FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295308271> ?p ?o ?g. }

• W4295308271 endingPage "1503" @default.
• W4295308271 startingPage "1490" @default.
• W4295308271 abstract "Neuromorphic computation-in-memory fabric based on emerging nonvolatile memories considered an attractive option to accelerate neural networks (NNs) in hardware as they provide high-performance, low-power, and reduced data movement. Although nonvolatile resistive memories (NVMs) offer many benefits, they are susceptible to data retention faults, where previously stored data are not retained after a certain amount of time due to external influence. These faults are more likely to happen unidirectional and severely impact the inference accuracy of the hardware implementation of NNs since the synaptic weights stored in the NVMs are subject to retention faults. In this work, we propose an approximate scrubbing technique for NVM-based neuromorphic fabric to mitigate unidirectional retention faults with virtually zero storage overhead depending on the definition of scrub area for multilayer perceptron (MLP) and convolutional NNs (CNNs). The training of the NNs is adjusted accordingly to meet the requirements of the proposed approximate scrubbing scheme. On different benchmarks, the proposed scrubbing approach can improve the inference accuracy up to 85.51% for MLP and 87.76% for CNN over the expected device operational time with negligible storage overhead." @default.
• W4295308271 created "2022-09-12" @default.
• W4295308271 creator A5030858550 @default.
• W4295308271 creator A5038362728 @default.
• W4295308271 creator A5045076645 @default.
• W4295308271 creator A5064445713 @default.
• W4295308271 date "2023-05-01" @default.
• W4295308271 modified "2023-10-15" @default.
• W4295308271 title "NeuroScrub+: Mitigating Retention Faults Using Flexible Approximate Scrubbing in Neuromorphic Fabric Based on Resistive Memories" @default.
• W4295308271 cites W1578894366 @default.
• W4295308271 cites W1677182931 @default.
• W4295308271 cites W1697514837 @default.
• W4295308271 cites W1976075132 @default.
• W4295308271 cites W1984987219 @default.
• W4295308271 cites W1996443105 @default.
• W4295308271 cites W2000716942 @default.
• W4295308271 cites W2010202670 @default.
• W4295308271 cites W2010216838 @default.
• W4295308271 cites W2022034350 @default.
• W4295308271 cites W2033811947 @default.
• W4295308271 cites W2042076387 @default.
• W4295308271 cites W2047797144 @default.
• W4295308271 cites W2117100053 @default.
• W4295308271 cites W2118803816 @default.
• W4295308271 cites W2119092821 @default.
• W4295308271 cites W2138384063 @default.
• W4295308271 cites W2300242332 @default.
• W4295308271 cites W2337180699 @default.
• W4295308271 cites W2398563917 @default.
• W4295308271 cites W2498844334 @default.
• W4295308271 cites W2526202524 @default.
• W4295308271 cites W2588666075 @default.
• W4295308271 cites W2606722458 @default.
• W4295308271 cites W2750962247 @default.
• W4295308271 cites W2769831305 @default.
• W4295308271 cites W2773498542 @default.
• W4295308271 cites W2785141883 @default.
• W4295308271 cites W2798554798 @default.
• W4295308271 cites W2894678934 @default.
• W4295308271 cites W2895842071 @default.
• W4295308271 cites W2908661440 @default.
• W4295308271 cites W3013186618 @default.
• W4295308271 cites W3033667356 @default.
• W4295308271 cites W3139448463 @default.
• W4295308271 cites W3152241699 @default.
• W4295308271 cites W3175897766 @default.
• W4295308271 cites W4239237187 @default.
• W4295308271 cites W4242612726 @default.
• W4295308271 doi "https://doi.org/10.1109/tcad.2022.3205872" @default.
• W4295308271 hasPublicationYear "2023" @default.
• W4295308271 type Work @default.
• W4295308271 citedByCount "1" @default.
• W4295308271 countsByYear W42953082712023 @default.
• W4295308271 crossrefType "journal-article" @default.
• W4295308271 hasAuthorship W4295308271A5030858550 @default.
• W4295308271 hasAuthorship W4295308271A5038362728 @default.
• W4295308271 hasAuthorship W4295308271A5045076645 @default.
• W4295308271 hasAuthorship W4295308271A5064445713 @default.
• W4295308271 hasConcept C111919701 @default.
• W4295308271 hasConcept C149635348 @default.
• W4295308271 hasConcept C151927369 @default.
• W4295308271 hasConcept C154945302 @default.
• W4295308271 hasConcept C177950962 @default.
• W4295308271 hasConcept C2776214188 @default.
• W4295308271 hasConcept C2779960059 @default.
• W4295308271 hasConcept C2780866740 @default.
• W4295308271 hasConcept C38652104 @default.
• W4295308271 hasConcept C41008148 @default.
• W4295308271 hasConcept C50644808 @default.
• W4295308271 hasConcept C60908668 @default.
• W4295308271 hasConcept C6899612 @default.
• W4295308271 hasConcept C81363708 @default.
• W4295308271 hasConcept C89529581 @default.
• W4295308271 hasConcept C9390403 @default.
• W4295308271 hasConceptScore W4295308271C111919701 @default.
• W4295308271 hasConceptScore W4295308271C149635348 @default.
• W4295308271 hasConceptScore W4295308271C151927369 @default.
• W4295308271 hasConceptScore W4295308271C154945302 @default.
• W4295308271 hasConceptScore W4295308271C177950962 @default.
• W4295308271 hasConceptScore W4295308271C2776214188 @default.
• W4295308271 hasConceptScore W4295308271C2779960059 @default.
• W4295308271 hasConceptScore W4295308271C2780866740 @default.
• W4295308271 hasConceptScore W4295308271C38652104 @default.
• W4295308271 hasConceptScore W4295308271C41008148 @default.
• W4295308271 hasConceptScore W4295308271C50644808 @default.
• W4295308271 hasConceptScore W4295308271C60908668 @default.
• W4295308271 hasConceptScore W4295308271C6899612 @default.
• W4295308271 hasConceptScore W4295308271C81363708 @default.
• W4295308271 hasConceptScore W4295308271C89529581 @default.
• W4295308271 hasConceptScore W4295308271C9390403 @default.
• W4295308271 hasFunder F4320320879 @default.
• W4295308271 hasIssue "5" @default.
• W4295308271 hasLocation W42953082711 @default.
• W4295308271 hasOpenAccess W4295308271 @default.
• W4295308271 hasPrimaryLocation W42953082711 @default.
• W4295308271 hasRelatedWork W2607188927 @default.
• W4295308271 hasRelatedWork W3132409984 @default.
• W4295308271 hasRelatedWork W3175897766 @default.

• next