Memristive non-idealities

Is there any practical implications for designing neural network chips?

Olga Krestinskaya, Aidana Irmanova, Alex James

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The impact of device-to-device, cycle-to-cycle, and parasitic variations in memristor devices on the performance of neural network architectures is not a fully understood topic. In this paper, we present an explicit analysis of memristor variabilities and non-idealities of memristive crossbar based learning architectures. The measurements of real devices and their effects on dot product operation in a memristive crossbar is reported. The effect of these non-idealities, limited resistive levels and variabilities on the performance and reliability of two-layer Artificial Neural Network (ANN), Convolutional Neural Network (CNN) and Binary Neural Network (BNN) is analyzed and presented.

Original languageEnglish
Title of host publication2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728103976
DOIs
Publication statusPublished - Jan 1 2019
Event2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan
Duration: May 26 2019May 29 2019

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2019-May
ISSN (Print)0271-4310

Conference

Conference2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
CountryJapan
CitySapporo
Period5/26/195/29/19

Fingerprint

Memristors
Neural networks
Network architecture

Keywords

  • Learning Architectures
  • Memristive Crossbar
  • Memristor
  • Variability

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Krestinskaya, O., Irmanova, A., & James, A. (2019). Memristive non-idealities: Is there any practical implications for designing neural network chips? In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings [8702245] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2019.8702245

Memristive non-idealities : Is there any practical implications for designing neural network chips? / Krestinskaya, Olga; Irmanova, Aidana; James, Alex.

2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8702245 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Krestinskaya, O, Irmanova, A & James, A 2019, Memristive non-idealities: Is there any practical implications for designing neural network chips? in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702245, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 5/26/19. https://doi.org/10.1109/ISCAS.2019.8702245
Krestinskaya O, Irmanova A, James A. Memristive non-idealities: Is there any practical implications for designing neural network chips? In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8702245. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2019.8702245
Krestinskaya, Olga ; Irmanova, Aidana ; James, Alex. / Memristive non-idealities : Is there any practical implications for designing neural network chips?. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{71570ac2f2d5462e84281706896fe31b,
title = "Memristive non-idealities: Is there any practical implications for designing neural network chips?",
abstract = "The impact of device-to-device, cycle-to-cycle, and parasitic variations in memristor devices on the performance of neural network architectures is not a fully understood topic. In this paper, we present an explicit analysis of memristor variabilities and non-idealities of memristive crossbar based learning architectures. The measurements of real devices and their effects on dot product operation in a memristive crossbar is reported. The effect of these non-idealities, limited resistive levels and variabilities on the performance and reliability of two-layer Artificial Neural Network (ANN), Convolutional Neural Network (CNN) and Binary Neural Network (BNN) is analyzed and presented.",
keywords = "Learning Architectures, Memristive Crossbar, Memristor, Variability",
author = "Olga Krestinskaya and Aidana Irmanova and Alex James",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ISCAS.2019.8702245",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Memristive non-idealities

T2 - Is there any practical implications for designing neural network chips?

AU - Krestinskaya, Olga

AU - Irmanova, Aidana

AU - James, Alex

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The impact of device-to-device, cycle-to-cycle, and parasitic variations in memristor devices on the performance of neural network architectures is not a fully understood topic. In this paper, we present an explicit analysis of memristor variabilities and non-idealities of memristive crossbar based learning architectures. The measurements of real devices and their effects on dot product operation in a memristive crossbar is reported. The effect of these non-idealities, limited resistive levels and variabilities on the performance and reliability of two-layer Artificial Neural Network (ANN), Convolutional Neural Network (CNN) and Binary Neural Network (BNN) is analyzed and presented.

AB - The impact of device-to-device, cycle-to-cycle, and parasitic variations in memristor devices on the performance of neural network architectures is not a fully understood topic. In this paper, we present an explicit analysis of memristor variabilities and non-idealities of memristive crossbar based learning architectures. The measurements of real devices and their effects on dot product operation in a memristive crossbar is reported. The effect of these non-idealities, limited resistive levels and variabilities on the performance and reliability of two-layer Artificial Neural Network (ANN), Convolutional Neural Network (CNN) and Binary Neural Network (BNN) is analyzed and presented.

KW - Learning Architectures

KW - Memristive Crossbar

KW - Memristor

KW - Variability

UR - http://www.scopus.com/inward/record.url?scp=85066797596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066797596&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702245

DO - 10.1109/ISCAS.2019.8702245

M3 - Conference contribution

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -