Matches in SemOpenAlex for { <https://semopenalex.org/work/W2080451019> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2080451019 abstract "The artificial neural network (ANN) is among the most widely used methods in data processing applications. The memristor-based neural network further demonstrates a power efficient hardware realization of ANN. Training phase is the critical operation of memristor-based neural network. However, the traditional training method for memristor-based neural network is time consuming and energy inefficient. Users have to first work out the parameters of memristors through digital computing systems and then tune the memristor to the corresponding state. In this work, we introduce a mixed-signal training acceleration framework, which realizes the self-training of memristor-based neural network. We first modify the original stochastic gradient descent algorithm by approximating calculations and designing an alternative computing method. We then propose a mixed-signal acceleration architecture for the modified training algorithm by equipping the original memristor-based neural network architecture with the copy crossbar technique, weight update units, sign calculation units and other assistant units. The experiment on the MNIST database demonstrates that the proposed mixed-signal acceleration is 3 orders of magnitude faster and 4 orders of magnitude more energy efficient than the CPU implementation counterpart at the cost of a slight decrease of the recognition accuracy (<; 5%)." @default.
- W2080451019 created "2016-06-24" @default.
- W2080451019 creator A5034029120 @default.
- W2080451019 creator A5058073627 @default.
- W2080451019 creator A5059222136 @default.
- W2080451019 creator A5079594267 @default.
- W2080451019 creator A5085347958 @default.
- W2080451019 date "2014-01-01" @default.
- W2080451019 modified "2023-09-23" @default.
- W2080451019 title "Training itself: Mixed-signal training acceleration for memristor-based neural network" @default.
- W2080451019 cites W1976075132 @default.
- W2080451019 cites W1980147176 @default.
- W2080451019 cites W1997611279 @default.
- W2080451019 cites W1998876510 @default.
- W2080451019 cites W2009464942 @default.
- W2080451019 cites W2028673792 @default.
- W2080451019 cites W2086672837 @default.
- W2080451019 cites W2094621017 @default.
- W2080451019 cites W2100495367 @default.
- W2080451019 cites W2112181056 @default.
- W2080451019 cites W2187230075 @default.
- W2080451019 doi "https://doi.org/10.1109/aspdac.2014.6742916" @default.
- W2080451019 hasPublicationYear "2014" @default.
- W2080451019 type Work @default.
- W2080451019 sameAs 2080451019 @default.
- W2080451019 citedByCount "67" @default.
- W2080451019 countsByYear W20804510192014 @default.
- W2080451019 countsByYear W20804510192015 @default.
- W2080451019 countsByYear W20804510192016 @default.
- W2080451019 countsByYear W20804510192017 @default.
- W2080451019 countsByYear W20804510192018 @default.
- W2080451019 countsByYear W20804510192019 @default.
- W2080451019 countsByYear W20804510192020 @default.
- W2080451019 countsByYear W20804510192021 @default.
- W2080451019 countsByYear W20804510192023 @default.
- W2080451019 crossrefType "proceedings-article" @default.
- W2080451019 hasAuthorship W2080451019A5034029120 @default.
- W2080451019 hasAuthorship W2080451019A5058073627 @default.
- W2080451019 hasAuthorship W2080451019A5059222136 @default.
- W2080451019 hasAuthorship W2080451019A5079594267 @default.
- W2080451019 hasAuthorship W2080451019A5085347958 @default.
- W2080451019 hasConcept C113775141 @default.
- W2080451019 hasConcept C117896860 @default.
- W2080451019 hasConcept C119599485 @default.
- W2080451019 hasConcept C121332964 @default.
- W2080451019 hasConcept C127413603 @default.
- W2080451019 hasConcept C150072547 @default.
- W2080451019 hasConcept C153258448 @default.
- W2080451019 hasConcept C154945302 @default.
- W2080451019 hasConcept C165801399 @default.
- W2080451019 hasConcept C182019814 @default.
- W2080451019 hasConcept C1895703 @default.
- W2080451019 hasConcept C190502265 @default.
- W2080451019 hasConcept C199360897 @default.
- W2080451019 hasConcept C24326235 @default.
- W2080451019 hasConcept C2779843651 @default.
- W2080451019 hasConcept C41008148 @default.
- W2080451019 hasConcept C50644808 @default.
- W2080451019 hasConcept C74650414 @default.
- W2080451019 hasConceptScore W2080451019C113775141 @default.
- W2080451019 hasConceptScore W2080451019C117896860 @default.
- W2080451019 hasConceptScore W2080451019C119599485 @default.
- W2080451019 hasConceptScore W2080451019C121332964 @default.
- W2080451019 hasConceptScore W2080451019C127413603 @default.
- W2080451019 hasConceptScore W2080451019C150072547 @default.
- W2080451019 hasConceptScore W2080451019C153258448 @default.
- W2080451019 hasConceptScore W2080451019C154945302 @default.
- W2080451019 hasConceptScore W2080451019C165801399 @default.
- W2080451019 hasConceptScore W2080451019C182019814 @default.
- W2080451019 hasConceptScore W2080451019C1895703 @default.
- W2080451019 hasConceptScore W2080451019C190502265 @default.
- W2080451019 hasConceptScore W2080451019C199360897 @default.
- W2080451019 hasConceptScore W2080451019C24326235 @default.
- W2080451019 hasConceptScore W2080451019C2779843651 @default.
- W2080451019 hasConceptScore W2080451019C41008148 @default.
- W2080451019 hasConceptScore W2080451019C50644808 @default.
- W2080451019 hasConceptScore W2080451019C74650414 @default.
- W2080451019 hasLocation W20804510191 @default.
- W2080451019 hasOpenAccess W2080451019 @default.
- W2080451019 hasPrimaryLocation W20804510191 @default.
- W2080451019 hasRelatedWork W1567000137 @default.
- W2080451019 hasRelatedWork W1968537616 @default.
- W2080451019 hasRelatedWork W2794822538 @default.
- W2080451019 hasRelatedWork W2942746354 @default.
- W2080451019 hasRelatedWork W2951280857 @default.
- W2080451019 hasRelatedWork W2996014398 @default.
- W2080451019 hasRelatedWork W3022712343 @default.
- W2080451019 hasRelatedWork W3208436135 @default.
- W2080451019 hasRelatedWork W4308413551 @default.
- W2080451019 hasRelatedWork W4313854508 @default.
- W2080451019 isParatext "false" @default.
- W2080451019 isRetracted "false" @default.
- W2080451019 magId "2080451019" @default.
- W2080451019 workType "article" @default.