Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280493096> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4280493096 abstract "Spiking neural networks (SNNs) recently gained momentum due to their low-power multiplication-free computing and the closer resemblance of biological processes in the nervous system of humans. However, SNNs require very long spike trains (up to 1000) to reach an accuracy similar to their artificial neural network (ANN) counterparts for large models, which offsets efficiency and inhibits its application to low-power systems for real-world use cases. To alleviate this problem, emerging neural encoding schemes are proposed to shorten the spike train while maintaining the high accuracy. However, current accelerators for SNN cannot well support the emerging encoding schemes. In this work, we present a novel hardware architecture that can efficiently support SNN with emerging neural encoding. Our implementation features energy and area efficient processing units with increased parallelism and reduced memory accesses. We verified the accelerator on FPGA and achieve 25% and 90% improvement over previous work in power consumption and latency, respectively. At the same time, high area efficiency allows us to scale for large neural network models. To the best of our knowledge, this is the first work to deploy the large neural network model VGG on physical FPGA-based neuromorphic hardware." @default.
- W4280493096 created "2022-05-22" @default.
- W4280493096 creator A5001599295 @default.
- W4280493096 creator A5003771677 @default.
- W4280493096 creator A5012391877 @default.
- W4280493096 creator A5050174081 @default.
- W4280493096 creator A5068318428 @default.
- W4280493096 date "2022-03-14" @default.
- W4280493096 modified "2023-09-30" @default.
- W4280493096 title "A Resource-efficient Spiking Neural Network Accelerator Supporting Emerging Neural Encoding" @default.
- W4280493096 cites W1666962919 @default.
- W4280493096 cites W2088192327 @default.
- W4280493096 cites W2114691690 @default.
- W4280493096 cites W2124311906 @default.
- W4280493096 cites W2964338223 @default.
- W4280493096 cites W2989431475 @default.
- W4280493096 cites W3033007178 @default.
- W4280493096 cites W3111474787 @default.
- W4280493096 cites W3129643976 @default.
- W4280493096 cites W3205015346 @default.
- W4280493096 cites W3217488171 @default.
- W4280493096 doi "https://doi.org/10.23919/date54114.2022.9774596" @default.
- W4280493096 hasPublicationYear "2022" @default.
- W4280493096 type Work @default.
- W4280493096 citedByCount "1" @default.
- W4280493096 countsByYear W42804930962023 @default.
- W4280493096 crossrefType "proceedings-article" @default.
- W4280493096 hasAuthorship W4280493096A5001599295 @default.
- W4280493096 hasAuthorship W4280493096A5003771677 @default.
- W4280493096 hasAuthorship W4280493096A5012391877 @default.
- W4280493096 hasAuthorship W4280493096A5050174081 @default.
- W4280493096 hasAuthorship W4280493096A5068318428 @default.
- W4280493096 hasBestOaLocation W42804930962 @default.
- W4280493096 hasConcept C115903868 @default.
- W4280493096 hasConcept C11731999 @default.
- W4280493096 hasConcept C118524514 @default.
- W4280493096 hasConcept C119599485 @default.
- W4280493096 hasConcept C125411270 @default.
- W4280493096 hasConcept C127413603 @default.
- W4280493096 hasConcept C149635348 @default.
- W4280493096 hasConcept C151927369 @default.
- W4280493096 hasConcept C154945302 @default.
- W4280493096 hasConcept C2742236 @default.
- W4280493096 hasConcept C2781390188 @default.
- W4280493096 hasConcept C41008148 @default.
- W4280493096 hasConcept C42935608 @default.
- W4280493096 hasConcept C50644808 @default.
- W4280493096 hasConceptScore W4280493096C115903868 @default.
- W4280493096 hasConceptScore W4280493096C11731999 @default.
- W4280493096 hasConceptScore W4280493096C118524514 @default.
- W4280493096 hasConceptScore W4280493096C119599485 @default.
- W4280493096 hasConceptScore W4280493096C125411270 @default.
- W4280493096 hasConceptScore W4280493096C127413603 @default.
- W4280493096 hasConceptScore W4280493096C149635348 @default.
- W4280493096 hasConceptScore W4280493096C151927369 @default.
- W4280493096 hasConceptScore W4280493096C154945302 @default.
- W4280493096 hasConceptScore W4280493096C2742236 @default.
- W4280493096 hasConceptScore W4280493096C2781390188 @default.
- W4280493096 hasConceptScore W4280493096C41008148 @default.
- W4280493096 hasConceptScore W4280493096C42935608 @default.
- W4280493096 hasConceptScore W4280493096C50644808 @default.
- W4280493096 hasLocation W42804930961 @default.
- W4280493096 hasLocation W42804930962 @default.
- W4280493096 hasOpenAccess W4280493096 @default.
- W4280493096 hasPrimaryLocation W42804930961 @default.
- W4280493096 hasRelatedWork W1779347319 @default.
- W4280493096 hasRelatedWork W2061056596 @default.
- W4280493096 hasRelatedWork W2793924511 @default.
- W4280493096 hasRelatedWork W2977464668 @default.
- W4280493096 hasRelatedWork W3142384962 @default.
- W4280493096 hasRelatedWork W3158181975 @default.
- W4280493096 hasRelatedWork W4280515050 @default.
- W4280493096 hasRelatedWork W4308575307 @default.
- W4280493096 hasRelatedWork W4313484726 @default.
- W4280493096 hasRelatedWork W4380286407 @default.
- W4280493096 isParatext "false" @default.
- W4280493096 isRetracted "false" @default.
- W4280493096 workType "article" @default.