Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990380762> ?p ?o ?g. }
- W2990380762 endingPage "187" @default.
- W2990380762 startingPage "182" @default.
- W2990380762 abstract "Analog electronic nonvolatile memories mimicking synaptic operations are being explored for the implementation of neuromorphic computing systems. Compound synapses consisting of ensembles of stochastic binary elements are alternatives to analog memory synapses to achieve multilevel memory operation. Among the existing binary memory technologies, magnetic tunneling junction (MTJ)-based magnetic random access memory (MRAM) technology has matured to the point of commercialization. More importantly for this work, stochasticity is natural to the MTJ switching physics, e.g., devices referred to as p-bits that mimic binary stochastic neurons. In this article, we experimentally demonstrate a novel compound synapse that uses stochastic spin–orbit-torque (SOT) switching of an ensemble of nanomagnets that are located on one shared spin Hall effect (SHE) material channel, i.e., tantalum. By using a properly chosen pulse scheme, we are able to demonstrate linear potentiation and depression in the synapse, as required for many neuromorphic architectures. In addition to this experimental effort, we also performed circuit simulations on an SOT-MRAM-based $784times 200times 10$ deep belief network (DBN) consisting of p-bit-based neurons and compound synapses. MNIST pattern recognition was used to evaluate the system performance, and our findings indicate that a significant reduction in recognition error rates can be achieved by improving the linearity of the potentiation and depression curves using an incremental pulse scheme." @default.
- W2990380762 created "2019-12-05" @default.
- W2990380762 creator A5002765080 @default.
- W2990380762 creator A5009261363 @default.
- W2990380762 creator A5069017725 @default.
- W2990380762 creator A5069279125 @default.
- W2990380762 date "2019-12-01" @default.
- W2990380762 modified "2023-10-13" @default.
- W2990380762 title "A Novel Compound Synapse Using Probabilistic Spin–Orbit-Torque Switching for MTJ-Based Deep Neural Networks" @default.
- W2990380762 cites W1497334427 @default.
- W2990380762 cites W1979879449 @default.
- W2990380762 cites W2010052203 @default.
- W2990380762 cites W2014744284 @default.
- W2990380762 cites W2040687898 @default.
- W2990380762 cites W2088797290 @default.
- W2990380762 cites W2112796928 @default.
- W2990380762 cites W2403784446 @default.
- W2990380762 cites W2461533533 @default.
- W2990380762 cites W2584998015 @default.
- W2990380762 cites W2742177062 @default.
- W2990380762 cites W2766775637 @default.
- W2990380762 cites W2785141883 @default.
- W2990380762 cites W2787453651 @default.
- W2990380762 cites W2796301411 @default.
- W2990380762 cites W2810376858 @default.
- W2990380762 cites W2894572679 @default.
- W2990380762 cites W2903012893 @default.
- W2990380762 cites W2912664664 @default.
- W2990380762 cites W2922523256 @default.
- W2990380762 cites W2963166057 @default.
- W2990380762 cites W3125659218 @default.
- W2990380762 cites W811376922 @default.
- W2990380762 doi "https://doi.org/10.1109/jxcdc.2019.2956468" @default.
- W2990380762 hasPublicationYear "2019" @default.
- W2990380762 type Work @default.
- W2990380762 sameAs 2990380762 @default.
- W2990380762 citedByCount "22" @default.
- W2990380762 countsByYear W29903807622019 @default.
- W2990380762 countsByYear W29903807622020 @default.
- W2990380762 countsByYear W29903807622021 @default.
- W2990380762 countsByYear W29903807622022 @default.
- W2990380762 countsByYear W29903807622023 @default.
- W2990380762 crossrefType "journal-article" @default.
- W2990380762 hasAuthorship W2990380762A5002765080 @default.
- W2990380762 hasAuthorship W2990380762A5009261363 @default.
- W2990380762 hasAuthorship W2990380762A5069017725 @default.
- W2990380762 hasAuthorship W2990380762A5069279125 @default.
- W2990380762 hasBestOaLocation W29903807621 @default.
- W2990380762 hasConcept C121332964 @default.
- W2990380762 hasConcept C127413603 @default.
- W2990380762 hasConcept C127445978 @default.
- W2990380762 hasConcept C144171764 @default.
- W2990380762 hasConcept C146978453 @default.
- W2990380762 hasConcept C154945302 @default.
- W2990380762 hasConcept C15744967 @default.
- W2990380762 hasConcept C169760540 @default.
- W2990380762 hasConcept C192562407 @default.
- W2990380762 hasConcept C196644772 @default.
- W2990380762 hasConcept C26873012 @default.
- W2990380762 hasConcept C41008148 @default.
- W2990380762 hasConcept C49937458 @default.
- W2990380762 hasConcept C50644808 @default.
- W2990380762 hasConcept C62520636 @default.
- W2990380762 hasConceptScore W2990380762C121332964 @default.
- W2990380762 hasConceptScore W2990380762C127413603 @default.
- W2990380762 hasConceptScore W2990380762C127445978 @default.
- W2990380762 hasConceptScore W2990380762C144171764 @default.
- W2990380762 hasConceptScore W2990380762C146978453 @default.
- W2990380762 hasConceptScore W2990380762C154945302 @default.
- W2990380762 hasConceptScore W2990380762C15744967 @default.
- W2990380762 hasConceptScore W2990380762C169760540 @default.
- W2990380762 hasConceptScore W2990380762C192562407 @default.
- W2990380762 hasConceptScore W2990380762C196644772 @default.
- W2990380762 hasConceptScore W2990380762C26873012 @default.
- W2990380762 hasConceptScore W2990380762C41008148 @default.
- W2990380762 hasConceptScore W2990380762C49937458 @default.
- W2990380762 hasConceptScore W2990380762C50644808 @default.
- W2990380762 hasConceptScore W2990380762C62520636 @default.
- W2990380762 hasIssue "2" @default.
- W2990380762 hasLocation W29903807621 @default.
- W2990380762 hasLocation W29903807622 @default.
- W2990380762 hasLocation W29903807623 @default.
- W2990380762 hasOpenAccess W2990380762 @default.
- W2990380762 hasPrimaryLocation W29903807621 @default.
- W2990380762 hasRelatedWork W1575659177 @default.
- W2990380762 hasRelatedWork W1603968847 @default.
- W2990380762 hasRelatedWork W1980456323 @default.
- W2990380762 hasRelatedWork W2131674028 @default.
- W2990380762 hasRelatedWork W2386387936 @default.
- W2990380762 hasRelatedWork W2417250347 @default.
- W2990380762 hasRelatedWork W2486701004 @default.
- W2990380762 hasRelatedWork W2899084033 @default.
- W2990380762 hasRelatedWork W2911738912 @default.
- W2990380762 hasRelatedWork W4290792893 @default.
- W2990380762 hasVolume "5" @default.
- W2990380762 isParatext "false" @default.
- W2990380762 isRetracted "false" @default.
- W2990380762 magId "2990380762" @default.