Memristor-based neural networks: Synaptic versus neuronal stochasticity

Handle URI:
http://hdl.handle.net/10754/621842
Title:
Memristor-based neural networks: Synaptic versus neuronal stochasticity
Authors:
Naous, Rawan ( 0000-0001-6129-7926 ) ; Alshedivat, Maruan; Neftci, Emre; Cauwenberghs, Gert; Salama, Khaled N. ( 0000-0001-7742-1282 )
Abstract:
In neuromorphic circuits, stochasticity in the cortex can be mapped into the synaptic or neuronal components. The hardware emulation of these stochastic neural networks are currently being extensively studied using resistive memories or memristors. The ionic process involved in the underlying switching behavior of the memristive elements is considered as the main source of stochasticity of its operation. Building on its inherent variability, the memristor is incorporated into abstract models of stochastic neurons and synapses. Two approaches of stochastic neural networks are investigated. Aside from the size and area perspective, the impact on the system performance, in terms of accuracy, recognition rates, and learning, among these two approaches and where the memristor would fall into place are the main comparison points to be considered.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program
Citation:
Naous R, AlShedivat M, Neftci E, Cauwenberghs G, Salama KN (2016) Memristor-based neural networks: Synaptic versus neuronal stochasticity. AIP Advances 6: 111304. Available: http://dx.doi.org/10.1063/1.4967352.
Publisher:
AIP Publishing
Journal:
AIP Advances
Issue Date:
2-Nov-2016
DOI:
10.1063/1.4967352
Type:
Article
ISSN:
2158-3226
Additional Links:
http://dx.doi.org/10.1063/1.4967352
Appears in Collections:
Articles; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorNaous, Rawanen
dc.contributor.authorAlshedivat, Maruanen
dc.contributor.authorNeftci, Emreen
dc.contributor.authorCauwenberghs, Gerten
dc.contributor.authorSalama, Khaled N.en
dc.date.accessioned2016-11-21T06:21:07Z-
dc.date.available2016-11-21T06:21:07Z-
dc.date.issued2016-11-02en
dc.identifier.citationNaous R, AlShedivat M, Neftci E, Cauwenberghs G, Salama KN (2016) Memristor-based neural networks: Synaptic versus neuronal stochasticity. AIP Advances 6: 111304. Available: http://dx.doi.org/10.1063/1.4967352.en
dc.identifier.issn2158-3226en
dc.identifier.doi10.1063/1.4967352en
dc.identifier.urihttp://hdl.handle.net/10754/621842-
dc.description.abstractIn neuromorphic circuits, stochasticity in the cortex can be mapped into the synaptic or neuronal components. The hardware emulation of these stochastic neural networks are currently being extensively studied using resistive memories or memristors. The ionic process involved in the underlying switching behavior of the memristive elements is considered as the main source of stochasticity of its operation. Building on its inherent variability, the memristor is incorporated into abstract models of stochastic neurons and synapses. Two approaches of stochastic neural networks are investigated. Aside from the size and area perspective, the impact on the system performance, in terms of accuracy, recognition rates, and learning, among these two approaches and where the memristor would fall into place are the main comparison points to be considered.en
dc.publisherAIP Publishingen
dc.relation.urlhttp://dx.doi.org/10.1063/1.4967352en
dc.rightsAll article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleMemristor-based neural networks: Synaptic versus neuronal stochasticityen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.identifier.journalAIP Advancesen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionCarnegie Mellon University, Pittsburgh 15289, USAen
dc.contributor.institutionUniversity of California Irvine, Irvine 92697, USAen
dc.contributor.institutionUniversity of California San Diego, San Diego 92093, USAen
kaust.authorNaous, Rawanen
kaust.authorSalama, Khaled N.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.