FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088973847> ?p ?o ?g. }

• W3088973847 abstract "Semi-Supervised Machine Learning (SSML) algorithms are combinations of unsupervised and supervised learning algorithms. This combination enables SSML algorithms to learn from both labelled and unlabelled data. One of the challenges is identifying the key contributing factors from both kinds of algorithms to the learning performance, in terms of training time, training loss, and accuracy. Previously, researchers have adopted Deep Neural Networks (DNNs) to construct the core learning models of SSML algorithms with improved accuracy. However, there is still a lacks of a systematic study to understand the key contributing factors and their effects. In this paper, we generalize the common components of SSML algorithms from state-of-the-art models (- Model, Temporal Ensembling and Mean-Teacher). We form a conceptual Semi-Supervised Computation Graph (SSCG) to inject different kinds of DNNs to the network classifier component in the computation graph. Such a combination illustrates two major aspects to investigate the effects: (1) parameter updates during the training across labelled and unlabelled data; (2) the ratio of labelled and unlabelled data. We performed 27 experiments with 3 SSML algorithms, 3 DNNs and 3 different ratios of labelled and unlabelled data. Our experimental results demonstrate that parameter updates are a dominating factor to the training loss and the learning precision. The experiments show that training loss is lowered by 6% and precision is increased by 4.21% using shake-shake26 as the network classifier in the SSML algorithm of Mean-Teacher, compared to all other combinations. We also observed a positive correlation with an R score value of 0.69 and the p-value of 0.03887 between the training time and the ratio of labelled to unlabelled data. Introducing more labelled data leads to longer training time, which triggers more parameter updates in back-and forward-propagations." @default.
• W3088973847 created "2020-10-01" @default.
• W3088973847 creator A5032248216 @default.
• W3088973847 creator A5043140119 @default.
• W3088973847 date "2020-07-01" @default.
• W3088973847 modified "2023-09-27" @default.
• W3088973847 title "Evaluation of Parameter Update Effects in Deep Semi-Supervised Learning Algorithms" @default.
• W3088973847 cites W1503398984 @default.
• W3088973847 cites W1677182931 @default.
• W3088973847 cites W1836465849 @default.
• W3088973847 cites W2156909104 @default.
• W3088973847 cites W2168231600 @default.
• W3088973847 cites W2183341477 @default.
• W3088973847 cites W2194775991 @default.
• W3088973847 cites W2331143823 @default.
• W3088973847 cites W2436522418 @default.
• W3088973847 cites W2550375374 @default.
• W3088973847 cites W2576960802 @default.
• W3088973847 cites W2619184049 @default.
• W3088973847 cites W2774000609 @default.
• W3088973847 cites W2962952793 @default.
• W3088973847 cites W2963446712 @default.
• W3088973847 doi "https://doi.org/10.1109/compsac48688.2020.0-221" @default.
• W3088973847 hasPublicationYear "2020" @default.
• W3088973847 type Work @default.
• W3088973847 sameAs 3088973847 @default.
• W3088973847 citedByCount "0" @default.
• W3088973847 crossrefType "proceedings-article" @default.
• W3088973847 hasAuthorship W3088973847A5032248216 @default.
• W3088973847 hasAuthorship W3088973847A5043140119 @default.
• W3088973847 hasConcept C11413529 @default.
• W3088973847 hasConcept C119857082 @default.
• W3088973847 hasConcept C132525143 @default.
• W3088973847 hasConcept C154945302 @default.
• W3088973847 hasConcept C26517878 @default.
• W3088973847 hasConcept C38652104 @default.
• W3088973847 hasConcept C41008148 @default.
• W3088973847 hasConcept C45374587 @default.
• W3088973847 hasConcept C50644808 @default.
• W3088973847 hasConcept C80444323 @default.
• W3088973847 hasConcept C95623464 @default.
• W3088973847 hasConceptScore W3088973847C11413529 @default.
• W3088973847 hasConceptScore W3088973847C119857082 @default.
• W3088973847 hasConceptScore W3088973847C132525143 @default.
• W3088973847 hasConceptScore W3088973847C154945302 @default.
• W3088973847 hasConceptScore W3088973847C26517878 @default.
• W3088973847 hasConceptScore W3088973847C38652104 @default.
• W3088973847 hasConceptScore W3088973847C41008148 @default.
• W3088973847 hasConceptScore W3088973847C45374587 @default.
• W3088973847 hasConceptScore W3088973847C50644808 @default.
• W3088973847 hasConceptScore W3088973847C80444323 @default.
• W3088973847 hasConceptScore W3088973847C95623464 @default.
• W3088973847 hasLocation W30889738471 @default.
• W3088973847 hasOpenAccess W3088973847 @default.
• W3088973847 hasPrimaryLocation W30889738471 @default.
• W3088973847 hasRelatedWork W11389402 @default.
• W3088973847 hasRelatedWork W13426584 @default.
• W3088973847 hasRelatedWork W3540334 @default.
• W3088973847 hasRelatedWork W382276 @default.
• W3088973847 hasRelatedWork W482721 @default.
• W3088973847 hasRelatedWork W6680660 @default.
• W3088973847 hasRelatedWork W8198582 @default.
• W3088973847 hasRelatedWork W9043603 @default.
• W3088973847 hasRelatedWork W9458969 @default.
• W3088973847 hasRelatedWork W2925925 @default.
• W3088973847 isParatext "false" @default.
• W3088973847 isRetracted "false" @default.
• W3088973847 magId "3088973847" @default.
• W3088973847 workType "article" @default.