Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118994820> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3118994820 abstract "Sequentially transferring machine learning (ML) models in a row over several data sets can result in an improvement of performance. Considering an increasing number of data sets, the possible number “transfer paths” of a transfer grows exponentially. Thus, in this paper, we present TL-MAST, a matching algorithm for identifying the optimal transfer of ML models to reduce the computational effort across a number of data sets—determining their transferability. This is achieved by suggesting suitable source data sets for pairing with a target data set at hand. The approach is based on a layer-wise, metric-supported comparison of individually trained base neural networks through meta machine learning as a proxy for their performance in a crosswise transfer scenario. We evaluate TL-MAST on two real-world data sets: a unique sales data set composed of two restaurant chains and a publicly available stock data set. We are able to identify the best performing transfer paths and therefore, drastically decrease computational time to find the optimal transfer." @default.
- W3118994820 created "2021-01-18" @default.
- W3118994820 creator A5025365948 @default.
- W3118994820 creator A5065193948 @default.
- W3118994820 date "2020-01-01" @default.
- W3118994820 modified "2023-09-25" @default.
- W3118994820 title "A Transfer Machine Learning Matching Algorithm for Source and Target (TL-MAST)" @default.
- W3118994820 cites W1544165511 @default.
- W3118994820 cites W1832693441 @default.
- W3118994820 cites W1965555277 @default.
- W3118994820 cites W2005267105 @default.
- W3118994820 cites W2009953698 @default.
- W3118994820 cites W2016064840 @default.
- W3118994820 cites W2016665082 @default.
- W3118994820 cites W2016770773 @default.
- W3118994820 cites W2023517245 @default.
- W3118994820 cites W2026680733 @default.
- W3118994820 cites W2079708060 @default.
- W3118994820 cites W2087309216 @default.
- W3118994820 cites W2138395440 @default.
- W3118994820 cites W2140448605 @default.
- W3118994820 cites W2143594378 @default.
- W3118994820 cites W2161381512 @default.
- W3118994820 cites W2163828439 @default.
- W3118994820 cites W2165698076 @default.
- W3118994820 cites W2386192529 @default.
- W3118994820 cites W2970677506 @default.
- W3118994820 cites W3097639800 @default.
- W3118994820 cites W4252684946 @default.
- W3118994820 cites W4255375128 @default.
- W3118994820 cites W4255655703 @default.
- W3118994820 doi "https://doi.org/10.1007/978-3-030-64580-9_45" @default.
- W3118994820 hasPublicationYear "2020" @default.
- W3118994820 type Work @default.
- W3118994820 sameAs 3118994820 @default.
- W3118994820 citedByCount "0" @default.
- W3118994820 crossrefType "book-chapter" @default.
- W3118994820 hasAuthorship W3118994820A5025365948 @default.
- W3118994820 hasAuthorship W3118994820A5065193948 @default.
- W3118994820 hasConcept C105795698 @default.
- W3118994820 hasConcept C11413529 @default.
- W3118994820 hasConcept C119857082 @default.
- W3118994820 hasConcept C124101348 @default.
- W3118994820 hasConcept C140331021 @default.
- W3118994820 hasConcept C150899416 @default.
- W3118994820 hasConcept C154945302 @default.
- W3118994820 hasConcept C165064840 @default.
- W3118994820 hasConcept C173608175 @default.
- W3118994820 hasConcept C2776175482 @default.
- W3118994820 hasConcept C33923547 @default.
- W3118994820 hasConcept C41008148 @default.
- W3118994820 hasConcept C51632099 @default.
- W3118994820 hasConcept C58489278 @default.
- W3118994820 hasConcept C61272859 @default.
- W3118994820 hasConceptScore W3118994820C105795698 @default.
- W3118994820 hasConceptScore W3118994820C11413529 @default.
- W3118994820 hasConceptScore W3118994820C119857082 @default.
- W3118994820 hasConceptScore W3118994820C124101348 @default.
- W3118994820 hasConceptScore W3118994820C140331021 @default.
- W3118994820 hasConceptScore W3118994820C150899416 @default.
- W3118994820 hasConceptScore W3118994820C154945302 @default.
- W3118994820 hasConceptScore W3118994820C165064840 @default.
- W3118994820 hasConceptScore W3118994820C173608175 @default.
- W3118994820 hasConceptScore W3118994820C2776175482 @default.
- W3118994820 hasConceptScore W3118994820C33923547 @default.
- W3118994820 hasConceptScore W3118994820C41008148 @default.
- W3118994820 hasConceptScore W3118994820C51632099 @default.
- W3118994820 hasConceptScore W3118994820C58489278 @default.
- W3118994820 hasConceptScore W3118994820C61272859 @default.
- W3118994820 hasLocation W31189948201 @default.
- W3118994820 hasOpenAccess W3118994820 @default.
- W3118994820 hasPrimaryLocation W31189948201 @default.
- W3118994820 hasRelatedWork W11344573 @default.
- W3118994820 hasRelatedWork W11546141 @default.
- W3118994820 hasRelatedWork W11910705 @default.
- W3118994820 hasRelatedWork W12246666 @default.
- W3118994820 hasRelatedWork W13478224 @default.
- W3118994820 hasRelatedWork W4771408 @default.
- W3118994820 hasRelatedWork W665583 @default.
- W3118994820 hasRelatedWork W7390500 @default.
- W3118994820 hasRelatedWork W845024 @default.
- W3118994820 hasRelatedWork W9177359 @default.
- W3118994820 isParatext "false" @default.
- W3118994820 isRetracted "false" @default.
- W3118994820 magId "3118994820" @default.
- W3118994820 workType "book-chapter" @default.