A Vision for All-Spin Neural Networks: A Device to System Perspective

Abhronil Sengupta; Kaushik Roy

doi:10.1109/TCSI.2016.2615312

A Vision for All-Spin Neural Networks: A Device to System Perspective

Abhronil Sengupta, Kaushik Roy

Electrical Engineering

Research output: Contribution to journal › Article › peer-review

59 Scopus citations

Abstract

Spin-transfer torque (STT) mechanisms in vertical and lateral spin valves and magnetization reversal/domain wall motion with spin-orbit torque (SOT) have opened up new possibilities of efficiently mimicking 'neural' and 'synaptic' functionalities with much lower area and energy consumption compared to CMOS implementations. In this paper, we review various STT/SOT devices that can provide a compact and area-efficient implementation of artificial neurons and synapses. We provide a device-circuit-system perspective and envision design of an All-Spin neuromorphic processor (with different degrees of bio-fidelity) that can be potentially appealing for ultra-low power cognitive applications.

Original language	English (US)
Article number	7755884
Pages (from-to)	2267-2277
Number of pages	11
Journal	IEEE Transactions on Circuits and Systems I: Regular Papers
Volume	63
Issue number	12
DOIs	https://doi.org/10.1109/TCSI.2016.2615312
State	Published - Dec 2016

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Electrical and Electronic Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TCSI.2016.2615312

Cite this

@article{2478742c4f864f85b21b6fecbad798c0,

title = "A Vision for All-Spin Neural Networks: A Device to System Perspective",

abstract = "Spin-transfer torque (STT) mechanisms in vertical and lateral spin valves and magnetization reversal/domain wall motion with spin-orbit torque (SOT) have opened up new possibilities of efficiently mimicking 'neural' and 'synaptic' functionalities with much lower area and energy consumption compared to CMOS implementations. In this paper, we review various STT/SOT devices that can provide a compact and area-efficient implementation of artificial neurons and synapses. We provide a device-circuit-system perspective and envision design of an All-Spin neuromorphic processor (with different degrees of bio-fidelity) that can be potentially appealing for ultra-low power cognitive applications.",

author = "Abhronil Sengupta and Kaushik Roy",

note = "Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2016",

month = dec,

doi = "10.1109/TCSI.2016.2615312",

language = "English (US)",

volume = "63",

pages = "2267--2277",

journal = "IEEE Transactions on Circuits and Systems I: Regular Papers",

issn = "1549-8328",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - A Vision for All-Spin Neural Networks

T2 - A Device to System Perspective

AU - Sengupta, Abhronil

AU - Roy, Kaushik

PY - 2016/12

Y1 - 2016/12

N2 - Spin-transfer torque (STT) mechanisms in vertical and lateral spin valves and magnetization reversal/domain wall motion with spin-orbit torque (SOT) have opened up new possibilities of efficiently mimicking 'neural' and 'synaptic' functionalities with much lower area and energy consumption compared to CMOS implementations. In this paper, we review various STT/SOT devices that can provide a compact and area-efficient implementation of artificial neurons and synapses. We provide a device-circuit-system perspective and envision design of an All-Spin neuromorphic processor (with different degrees of bio-fidelity) that can be potentially appealing for ultra-low power cognitive applications.

AB - Spin-transfer torque (STT) mechanisms in vertical and lateral spin valves and magnetization reversal/domain wall motion with spin-orbit torque (SOT) have opened up new possibilities of efficiently mimicking 'neural' and 'synaptic' functionalities with much lower area and energy consumption compared to CMOS implementations. In this paper, we review various STT/SOT devices that can provide a compact and area-efficient implementation of artificial neurons and synapses. We provide a device-circuit-system perspective and envision design of an All-Spin neuromorphic processor (with different degrees of bio-fidelity) that can be potentially appealing for ultra-low power cognitive applications.

UR - http://www.scopus.com/inward/record.url?scp=85002902556&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002902556&partnerID=8YFLogxK

U2 - 10.1109/TCSI.2016.2615312

DO - 10.1109/TCSI.2016.2615312

M3 - Article

AN - SCOPUS:85002902556

SN - 1549-8328

VL - 63

SP - 2267

EP - 2277

JO - IEEE Transactions on Circuits and Systems I: Regular Papers

JF - IEEE Transactions on Circuits and Systems I: Regular Papers

IS - 12

M1 - 7755884

ER -

A Vision for All-Spin Neural Networks: A Device to System Perspective

Abstract

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this