Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945540071> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2945540071 abstract "Self-training is a semi-supervised learning approach for utilizing unlabeled data to create better learners. The efficacy of self-training algorithms depends on their data sampling techniques. The majority of current sampling techniques are based on predetermined policies which may not effectively explore the data space or improve model generalizability. In this work, we tackle the above challenges by introducing a new data sampling technique based on spaced repetition that dynamically samples informative and diverse unlabeled instances with respect to individual learner and instance characteristics. The proposed model is specifically effective in the context of neural models which can suffer from overfitting and high-variance gradients when trained with small amount of labeled data. Our model outperforms current semi-supervised learning approaches developed for neural networks on publicly-available datasets." @default.
- W2945540071 created "2019-05-29" @default.
- W2945540071 creator A5074007015 @default.
- W2945540071 date "2019-01-01" @default.
- W2945540071 modified "2023-09-25" @default.
- W2945540071 title "Neural Self-Training through Spaced Repetition" @default.
- W2945540071 cites W197270748 @default.
- W2945540071 cites W1990334093 @default.
- W2945540071 cites W1998593585 @default.
- W2945540071 cites W2029507764 @default.
- W2945540071 cites W2048679005 @default.
- W2945540071 cites W2049428464 @default.
- W2945540071 cites W2100495367 @default.
- W2945540071 cites W2101210369 @default.
- W2945540071 cites W2110798204 @default.
- W2945540071 cites W2111702745 @default.
- W2945540071 cites W2113459411 @default.
- W2945540071 cites W2136504847 @default.
- W2945540071 cites W2138857742 @default.
- W2945540071 cites W2145094598 @default.
- W2945540071 cites W2167404615 @default.
- W2945540071 cites W2170973209 @default.
- W2945540071 cites W2218470667 @default.
- W2945540071 cites W2250473257 @default.
- W2945540071 cites W2589226201 @default.
- W2945540071 cites W2752172973 @default.
- W2945540071 cites W2760035721 @default.
- W2945540071 cites W2950577311 @default.
- W2945540071 cites W2963465221 @default.
- W2945540071 cites W2963626623 @default.
- W2945540071 cites W2964005754 @default.
- W2945540071 cites W2964301648 @default.
- W2945540071 cites W2978358955 @default.
- W2945540071 cites W71104953 @default.
- W2945540071 doi "https://doi.org/10.18653/v1/n19-1003" @default.
- W2945540071 hasPublicationYear "2019" @default.
- W2945540071 type Work @default.
- W2945540071 sameAs 2945540071 @default.
- W2945540071 citedByCount "9" @default.
- W2945540071 countsByYear W29455400712020 @default.
- W2945540071 countsByYear W29455400712021 @default.
- W2945540071 countsByYear W29455400712023 @default.
- W2945540071 crossrefType "proceedings-article" @default.
- W2945540071 hasAuthorship W2945540071A5074007015 @default.
- W2945540071 hasConcept C121332964 @default.
- W2945540071 hasConcept C138885662 @default.
- W2945540071 hasConcept C153294291 @default.
- W2945540071 hasConcept C154945302 @default.
- W2945540071 hasConcept C2776141515 @default.
- W2945540071 hasConcept C2777211547 @default.
- W2945540071 hasConcept C28490314 @default.
- W2945540071 hasConcept C41008148 @default.
- W2945540071 hasConcept C41895202 @default.
- W2945540071 hasConceptScore W2945540071C121332964 @default.
- W2945540071 hasConceptScore W2945540071C138885662 @default.
- W2945540071 hasConceptScore W2945540071C153294291 @default.
- W2945540071 hasConceptScore W2945540071C154945302 @default.
- W2945540071 hasConceptScore W2945540071C2776141515 @default.
- W2945540071 hasConceptScore W2945540071C2777211547 @default.
- W2945540071 hasConceptScore W2945540071C28490314 @default.
- W2945540071 hasConceptScore W2945540071C41008148 @default.
- W2945540071 hasConceptScore W2945540071C41895202 @default.
- W2945540071 hasLocation W29455400711 @default.
- W2945540071 hasOpenAccess W2945540071 @default.
- W2945540071 hasPrimaryLocation W29455400711 @default.
- W2945540071 hasRelatedWork W2312116756 @default.
- W2945540071 hasRelatedWork W2362289407 @default.
- W2945540071 hasRelatedWork W2368779261 @default.
- W2945540071 hasRelatedWork W2778699561 @default.
- W2945540071 hasRelatedWork W2794438528 @default.
- W2945540071 hasRelatedWork W2893763841 @default.
- W2945540071 hasRelatedWork W2995996972 @default.
- W2945540071 hasRelatedWork W3107474891 @default.
- W2945540071 hasRelatedWork W3128571556 @default.
- W2945540071 hasRelatedWork W4304891817 @default.
- W2945540071 isParatext "false" @default.
- W2945540071 isRetracted "false" @default.
- W2945540071 magId "2945540071" @default.
- W2945540071 workType "article" @default.