Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225957505> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4225957505 abstract "Compiler frameworks are crucial for the widespread use of FPGA-based deep learning accelerators. They allow researchers and developers, who are not familiar with hardware engineering, to harness the performance attained by domain-specific logic. There exists a variety of frameworks for conventional artificial neural networks. However, not much research effort has been put into the creation of frameworks optimized for spiking neural networks (SNNs). This new generation of neural networks becomes increasingly interesting for the deployment of AI on edge devices, which have tight power and resource constraints. Our end-to-end framework E3NE automates the generation of efficient SNN inference logic for FPGAs. Based on a PyTorch model and user parameters, it applies various optimizations and assesses trade-offs inherent to spike-based accelerators. Multiple levels of parallelism and the use of an emerging neural encoding scheme result in an efficiency superior to previous SNN hardware implementations. For a similar model, E3NE uses less than 50% of hardware resources and 20% less power, while reducing the latency by an order of magnitude. Furthermore, scalability and generality allowed the deployment of the large-scale SNN models AlexNet and VGG." @default.
- W4225957505 created "2022-05-05" @default.
- W4225957505 creator A5001599295 @default.
- W4225957505 creator A5003771677 @default.
- W4225957505 creator A5012391877 @default.
- W4225957505 creator A5033982342 @default.
- W4225957505 creator A5068318428 @default.
- W4225957505 date "2021-11-18" @default.
- W4225957505 modified "2023-09-24" @default.
- W4225957505 title "E3NE: An End-to-End Framework for Accelerating Spiking Neural Networks with Emerging Neural Encoding on FPGAs" @default.
- W4225957505 hasPublicationYear "2021" @default.
- W4225957505 type Work @default.
- W4225957505 citedByCount "0" @default.
- W4225957505 crossrefType "posted-content" @default.
- W4225957505 hasAuthorship W4225957505A5001599295 @default.
- W4225957505 hasAuthorship W4225957505A5003771677 @default.
- W4225957505 hasAuthorship W4225957505A5012391877 @default.
- W4225957505 hasAuthorship W4225957505A5033982342 @default.
- W4225957505 hasAuthorship W4225957505A5068318428 @default.
- W4225957505 hasBestOaLocation W42259575051 @default.
- W4225957505 hasConcept C105339364 @default.
- W4225957505 hasConcept C108583219 @default.
- W4225957505 hasConcept C111919701 @default.
- W4225957505 hasConcept C115903868 @default.
- W4225957505 hasConcept C11731999 @default.
- W4225957505 hasConcept C118524514 @default.
- W4225957505 hasConcept C149635348 @default.
- W4225957505 hasConcept C154945302 @default.
- W4225957505 hasConcept C173608175 @default.
- W4225957505 hasConcept C2776214188 @default.
- W4225957505 hasConcept C41008148 @default.
- W4225957505 hasConcept C42935608 @default.
- W4225957505 hasConcept C48044578 @default.
- W4225957505 hasConcept C50644808 @default.
- W4225957505 hasConceptScore W4225957505C105339364 @default.
- W4225957505 hasConceptScore W4225957505C108583219 @default.
- W4225957505 hasConceptScore W4225957505C111919701 @default.
- W4225957505 hasConceptScore W4225957505C115903868 @default.
- W4225957505 hasConceptScore W4225957505C11731999 @default.
- W4225957505 hasConceptScore W4225957505C118524514 @default.
- W4225957505 hasConceptScore W4225957505C149635348 @default.
- W4225957505 hasConceptScore W4225957505C154945302 @default.
- W4225957505 hasConceptScore W4225957505C173608175 @default.
- W4225957505 hasConceptScore W4225957505C2776214188 @default.
- W4225957505 hasConceptScore W4225957505C41008148 @default.
- W4225957505 hasConceptScore W4225957505C42935608 @default.
- W4225957505 hasConceptScore W4225957505C48044578 @default.
- W4225957505 hasConceptScore W4225957505C50644808 @default.
- W4225957505 hasLocation W42259575051 @default.
- W4225957505 hasOpenAccess W4225957505 @default.
- W4225957505 hasPrimaryLocation W42259575051 @default.
- W4225957505 hasRelatedWork W12103515 @default.
- W4225957505 hasRelatedWork W1347062 @default.
- W4225957505 hasRelatedWork W14855716 @default.
- W4225957505 hasRelatedWork W2339867 @default.
- W4225957505 hasRelatedWork W320786 @default.
- W4225957505 hasRelatedWork W4399642 @default.
- W4225957505 hasRelatedWork W7451177 @default.
- W4225957505 hasRelatedWork W7620075 @default.
- W4225957505 hasRelatedWork W7907410 @default.
- W4225957505 hasRelatedWork W93090 @default.
- W4225957505 isParatext "false" @default.
- W4225957505 isRetracted "false" @default.
- W4225957505 workType "article" @default.