Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/148658
Title: Exploring the impact of variability in resistance distributions of RRAM on the prediction accuracy of deep learning neural networks
Authors: Prabhu, Nagaraj Lakshmana
Loy, Desmond Jia Jun
Dananjaya, Putu Andhita
Lew, Wen Siang
Toh, Eng Huat
Raghavan, Nagarajan
Keywords: Science::Physics
Issue Date: 2020
Source: Prabhu, 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/electronics9030414
Project: A18A5b0056
RCA – 16/216
NRF2015-IIP001-001
Journal: Electronics
Abstract: In 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.
URI: https://hdl.handle.net/10356/148658
ISSN: 2079-9292
DOI: 10.3390/electronics9030414
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/).
Fulltext Permission: open
Fulltext Availability: With 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)

68
Updated on Jan 17, 2022

Download(s)

6
Updated on Jan 17, 2022

Google ScholarTM

Check

Altmetric


Plumx

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