Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210515523> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4210515523 endingPage "379" @default.
- W4210515523 startingPage "365" @default.
- W4210515523 abstract "AbstractWe propose a semi-supervised learning strategy for deep Convolutional Neural Networks (CNNs) in which an unsupervised pre-training stage, performed using biologically inspired Hebbian learning algorithms, is followed by supervised end-to-end backprop fine-tuning. We explored two Hebbian learning rules for the unsupervised pre-training stage: soft-Winner-Takes-All (soft-WTA) and nonlinear Hebbian Principal Component Analysis (HPCA). Our approach was applied in sample efficiency scenarios, where the amount of available labeled training samples is very limited, and unsupervised pre-training is therefore beneficial. We performed experiments on CIFAR10, CIFAR100, and Tiny ImageNet datasets. Our results show that Hebbian outperforms Variational Auto-Encoder (VAE) pre-training in almost all the cases, with HPCA generally performing better than soft-WTA.KeywordsHebbian learningDeep learningSemi-supervisedSample efficiencyNeural networksBio-inspired" @default.
- W4210515523 created "2022-02-08" @default.
- W4210515523 creator A5025605185 @default.
- W4210515523 creator A5047189288 @default.
- W4210515523 creator A5072396889 @default.
- W4210515523 creator A5072879702 @default.
- W4210515523 date "2022-01-01" @default.
- W4210515523 modified "2023-09-27" @default.
- W4210515523 title "Evaluating Hebbian Learning in a Semi-supervised Setting" @default.
- W4210515523 cites W1967011375 @default.
- W4210515523 cites W1984121966 @default.
- W4210515523 cites W2056415038 @default.
- W4210515523 cites W2100543212 @default.
- W4210515523 cites W2131329059 @default.
- W4210515523 cites W2145889472 @default.
- W4210515523 cites W2160921898 @default.
- W4210515523 cites W2162737890 @default.
- W4210515523 cites W2194775991 @default.
- W4210515523 cites W2257979135 @default.
- W4210515523 cites W2263039277 @default.
- W4210515523 cites W2407712691 @default.
- W4210515523 cites W2766363025 @default.
- W4210515523 cites W2810701348 @default.
- W4210515523 cites W2972047812 @default.
- W4210515523 cites W2979805229 @default.
- W4210515523 cites W3010448671 @default.
- W4210515523 cites W3049227448 @default.
- W4210515523 cites W3091880370 @default.
- W4210515523 cites W3102303919 @default.
- W4210515523 cites W4238614602 @default.
- W4210515523 cites W4255229883 @default.
- W4210515523 cites W4296916076 @default.
- W4210515523 doi "https://doi.org/10.1007/978-3-030-95470-3_28" @default.
- W4210515523 hasPublicationYear "2022" @default.
- W4210515523 type Work @default.
- W4210515523 citedByCount "2" @default.
- W4210515523 countsByYear W42105155232022 @default.
- W4210515523 crossrefType "book-chapter" @default.
- W4210515523 hasAuthorship W4210515523A5025605185 @default.
- W4210515523 hasAuthorship W4210515523A5047189288 @default.
- W4210515523 hasAuthorship W4210515523A5072396889 @default.
- W4210515523 hasAuthorship W4210515523A5072879702 @default.
- W4210515523 hasBestOaLocation W42105155232 @default.
- W4210515523 hasConcept C111437709 @default.
- W4210515523 hasConcept C117765406 @default.
- W4210515523 hasConcept C119857082 @default.
- W4210515523 hasConcept C136389625 @default.
- W4210515523 hasConcept C153180895 @default.
- W4210515523 hasConcept C154945302 @default.
- W4210515523 hasConcept C17061570 @default.
- W4210515523 hasConcept C41008148 @default.
- W4210515523 hasConcept C50644808 @default.
- W4210515523 hasConcept C8038995 @default.
- W4210515523 hasConcept C81363708 @default.
- W4210515523 hasConcept C97108695 @default.
- W4210515523 hasConceptScore W4210515523C111437709 @default.
- W4210515523 hasConceptScore W4210515523C117765406 @default.
- W4210515523 hasConceptScore W4210515523C119857082 @default.
- W4210515523 hasConceptScore W4210515523C136389625 @default.
- W4210515523 hasConceptScore W4210515523C153180895 @default.
- W4210515523 hasConceptScore W4210515523C154945302 @default.
- W4210515523 hasConceptScore W4210515523C17061570 @default.
- W4210515523 hasConceptScore W4210515523C41008148 @default.
- W4210515523 hasConceptScore W4210515523C50644808 @default.
- W4210515523 hasConceptScore W4210515523C8038995 @default.
- W4210515523 hasConceptScore W4210515523C81363708 @default.
- W4210515523 hasConceptScore W4210515523C97108695 @default.
- W4210515523 hasLocation W42105155231 @default.
- W4210515523 hasLocation W42105155232 @default.
- W4210515523 hasOpenAccess W4210515523 @default.
- W4210515523 hasPrimaryLocation W42105155231 @default.
- W4210515523 hasRelatedWork W2899454144 @default.
- W4210515523 hasRelatedWork W2986085304 @default.
- W4210515523 hasRelatedWork W3046775127 @default.
- W4210515523 hasRelatedWork W3090869887 @default.
- W4210515523 hasRelatedWork W3094076422 @default.
- W4210515523 hasRelatedWork W3095538999 @default.
- W4210515523 hasRelatedWork W3170950703 @default.
- W4210515523 hasRelatedWork W3210156800 @default.
- W4210515523 hasRelatedWork W4220882831 @default.
- W4210515523 hasRelatedWork W4237783923 @default.
- W4210515523 isParatext "false" @default.
- W4210515523 isRetracted "false" @default.
- W4210515523 workType "book-chapter" @default.