Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213324488> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3213324488 abstract "Microcontroller Units (MCUs) are widely used for industrial field applications, and are now ever more being used also for machine learning on the edge, because of their reliability, low cost, and energy efficiency. Due to the MCU resource limitations, the deployed ML models need to be optimized particularly in terms of memory footprint. In this paper, we propose an in-place computation strategy to reduce memory requirements of neural network inference. The strategy exploits the MCU single-core architecture, with sequential execution. Experimental analysis using the CMSIS-NN library on the CIFAE-10 dataset shows that the proposed optimization method can reduce the memory required by a NN model by more than 9%, without impacting the execution performance nor accuracy. The amount of reduction further increases with deeper network architectures." @default.
- W3213324488 created "2021-11-22" @default.
- W3213324488 creator A5002561390 @default.
- W3213324488 creator A5011105820 @default.
- W3213324488 creator A5029949770 @default.
- W3213324488 creator A5056890512 @default.
- W3213324488 creator A5082344846 @default.
- W3213324488 date "2021-08-01" @default.
- W3213324488 modified "2023-09-27" @default.
- W3213324488 title "Memory-Efficient CMSIS-NN with Replacement Strategy" @default.
- W3213324488 cites W2155893237 @default.
- W3213324488 cites W2809254203 @default.
- W3213324488 cites W2985361718 @default.
- W3213324488 cites W3021575660 @default.
- W3213324488 cites W3038988173 @default.
- W3213324488 doi "https://doi.org/10.1109/ficloud49777.2021.00050" @default.
- W3213324488 hasPublicationYear "2021" @default.
- W3213324488 type Work @default.
- W3213324488 sameAs 3213324488 @default.
- W3213324488 citedByCount "4" @default.
- W3213324488 countsByYear W32133244882022 @default.
- W3213324488 crossrefType "proceedings-article" @default.
- W3213324488 hasAuthorship W3213324488A5002561390 @default.
- W3213324488 hasAuthorship W3213324488A5011105820 @default.
- W3213324488 hasAuthorship W3213324488A5029949770 @default.
- W3213324488 hasAuthorship W3213324488A5056890512 @default.
- W3213324488 hasAuthorship W3213324488A5082344846 @default.
- W3213324488 hasBestOaLocation W32133244882 @default.
- W3213324488 hasConcept C111335779 @default.
- W3213324488 hasConcept C111919701 @default.
- W3213324488 hasConcept C113775141 @default.
- W3213324488 hasConcept C11413529 @default.
- W3213324488 hasConcept C121332964 @default.
- W3213324488 hasConcept C132943942 @default.
- W3213324488 hasConcept C149635348 @default.
- W3213324488 hasConcept C151730666 @default.
- W3213324488 hasConcept C154945302 @default.
- W3213324488 hasConcept C162307627 @default.
- W3213324488 hasConcept C163258240 @default.
- W3213324488 hasConcept C165696696 @default.
- W3213324488 hasConcept C173018170 @default.
- W3213324488 hasConcept C202444582 @default.
- W3213324488 hasConcept C2524010 @default.
- W3213324488 hasConcept C2776214188 @default.
- W3213324488 hasConcept C33923547 @default.
- W3213324488 hasConcept C38652104 @default.
- W3213324488 hasConcept C41008148 @default.
- W3213324488 hasConcept C43214815 @default.
- W3213324488 hasConcept C45374587 @default.
- W3213324488 hasConcept C50644808 @default.
- W3213324488 hasConcept C62520636 @default.
- W3213324488 hasConcept C74912251 @default.
- W3213324488 hasConcept C86803240 @default.
- W3213324488 hasConcept C9652623 @default.
- W3213324488 hasConceptScore W3213324488C111335779 @default.
- W3213324488 hasConceptScore W3213324488C111919701 @default.
- W3213324488 hasConceptScore W3213324488C113775141 @default.
- W3213324488 hasConceptScore W3213324488C11413529 @default.
- W3213324488 hasConceptScore W3213324488C121332964 @default.
- W3213324488 hasConceptScore W3213324488C132943942 @default.
- W3213324488 hasConceptScore W3213324488C149635348 @default.
- W3213324488 hasConceptScore W3213324488C151730666 @default.
- W3213324488 hasConceptScore W3213324488C154945302 @default.
- W3213324488 hasConceptScore W3213324488C162307627 @default.
- W3213324488 hasConceptScore W3213324488C163258240 @default.
- W3213324488 hasConceptScore W3213324488C165696696 @default.
- W3213324488 hasConceptScore W3213324488C173018170 @default.
- W3213324488 hasConceptScore W3213324488C202444582 @default.
- W3213324488 hasConceptScore W3213324488C2524010 @default.
- W3213324488 hasConceptScore W3213324488C2776214188 @default.
- W3213324488 hasConceptScore W3213324488C33923547 @default.
- W3213324488 hasConceptScore W3213324488C38652104 @default.
- W3213324488 hasConceptScore W3213324488C41008148 @default.
- W3213324488 hasConceptScore W3213324488C43214815 @default.
- W3213324488 hasConceptScore W3213324488C45374587 @default.
- W3213324488 hasConceptScore W3213324488C50644808 @default.
- W3213324488 hasConceptScore W3213324488C62520636 @default.
- W3213324488 hasConceptScore W3213324488C74912251 @default.
- W3213324488 hasConceptScore W3213324488C86803240 @default.
- W3213324488 hasConceptScore W3213324488C9652623 @default.
- W3213324488 hasLocation W32133244881 @default.
- W3213324488 hasLocation W32133244882 @default.
- W3213324488 hasOpenAccess W3213324488 @default.
- W3213324488 hasPrimaryLocation W32133244881 @default.
- W3213324488 hasRelatedWork W1531523799 @default.
- W3213324488 hasRelatedWork W2077517968 @default.
- W3213324488 hasRelatedWork W2748075515 @default.
- W3213324488 hasRelatedWork W2753893836 @default.
- W3213324488 hasRelatedWork W2989484458 @default.
- W3213324488 hasRelatedWork W3212071806 @default.
- W3213324488 hasRelatedWork W3213324488 @default.
- W3213324488 hasRelatedWork W4224213347 @default.
- W3213324488 hasRelatedWork W4293057825 @default.
- W3213324488 hasRelatedWork W2140048163 @default.
- W3213324488 isParatext "false" @default.
- W3213324488 isRetracted "false" @default.
- W3213324488 magId "3213324488" @default.
- W3213324488 workType "article" @default.