Matches in SemOpenAlex for { <https://semopenalex.org/work/W3163156747> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3163156747 abstract "Summary form only given, as follows. A complete record of the panel discussion was not made available for publication as part of the conference proceedings. Deep leaning algorithms are resource-demanding. This talk will present techniques to reduce the computation recourse, human resource, and data resource for deep learning. First, I’ll present MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the light-weight inference engine (TinyEngine), enabling ImageNet-scale inference on tiny MCUs that has only 256KB SRAM and 1MB Flash. Next, I’ll present Once-for-All Network a push-the-button solution that can automatically design specialized neural network architectures that best fit many different hardware platforms, which is the winning solution for the 3rd/4th/5th IEEE Low Power Computer Vision Challenge. Finally, I’ll present DiffAugment for data-efficient GAN training, which greatly reduces the training data and can generate high-fidelity images using only training 100 images. I’ll conclude by discussing the applications of these efficient techniques on AIoT, automotive and data center applications." @default.
- W3163156747 created "2021-05-24" @default.
- W3163156747 creator A5070926896 @default.
- W3163156747 date "2021-04-19" @default.
- W3163156747 modified "2023-09-23" @default.
- W3163156747 title "Putting AI on Diet: TinyML and Efficient Deep Learning" @default.
- W3163156747 doi "https://doi.org/10.1109/vlsi-dat52063.2021.9427348" @default.
- W3163156747 hasPublicationYear "2021" @default.
- W3163156747 type Work @default.
- W3163156747 sameAs 3163156747 @default.
- W3163156747 citedByCount "2" @default.
- W3163156747 countsByYear W31631567472021 @default.
- W3163156747 countsByYear W31631567472022 @default.
- W3163156747 crossrefType "proceedings-article" @default.
- W3163156747 hasAuthorship W3163156747A5070926896 @default.
- W3163156747 hasConcept C108583219 @default.
- W3163156747 hasConcept C113775141 @default.
- W3163156747 hasConcept C118524514 @default.
- W3163156747 hasConcept C119857082 @default.
- W3163156747 hasConcept C149635348 @default.
- W3163156747 hasConcept C154945302 @default.
- W3163156747 hasConcept C199360897 @default.
- W3163156747 hasConcept C206345919 @default.
- W3163156747 hasConcept C2776214188 @default.
- W3163156747 hasConcept C2776459999 @default.
- W3163156747 hasConcept C2984842247 @default.
- W3163156747 hasConcept C31258907 @default.
- W3163156747 hasConcept C41008148 @default.
- W3163156747 hasConcept C45374587 @default.
- W3163156747 hasConcept C46743427 @default.
- W3163156747 hasConcept C50644808 @default.
- W3163156747 hasConcept C76155785 @default.
- W3163156747 hasConceptScore W3163156747C108583219 @default.
- W3163156747 hasConceptScore W3163156747C113775141 @default.
- W3163156747 hasConceptScore W3163156747C118524514 @default.
- W3163156747 hasConceptScore W3163156747C119857082 @default.
- W3163156747 hasConceptScore W3163156747C149635348 @default.
- W3163156747 hasConceptScore W3163156747C154945302 @default.
- W3163156747 hasConceptScore W3163156747C199360897 @default.
- W3163156747 hasConceptScore W3163156747C206345919 @default.
- W3163156747 hasConceptScore W3163156747C2776214188 @default.
- W3163156747 hasConceptScore W3163156747C2776459999 @default.
- W3163156747 hasConceptScore W3163156747C2984842247 @default.
- W3163156747 hasConceptScore W3163156747C31258907 @default.
- W3163156747 hasConceptScore W3163156747C41008148 @default.
- W3163156747 hasConceptScore W3163156747C45374587 @default.
- W3163156747 hasConceptScore W3163156747C46743427 @default.
- W3163156747 hasConceptScore W3163156747C50644808 @default.
- W3163156747 hasConceptScore W3163156747C76155785 @default.
- W3163156747 hasLocation W31631567471 @default.
- W3163156747 hasOpenAccess W3163156747 @default.
- W3163156747 hasPrimaryLocation W31631567471 @default.
- W3163156747 hasRelatedWork W10202958 @default.
- W3163156747 hasRelatedWork W12793662 @default.
- W3163156747 hasRelatedWork W13678974 @default.
- W3163156747 hasRelatedWork W13846533 @default.
- W3163156747 hasRelatedWork W6468916 @default.
- W3163156747 hasRelatedWork W7303821 @default.
- W3163156747 hasRelatedWork W8021486 @default.
- W3163156747 hasRelatedWork W9190101 @default.
- W3163156747 hasRelatedWork W9333608 @default.
- W3163156747 hasRelatedWork W6364452 @default.
- W3163156747 isParatext "false" @default.
- W3163156747 isRetracted "false" @default.
- W3163156747 magId "3163156747" @default.
- W3163156747 workType "article" @default.