Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043245827> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3043245827 endingPage "15" @default.
- W3043245827 startingPage "1" @default.
- W3043245827 abstract "Generating an Adversarial network (GAN) has shown great development prospects in image generation and semi-supervised learning and has evolved into TripleGAN. However, there are still two problems that need to be solved in Triple-GAN: based on the KL divergence distribution structure, gradients are easy to disappear and training instability occurs. Since Triple-GAN tags the samples manually, the manual marking workload is too large. Marked uneven and so on. This article builds on this improved Triple-GAN model (Improved Triple-GAN), which uses Random Forests to classify real samples, automate tagging of leaf nodes, and use Least Squares Generative Adversarial Networks (LSGAN) ideological structure loss function to avoid gradients disappear. Experiments were performed on the Improved Triple-GAN model and the Triple-GAN model using the MINIST, cifar10 and cifar100 datasets respectively, experiments show that the error rate of generated samples is greatly reduced. At the same time, the classification effect of the data set and the sharpness of the samples are greatly improved. And it has greatly improved the stability of model training and automation of labels." @default.
- W3043245827 created "2020-07-23" @default.
- W3043245827 creator A5032631290 @default.
- W3043245827 creator A5046735380 @default.
- W3043245827 date "2020-01-01" @default.
- W3043245827 modified "2023-09-25" @default.
- W3043245827 title "Classification Algorithm Optimization Based on Triple-GAN" @default.
- W3043245827 cites W1983736598 @default.
- W3043245827 cites W2017100743 @default.
- W3043245827 cites W2432004435 @default.
- W3043245827 cites W2596763562 @default.
- W3043245827 cites W2893749619 @default.
- W3043245827 cites W2911910629 @default.
- W3043245827 cites W2950863313 @default.
- W3043245827 cites W2964201867 @default.
- W3043245827 doi "https://doi.org/10.32604/jai.2020.09738" @default.
- W3043245827 hasPublicationYear "2020" @default.
- W3043245827 type Work @default.
- W3043245827 sameAs 3043245827 @default.
- W3043245827 citedByCount "7" @default.
- W3043245827 countsByYear W30432458272021 @default.
- W3043245827 countsByYear W30432458272022 @default.
- W3043245827 crossrefType "journal-article" @default.
- W3043245827 hasAuthorship W3043245827A5032631290 @default.
- W3043245827 hasAuthorship W3043245827A5046735380 @default.
- W3043245827 hasBestOaLocation W30432458271 @default.
- W3043245827 hasConcept C111919701 @default.
- W3043245827 hasConcept C112972136 @default.
- W3043245827 hasConcept C11413529 @default.
- W3043245827 hasConcept C119857082 @default.
- W3043245827 hasConcept C138885662 @default.
- W3043245827 hasConcept C14036430 @default.
- W3043245827 hasConcept C153180895 @default.
- W3043245827 hasConcept C154945302 @default.
- W3043245827 hasConcept C177264268 @default.
- W3043245827 hasConcept C199360897 @default.
- W3043245827 hasConcept C207390915 @default.
- W3043245827 hasConcept C2778476105 @default.
- W3043245827 hasConcept C41008148 @default.
- W3043245827 hasConcept C41895202 @default.
- W3043245827 hasConcept C78458016 @default.
- W3043245827 hasConcept C86803240 @default.
- W3043245827 hasConceptScore W3043245827C111919701 @default.
- W3043245827 hasConceptScore W3043245827C112972136 @default.
- W3043245827 hasConceptScore W3043245827C11413529 @default.
- W3043245827 hasConceptScore W3043245827C119857082 @default.
- W3043245827 hasConceptScore W3043245827C138885662 @default.
- W3043245827 hasConceptScore W3043245827C14036430 @default.
- W3043245827 hasConceptScore W3043245827C153180895 @default.
- W3043245827 hasConceptScore W3043245827C154945302 @default.
- W3043245827 hasConceptScore W3043245827C177264268 @default.
- W3043245827 hasConceptScore W3043245827C199360897 @default.
- W3043245827 hasConceptScore W3043245827C207390915 @default.
- W3043245827 hasConceptScore W3043245827C2778476105 @default.
- W3043245827 hasConceptScore W3043245827C41008148 @default.
- W3043245827 hasConceptScore W3043245827C41895202 @default.
- W3043245827 hasConceptScore W3043245827C78458016 @default.
- W3043245827 hasConceptScore W3043245827C86803240 @default.
- W3043245827 hasIssue "1" @default.
- W3043245827 hasLocation W30432458271 @default.
- W3043245827 hasOpenAccess W3043245827 @default.
- W3043245827 hasPrimaryLocation W30432458271 @default.
- W3043245827 hasRelatedWork W2039836583 @default.
- W3043245827 hasRelatedWork W2329086085 @default.
- W3043245827 hasRelatedWork W2390710122 @default.
- W3043245827 hasRelatedWork W2392884863 @default.
- W3043245827 hasRelatedWork W2929716001 @default.
- W3043245827 hasRelatedWork W2961085424 @default.
- W3043245827 hasRelatedWork W3008868450 @default.
- W3043245827 hasRelatedWork W3134022218 @default.
- W3043245827 hasRelatedWork W4306674287 @default.
- W3043245827 hasRelatedWork W4224009465 @default.
- W3043245827 hasVolume "2" @default.
- W3043245827 isParatext "false" @default.
- W3043245827 isRetracted "false" @default.
- W3043245827 magId "3043245827" @default.
- W3043245827 workType "article" @default.