Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209739718> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3209739718 abstract "The energy consumption associated with data movement between memory and processing units is the main roadblock for the massive deployment of edge Artificial Intelligence. To overcome this challenge, Binarized Neural Networks (BNN) coupled with RRAM-based in- or near-memory computing constitute an appealing solution. However, proposals from the literature tend to involve significant periphery circuit overheads. In this work, we propose and demonstrate experimentally, on a fabricated hybrid CMOS-RRAM integrated circuit, a robust in-memory XOR operation based on a 2 <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$T$</tex> 2R cell used in a resistive bridge manner. With this architecture, the RRAM read operation and the BNN multiplication operation can be achieved simultaneously, requiring only inverters connected to each Source Line of the memory array, and the BNN POPCOUNT operation can be realized with an analog capacitive neuron. Based on our measurements and extensive Monte Carlo simulations, we validate that this approach is suitable for large neurons with a low error rate (3.12% of error considering the full range of POPCOUNT values). Based on the circuit simulation results, we highlight the resilience of this approach at the network level, with a minimal accuracy degradation on the MNIST (0.07 <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>%</sup> ) and CIFAR-10 (0.35%) tasks with regards to software solutions." @default.
- W3209739718 created "2021-11-08" @default.
- W3209739718 creator A5025225758 @default.
- W3209739718 creator A5027738561 @default.
- W3209739718 creator A5032162752 @default.
- W3209739718 creator A5049000221 @default.
- W3209739718 creator A5053227652 @default.
- W3209739718 creator A5063819347 @default.
- W3209739718 creator A5069215871 @default.
- W3209739718 creator A5083078831 @default.
- W3209739718 date "2021-09-13" @default.
- W3209739718 modified "2023-09-24" @default.
- W3209739718 title "Low-Overhead Implementation of Binarized Neural Networks Employing Robust 2T2R Resistive RAM Bridges" @default.
- W3209739718 cites W1999085092 @default.
- W3209739718 cites W2788013190 @default.
- W3209739718 cites W2912358078 @default.
- W3209739718 cites W2920326572 @default.
- W3209739718 cites W2921329602 @default.
- W3209739718 doi "https://doi.org/10.1109/esscirc53450.2021.9567742" @default.
- W3209739718 hasPublicationYear "2021" @default.
- W3209739718 type Work @default.
- W3209739718 sameAs 3209739718 @default.
- W3209739718 citedByCount "3" @default.
- W3209739718 countsByYear W32097397182022 @default.
- W3209739718 countsByYear W32097397182023 @default.
- W3209739718 crossrefType "proceedings-article" @default.
- W3209739718 hasAuthorship W3209739718A5025225758 @default.
- W3209739718 hasAuthorship W3209739718A5027738561 @default.
- W3209739718 hasAuthorship W3209739718A5032162752 @default.
- W3209739718 hasAuthorship W3209739718A5049000221 @default.
- W3209739718 hasAuthorship W3209739718A5053227652 @default.
- W3209739718 hasAuthorship W3209739718A5063819347 @default.
- W3209739718 hasAuthorship W3209739718A5069215871 @default.
- W3209739718 hasAuthorship W3209739718A5083078831 @default.
- W3209739718 hasBestOaLocation W32097397182 @default.
- W3209739718 hasConcept C111919701 @default.
- W3209739718 hasConcept C113775141 @default.
- W3209739718 hasConcept C119599485 @default.
- W3209739718 hasConcept C127413603 @default.
- W3209739718 hasConcept C154945302 @default.
- W3209739718 hasConcept C165801399 @default.
- W3209739718 hasConcept C182019814 @default.
- W3209739718 hasConcept C190502265 @default.
- W3209739718 hasConcept C2779960059 @default.
- W3209739718 hasConcept C2780971903 @default.
- W3209739718 hasConcept C41008148 @default.
- W3209739718 hasConcept C50644808 @default.
- W3209739718 hasConcept C9390403 @default.
- W3209739718 hasConceptScore W3209739718C111919701 @default.
- W3209739718 hasConceptScore W3209739718C113775141 @default.
- W3209739718 hasConceptScore W3209739718C119599485 @default.
- W3209739718 hasConceptScore W3209739718C127413603 @default.
- W3209739718 hasConceptScore W3209739718C154945302 @default.
- W3209739718 hasConceptScore W3209739718C165801399 @default.
- W3209739718 hasConceptScore W3209739718C182019814 @default.
- W3209739718 hasConceptScore W3209739718C190502265 @default.
- W3209739718 hasConceptScore W3209739718C2779960059 @default.
- W3209739718 hasConceptScore W3209739718C2780971903 @default.
- W3209739718 hasConceptScore W3209739718C41008148 @default.
- W3209739718 hasConceptScore W3209739718C50644808 @default.
- W3209739718 hasConceptScore W3209739718C9390403 @default.
- W3209739718 hasFunder F4320338335 @default.
- W3209739718 hasLocation W32097397181 @default.
- W3209739718 hasLocation W32097397182 @default.
- W3209739718 hasLocation W32097397183 @default.
- W3209739718 hasLocation W32097397184 @default.
- W3209739718 hasLocation W32097397185 @default.
- W3209739718 hasOpenAccess W3209739718 @default.
- W3209739718 hasPrimaryLocation W32097397181 @default.
- W3209739718 hasRelatedWork W2792016738 @default.
- W3209739718 hasRelatedWork W2951280857 @default.
- W3209739718 hasRelatedWork W2966504439 @default.
- W3209739718 hasRelatedWork W3006566323 @default.
- W3209739718 hasRelatedWork W3104287241 @default.
- W3209739718 hasRelatedWork W4236949603 @default.
- W3209739718 hasRelatedWork W4245795187 @default.
- W3209739718 hasRelatedWork W4283781448 @default.
- W3209739718 hasRelatedWork W4285409154 @default.
- W3209739718 hasRelatedWork W4286799979 @default.
- W3209739718 isParatext "false" @default.
- W3209739718 isRetracted "false" @default.
- W3209739718 magId "3209739718" @default.
- W3209739718 workType "article" @default.