Show simple item record

dc.contributor.authorFouda, Mohammed E.
dc.contributor.authorNeftci, E.
dc.contributor.authorEltawil, Ahmed
dc.contributor.authorKurdahi, F.
dc.date.accessioned2020-04-27T10:47:56Z
dc.date.available2020-04-27T10:47:56Z
dc.date.issued2020-03-31
dc.identifier.citationFouda, M. E., Neftci, E., Eltawil, A., & Kurdahi, F. (2019). Effect of Asymmetric Nonlinearity Dynamics in RRAMs on Spiking Neural Network Performance. 2019 53rd Asilomar Conference on Signals, Systems, and Computers. doi:10.1109/ieeeconf44664.2019.9049043
dc.identifier.isbn9781728143002
dc.identifier.issn1058-6393
dc.identifier.doi10.1109/IEEECONF44664.2019.9049043
dc.identifier.urihttp://hdl.handle.net/10754/662658
dc.description.abstractCrossbar-based Resistive Random Access Memory (RRAM) array is a promising candidate for fast and efficient implementation of the vector-matrix multiplication, an essential step in a wide variety of workloads. However, several RRAM devices, demonstrating promising synaptic behaviors, are characterized by nonlinear and asymmetric update dynamics, which is a major obstacle for large-scale deployment in neural networks, especially for online learning tasks. In this work, we first introduce a memristive Spiking Neural Network (SNN) with local learning. Then, we study the effect of this asymmetric and nonlinear behavior on the spiking neural network performance and propose a method to overcome the performance degradation without extra nonlinearity cancellation hardware and read cycles. The performance of the proposed method approaches the baseline performance with 1 ∼ 2% drop in recognition accuracy.
dc.publisherIEEE
dc.relation.urlhttps://ieeexplore.ieee.org/document/9049043/
dc.rightsArchived with thanks to IEEE
dc.titleEffect of Asymmetric Nonlinearity Dynamics in RRAMs on Spiking Neural Network Performance
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.date2019-11-03 to 2019-11-06
dc.conference.name53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
dc.conference.locationPacific Grove, CA, USA
dc.eprint.versionPost-print
dc.contributor.institutionUniversity of California,Electrical Engineering and Computer Science Dept.,Irvine,CA,USA,92697-2625
dc.contributor.institutionUniversity of California,Cognitive Sciences Dept.,Irvine,CA,USA,92697-2625
dc.identifier.volume2019-November
dc.identifier.pages495-499
kaust.personEltawil, Ahmed Mohamed
dc.identifier.eid2-s2.0-85083300381
refterms.dateFOA2020-04-28T07:30:42Z


Files in this item

Thumbnail
Name:
Effect of.pdf
Size:
566.3Kb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record