FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980235527> ?p ?o ?g. }

• W2980235527 endingPage "328" @default.
• W2980235527 startingPage "317" @default.
• W2980235527 abstract "Improving the accuracy of a neural network (NN) usually requires using larger hardware that consumes more energy. However, the error tolerance of NNs and their applications allow approximate computing techniques to be applied to reduce implementation costs. Given that multiplication is the most resource-intensive and power-hungry operation in NNs, more economical approximate multipliers (AMs) can significantly reduce hardware costs. In this article, we show that using AMs can also improve the NN accuracy by introducing noise. We consider two categories of AMs: 1) deliberately designed and 2) Cartesian genetic programing (CGP)-based AMs. The exact multipliers in two representative NNs, a multilayer perceptron (MLP) and a convolutional NN (CNN), are replaced with approximate designs to evaluate their effect on the classification accuracy of the Mixed National Institute of Standards and Technology (MNIST) and Street View House Numbers (SVHN) data sets, respectively. Interestingly, up to 0.63% improvement in the classification accuracy is achieved with reductions of 71.45% and 61.55% in the energy consumption and area, respectively. Finally, the features in an AM are identified that tend to make one design outperform others with respect to NN accuracy. Those features are then used to train a predictor that indicates how well an AM is likely to work in an NN." @default.
• W2980235527 created "2019-10-18" @default.
• W2980235527 creator A5005550142 @default.
• W2980235527 creator A5013568704 @default.
• W2980235527 creator A5055549968 @default.
• W2980235527 creator A5067842678 @default.
• W2980235527 creator A5071584701 @default.
• W2980235527 creator A5086941203 @default.
• W2980235527 date "2020-02-01" @default.
• W2980235527 modified "2023-10-18" @default.
• W2980235527 title "Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers" @default.
• W2980235527 cites W1992348535 @default.
• W2980235527 cites W1998917233 @default.
• W2980235527 cites W2020217519 @default.
• W2980235527 cites W2034581485 @default.
• W2980235527 cites W2056132907 @default.
• W2980235527 cites W2074623298 @default.
• W2980235527 cites W2076063813 @default.
• W2980235527 cites W2082454542 @default.
• W2980235527 cites W2092939357 @default.
• W2980235527 cites W2106484393 @default.
• W2980235527 cites W2111388763 @default.
• W2980235527 cites W2112796928 @default.
• W2980235527 cites W2112882360 @default.
• W2980235527 cites W2121819644 @default.
• W2980235527 cites W2124651102 @default.
• W2980235527 cites W2135089667 @default.
• W2980235527 cites W2143426320 @default.
• W2980235527 cites W2145249131 @default.
• W2980235527 cites W2275115695 @default.
• W2980235527 cites W2289567715 @default.
• W2980235527 cites W2461274627 @default.
• W2980235527 cites W2475884125 @default.
• W2980235527 cites W2533121491 @default.
• W2980235527 cites W2577325230 @default.
• W2980235527 cites W2606722458 @default.
• W2980235527 cites W2612199584 @default.
• W2980235527 cites W2742536119 @default.
• W2980235527 cites W2799283557 @default.
• W2980235527 cites W2844381982 @default.
• W2980235527 cites W2871705258 @default.
• W2980235527 cites W2964057022 @default.
• W2980235527 cites W4236363946 @default.
• W2980235527 doi "https://doi.org/10.1109/tvlsi.2019.2940943" @default.
• W2980235527 hasPublicationYear "2020" @default.
• W2980235527 type Work @default.
• W2980235527 sameAs 2980235527 @default.
• W2980235527 citedByCount "73" @default.
• W2980235527 countsByYear W29802355272012 @default.
• W2980235527 countsByYear W29802355272020 @default.
• W2980235527 countsByYear W29802355272021 @default.
• W2980235527 countsByYear W29802355272022 @default.
• W2980235527 countsByYear W29802355272023 @default.
• W2980235527 crossrefType "journal-article" @default.
• W2980235527 hasAuthorship W2980235527A5005550142 @default.
• W2980235527 hasAuthorship W2980235527A5013568704 @default.
• W2980235527 hasAuthorship W2980235527A5055549968 @default.
• W2980235527 hasAuthorship W2980235527A5067842678 @default.
• W2980235527 hasAuthorship W2980235527A5071584701 @default.
• W2980235527 hasAuthorship W2980235527A5086941203 @default.
• W2980235527 hasConcept C113775141 @default.
• W2980235527 hasConcept C114614502 @default.
• W2980235527 hasConcept C115961682 @default.
• W2980235527 hasConcept C119599485 @default.
• W2980235527 hasConcept C119857082 @default.
• W2980235527 hasConcept C127413603 @default.
• W2980235527 hasConcept C154945302 @default.
• W2980235527 hasConcept C179717631 @default.
• W2980235527 hasConcept C190502265 @default.
• W2980235527 hasConcept C2742236 @default.
• W2980235527 hasConcept C2780595030 @default.
• W2980235527 hasConcept C33923547 @default.
• W2980235527 hasConcept C41008148 @default.
• W2980235527 hasConcept C50644808 @default.
• W2980235527 hasConcept C81363708 @default.
• W2980235527 hasConcept C99498987 @default.
• W2980235527 hasConceptScore W2980235527C113775141 @default.
• W2980235527 hasConceptScore W2980235527C114614502 @default.
• W2980235527 hasConceptScore W2980235527C115961682 @default.
• W2980235527 hasConceptScore W2980235527C119599485 @default.
• W2980235527 hasConceptScore W2980235527C119857082 @default.
• W2980235527 hasConceptScore W2980235527C127413603 @default.
• W2980235527 hasConceptScore W2980235527C154945302 @default.
• W2980235527 hasConceptScore W2980235527C179717631 @default.
• W2980235527 hasConceptScore W2980235527C190502265 @default.
• W2980235527 hasConceptScore W2980235527C2742236 @default.
• W2980235527 hasConceptScore W2980235527C2780595030 @default.
• W2980235527 hasConceptScore W2980235527C33923547 @default.
• W2980235527 hasConceptScore W2980235527C41008148 @default.
• W2980235527 hasConceptScore W2980235527C50644808 @default.
• W2980235527 hasConceptScore W2980235527C81363708 @default.
• W2980235527 hasConceptScore W2980235527C99498987 @default.
• W2980235527 hasFunder F4320334593 @default.
• W2980235527 hasIssue "2" @default.
• W2980235527 hasLocation W29802355271 @default.
• W2980235527 hasOpenAccess W2980235527 @default.
• W2980235527 hasPrimaryLocation W29802355271 @default.
• W2980235527 hasRelatedWork W2529764055 @default.

• next