Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/148658
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPrabhu, Nagaraj Lakshmanaen_US
dc.contributor.authorLoy, Desmond Jia Junen_US
dc.contributor.authorDananjaya, Putu Andhitaen_US
dc.contributor.authorLew, Wen Siangen_US
dc.contributor.authorToh, Eng Huaten_US
dc.contributor.authorRaghavan, Nagarajanen_US
dc.date.accessioned2021-05-31T07:54:07Z-
dc.date.available2021-05-31T07:54:07Z-
dc.date.issued2020-
dc.identifier.citationPrabhu, N. L., Loy, D. J. J., Dananjaya, P. A., Lew, W. S., Toh, E. H. & Raghavan, N. (2020). Exploring the impact of variability in resistance distributions of RRAM on the prediction accuracy of deep learning neural networks. Electronics, 9(3). https://dx.doi.org/10.3390/electronics9030414en_US
dc.identifier.issn2079-9292en_US
dc.identifier.urihttps://hdl.handle.net/10356/148658-
dc.description.abstractIn this work, we explore the use of the resistive random access memory (RRAM) device as a synapse for mimicking the trained weights linking neurons in a deep learning neural network (DNN) (AlexNet). The RRAM devices were fabricated in-house and subjected to 1000 bipolar read-write cycles to measure the resistances recorded for Logic-0 and Logic-1 (we demonstrate the feasibility of achieving eight discrete resistance states in the same device depending on the RESET stop voltage). DNN simulations have been performed to compare the relative error between the output of AlexNet Layer 1 (Convolution) implemented with the standard backpropagation (BP) algorithm trained weights versus the weights that are encoded using the measured resistance distributions from RRAM. The IMAGENET dataset is used for classification purpose here. We focus only on the Layer 1 weights in the AlexNet framework with 11 × 11 × 96 filters values coded into a binary floating point and substituted with the RRAM resistance values corresponding to Logic-0 and Logic-1. The impact of variability in the resistance states of RRAM for the low and high resistance states on the accuracy of image classification is studied by formulating a look-up table (LUT) for the RRAM (from measured I-V data) and comparing the convolution computation output of AlexNet Layer 1 with the standard outputs from the BP-based pre-trained weights. This is one of the first studies dedicated to exploring the impact of RRAM device resistance variability on the prediction accuracy of a convolutional neural network (CNN) on an AlexNet platform through a framework that requires limited actual device switching test data.en_US
dc.description.sponsorshipAgency for Science, Technology and Research (A*STAR)en_US
dc.description.sponsorshipEconomic Development Board (EDB)en_US
dc.description.sponsorshipNational Research Foundation (NRF)en_US
dc.language.isoenen_US
dc.relationA18A5b0056en_US
dc.relationRCA – 16/216en_US
dc.relationNRF2015-IIP001-001en_US
dc.relation.ispartofElectronicsen_US
dc.rights© 2020 The Author(s). Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).en_US
dc.subjectScience::Physicsen_US
dc.titleExploring the impact of variability in resistance distributions of RRAM on the prediction accuracy of deep learning neural networksen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Physical and Mathematical Sciencesen_US
dc.identifier.doi10.3390/electronics9030414-
dc.description.versionPublished versionen_US
dc.identifier.scopus2-s2.0-85081022579-
dc.identifier.issue3en_US
dc.identifier.volume9en_US
dc.subject.keywordsConvolutional Neural Networken_US
dc.subject.keywordsLook-up-tableen_US
dc.description.acknowledgementThis research was funded by A*STAR BRENAIC Research Project No. A18A5b0056 and the APC associated with the publication as well. Funding support for fabrication and characterization of devices were provided by the Economic Development Board EDB-IPP (RCA – 16/216) program and the Industry-IHL Partnership Program (NRF2015-IIP001-001).en_US
item.grantfulltextopen-
item.fulltextWith Fulltext-
Appears in Collections:SPMS Journal Articles
Files in This Item:
File Description SizeFormat 
electronics-09-00414-v2.pdf4.48 MBAdobe PDFView/Open

Page view(s)

112
Updated on May 21, 2022

Download(s)

13
Updated on May 21, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.