Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295036167> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4295036167 endingPage "540" @default.
- W4295036167 startingPage "534" @default.
- W4295036167 abstract "Herein, we develop a programmable energy-efficient hardware implementation for Recurrent Neural Networks (RNNs) with Resistive Random-Access Memory (ReRAM) synapses and ultra-low power, area-efficient spin-based activation functions. To attain high energy-efficiency while maintaining accuracy, a novel Computing-in-Memory (CiM) architecture is proposed to leverage data-level parallelism during the evaluation phase. We employ an MRAM-based Adjustable Probabilistic Activation Function (APAF) via a low-power tunable activation mechanism, providing adjustable levels of accuracy to mimic ideal sigmoid and tanh thresholding along with a matching algorithm to regulate the neuron properties. Our hardware/software cross-layer simulation shows that our proposed design achieves up to 74.5× energy-efficiency with ∼11× area reduction compared to its counterpart designs while keeping the accuracy comparable." @default.
- W4295036167 created "2022-09-09" @default.
- W4295036167 creator A5051680668 @default.
- W4295036167 creator A5063031794 @default.
- W4295036167 creator A5069017725 @default.
- W4295036167 date "2023-04-01" @default.
- W4295036167 modified "2023-10-11" @default.
- W4295036167 title "Energy-Efficient Recurrent Neural Network With MRAM-Based Probabilistic Activation Functions" @default.
- W4295036167 cites W2004823737 @default.
- W4295036167 cites W2045431893 @default.
- W4295036167 cites W2219959730 @default.
- W4295036167 cites W2331737637 @default.
- W4295036167 cites W2396622873 @default.
- W4295036167 cites W2508602506 @default.
- W4295036167 cites W2556936974 @default.
- W4295036167 cites W2593197369 @default.
- W4295036167 cites W2593865516 @default.
- W4295036167 cites W2594492285 @default.
- W4295036167 cites W2736591611 @default.
- W4295036167 cites W2807384691 @default.
- W4295036167 cites W2811080765 @default.
- W4295036167 cites W2964447465 @default.
- W4295036167 cites W3104804488 @default.
- W4295036167 cites W3195416337 @default.
- W4295036167 doi "https://doi.org/10.1109/tetc.2022.3202112" @default.
- W4295036167 hasPublicationYear "2023" @default.
- W4295036167 type Work @default.
- W4295036167 citedByCount "0" @default.
- W4295036167 crossrefType "journal-article" @default.
- W4295036167 hasAuthorship W4295036167A5051680668 @default.
- W4295036167 hasAuthorship W4295036167A5063031794 @default.
- W4295036167 hasAuthorship W4295036167A5069017725 @default.
- W4295036167 hasConcept C118524514 @default.
- W4295036167 hasConcept C119599485 @default.
- W4295036167 hasConcept C121332964 @default.
- W4295036167 hasConcept C127413603 @default.
- W4295036167 hasConcept C13280743 @default.
- W4295036167 hasConcept C147168706 @default.
- W4295036167 hasConcept C149635348 @default.
- W4295036167 hasConcept C151927369 @default.
- W4295036167 hasConcept C153083717 @default.
- W4295036167 hasConcept C154945302 @default.
- W4295036167 hasConcept C165801399 @default.
- W4295036167 hasConcept C182019814 @default.
- W4295036167 hasConcept C185798385 @default.
- W4295036167 hasConcept C205649164 @default.
- W4295036167 hasConcept C2742236 @default.
- W4295036167 hasConcept C38365724 @default.
- W4295036167 hasConcept C41008148 @default.
- W4295036167 hasConcept C49937458 @default.
- W4295036167 hasConcept C50644808 @default.
- W4295036167 hasConcept C62520636 @default.
- W4295036167 hasConcept C9390403 @default.
- W4295036167 hasConceptScore W4295036167C118524514 @default.
- W4295036167 hasConceptScore W4295036167C119599485 @default.
- W4295036167 hasConceptScore W4295036167C121332964 @default.
- W4295036167 hasConceptScore W4295036167C127413603 @default.
- W4295036167 hasConceptScore W4295036167C13280743 @default.
- W4295036167 hasConceptScore W4295036167C147168706 @default.
- W4295036167 hasConceptScore W4295036167C149635348 @default.
- W4295036167 hasConceptScore W4295036167C151927369 @default.
- W4295036167 hasConceptScore W4295036167C153083717 @default.
- W4295036167 hasConceptScore W4295036167C154945302 @default.
- W4295036167 hasConceptScore W4295036167C165801399 @default.
- W4295036167 hasConceptScore W4295036167C182019814 @default.
- W4295036167 hasConceptScore W4295036167C185798385 @default.
- W4295036167 hasConceptScore W4295036167C205649164 @default.
- W4295036167 hasConceptScore W4295036167C2742236 @default.
- W4295036167 hasConceptScore W4295036167C38365724 @default.
- W4295036167 hasConceptScore W4295036167C41008148 @default.
- W4295036167 hasConceptScore W4295036167C49937458 @default.
- W4295036167 hasConceptScore W4295036167C50644808 @default.
- W4295036167 hasConceptScore W4295036167C62520636 @default.
- W4295036167 hasConceptScore W4295036167C9390403 @default.
- W4295036167 hasIssue "2" @default.
- W4295036167 hasLocation W42950361671 @default.
- W4295036167 hasOpenAccess W4295036167 @default.
- W4295036167 hasPrimaryLocation W42950361671 @default.
- W4295036167 hasRelatedWork W1967489488 @default.
- W4295036167 hasRelatedWork W2785635065 @default.
- W4295036167 hasRelatedWork W2790329865 @default.
- W4295036167 hasRelatedWork W2793181810 @default.
- W4295036167 hasRelatedWork W2806638311 @default.
- W4295036167 hasRelatedWork W2891417865 @default.
- W4295036167 hasRelatedWork W2893723691 @default.
- W4295036167 hasRelatedWork W2912892722 @default.
- W4295036167 hasRelatedWork W3104237246 @default.
- W4295036167 hasRelatedWork W4386475142 @default.
- W4295036167 hasVolume "11" @default.
- W4295036167 isParatext "false" @default.
- W4295036167 isRetracted "false" @default.
- W4295036167 workType "article" @default.