FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970241502> ?p ?o ?g. }

• W2970241502 endingPage "422" @default.
• W2970241502 startingPage "408" @default.
• W2970241502 abstract "A large variety of applications rely on deep learning to process big data, learn sophisticated features, and perform complicated tasks. Utilizing emerging non-volatile memory (NVM)'s unique characteristics, including the crossbar array structure and gray-scale cell resistances, to perform neural network (NN) computation is a well-studied approach in accelerating deep learning applications. Compared to other NVM technologies, STT-MRAM has its unique advantages in performing NN computation. However, the state-of-the-art research have not utilized STT-MRAM for deep learning acceleration due to its device and architecture-level challenges. Consequently, this paper enables STT-MRAM, for the first time, as an effective and practical deep learning accelerator. In particular, it proposes a full-stack framework iCELIA spanning multiple design levels, including device-level fabrication, circuit-level enhancements, architecture-level synaptic weight quantization, and system-level accelerator design. The primary contributions of iCELIA over our prior work CELIA include a new non-uniform weight quantization scheme and much enhanced accelerator system design. The proposed framework significantly mitigates the model accuracy loss due to reduced data precision in a cohesive manner, constructing a comprehensive STT-MRAM accelerator system for fast NN computation with high energy efficiency and low cost." @default.
• W2970241502 created "2019-09-05" @default.
• W2970241502 creator A5047215143 @default.
• W2970241502 creator A5049252927 @default.
• W2970241502 creator A5064737582 @default.
• W2970241502 creator A5065135733 @default.
• W2970241502 creator A5091268132 @default.
• W2970241502 date "2020-02-01" @default.
• W2970241502 modified "2023-10-01" @default.
• W2970241502 title "iCELIA: A Full-Stack Framework for STT-MRAM-Based Deep Learning Acceleration" @default.
• W2970241502 cites W1969349120 @default.
• W2970241502 cites W1976515507 @default.
• W2970241502 cites W2004823737 @default.
• W2970241502 cites W2010202670 @default.
• W2970241502 cites W2014268383 @default.
• W2970241502 cites W2047379549 @default.
• W2970241502 cites W2048266589 @default.
• W2970241502 cites W2060969833 @default.
• W2970241502 cites W2084007230 @default.
• W2970241502 cites W2088797290 @default.
• W2970241502 cites W2102449048 @default.
• W2970241502 cites W2108048675 @default.
• W2970241502 cites W2117539524 @default.
• W2970241502 cites W2147926533 @default.
• W2970241502 cites W2150593711 @default.
• W2970241502 cites W2152839228 @default.
• W2970241502 cites W2155551886 @default.
• W2970241502 cites W2155893237 @default.
• W2970241502 cites W2162639668 @default.
• W2970241502 cites W2276486856 @default.
• W2970241502 cites W2442974303 @default.
• W2970241502 cites W2490216016 @default.
• W2970241502 cites W2507278625 @default.
• W2970241502 cites W2508602506 @default.
• W2970241502 cites W2508890046 @default.
• W2970241502 cites W2518281301 @default.
• W2970241502 cites W2580984468 @default.
• W2970241502 cites W2584580867 @default.
• W2970241502 cites W2604319603 @default.
• W2970241502 cites W2606722458 @default.
• W2970241502 cites W2613168994 @default.
• W2970241502 cites W2613569094 @default.
• W2970241502 cites W2613989746 @default.
• W2970241502 cites W2694935213 @default.
• W2970241502 cites W2760264276 @default.
• W2970241502 cites W2768900401 @default.
• W2970241502 cites W2791559636 @default.
• W2970241502 doi "https://doi.org/10.1109/tpds.2019.2937517" @default.
• W2970241502 hasPublicationYear "2020" @default.
• W2970241502 type Work @default.
• W2970241502 sameAs 2970241502 @default.
• W2970241502 citedByCount "14" @default.
• W2970241502 countsByYear W29702415022020 @default.
• W2970241502 countsByYear W29702415022021 @default.
• W2970241502 countsByYear W29702415022022 @default.
• W2970241502 countsByYear W29702415022023 @default.
• W2970241502 crossrefType "journal-article" @default.
• W2970241502 hasAuthorship W2970241502A5047215143 @default.
• W2970241502 hasAuthorship W2970241502A5049252927 @default.
• W2970241502 hasAuthorship W2970241502A5064737582 @default.
• W2970241502 hasAuthorship W2970241502A5065135733 @default.
• W2970241502 hasAuthorship W2970241502A5091268132 @default.
• W2970241502 hasConcept C108583219 @default.
• W2970241502 hasConcept C113775141 @default.
• W2970241502 hasConcept C11413529 @default.
• W2970241502 hasConcept C118524514 @default.
• W2970241502 hasConcept C119599485 @default.
• W2970241502 hasConcept C127413603 @default.
• W2970241502 hasConcept C13164978 @default.
• W2970241502 hasConcept C149635348 @default.
• W2970241502 hasConcept C154945302 @default.
• W2970241502 hasConcept C199360897 @default.
• W2970241502 hasConcept C2742236 @default.
• W2970241502 hasConcept C28855332 @default.
• W2970241502 hasConcept C2994168587 @default.
• W2970241502 hasConcept C29984679 @default.
• W2970241502 hasConcept C41008148 @default.
• W2970241502 hasConcept C42935608 @default.
• W2970241502 hasConcept C45374587 @default.
• W2970241502 hasConcept C46891859 @default.
• W2970241502 hasConcept C50644808 @default.
• W2970241502 hasConcept C76155785 @default.
• W2970241502 hasConcept C9390403 @default.
• W2970241502 hasConcept C9395851 @default.
• W2970241502 hasConceptScore W2970241502C108583219 @default.
• W2970241502 hasConceptScore W2970241502C113775141 @default.
• W2970241502 hasConceptScore W2970241502C11413529 @default.
• W2970241502 hasConceptScore W2970241502C118524514 @default.
• W2970241502 hasConceptScore W2970241502C119599485 @default.
• W2970241502 hasConceptScore W2970241502C127413603 @default.
• W2970241502 hasConceptScore W2970241502C13164978 @default.
• W2970241502 hasConceptScore W2970241502C149635348 @default.
• W2970241502 hasConceptScore W2970241502C154945302 @default.
• W2970241502 hasConceptScore W2970241502C199360897 @default.
• W2970241502 hasConceptScore W2970241502C2742236 @default.
• W2970241502 hasConceptScore W2970241502C28855332 @default.
• W2970241502 hasConceptScore W2970241502C2994168587 @default.
• W2970241502 hasConceptScore W2970241502C29984679 @default.

• next