Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285059172> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4285059172 endingPage "482" @default.
- W4285059172 startingPage "473" @default.
- W4285059172 abstract "Hardware acceleration enables neural network (NN) inferencing on edge devices and for high throughput applications. Most approaches use neural processing elements for computation while storing weights in memory blocks. To avoid costly memory access, recent efforts seek direct logic implementation with weights hardwired into the circuit. However, special training strategies are often needed, and they could not maintain accuracy. In contrast, we take a trained and quantized NN as input and synthesize it by Booth encoding and logic sharing, resulting in a hardware accelerator without degrading accuracy. Experiments demonstrate that our method outperforms existing work in area reduction and/or throughput and power efficiency." @default.
- W4285059172 created "2022-07-13" @default.
- W4285059172 creator A5009636531 @default.
- W4285059172 creator A5028097221 @default.
- W4285059172 creator A5078604015 @default.
- W4285059172 date "2023-02-01" @default.
- W4285059172 modified "2023-10-18" @default.
- W4285059172 title "Quantized Neural Network Synthesis for Direct Logic Circuit Implementation" @default.
- W4285059172 cites W2026445983 @default.
- W4285059172 cites W2080090262 @default.
- W4285059172 cites W2194775991 @default.
- W4285059172 cites W2296509296 @default.
- W4285059172 cites W2334853001 @default.
- W4285059172 cites W2891946740 @default.
- W4285059172 cites W2899954960 @default.
- W4285059172 cites W2908561972 @default.
- W4285059172 cites W2949870694 @default.
- W4285059172 cites W2963122961 @default.
- W4285059172 cites W2981240861 @default.
- W4285059172 cites W2981751377 @default.
- W4285059172 cites W3006216178 @default.
- W4285059172 cites W3009849929 @default.
- W4285059172 cites W3027524057 @default.
- W4285059172 cites W3093982621 @default.
- W4285059172 cites W3102169921 @default.
- W4285059172 cites W3159008243 @default.
- W4285059172 cites W3177366646 @default.
- W4285059172 doi "https://doi.org/10.1109/tcad.2022.3183547" @default.
- W4285059172 hasPublicationYear "2023" @default.
- W4285059172 type Work @default.
- W4285059172 citedByCount "0" @default.
- W4285059172 crossrefType "journal-article" @default.
- W4285059172 hasAuthorship W4285059172A5009636531 @default.
- W4285059172 hasAuthorship W4285059172A5028097221 @default.
- W4285059172 hasAuthorship W4285059172A5078604015 @default.
- W4285059172 hasConcept C111335779 @default.
- W4285059172 hasConcept C111919701 @default.
- W4285059172 hasConcept C113775141 @default.
- W4285059172 hasConcept C11413529 @default.
- W4285059172 hasConcept C118524514 @default.
- W4285059172 hasConcept C125411270 @default.
- W4285059172 hasConcept C131017901 @default.
- W4285059172 hasConcept C13164978 @default.
- W4285059172 hasConcept C138236772 @default.
- W4285059172 hasConcept C154945302 @default.
- W4285059172 hasConcept C157764524 @default.
- W4285059172 hasConcept C2524010 @default.
- W4285059172 hasConcept C33923547 @default.
- W4285059172 hasConcept C41008148 @default.
- W4285059172 hasConcept C42935608 @default.
- W4285059172 hasConcept C45374587 @default.
- W4285059172 hasConcept C50644808 @default.
- W4285059172 hasConcept C555944384 @default.
- W4285059172 hasConcept C76155785 @default.
- W4285059172 hasConcept C79974875 @default.
- W4285059172 hasConcept C9390403 @default.
- W4285059172 hasConceptScore W4285059172C111335779 @default.
- W4285059172 hasConceptScore W4285059172C111919701 @default.
- W4285059172 hasConceptScore W4285059172C113775141 @default.
- W4285059172 hasConceptScore W4285059172C11413529 @default.
- W4285059172 hasConceptScore W4285059172C118524514 @default.
- W4285059172 hasConceptScore W4285059172C125411270 @default.
- W4285059172 hasConceptScore W4285059172C131017901 @default.
- W4285059172 hasConceptScore W4285059172C13164978 @default.
- W4285059172 hasConceptScore W4285059172C138236772 @default.
- W4285059172 hasConceptScore W4285059172C154945302 @default.
- W4285059172 hasConceptScore W4285059172C157764524 @default.
- W4285059172 hasConceptScore W4285059172C2524010 @default.
- W4285059172 hasConceptScore W4285059172C33923547 @default.
- W4285059172 hasConceptScore W4285059172C41008148 @default.
- W4285059172 hasConceptScore W4285059172C42935608 @default.
- W4285059172 hasConceptScore W4285059172C45374587 @default.
- W4285059172 hasConceptScore W4285059172C50644808 @default.
- W4285059172 hasConceptScore W4285059172C555944384 @default.
- W4285059172 hasConceptScore W4285059172C76155785 @default.
- W4285059172 hasConceptScore W4285059172C79974875 @default.
- W4285059172 hasConceptScore W4285059172C9390403 @default.
- W4285059172 hasFunder F4320322795 @default.
- W4285059172 hasIssue "2" @default.
- W4285059172 hasLocation W42850591721 @default.
- W4285059172 hasOpenAccess W4285059172 @default.
- W4285059172 hasPrimaryLocation W42850591721 @default.
- W4285059172 hasRelatedWork W2121958647 @default.
- W4285059172 hasRelatedWork W2320205417 @default.
- W4285059172 hasRelatedWork W2352648941 @default.
- W4285059172 hasRelatedWork W2910518169 @default.
- W4285059172 hasRelatedWork W3157721836 @default.
- W4285059172 hasRelatedWork W3214560281 @default.
- W4285059172 hasRelatedWork W3216454443 @default.
- W4285059172 hasRelatedWork W4246896219 @default.
- W4285059172 hasRelatedWork W4292632107 @default.
- W4285059172 hasRelatedWork W4311410588 @default.
- W4285059172 hasVolume "42" @default.
- W4285059172 isParatext "false" @default.
- W4285059172 isRetracted "false" @default.
- W4285059172 workType "article" @default.