Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210763918> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4210763918 abstract "Success of machine learning algorithms hinges on access to labeled dataset. Obtaining a labeled dataset is an expensive, challenging and time-consuming process, leading to the development of transfer learning (TL) methodology. TL incorporates gained knowledge from a previously trained source model into specific yet similar task models with limited data domain coverage. In this paper, we propose an automated targeted transfer learning (ATTL) method to resolve the transferability between source and target with minimal data requirements. The ATTL method decides how much target data is essential for model training, along with selected source data, to obtain the skateholder's specified performance metrics. The ATTL framework optimizes the system to select minimal target data based on two approaches: combinatorial coverage and adaptive selection methodology, along with specific source data for fine-tuning given a pre-trained source model. We evaluated the ATTL method on the Kaggle's ‘planes in satellite imagery’ dataset and the results identified that acquiring a small number of intentionally well-chosen samples from the target environment can achieve model performance of 97% in comparison to the baseline transfer learning accuracy of 92%." @default.
- W4210763918 created "2022-02-08" @default.
- W4210763918 creator A5001461808 @default.
- W4210763918 creator A5019081200 @default.
- W4210763918 creator A5030759234 @default.
- W4210763918 creator A5054460502 @default.
- W4210763918 creator A5059050900 @default.
- W4210763918 date "2021-12-01" @default.
- W4210763918 modified "2023-10-16" @default.
- W4210763918 title "ATTL: An Automated Targeted Transfer Learning with Deep Neural Networks" @default.
- W4210763918 cites W1987220198 @default.
- W4210763918 cites W2591924527 @default.
- W4210763918 cites W2736761179 @default.
- W4210763918 cites W2809254203 @default.
- W4210763918 cites W2901474455 @default.
- W4210763918 cites W2940934424 @default.
- W4210763918 cites W2973459053 @default.
- W4210763918 cites W2997265920 @default.
- W4210763918 cites W3009371949 @default.
- W4210763918 cites W3023764908 @default.
- W4210763918 cites W3170449064 @default.
- W4210763918 doi "https://doi.org/10.1109/globecom46510.2021.9685826" @default.
- W4210763918 hasPublicationYear "2021" @default.
- W4210763918 type Work @default.
- W4210763918 citedByCount "1" @default.
- W4210763918 countsByYear W42107639182023 @default.
- W4210763918 crossrefType "proceedings-article" @default.
- W4210763918 hasAuthorship W4210763918A5001461808 @default.
- W4210763918 hasAuthorship W4210763918A5019081200 @default.
- W4210763918 hasAuthorship W4210763918A5030759234 @default.
- W4210763918 hasAuthorship W4210763918A5054460502 @default.
- W4210763918 hasAuthorship W4210763918A5059050900 @default.
- W4210763918 hasConcept C108583219 @default.
- W4210763918 hasConcept C111919701 @default.
- W4210763918 hasConcept C119857082 @default.
- W4210763918 hasConcept C124101348 @default.
- W4210763918 hasConcept C140331021 @default.
- W4210763918 hasConcept C150899416 @default.
- W4210763918 hasConcept C154945302 @default.
- W4210763918 hasConcept C41008148 @default.
- W4210763918 hasConcept C50644808 @default.
- W4210763918 hasConcept C61272859 @default.
- W4210763918 hasConcept C98045186 @default.
- W4210763918 hasConceptScore W4210763918C108583219 @default.
- W4210763918 hasConceptScore W4210763918C111919701 @default.
- W4210763918 hasConceptScore W4210763918C119857082 @default.
- W4210763918 hasConceptScore W4210763918C124101348 @default.
- W4210763918 hasConceptScore W4210763918C140331021 @default.
- W4210763918 hasConceptScore W4210763918C150899416 @default.
- W4210763918 hasConceptScore W4210763918C154945302 @default.
- W4210763918 hasConceptScore W4210763918C41008148 @default.
- W4210763918 hasConceptScore W4210763918C50644808 @default.
- W4210763918 hasConceptScore W4210763918C61272859 @default.
- W4210763918 hasConceptScore W4210763918C98045186 @default.
- W4210763918 hasFunder F4320338295 @default.
- W4210763918 hasLocation W42107639181 @default.
- W4210763918 hasOpenAccess W4210763918 @default.
- W4210763918 hasPrimaryLocation W42107639181 @default.
- W4210763918 hasRelatedWork W2889705046 @default.
- W4210763918 hasRelatedWork W2960456850 @default.
- W4210763918 hasRelatedWork W3192840557 @default.
- W4210763918 hasRelatedWork W4223943233 @default.
- W4210763918 hasRelatedWork W4312200629 @default.
- W4210763918 hasRelatedWork W4317565044 @default.
- W4210763918 hasRelatedWork W4360585206 @default.
- W4210763918 hasRelatedWork W4380075502 @default.
- W4210763918 hasRelatedWork W4382286161 @default.
- W4210763918 hasRelatedWork W4386213806 @default.
- W4210763918 isParatext "false" @default.
- W4210763918 isRetracted "false" @default.
- W4210763918 workType "article" @default.