Integrated Crossbar Array with Resistive Synapses and Oscillation Neurons

Jiyong Woo, Panni Wang, Shimeng Yu

Research output: Contribution to journalArticle

Abstract

In this letter, we fabricate a crossbar array that structurally resembles a column of the neural network, where one neuron is connected with multiple synapses in parallel for on-chip integration. Instead of using complex CMOS neuronal circuit, we integrate a threshold switch at the edge of the crossbar array as a compact oscillation neuron, which converts the weighted sum to an oscillation frequency. When the input vectors are loaded into multiple rows of the array, the oscillation frequency is measured to be proportional to the analog column current. This is the first experimental demonstration of an integrated crossbar array with both synapses and neurons, paving the path to a fully parallel computation and processing using emerging device technologies for the neuromorphic computing.

Original languageEnglish (US)
Article number8733058
Pages (from-to)1313-1316
Number of pages4
JournalIEEE Electron Device Letters
Volume40
Issue number8
DOIs
StatePublished - Aug 1 2019

Fingerprint

Neurons
Demonstrations
Switches
Neural networks
Networks (circuits)
Processing

Keywords

  • crossbar array
  • neuromorphic computing
  • oscillation neuron
  • Resistive synapse

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Integrated Crossbar Array with Resistive Synapses and Oscillation Neurons. / Woo, Jiyong; Wang, Panni; Yu, Shimeng.

In: IEEE Electron Device Letters, Vol. 40, No. 8, 8733058, 01.08.2019, p. 1313-1316.

Research output: Contribution to journalArticle

Woo, Jiyong ; Wang, Panni ; Yu, Shimeng. / Integrated Crossbar Array with Resistive Synapses and Oscillation Neurons. In: IEEE Electron Device Letters. 2019 ; Vol. 40, No. 8. pp. 1313-1316.
@article{1bd14b15047547d88354456ea34edd86,
title = "Integrated Crossbar Array with Resistive Synapses and Oscillation Neurons",
abstract = "In this letter, we fabricate a crossbar array that structurally resembles a column of the neural network, where one neuron is connected with multiple synapses in parallel for on-chip integration. Instead of using complex CMOS neuronal circuit, we integrate a threshold switch at the edge of the crossbar array as a compact oscillation neuron, which converts the weighted sum to an oscillation frequency. When the input vectors are loaded into multiple rows of the array, the oscillation frequency is measured to be proportional to the analog column current. This is the first experimental demonstration of an integrated crossbar array with both synapses and neurons, paving the path to a fully parallel computation and processing using emerging device technologies for the neuromorphic computing.",
keywords = "crossbar array, neuromorphic computing, oscillation neuron, Resistive synapse",
author = "Jiyong Woo and Panni Wang and Shimeng Yu",
year = "2019",
month = "8",
day = "1",
doi = "10.1109/LED.2019.2921656",
language = "English (US)",
volume = "40",
pages = "1313--1316",
journal = "IEEE Electron Device Letters",
issn = "0741-3106",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Integrated Crossbar Array with Resistive Synapses and Oscillation Neurons

AU - Woo, Jiyong

AU - Wang, Panni

AU - Yu, Shimeng

PY - 2019/8/1

Y1 - 2019/8/1

N2 - In this letter, we fabricate a crossbar array that structurally resembles a column of the neural network, where one neuron is connected with multiple synapses in parallel for on-chip integration. Instead of using complex CMOS neuronal circuit, we integrate a threshold switch at the edge of the crossbar array as a compact oscillation neuron, which converts the weighted sum to an oscillation frequency. When the input vectors are loaded into multiple rows of the array, the oscillation frequency is measured to be proportional to the analog column current. This is the first experimental demonstration of an integrated crossbar array with both synapses and neurons, paving the path to a fully parallel computation and processing using emerging device technologies for the neuromorphic computing.

AB - In this letter, we fabricate a crossbar array that structurally resembles a column of the neural network, where one neuron is connected with multiple synapses in parallel for on-chip integration. Instead of using complex CMOS neuronal circuit, we integrate a threshold switch at the edge of the crossbar array as a compact oscillation neuron, which converts the weighted sum to an oscillation frequency. When the input vectors are loaded into multiple rows of the array, the oscillation frequency is measured to be proportional to the analog column current. This is the first experimental demonstration of an integrated crossbar array with both synapses and neurons, paving the path to a fully parallel computation and processing using emerging device technologies for the neuromorphic computing.

KW - crossbar array

KW - neuromorphic computing

KW - oscillation neuron

KW - Resistive synapse

UR - http://www.scopus.com/inward/record.url?scp=85069835813&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069835813&partnerID=8YFLogxK

U2 - 10.1109/LED.2019.2921656

DO - 10.1109/LED.2019.2921656

M3 - Article

VL - 40

SP - 1313

EP - 1316

JO - IEEE Electron Device Letters

JF - IEEE Electron Device Letters

SN - 0741-3106

IS - 8

M1 - 8733058

ER -