Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912093838> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2912093838 abstract "A semi-supervised learning framework using the feedforward-designed convolutional neural networks (FF-CNNs) is proposed for image classification in this work. One unique property of FF-CNNs is that no backpropagation is used in model parameters determination. Since unlabeled data may not always enhance semi-supervised learning, we define an effective quality score and use it to select a subset of unlabeled data in the training process. We conduct experiments on the MNIST, SVHN, and CIFAR-10 datasets, and show that the proposed semi-supervised FF-CNN solution outperforms the CNN trained by backpropagation (BP-CNN) when the amount of labeled data is reduced. Furthermore, we develop an ensemble system that combines the output decision vectors of different semi-supervised FF-CNNs to boost classification accuracy. The ensemble systems can achieve further performance gains on all three benchmarking datasets." @default.
- W2912093838 created "2019-02-21" @default.
- W2912093838 creator A5009039461 @default.
- W2912093838 creator A5018408927 @default.
- W2912093838 creator A5029626801 @default.
- W2912093838 creator A5053204257 @default.
- W2912093838 date "2019-02-05" @default.
- W2912093838 modified "2023-09-27" @default.
- W2912093838 title "Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks" @default.
- W2912093838 cites W1630959083 @default.
- W2912093838 cites W2048679005 @default.
- W2912093838 cites W2061526129 @default.
- W2912093838 cites W2079057609 @default.
- W2912093838 cites W2107008379 @default.
- W2912093838 cites W2107167693 @default.
- W2912093838 cites W2108501770 @default.
- W2912093838 cites W2112796928 @default.
- W2912093838 cites W2115629999 @default.
- W2912093838 cites W2136504847 @default.
- W2912093838 cites W2167055186 @default.
- W2912093838 cites W2311440533 @default.
- W2912093838 cites W2335728318 @default.
- W2912093838 cites W2519796145 @default.
- W2912093838 cites W2608422103 @default.
- W2912093838 cites W2766695926 @default.
- W2912093838 cites W2910090831 @default.
- W2912093838 cites W2949474319 @default.
- W2912093838 cites W2951308125 @default.
- W2912093838 cites W2962690605 @default.
- W2912093838 cites W2963170156 @default.
- W2912093838 cites W2963373786 @default.
- W2912093838 cites W3118608800 @default.
- W2912093838 cites W613690151 @default.
- W2912093838 doi "https://doi.org/10.48550/arxiv.1902.01980" @default.
- W2912093838 hasPublicationYear "2019" @default.
- W2912093838 type Work @default.
- W2912093838 sameAs 2912093838 @default.
- W2912093838 citedByCount "0" @default.
- W2912093838 crossrefType "posted-content" @default.
- W2912093838 hasAuthorship W2912093838A5009039461 @default.
- W2912093838 hasAuthorship W2912093838A5018408927 @default.
- W2912093838 hasAuthorship W2912093838A5029626801 @default.
- W2912093838 hasAuthorship W2912093838A5053204257 @default.
- W2912093838 hasBestOaLocation W29120938381 @default.
- W2912093838 hasConcept C111919701 @default.
- W2912093838 hasConcept C119857082 @default.
- W2912093838 hasConcept C127413603 @default.
- W2912093838 hasConcept C133731056 @default.
- W2912093838 hasConcept C136389625 @default.
- W2912093838 hasConcept C144133560 @default.
- W2912093838 hasConcept C153180895 @default.
- W2912093838 hasConcept C154945302 @default.
- W2912093838 hasConcept C155032097 @default.
- W2912093838 hasConcept C162853370 @default.
- W2912093838 hasConcept C190502265 @default.
- W2912093838 hasConcept C38858127 @default.
- W2912093838 hasConcept C41008148 @default.
- W2912093838 hasConcept C50644808 @default.
- W2912093838 hasConcept C81363708 @default.
- W2912093838 hasConcept C86251818 @default.
- W2912093838 hasConcept C98045186 @default.
- W2912093838 hasConceptScore W2912093838C111919701 @default.
- W2912093838 hasConceptScore W2912093838C119857082 @default.
- W2912093838 hasConceptScore W2912093838C127413603 @default.
- W2912093838 hasConceptScore W2912093838C133731056 @default.
- W2912093838 hasConceptScore W2912093838C136389625 @default.
- W2912093838 hasConceptScore W2912093838C144133560 @default.
- W2912093838 hasConceptScore W2912093838C153180895 @default.
- W2912093838 hasConceptScore W2912093838C154945302 @default.
- W2912093838 hasConceptScore W2912093838C155032097 @default.
- W2912093838 hasConceptScore W2912093838C162853370 @default.
- W2912093838 hasConceptScore W2912093838C190502265 @default.
- W2912093838 hasConceptScore W2912093838C38858127 @default.
- W2912093838 hasConceptScore W2912093838C41008148 @default.
- W2912093838 hasConceptScore W2912093838C50644808 @default.
- W2912093838 hasConceptScore W2912093838C81363708 @default.
- W2912093838 hasConceptScore W2912093838C86251818 @default.
- W2912093838 hasConceptScore W2912093838C98045186 @default.
- W2912093838 hasLocation W29120938381 @default.
- W2912093838 hasLocation W29120938382 @default.
- W2912093838 hasOpenAccess W2912093838 @default.
- W2912093838 hasPrimaryLocation W29120938381 @default.
- W2912093838 hasRelatedWork W1604847762 @default.
- W2912093838 hasRelatedWork W2529764055 @default.
- W2912093838 hasRelatedWork W2810865670 @default.
- W2912093838 hasRelatedWork W2901435809 @default.
- W2912093838 hasRelatedWork W2913749182 @default.
- W2912093838 hasRelatedWork W3027997911 @default.
- W2912093838 hasRelatedWork W3156786002 @default.
- W2912093838 hasRelatedWork W3208266890 @default.
- W2912093838 hasRelatedWork W4200076245 @default.
- W2912093838 hasRelatedWork W4287776258 @default.
- W2912093838 isParatext "false" @default.
- W2912093838 isRetracted "false" @default.
- W2912093838 magId "2912093838" @default.
- W2912093838 workType "article" @default.