Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306645249> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4306645249 endingPage "11" @default.
- W4306645249 startingPage "1" @default.
- W4306645249 abstract "Convolutional neural network (CNN) training often necessitates a considerable amount of computational resources. In recent years, several studies have proposed for CNN inference and training accelerators in which the FPGAs have previously demonstrated good performance and energy efficiency. To speed up the processing, CNN requires additional computational resources such as memory bandwidth, a FPGA platform resource usage, time, power consumption, and large datasets for training. They are constrained by the requirement for improved hardware acceleration to support scalability beyond existing data and model sizes. This paper proposes a procedure for energy efficient CNN training in collaboration with an FPGA-based accelerator. We employed optimizations such as quantization, which is a common model compression technique, to speed up the CNN training process. Additionally, a gradient accumulation buffer is used to ensure maximum operating efficiency while maintaining gradient descent of the learning algorithm. To validate the design, we implemented the AlexNet and VGG-16 models on an FPGA board and laptop CPU along side GPU. It achieves 203.75 GOPS on Terasic DE1 SoC with the AlexNet model and 196.50 GOPS with the VGG-16 model on Terasic DE-SoC. Our result also exhibits that the FPGA accelerators are more energy efficient than other platforms." @default.
- W4306645249 created "2022-10-18" @default.
- W4306645249 creator A5006494540 @default.
- W4306645249 creator A5066170203 @default.
- W4306645249 creator A5077844947 @default.
- W4306645249 date "2022-10-17" @default.
- W4306645249 modified "2023-10-02" @default.
- W4306645249 title "Acceleration of Deep Neural Network Training Using Field Programmable Gate Arrays" @default.
- W4306645249 cites W2183341477 @default.
- W4306645249 cites W2616014673 @default.
- W4306645249 cites W2781735277 @default.
- W4306645249 cites W2907463061 @default.
- W4306645249 cites W2907579173 @default.
- W4306645249 cites W2918817571 @default.
- W4306645249 cites W2919512338 @default.
- W4306645249 cites W2997106510 @default.
- W4306645249 doi "https://doi.org/10.1155/2022/8387364" @default.
- W4306645249 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36299439" @default.
- W4306645249 hasPublicationYear "2022" @default.
- W4306645249 type Work @default.
- W4306645249 citedByCount "2" @default.
- W4306645249 countsByYear W43066452492023 @default.
- W4306645249 crossrefType "journal-article" @default.
- W4306645249 hasAuthorship W4306645249A5006494540 @default.
- W4306645249 hasAuthorship W4306645249A5066170203 @default.
- W4306645249 hasAuthorship W4306645249A5077844947 @default.
- W4306645249 hasBestOaLocation W43066452491 @default.
- W4306645249 hasConcept C108583219 @default.
- W4306645249 hasConcept C113775141 @default.
- W4306645249 hasConcept C117896860 @default.
- W4306645249 hasConcept C119599485 @default.
- W4306645249 hasConcept C121332964 @default.
- W4306645249 hasConcept C127413603 @default.
- W4306645249 hasConcept C13164978 @default.
- W4306645249 hasConcept C149635348 @default.
- W4306645249 hasConcept C154945302 @default.
- W4306645249 hasConcept C18903297 @default.
- W4306645249 hasConcept C2742236 @default.
- W4306645249 hasConcept C2780165032 @default.
- W4306645249 hasConcept C41008148 @default.
- W4306645249 hasConcept C42935608 @default.
- W4306645249 hasConcept C48044578 @default.
- W4306645249 hasConcept C50644808 @default.
- W4306645249 hasConcept C74650414 @default.
- W4306645249 hasConcept C77088390 @default.
- W4306645249 hasConcept C81363708 @default.
- W4306645249 hasConcept C86803240 @default.
- W4306645249 hasConcept C9390403 @default.
- W4306645249 hasConceptScore W4306645249C108583219 @default.
- W4306645249 hasConceptScore W4306645249C113775141 @default.
- W4306645249 hasConceptScore W4306645249C117896860 @default.
- W4306645249 hasConceptScore W4306645249C119599485 @default.
- W4306645249 hasConceptScore W4306645249C121332964 @default.
- W4306645249 hasConceptScore W4306645249C127413603 @default.
- W4306645249 hasConceptScore W4306645249C13164978 @default.
- W4306645249 hasConceptScore W4306645249C149635348 @default.
- W4306645249 hasConceptScore W4306645249C154945302 @default.
- W4306645249 hasConceptScore W4306645249C18903297 @default.
- W4306645249 hasConceptScore W4306645249C2742236 @default.
- W4306645249 hasConceptScore W4306645249C2780165032 @default.
- W4306645249 hasConceptScore W4306645249C41008148 @default.
- W4306645249 hasConceptScore W4306645249C42935608 @default.
- W4306645249 hasConceptScore W4306645249C48044578 @default.
- W4306645249 hasConceptScore W4306645249C50644808 @default.
- W4306645249 hasConceptScore W4306645249C74650414 @default.
- W4306645249 hasConceptScore W4306645249C77088390 @default.
- W4306645249 hasConceptScore W4306645249C81363708 @default.
- W4306645249 hasConceptScore W4306645249C86803240 @default.
- W4306645249 hasConceptScore W4306645249C9390403 @default.
- W4306645249 hasLocation W43066452491 @default.
- W4306645249 hasLocation W43066452492 @default.
- W4306645249 hasLocation W43066452493 @default.
- W4306645249 hasLocation W43066452494 @default.
- W4306645249 hasOpenAccess W4306645249 @default.
- W4306645249 hasPrimaryLocation W43066452491 @default.
- W4306645249 hasRelatedWork W2295680811 @default.
- W4306645249 hasRelatedWork W2351404747 @default.
- W4306645249 hasRelatedWork W2731899572 @default.
- W4306645249 hasRelatedWork W2999805992 @default.
- W4306645249 hasRelatedWork W3035319544 @default.
- W4306645249 hasRelatedWork W3116150086 @default.
- W4306645249 hasRelatedWork W3133861977 @default.
- W4306645249 hasRelatedWork W4200173597 @default.
- W4306645249 hasRelatedWork W4312417841 @default.
- W4306645249 hasRelatedWork W4321369474 @default.
- W4306645249 hasVolume "2022" @default.
- W4306645249 isParatext "false" @default.
- W4306645249 isRetracted "false" @default.
- W4306645249 workType "article" @default.