Design considerations of synaptic device for neuromorphic computing

Shimeng Yu, Duygu Kuzum, H. S Philip Wong

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

13 Citations (Scopus)

Abstract

Hardware implementation of neuromorphic computing is attractive as a computing paradigm beyond the conventional digital Boolean computing. Recently, two-terminal emerging memory devices that show electrically-triggered resistance modulation have been proposed as synaptic devices for neuromorphic computing. The synaptic device candidates include phase change memory (PCM), resistive RAM (RRAM) and conductive bridge RAM (CBRAM), etc. In this paper, we discuss the general design considerations of synaptic devices for plasticity and learning. As a rule of thumb for performance metrics assessment, an ideal synaptic device should have characteristics such as dimension, energy consumption, operation frequency, dynamic range, etc. that are scalable to biological systems with comparable complexity.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1062-1065
Number of pages4
ISBN (Print)9781479934324
DOIs
StatePublished - 2014
Event2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014 - Melbourne, VIC, Australia
Duration: Jun 1 2014Jun 5 2014

Other

Other2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014
CountryAustralia
CityMelbourne, VIC
Period6/1/146/5/14

Fingerprint

Phase change memory
Biological systems
Plasticity
Energy utilization
Modulation
Hardware
Data storage equipment
RRAM

Keywords

  • CBRAM
  • learning
  • neuromorphic computing
  • PCM
  • plasticity
  • RRAM
  • synaptice device

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Yu, S., Kuzum, D., & Wong, H. S. P. (2014). Design considerations of synaptic device for neuromorphic computing. In Proceedings - IEEE International Symposium on Circuits and Systems (pp. 1062-1065). [6865322] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2014.6865322

Design considerations of synaptic device for neuromorphic computing. / Yu, Shimeng; Kuzum, Duygu; Wong, H. S Philip.

Proceedings - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1062-1065 6865322.

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

Yu, S, Kuzum, D & Wong, HSP 2014, Design considerations of synaptic device for neuromorphic computing. in Proceedings - IEEE International Symposium on Circuits and Systems., 6865322, Institute of Electrical and Electronics Engineers Inc., pp. 1062-1065, 2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014, Melbourne, VIC, Australia, 6/1/14. https://doi.org/10.1109/ISCAS.2014.6865322
Yu S, Kuzum D, Wong HSP. Design considerations of synaptic device for neuromorphic computing. In Proceedings - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1062-1065. 6865322 https://doi.org/10.1109/ISCAS.2014.6865322
Yu, Shimeng ; Kuzum, Duygu ; Wong, H. S Philip. / Design considerations of synaptic device for neuromorphic computing. Proceedings - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1062-1065
@inproceedings{268122c037c0492aab1a4c333a3ad5e5,
title = "Design considerations of synaptic device for neuromorphic computing",
abstract = "Hardware implementation of neuromorphic computing is attractive as a computing paradigm beyond the conventional digital Boolean computing. Recently, two-terminal emerging memory devices that show electrically-triggered resistance modulation have been proposed as synaptic devices for neuromorphic computing. The synaptic device candidates include phase change memory (PCM), resistive RAM (RRAM) and conductive bridge RAM (CBRAM), etc. In this paper, we discuss the general design considerations of synaptic devices for plasticity and learning. As a rule of thumb for performance metrics assessment, an ideal synaptic device should have characteristics such as dimension, energy consumption, operation frequency, dynamic range, etc. that are scalable to biological systems with comparable complexity.",
keywords = "CBRAM, learning, neuromorphic computing, PCM, plasticity, RRAM, synaptice device",
author = "Shimeng Yu and Duygu Kuzum and Wong, {H. S Philip}",
year = "2014",
doi = "10.1109/ISCAS.2014.6865322",
language = "English (US)",
isbn = "9781479934324",
pages = "1062--1065",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Design considerations of synaptic device for neuromorphic computing

AU - Yu, Shimeng

AU - Kuzum, Duygu

AU - Wong, H. S Philip

PY - 2014

Y1 - 2014

N2 - Hardware implementation of neuromorphic computing is attractive as a computing paradigm beyond the conventional digital Boolean computing. Recently, two-terminal emerging memory devices that show electrically-triggered resistance modulation have been proposed as synaptic devices for neuromorphic computing. The synaptic device candidates include phase change memory (PCM), resistive RAM (RRAM) and conductive bridge RAM (CBRAM), etc. In this paper, we discuss the general design considerations of synaptic devices for plasticity and learning. As a rule of thumb for performance metrics assessment, an ideal synaptic device should have characteristics such as dimension, energy consumption, operation frequency, dynamic range, etc. that are scalable to biological systems with comparable complexity.

AB - Hardware implementation of neuromorphic computing is attractive as a computing paradigm beyond the conventional digital Boolean computing. Recently, two-terminal emerging memory devices that show electrically-triggered resistance modulation have been proposed as synaptic devices for neuromorphic computing. The synaptic device candidates include phase change memory (PCM), resistive RAM (RRAM) and conductive bridge RAM (CBRAM), etc. In this paper, we discuss the general design considerations of synaptic devices for plasticity and learning. As a rule of thumb for performance metrics assessment, an ideal synaptic device should have characteristics such as dimension, energy consumption, operation frequency, dynamic range, etc. that are scalable to biological systems with comparable complexity.

KW - CBRAM

KW - learning

KW - neuromorphic computing

KW - PCM

KW - plasticity

KW - RRAM

KW - synaptice device

UR - http://www.scopus.com/inward/record.url?scp=84907408126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907408126&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2014.6865322

DO - 10.1109/ISCAS.2014.6865322

M3 - Conference contribution

AN - SCOPUS:84907408126

SN - 9781479934324

SP - 1062

EP - 1065

BT - Proceedings - IEEE International Symposium on Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -