File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Experimental Demonstration of Conversion-Based SNNs with 1T1R Mott Neurons for Neuromorphic Inference

TitleExperimental Demonstration of Conversion-Based SNNs with 1T1R Mott Neurons for Neuromorphic Inference
Authors
Issue Date2019
Citation
Technical Digest - International Electron Devices Meeting, IEDM, 2019, v. 2019-December How to Cite?
Abstract© 2019 IEEE. SNNs using the conversion-based approach could benefit the energy efficiency of inference and retain high accuracy of DLNs. However, transistor-based spiking neurons and synapses are not scalable and inefficient. In this work, a Mott neuron with 1T1R structure is designed to meet the requirement of the conversion-based approach, whose spiking rates dependence on voltage naturally implements the rectified linear unit (ReLU). Based on the 1T1R Mott neuron, we experimentally demonstrated a one-layer SNN (320 ×10), which consists of RRAM synaptic weight elements and Mott-type output neurons, for the first time. Attributes to the rectified linear voltage-rates relationship of the 1T1R neuron and its inherent stochasticity, 95.7% converting accuracy of the neurons and 85.7% recognition accuracy in MNIST datasets are obtained. At last, a neuron X-bar architecture is proposed for parallel multi-tasking and better system integration.
Persistent Identifierhttp://hdl.handle.net/10722/287021
ISSN
2023 SCImago Journal Rankings: 1.047
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Xumeng-
dc.contributor.authorYang, J. Joshua-
dc.contributor.authorLiu, Qi-
dc.contributor.authorLiu, Ming-
dc.contributor.authorWang, Zhongrui-
dc.contributor.authorSong, Wenhao-
dc.contributor.authorMidya, Rivu-
dc.contributor.authorZhuo, Ye-
dc.contributor.authorWang, Rui-
dc.contributor.authorRao, Mingyi-
dc.contributor.authorUpadhyay, Navnidhi K.-
dc.contributor.authorXia, Qiangfei-
dc.date.accessioned2020-09-07T11:46:17Z-
dc.date.available2020-09-07T11:46:17Z-
dc.date.issued2019-
dc.identifier.citationTechnical Digest - International Electron Devices Meeting, IEDM, 2019, v. 2019-December-
dc.identifier.issn0163-1918-
dc.identifier.urihttp://hdl.handle.net/10722/287021-
dc.description.abstract© 2019 IEEE. SNNs using the conversion-based approach could benefit the energy efficiency of inference and retain high accuracy of DLNs. However, transistor-based spiking neurons and synapses are not scalable and inefficient. In this work, a Mott neuron with 1T1R structure is designed to meet the requirement of the conversion-based approach, whose spiking rates dependence on voltage naturally implements the rectified linear unit (ReLU). Based on the 1T1R Mott neuron, we experimentally demonstrated a one-layer SNN (320 ×10), which consists of RRAM synaptic weight elements and Mott-type output neurons, for the first time. Attributes to the rectified linear voltage-rates relationship of the 1T1R neuron and its inherent stochasticity, 95.7% converting accuracy of the neurons and 85.7% recognition accuracy in MNIST datasets are obtained. At last, a neuron X-bar architecture is proposed for parallel multi-tasking and better system integration.-
dc.languageeng-
dc.relation.ispartofTechnical Digest - International Electron Devices Meeting, IEDM-
dc.titleExperimental Demonstration of Conversion-Based SNNs with 1T1R Mott Neurons for Neuromorphic Inference-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/IEDM19573.2019.8993519-
dc.identifier.scopuseid_2-s2.0-85081046026-
dc.identifier.volume2019-December-
dc.identifier.spagenull-
dc.identifier.epagenull-
dc.identifier.isiWOS:000553550000088-
dc.identifier.issnl0163-1918-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats