Matches in SemOpenAlex for { <https://semopenalex.org/work/W2014307680> ?p ?o ?g. }
- W2014307680 endingPage "281" @default.
- W2014307680 startingPage "270" @default.
- W2014307680 abstract "An analog implementation of a deep machine-learning system for efficient feature extraction is presented in this work. It features online unsupervised trainability and non-volatile floating-gate analog storage. It utilizes a massively parallel reconfigurable current-mode analog architecture to realize efficient computation, and leverages algorithm-level feedback to provide robustness to circuit imperfections in analog signal processing. A 3-layer, 7-node analog deep machine-learning engine was fabricated in a 0.13 μm standard CMOS process, occupying 0.36 mm 2 active area. At a processing speed of 8300 input vectors per second, it consumes 11.4 μW from the 3 V supply, achieving 1×10 12 operation per second per Watt of peak energy efficiency. Measurement demonstrates real-time cluster analysis, and feature extraction for pattern recognition with 8-fold dimension reduction with an accuracy comparable to the floating-point software simulation baseline." @default.
- W2014307680 created "2016-06-24" @default.
- W2014307680 creator A5001161475 @default.
- W2014307680 creator A5029444976 @default.
- W2014307680 creator A5035780973 @default.
- W2014307680 creator A5077738281 @default.
- W2014307680 date "2015-01-01" @default.
- W2014307680 modified "2023-10-17" @default.
- W2014307680 title "A 1 TOPS/W Analog Deep Machine-Learning Engine With Floating-Gate Storage in 0.13 µm CMOS" @default.
- W2014307680 cites W1968745054 @default.
- W2014307680 cites W1991523464 @default.
- W2014307680 cites W1995451961 @default.
- W2014307680 cites W1998399571 @default.
- W2014307680 cites W2035371449 @default.
- W2014307680 cites W2055701312 @default.
- W2014307680 cites W2069363022 @default.
- W2014307680 cites W2077386045 @default.
- W2014307680 cites W2112980946 @default.
- W2014307680 cites W2118216984 @default.
- W2014307680 cites W2120461003 @default.
- W2014307680 cites W2120695048 @default.
- W2014307680 cites W2125010820 @default.
- W2014307680 cites W2140576958 @default.
- W2014307680 cites W2140823559 @default.
- W2014307680 cites W2152244814 @default.
- W2014307680 cites W2153087248 @default.
- W2014307680 cites W2153827622 @default.
- W2014307680 cites W2155295500 @default.
- W2014307680 cites W2160990975 @default.
- W2014307680 cites W2165445079 @default.
- W2014307680 cites W4237171445 @default.
- W2014307680 doi "https://doi.org/10.1109/jssc.2014.2356197" @default.
- W2014307680 hasPublicationYear "2015" @default.
- W2014307680 type Work @default.
- W2014307680 sameAs 2014307680 @default.
- W2014307680 citedByCount "100" @default.
- W2014307680 countsByYear W20143076802014 @default.
- W2014307680 countsByYear W20143076802015 @default.
- W2014307680 countsByYear W20143076802016 @default.
- W2014307680 countsByYear W20143076802017 @default.
- W2014307680 countsByYear W20143076802018 @default.
- W2014307680 countsByYear W20143076802019 @default.
- W2014307680 countsByYear W20143076802020 @default.
- W2014307680 countsByYear W20143076802021 @default.
- W2014307680 countsByYear W20143076802022 @default.
- W2014307680 countsByYear W20143076802023 @default.
- W2014307680 crossrefType "journal-article" @default.
- W2014307680 hasAuthorship W2014307680A5001161475 @default.
- W2014307680 hasAuthorship W2014307680A5029444976 @default.
- W2014307680 hasAuthorship W2014307680A5035780973 @default.
- W2014307680 hasAuthorship W2014307680A5077738281 @default.
- W2014307680 hasBestOaLocation W20143076801 @default.
- W2014307680 hasConcept C104317684 @default.
- W2014307680 hasConcept C11413529 @default.
- W2014307680 hasConcept C115961682 @default.
- W2014307680 hasConcept C119599485 @default.
- W2014307680 hasConcept C127413603 @default.
- W2014307680 hasConcept C13412647 @default.
- W2014307680 hasConcept C134146338 @default.
- W2014307680 hasConcept C154945302 @default.
- W2014307680 hasConcept C185592680 @default.
- W2014307680 hasConcept C193828747 @default.
- W2014307680 hasConcept C24326235 @default.
- W2014307680 hasConcept C28525508 @default.
- W2014307680 hasConcept C29074008 @default.
- W2014307680 hasConcept C379707 @default.
- W2014307680 hasConcept C41008148 @default.
- W2014307680 hasConcept C46362747 @default.
- W2014307680 hasConcept C52622490 @default.
- W2014307680 hasConcept C55493867 @default.
- W2014307680 hasConcept C63479239 @default.
- W2014307680 hasConcept C84211073 @default.
- W2014307680 hasConcept C84462506 @default.
- W2014307680 hasConcept C90915687 @default.
- W2014307680 hasConcept C9390403 @default.
- W2014307680 hasConcept C9417928 @default.
- W2014307680 hasConceptScore W2014307680C104317684 @default.
- W2014307680 hasConceptScore W2014307680C11413529 @default.
- W2014307680 hasConceptScore W2014307680C115961682 @default.
- W2014307680 hasConceptScore W2014307680C119599485 @default.
- W2014307680 hasConceptScore W2014307680C127413603 @default.
- W2014307680 hasConceptScore W2014307680C13412647 @default.
- W2014307680 hasConceptScore W2014307680C134146338 @default.
- W2014307680 hasConceptScore W2014307680C154945302 @default.
- W2014307680 hasConceptScore W2014307680C185592680 @default.
- W2014307680 hasConceptScore W2014307680C193828747 @default.
- W2014307680 hasConceptScore W2014307680C24326235 @default.
- W2014307680 hasConceptScore W2014307680C28525508 @default.
- W2014307680 hasConceptScore W2014307680C29074008 @default.
- W2014307680 hasConceptScore W2014307680C379707 @default.
- W2014307680 hasConceptScore W2014307680C41008148 @default.
- W2014307680 hasConceptScore W2014307680C46362747 @default.
- W2014307680 hasConceptScore W2014307680C52622490 @default.
- W2014307680 hasConceptScore W2014307680C55493867 @default.
- W2014307680 hasConceptScore W2014307680C63479239 @default.
- W2014307680 hasConceptScore W2014307680C84211073 @default.
- W2014307680 hasConceptScore W2014307680C84462506 @default.
- W2014307680 hasConceptScore W2014307680C90915687 @default.