FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208493659> ?p ?o ?g. }

• W3208493659 endingPage "104359" @default.
• W3208493659 startingPage "104359" @default.
• W3208493659 abstract "Binarized neural networks, or BNNs, show great promise in edge-side applications with resource limited hardware, but raise the concerns of reduced accuracy. Motivated by the complex neural networks, in this paper we introduce complex representation into the BNNs and propose Binary complex neural network – a novel network design that processes binary complex inputs and weights through complex convolution, but still can harvest the extraordinary computation efficiency of BNNs. To ensure fast convergence rate, we propose novel BCNN based batch normalization and weight initialization strategies. Experimental results on image and radio signal classifications show that BCNN can achieve better accuracy compared to the original BNN models. BCNN improves BNN by strengthening its learning capability through complex representation and extending its applicability to complex-valued input data. Our code is available at https://github.com/flying-Yan/BCNN." @default.
• W3208493659 created "2021-11-08" @default.
• W3208493659 creator A5035885712 @default.
• W3208493659 creator A5059605240 @default.
• W3208493659 creator A5060138777 @default.
• W3208493659 creator A5078443672 @default.
• W3208493659 date "2021-11-01" @default.
• W3208493659 modified "2023-10-09" @default.
• W3208493659 title "BCNN: Binary complex neural network" @default.
• W3208493659 cites W1528288284 @default.
• W3208493659 cites W1677182931 @default.
• W3208493659 cites W2010961394 @default.
• W3208493659 cites W2037095848 @default.
• W3208493659 cites W2058399474 @default.
• W3208493659 cites W2059860225 @default.
• W3208493659 cites W2113058706 @default.
• W3208493659 cites W2127497238 @default.
• W3208493659 cites W2135858797 @default.
• W3208493659 cites W2143572124 @default.
• W3208493659 cites W2164177859 @default.
• W3208493659 cites W2165491005 @default.
• W3208493659 cites W2194775991 @default.
• W3208493659 cites W2604700561 @default.
• W3208493659 cites W2773170971 @default.
• W3208493659 cites W2810566158 @default.
• W3208493659 cites W2812373594 @default.
• W3208493659 cites W2852179785 @default.
• W3208493659 cites W2887447938 @default.
• W3208493659 cites W2949744956 @default.
• W3208493659 cites W2952797486 @default.
• W3208493659 cites W2963446712 @default.
• W3208493659 cites W2963673089 @default.
• W3208493659 cites W2970691381 @default.
• W3208493659 cites W2971595222 @default.
• W3208493659 cites W2981819390 @default.
• W3208493659 cites W2989067579 @default.
• W3208493659 cites W3004715589 @default.
• W3208493659 cites W3008515144 @default.
• W3208493659 cites W3034297393 @default.
• W3208493659 cites W3034344052 @default.
• W3208493659 cites W3040090953 @default.
• W3208493659 cites W3047345547 @default.
• W3208493659 cites W3102169921 @default.
• W3208493659 cites W3117765988 @default.
• W3208493659 cites W3120586104 @default.
• W3208493659 cites W3126842106 @default.
• W3208493659 doi "https://doi.org/10.1016/j.micpro.2021.104359" @default.
• W3208493659 hasPublicationYear "2021" @default.
• W3208493659 type Work @default.
• W3208493659 sameAs 3208493659 @default.
• W3208493659 citedByCount "4" @default.
• W3208493659 countsByYear W32084936592021 @default.
• W3208493659 countsByYear W32084936592022 @default.
• W3208493659 countsByYear W32084936592023 @default.
• W3208493659 crossrefType "journal-article" @default.
• W3208493659 hasAuthorship W3208493659A5035885712 @default.
• W3208493659 hasAuthorship W3208493659A5059605240 @default.
• W3208493659 hasAuthorship W3208493659A5060138777 @default.
• W3208493659 hasAuthorship W3208493659A5078443672 @default.
• W3208493659 hasBestOaLocation W32084936592 @default.
• W3208493659 hasConcept C11413529 @default.
• W3208493659 hasConcept C114466953 @default.
• W3208493659 hasConcept C119857082 @default.
• W3208493659 hasConcept C136764020 @default.
• W3208493659 hasConcept C136886441 @default.
• W3208493659 hasConcept C144024400 @default.
• W3208493659 hasConcept C154945302 @default.
• W3208493659 hasConcept C162307627 @default.
• W3208493659 hasConcept C177264268 @default.
• W3208493659 hasConcept C17744445 @default.
• W3208493659 hasConcept C19165224 @default.
• W3208493659 hasConcept C199360897 @default.
• W3208493659 hasConcept C199539241 @default.
• W3208493659 hasConcept C2776359362 @default.
• W3208493659 hasConcept C2776760102 @default.
• W3208493659 hasConcept C33923547 @default.
• W3208493659 hasConcept C34947359 @default.
• W3208493659 hasConcept C41008148 @default.
• W3208493659 hasConcept C45347329 @default.
• W3208493659 hasConcept C45374587 @default.
• W3208493659 hasConcept C47822265 @default.
• W3208493659 hasConcept C48372109 @default.
• W3208493659 hasConcept C50644808 @default.
• W3208493659 hasConcept C80444323 @default.
• W3208493659 hasConcept C94375191 @default.
• W3208493659 hasConcept C94625758 @default.
• W3208493659 hasConceptScore W3208493659C11413529 @default.
• W3208493659 hasConceptScore W3208493659C114466953 @default.
• W3208493659 hasConceptScore W3208493659C119857082 @default.
• W3208493659 hasConceptScore W3208493659C136764020 @default.
• W3208493659 hasConceptScore W3208493659C136886441 @default.
• W3208493659 hasConceptScore W3208493659C144024400 @default.
• W3208493659 hasConceptScore W3208493659C154945302 @default.
• W3208493659 hasConceptScore W3208493659C162307627 @default.
• W3208493659 hasConceptScore W3208493659C177264268 @default.
• W3208493659 hasConceptScore W3208493659C17744445 @default.
• W3208493659 hasConceptScore W3208493659C19165224 @default.
• W3208493659 hasConceptScore W3208493659C199360897 @default.

• next