Custom Sub-Systems and Circuits for Deep Learning

Guest Editorial Overview

Chia Yu Chen, Boris Murmann, Jae-sun Seo, Hoi Jun Yoo

Research output: Contribution to journalArticle

Abstract

This survey paper summarizes recent progress of deep learning circuits and systems technologies and contains four topics: hardware-centric deep learning algorithms, digital architectures, analog architectures, and system demonstrations. We present an overview of these four areas and introduce key contributions of papers in this special issue.

Original languageEnglish (US)
Article number8720273
Pages (from-to)247-252
Number of pages6
JournalIEEE Journal on Emerging and Selected Topics in Circuits and Systems
Volume9
Issue number2
DOIs
StatePublished - Jun 1 2019

Fingerprint

Networks (circuits)
Learning algorithms
Demonstrations
Hardware
Deep learning

Keywords

  • accelerators
  • approximate computing
  • computer architectures
  • data-flow architectures
  • Deep learning
  • distributed learning
  • in-memory computing
  • integrated circuit designs
  • machine learning
  • neural network hardware
  • reduced-precision

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Custom Sub-Systems and Circuits for Deep Learning : Guest Editorial Overview. / Chen, Chia Yu; Murmann, Boris; Seo, Jae-sun; Yoo, Hoi Jun.

In: IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Vol. 9, No. 2, 8720273, 01.06.2019, p. 247-252.

Research output: Contribution to journalArticle

@article{948ee1148cd9478abcacc54b7b4396d5,
title = "Custom Sub-Systems and Circuits for Deep Learning: Guest Editorial Overview",
abstract = "This survey paper summarizes recent progress of deep learning circuits and systems technologies and contains four topics: hardware-centric deep learning algorithms, digital architectures, analog architectures, and system demonstrations. We present an overview of these four areas and introduce key contributions of papers in this special issue.",
keywords = "accelerators, approximate computing, computer architectures, data-flow architectures, Deep learning, distributed learning, in-memory computing, integrated circuit designs, machine learning, neural network hardware, reduced-precision",
author = "Chen, {Chia Yu} and Boris Murmann and Jae-sun Seo and Yoo, {Hoi Jun}",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/JETCAS.2019.2918317",
language = "English (US)",
volume = "9",
pages = "247--252",
journal = "IEEE Journal on Emerging and Selected Topics in Circuits and Systems",
issn = "2156-3357",
publisher = "IEEE Circuits and Systems Society",
number = "2",

}

TY - JOUR

T1 - Custom Sub-Systems and Circuits for Deep Learning

T2 - Guest Editorial Overview

AU - Chen, Chia Yu

AU - Murmann, Boris

AU - Seo, Jae-sun

AU - Yoo, Hoi Jun

PY - 2019/6/1

Y1 - 2019/6/1

N2 - This survey paper summarizes recent progress of deep learning circuits and systems technologies and contains four topics: hardware-centric deep learning algorithms, digital architectures, analog architectures, and system demonstrations. We present an overview of these four areas and introduce key contributions of papers in this special issue.

AB - This survey paper summarizes recent progress of deep learning circuits and systems technologies and contains four topics: hardware-centric deep learning algorithms, digital architectures, analog architectures, and system demonstrations. We present an overview of these four areas and introduce key contributions of papers in this special issue.

KW - accelerators

KW - approximate computing

KW - computer architectures

KW - data-flow architectures

KW - Deep learning

KW - distributed learning

KW - in-memory computing

KW - integrated circuit designs

KW - machine learning

KW - neural network hardware

KW - reduced-precision

UR - http://www.scopus.com/inward/record.url?scp=85067000225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067000225&partnerID=8YFLogxK

U2 - 10.1109/JETCAS.2019.2918317

DO - 10.1109/JETCAS.2019.2918317

M3 - Article

VL - 9

SP - 247

EP - 252

JO - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

JF - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

SN - 2156-3357

IS - 2

M1 - 8720273

ER -