FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895580425> ?p ?o ?g. }

• W2895580425 endingPage "26" @default.
• W2895580425 startingPage "1" @default.
• W2895580425 abstract "Deep neural network (DNN) accelerators with improved energy and delay are desirable for meeting the requirements of hardware targeted for IoT and edge computing systems. Convolutional neural networks (CoNNs) belong to one of the most popular types of DNN architectures. This article presents the design and evaluation of an accelerator for CoNNs. The system-level architecture is based on mixed-signal, cellular neural networks (CeNNs). Specifically, we present (i) the implementation of different layers, including convolution, ReLU, and pooling, in a CoNN using CeNN, (ii) modified CoNN structures with CeNN-friendly layers to reduce computational overheads typically associated with a CoNN, (iii) a mixed-signal CeNN architecture that performs CoNN computations in the analog and mixed signal domain, and (iv) design space exploration that identifies what CeNN-based algorithm and architectural features fare best compared to existing algorithms and architectures when evaluated over common datasets—MNIST and CIFAR-10. Notably, the proposed approach can lead to 8.7× improvements in energy-delay product (EDP) per digit classification for the MNIST dataset at iso-accuracy when compared with the state-of-the-art DNN engine, while our approach could offer 4.3× improvements in EDP when compared to other network implementations for the CIFAR-10 dataset." @default.
• W2895580425 created "2018-10-12" @default.
• W2895580425 creator A5003032564 @default.
• W2895580425 creator A5004724074 @default.
• W2895580425 creator A5037184528 @default.
• W2895580425 creator A5064738995 @default.
• W2895580425 creator A5070051531 @default.
• W2895580425 creator A5080526846 @default.
• W2895580425 creator A5087244134 @default.
• W2895580425 date "2019-03-26" @default.
• W2895580425 modified "2023-10-16" @default.
• W2895580425 title "A Mixed Signal Architecture for Convolutional Neural Networks" @default.
• W2895580425 cites W1491802337 @default.
• W2895580425 cites W2006654769 @default.
• W2895580425 cites W2014102223 @default.
• W2895580425 cites W2034248562 @default.
• W2895580425 cites W2040475153 @default.
• W2895580425 cites W2056717940 @default.
• W2895580425 cites W2066789378 @default.
• W2895580425 cites W2069345435 @default.
• W2895580425 cites W2087748124 @default.
• W2895580425 cites W2097117768 @default.
• W2895580425 cites W2112796928 @default.
• W2895580425 cites W2117148079 @default.
• W2895580425 cites W2133773098 @default.
• W2895580425 cites W2136318306 @default.
• W2895580425 cites W2143612262 @default.
• W2895580425 cites W2148206069 @default.
• W2895580425 cites W2174613990 @default.
• W2895580425 cites W2414564754 @default.
• W2895580425 cites W2524119748 @default.
• W2895580425 cites W2558350234 @default.
• W2895580425 cites W2588666075 @default.
• W2895580425 cites W2592547566 @default.
• W2895580425 cites W2604319603 @default.
• W2895580425 cites W2606722458 @default.
• W2895580425 cites W2608111952 @default.
• W2895580425 cites W2613205562 @default.
• W2895580425 cites W2725159389 @default.
• W2895580425 cites W2758121337 @default.
• W2895580425 cites W2766447205 @default.
• W2895580425 cites W2773141653 @default.
• W2895580425 cites W2774486139 @default.
• W2895580425 cites W2787759178 @default.
• W2895580425 cites W2792893539 @default.
• W2895580425 cites W2915935370 @default.
• W2895580425 cites W2950656546 @default.
• W2895580425 cites W2963893493 @default.
• W2895580425 cites W4243519499 @default.
• W2895580425 cites W4245199738 @default.
• W2895580425 cites W4251607986 @default.
• W2895580425 doi "https://doi.org/10.1145/3304110" @default.
• W2895580425 hasPublicationYear "2019" @default.
• W2895580425 type Work @default.
• W2895580425 sameAs 2895580425 @default.
• W2895580425 citedByCount "17" @default.
• W2895580425 countsByYear W28955804252019 @default.
• W2895580425 countsByYear W28955804252020 @default.
• W2895580425 countsByYear W28955804252021 @default.
• W2895580425 countsByYear W28955804252022 @default.
• W2895580425 crossrefType "journal-article" @default.
• W2895580425 hasAuthorship W2895580425A5003032564 @default.
• W2895580425 hasAuthorship W2895580425A5004724074 @default.
• W2895580425 hasAuthorship W2895580425A5037184528 @default.
• W2895580425 hasAuthorship W2895580425A5064738995 @default.
• W2895580425 hasAuthorship W2895580425A5070051531 @default.
• W2895580425 hasAuthorship W2895580425A5080526846 @default.
• W2895580425 hasAuthorship W2895580425A5087244134 @default.
• W2895580425 hasBestOaLocation W28955804251 @default.
• W2895580425 hasConcept C104267543 @default.
• W2895580425 hasConcept C113775141 @default.
• W2895580425 hasConcept C11413529 @default.
• W2895580425 hasConcept C118524514 @default.
• W2895580425 hasConcept C149635348 @default.
• W2895580425 hasConcept C154945302 @default.
• W2895580425 hasConcept C190502265 @default.
• W2895580425 hasConcept C2776221188 @default.
• W2895580425 hasConcept C41008148 @default.
• W2895580425 hasConcept C45347329 @default.
• W2895580425 hasConcept C45374587 @default.
• W2895580425 hasConcept C50644808 @default.
• W2895580425 hasConcept C70437156 @default.
• W2895580425 hasConcept C81363708 @default.
• W2895580425 hasConcept C84462506 @default.
• W2895580425 hasConcept C9390403 @default.
• W2895580425 hasConceptScore W2895580425C104267543 @default.
• W2895580425 hasConceptScore W2895580425C113775141 @default.
• W2895580425 hasConceptScore W2895580425C11413529 @default.
• W2895580425 hasConceptScore W2895580425C118524514 @default.
• W2895580425 hasConceptScore W2895580425C149635348 @default.
• W2895580425 hasConceptScore W2895580425C154945302 @default.
• W2895580425 hasConceptScore W2895580425C190502265 @default.
• W2895580425 hasConceptScore W2895580425C2776221188 @default.
• W2895580425 hasConceptScore W2895580425C41008148 @default.
• W2895580425 hasConceptScore W2895580425C45347329 @default.
• W2895580425 hasConceptScore W2895580425C45374587 @default.
• W2895580425 hasConceptScore W2895580425C50644808 @default.
• W2895580425 hasConceptScore W2895580425C70437156 @default.

• next