveal how the effect of mixup changes in each situation. Furthermore, we also investigated the effects of changes in the parameter of mixup. Our work contributes to searching for the optimal parameters and estimating the effects of the parameters currently used. The results of this study provide a theoretical clarification of when and how effective regularization by mixup is." @default.
- W3034670733 created "2020-06-19" @default.
- W3034670733 creator A5065015874 @default.
- W3034670733 date "2021-05-04" @default.
- W3034670733 modified "2023-09-27" @default.
- W3034670733 title "Mixup Training as the Complexity Reduction" @default.
- W3034670733 cites W2001619934 @default.
- W3034670733 cites W2194775991 @default.
- W3034670733 cites W2579923771 @default.
- W3034670733 cites W2765407302 @default.
- W3034670733 cites W2963108767 @default.
- W3034670733 cites W3001197829 @default.
- W3034670733 cites W3118608800 @default.
- W3034670733 hasPublicationYear "2021" @default.
- W3034670733 type Work @default.
- W3034670733 sameAs 3034670733 @default.
- W3034670733 citedByCount "3" @default.
- W3034670733 countsByYear W30346707332020 @default.
- W3034670733 countsByYear W30346707332021 @default.
- W3034670733 crossrefType "journal-article" @default.
- W3034670733 hasAuthorship W3034670733A5065015874 @default.
- W3034670733 hasConcept C11413529 @default.
- W3034670733 hasConcept C119857082 @default.
- W3034670733 hasConcept C154945302 @default.
- W3034670733 hasConcept C2776135515 @default.
- W3034670733 hasConcept C41008148 @default.
- W3034670733 hasConcept C51632099 @default.
- W3034670733 hasConceptScore W3034670733C11413529 @default.
- W3034670733 hasConceptScore W3034670733C119857082 @default.
- W3034670733 hasConceptScore W3034670733C154945302 @default.
- W3034670733 hasConceptScore W3034670733C2776135515 @default.
- W3034670733 hasConceptScore W3034670733C41008148 @default.
- W3034670733 hasConceptScore W3034670733C51632099 @default.
- W3034670733 hasLocation W30346707331 @default.
- W3034670733 hasOpenAccess W3034670733 @default.
- W3034670733 hasPrimaryLocation W30346707331 @default.
- W3034670733 hasRelatedWork W2047278993 @default.
- W3034670733 hasRelatedWork W2069735839 @default.
- W3034670733 hasRelatedWork W2774684800 @default.
- W3034670733 hasRelatedWork W2892986808 @default.
- W3034670733 hasRelatedWork W2898347199 @default.
- W3034670733 hasRelatedWork W2963341057 @default.
- W3034670733 hasRelatedWork W2993587506 @default.
- W3034670733 hasRelatedWork W3037943408 @default.
- W3034670733 hasRelatedWork W3045401084 @default.
- W3034670733 hasRelatedWork W3047452952 @default.
- W3034670733 hasRelatedWork W3080700717 @default.
- W3034670733 hasRelatedWork W3091860746 @default.
- W3034670733 hasRelatedWork W3094105627 @default.
- W3034670733 hasRelatedWork W3124367822 @default.
- W3034670733 hasRelatedWork W3198407848 @default.
- W3034670733 hasRelatedWork W3199148528 @default.
- W3034670733 hasRelatedWork W3204726504 @default.
- W3034670733 hasRelatedWork W3213822864 @default.
- W3034670733 hasRelatedWork W36398315 @default.
- W3034670733 hasRelatedWork W3180220823 @default.
- W3034670733 isParatext "false" @default.
- W3034670733 isRetracted "false" @default.
- W3034670733 magId "3034670733" @default.
- W3034670733 workType "article" @default.