Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320233681> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4320233681 abstract "Supervised transfer learning (TL) has received considerable attention because of its potential to boost the predictive power of machine learning in cases with limited data. In a conventional scenario, cross-domain differences are modeled and estimated using a given set of source models and samples from a target domain. For example, if there is a functional relationship between source and target domains, only domain-specific factors are additionally learned using target samples to shift the source models to the target. However, the general methodology for modeling and estimating such cross-domain shifts has been less studied. This study presents a TL framework that simultaneously and separately estimates domain shifts and domain-specific factors using given target samples. Assuming consistency and invertibility of the domain transformation functions, we derive an optimal family of functions to represent the cross-domain shift. The newly derived class of transformation functions takes the same form as invertible neural networks using affine coupling layers, which are widely used in generative deep learning. We show that the proposed method encompasses a wide range of existing methods, including the most common TL procedure based on feature extraction using neural networks. We also clarify the theoretical properties of the proposed method, such as the convergence rate of the generalization error, and demonstrate the practical benefits of separately modeling and estimating domain-specific factors through several case studies." @default.
- W4320233681 created "2023-02-13" @default.
- W4320233681 creator A5000394070 @default.
- W4320233681 creator A5012922872 @default.
- W4320233681 creator A5069627264 @default.
- W4320233681 creator A5072124735 @default.
- W4320233681 date "2022-10-18" @default.
- W4320233681 modified "2023-09-23" @default.
- W4320233681 title "Transfer learning with affine model transformation" @default.
- W4320233681 doi "https://doi.org/10.48550/arxiv.2210.09745" @default.
- W4320233681 hasPublicationYear "2022" @default.
- W4320233681 type Work @default.
- W4320233681 citedByCount "0" @default.
- W4320233681 crossrefType "posted-content" @default.
- W4320233681 hasAuthorship W4320233681A5000394070 @default.
- W4320233681 hasAuthorship W4320233681A5012922872 @default.
- W4320233681 hasAuthorship W4320233681A5069627264 @default.
- W4320233681 hasAuthorship W4320233681A5072124735 @default.
- W4320233681 hasBestOaLocation W43202336811 @default.
- W4320233681 hasConcept C104317684 @default.
- W4320233681 hasConcept C11413529 @default.
- W4320233681 hasConcept C119857082 @default.
- W4320233681 hasConcept C134306372 @default.
- W4320233681 hasConcept C150899416 @default.
- W4320233681 hasConcept C153180895 @default.
- W4320233681 hasConcept C154945302 @default.
- W4320233681 hasConcept C159985019 @default.
- W4320233681 hasConcept C162324750 @default.
- W4320233681 hasConcept C177148314 @default.
- W4320233681 hasConcept C185592680 @default.
- W4320233681 hasConcept C192562407 @default.
- W4320233681 hasConcept C202444582 @default.
- W4320233681 hasConcept C204241405 @default.
- W4320233681 hasConcept C204323151 @default.
- W4320233681 hasConcept C2776436953 @default.
- W4320233681 hasConcept C2777303404 @default.
- W4320233681 hasConcept C33923547 @default.
- W4320233681 hasConcept C36503486 @default.
- W4320233681 hasConcept C41008148 @default.
- W4320233681 hasConcept C50522688 @default.
- W4320233681 hasConcept C50644808 @default.
- W4320233681 hasConcept C55493867 @default.
- W4320233681 hasConcept C92757383 @default.
- W4320233681 hasConceptScore W4320233681C104317684 @default.
- W4320233681 hasConceptScore W4320233681C11413529 @default.
- W4320233681 hasConceptScore W4320233681C119857082 @default.
- W4320233681 hasConceptScore W4320233681C134306372 @default.
- W4320233681 hasConceptScore W4320233681C150899416 @default.
- W4320233681 hasConceptScore W4320233681C153180895 @default.
- W4320233681 hasConceptScore W4320233681C154945302 @default.
- W4320233681 hasConceptScore W4320233681C159985019 @default.
- W4320233681 hasConceptScore W4320233681C162324750 @default.
- W4320233681 hasConceptScore W4320233681C177148314 @default.
- W4320233681 hasConceptScore W4320233681C185592680 @default.
- W4320233681 hasConceptScore W4320233681C192562407 @default.
- W4320233681 hasConceptScore W4320233681C202444582 @default.
- W4320233681 hasConceptScore W4320233681C204241405 @default.
- W4320233681 hasConceptScore W4320233681C204323151 @default.
- W4320233681 hasConceptScore W4320233681C2776436953 @default.
- W4320233681 hasConceptScore W4320233681C2777303404 @default.
- W4320233681 hasConceptScore W4320233681C33923547 @default.
- W4320233681 hasConceptScore W4320233681C36503486 @default.
- W4320233681 hasConceptScore W4320233681C41008148 @default.
- W4320233681 hasConceptScore W4320233681C50522688 @default.
- W4320233681 hasConceptScore W4320233681C50644808 @default.
- W4320233681 hasConceptScore W4320233681C55493867 @default.
- W4320233681 hasConceptScore W4320233681C92757383 @default.
- W4320233681 hasLocation W43202336811 @default.
- W4320233681 hasOpenAccess W4320233681 @default.
- W4320233681 hasPrimaryLocation W43202336811 @default.
- W4320233681 hasRelatedWork W2068101419 @default.
- W4320233681 hasRelatedWork W2356755074 @default.
- W4320233681 hasRelatedWork W2949280030 @default.
- W4320233681 hasRelatedWork W2960456850 @default.
- W4320233681 hasRelatedWork W2989932438 @default.
- W4320233681 hasRelatedWork W3021430260 @default.
- W4320233681 hasRelatedWork W4281382123 @default.
- W4320233681 hasRelatedWork W4308262314 @default.
- W4320233681 hasRelatedWork W4318834068 @default.
- W4320233681 hasRelatedWork W1629725936 @default.
- W4320233681 isParatext "false" @default.
- W4320233681 isRetracted "false" @default.
- W4320233681 workType "article" @default.