Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088098049> ?p ?o ?g. }
- W3088098049 endingPage "12" @default.
- W3088098049 startingPage "1" @default.
- W3088098049 abstract "Magnetic skyrmions are emerging as potential candidates for next generation non-volatile memories. In this paper, we propose an in-memory binary neural network (BNN) accelerator based on the non-volatile skyrmionic memory, which we call as SIMBA. SIMBA consumes 26.7 mJ of energy and 2.7 ms of latency when running an inference on a VGG-like BNN. Furthermore, we demonstrate improvements in the performance of SIMBA by optimizing material parameters such as saturation magnetization, anisotropic energy and damping ratio. Finally, we show that the inference accuracy of BNNs is robust against the possible stochastic behavior of SIMBA (88.5% +/- 1%)." @default.
- W3088098049 created "2020-10-01" @default.
- W3088098049 creator A5036094801 @default.
- W3088098049 creator A5055456290 @default.
- W3088098049 creator A5085588788 @default.
- W3088098049 date "2020-11-01" @default.
- W3088098049 modified "2023-10-14" @default.
- W3088098049 title "SIMBA: A Skyrmionic In-Memory Binary Neural Network Accelerator" @default.
- W3088098049 cites W1975724328 @default.
- W3088098049 cites W1981443800 @default.
- W3088098049 cites W1991395163 @default.
- W3088098049 cites W2010202670 @default.
- W3088098049 cites W2013792423 @default.
- W3088098049 cites W2014744284 @default.
- W3088098049 cites W2034258734 @default.
- W3088098049 cites W2037626369 @default.
- W3088098049 cites W2065991180 @default.
- W3088098049 cites W2079103493 @default.
- W3088098049 cites W2082355550 @default.
- W3088098049 cites W2091773052 @default.
- W3088098049 cites W2093283551 @default.
- W3088098049 cites W2096445739 @default.
- W3088098049 cites W2142805504 @default.
- W3088098049 cites W2508602506 @default.
- W3088098049 cites W2585560244 @default.
- W3088098049 cites W2602380804 @default.
- W3088098049 cites W2742841780 @default.
- W3088098049 cites W2768900401 @default.
- W3088098049 cites W2784141108 @default.
- W3088098049 cites W2803368688 @default.
- W3088098049 cites W2904282303 @default.
- W3088098049 cites W2908156791 @default.
- W3088098049 cites W2915743978 @default.
- W3088098049 cites W2921421881 @default.
- W3088098049 cites W2940840342 @default.
- W3088098049 cites W2941835181 @default.
- W3088098049 cites W2963078171 @default.
- W3088098049 cites W2963602484 @default.
- W3088098049 cites W2969725113 @default.
- W3088098049 cites W3002638775 @default.
- W3088098049 cites W3100100072 @default.
- W3088098049 cites W3100847708 @default.
- W3088098049 cites W3102098294 @default.
- W3088098049 cites W3103699933 @default.
- W3088098049 doi "https://doi.org/10.1109/tmag.2020.3024172" @default.
- W3088098049 hasPublicationYear "2020" @default.
- W3088098049 type Work @default.
- W3088098049 sameAs 3088098049 @default.
- W3088098049 citedByCount "2" @default.
- W3088098049 countsByYear W30880980492022 @default.
- W3088098049 countsByYear W30880980492023 @default.
- W3088098049 crossrefType "journal-article" @default.
- W3088098049 hasAuthorship W3088098049A5036094801 @default.
- W3088098049 hasAuthorship W3088098049A5055456290 @default.
- W3088098049 hasAuthorship W3088098049A5085588788 @default.
- W3088098049 hasBestOaLocation W30880980492 @default.
- W3088098049 hasConcept C114614502 @default.
- W3088098049 hasConcept C121332964 @default.
- W3088098049 hasConcept C154945302 @default.
- W3088098049 hasConcept C26873012 @default.
- W3088098049 hasConcept C2776214188 @default.
- W3088098049 hasConcept C33923547 @default.
- W3088098049 hasConcept C41008148 @default.
- W3088098049 hasConcept C48372109 @default.
- W3088098049 hasConcept C50644808 @default.
- W3088098049 hasConcept C76155785 @default.
- W3088098049 hasConcept C82876162 @default.
- W3088098049 hasConcept C88020606 @default.
- W3088098049 hasConcept C94375191 @default.
- W3088098049 hasConcept C9930424 @default.
- W3088098049 hasConceptScore W3088098049C114614502 @default.
- W3088098049 hasConceptScore W3088098049C121332964 @default.
- W3088098049 hasConceptScore W3088098049C154945302 @default.
- W3088098049 hasConceptScore W3088098049C26873012 @default.
- W3088098049 hasConceptScore W3088098049C2776214188 @default.
- W3088098049 hasConceptScore W3088098049C33923547 @default.
- W3088098049 hasConceptScore W3088098049C41008148 @default.
- W3088098049 hasConceptScore W3088098049C48372109 @default.
- W3088098049 hasConceptScore W3088098049C50644808 @default.
- W3088098049 hasConceptScore W3088098049C76155785 @default.
- W3088098049 hasConceptScore W3088098049C82876162 @default.
- W3088098049 hasConceptScore W3088098049C88020606 @default.
- W3088098049 hasConceptScore W3088098049C94375191 @default.
- W3088098049 hasConceptScore W3088098049C9930424 @default.
- W3088098049 hasFunder F4320320696 @default.
- W3088098049 hasFunder F4320320698 @default.
- W3088098049 hasIssue "11" @default.
- W3088098049 hasLocation W30880980491 @default.
- W3088098049 hasLocation W30880980492 @default.
- W3088098049 hasOpenAccess W3088098049 @default.
- W3088098049 hasPrimaryLocation W30880980491 @default.
- W3088098049 hasRelatedWork W1579157801 @default.
- W3088098049 hasRelatedWork W2027596801 @default.
- W3088098049 hasRelatedWork W2047536660 @default.
- W3088098049 hasRelatedWork W2053929918 @default.
- W3088098049 hasRelatedWork W2069881048 @default.
- W3088098049 hasRelatedWork W2100534810 @default.
- W3088098049 hasRelatedWork W2527563933 @default.