Neuromemristive Circuits for Edge Computing: A Review

Olga Krestinskaya; Alex Pappachen James; Leon Ong Chua

doi:10.1109/TNNLS.2019.2899262

Neuromemristive Circuits for Edge Computing: A Review

Olga Krestinskaya, Alex Pappachen James, Leon Ong Chua

Department of Electrical and Computer Engineering

Research output: Contribution to journal › Review article

5 Citations (Scopus)

Abstract

The volume, veracity, variability, and velocity of data produced from the ever increasing network of sensors connected to Internet pose challenges for power management, scalability, and sustainability of cloud computing infrastructure. Increasing the data processing capability of edge computing devices at lower power requirements can reduce several overheads for cloud computing solutions. This paper provides the review of neuromorphic CMOS-memristive architectures that can be integrated into edge computing devices. We discuss why the neuromorphic architectures are useful for edge devices and show the advantages, drawbacks, and open problems in the field of neuromemristive circuits for edge computing.

Original language	English
Article number	8667457
Pages (from-to)	4-23
Number of pages	20
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	31
Issue number	1
DOIs	https://doi.org/10.1109/TNNLS.2019.2899262
Publication status	Published - Jan 2020

Fingerprint

Keywords

Cellular neural network (CeNN)
convolutional neural network (CNN)
deep learning neural network
hierarchical temporal memory (HTM)
long short-term memory (LSTM)
memristor circuits
memristors
neural networks
spiking neural networks (SNNs)

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Cite this

Krestinskaya, O., James, A. P., & Chua, L. O. (2020). Neuromemristive Circuits for Edge Computing: A Review. IEEE Transactions on Neural Networks and Learning Systems, 31(1), 4-23. [8667457]. https://doi.org/10.1109/TNNLS.2019.2899262

@article{429b00169a3047beb265f4769eccd6fc,

title = "Neuromemristive Circuits for Edge Computing: A Review",

abstract = "The volume, veracity, variability, and velocity of data produced from the ever increasing network of sensors connected to Internet pose challenges for power management, scalability, and sustainability of cloud computing infrastructure. Increasing the data processing capability of edge computing devices at lower power requirements can reduce several overheads for cloud computing solutions. This paper provides the review of neuromorphic CMOS-memristive architectures that can be integrated into edge computing devices. We discuss why the neuromorphic architectures are useful for edge devices and show the advantages, drawbacks, and open problems in the field of neuromemristive circuits for edge computing.",

keywords = "Cellular neural network (CeNN), convolutional neural network (CNN), deep learning neural network, hierarchical temporal memory (HTM), long short-term memory (LSTM), memristor circuits, memristors, neural networks, spiking neural networks (SNNs)",

author = "Olga Krestinskaya and James, {Alex Pappachen} and Chua, {Leon Ong}",

year = "2020",

month = jan

doi = "10.1109/TNNLS.2019.2899262",

language = "English",

volume = "31",

pages = "4--23",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE",

number = "1",

}

TY - JOUR

T1 - Neuromemristive Circuits for Edge Computing

T2 - A Review

AU - Krestinskaya, Olga

AU - James, Alex Pappachen

AU - Chua, Leon Ong

PY - 2020/1

Y1 - 2020/1

N2 - The volume, veracity, variability, and velocity of data produced from the ever increasing network of sensors connected to Internet pose challenges for power management, scalability, and sustainability of cloud computing infrastructure. Increasing the data processing capability of edge computing devices at lower power requirements can reduce several overheads for cloud computing solutions. This paper provides the review of neuromorphic CMOS-memristive architectures that can be integrated into edge computing devices. We discuss why the neuromorphic architectures are useful for edge devices and show the advantages, drawbacks, and open problems in the field of neuromemristive circuits for edge computing.

AB - The volume, veracity, variability, and velocity of data produced from the ever increasing network of sensors connected to Internet pose challenges for power management, scalability, and sustainability of cloud computing infrastructure. Increasing the data processing capability of edge computing devices at lower power requirements can reduce several overheads for cloud computing solutions. This paper provides the review of neuromorphic CMOS-memristive architectures that can be integrated into edge computing devices. We discuss why the neuromorphic architectures are useful for edge devices and show the advantages, drawbacks, and open problems in the field of neuromemristive circuits for edge computing.

KW - Cellular neural network (CeNN)

KW - convolutional neural network (CNN)

KW - deep learning neural network

KW - hierarchical temporal memory (HTM)

KW - long short-term memory (LSTM)

KW - memristor circuits

KW - memristors

KW - neural networks

KW - spiking neural networks (SNNs)

UR - http://www.scopus.com/inward/record.url?scp=85077664697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077664697&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2019.2899262

DO - 10.1109/TNNLS.2019.2899262

M3 - Review article

C2 - 30892238

AN - SCOPUS:85077664697

VL - 31

SP - 4

EP - 23

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 1

M1 - 8667457

ER -

Access to Document

10.1109/TNNLS.2019.2899262