Neuromorphic Photonic Integrated Circuits

Hsuan Tung Peng; Mitchell A. Nahmias; Thomas Ferreira De Lima; Alexander N. Tait; Bhavin J. Shastri; Paul R. Prucnal

doi:10.1109/JSTQE.2018.2840448

Neuromorphic Photonic Integrated Circuits

Hsuan Tung Peng, Mitchell A. Nahmias, Thomas Ferreira De Lima, Alexander N. Tait, Bhavin J. Shastri, Paul R. Prucnal

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

176 Scopus citations

Abstract

This paper reviews some recent progress in the field of neuromorphic photonics, with a particular focus on scalability. We provide a framework for understanding the underlying models, and demonstrate a neuron-like processing device - an excitable laser - that has many favorable properties for integration with emerging photonic integrated circuit platforms. On a systems level, we compare several proposed interconnection frameworks that allow for fully tunable networks of photonic neurons.

Original language	English (US)
Article number	8364605
Journal	IEEE Journal of Selected Topics in Quantum Electronics
Volume	24
Issue number	6
DOIs	https://doi.org/10.1109/JSTQE.2018.2840448
State	Published - Nov 1 2018

All Science Journal Classification (ASJC) codes

Atomic and Molecular Physics, and Optics
Electrical and Electronic Engineering

Keywords

Bifurcation
excitability
multiple-accumulate (MAC)
neural networks
neuromorphic computing
neuromorphic photonics
optoelectronics
photonic integrated circuits (PICs)
recurrent network
semiconductor lasers
spiking neural networks (SNNs)
wavelength-divison multiplexing (WDM)

Access to Document

10.1109/JSTQE.2018.2840448

Cite this

@article{9bdb646c298d4342afd3ba5df6e66bab,

title = "Neuromorphic Photonic Integrated Circuits",

abstract = "This paper reviews some recent progress in the field of neuromorphic photonics, with a particular focus on scalability. We provide a framework for understanding the underlying models, and demonstrate a neuron-like processing device - an excitable laser - that has many favorable properties for integration with emerging photonic integrated circuit platforms. On a systems level, we compare several proposed interconnection frameworks that allow for fully tunable networks of photonic neurons.",

keywords = "Bifurcation, excitability, multiple-accumulate (MAC), neural networks, neuromorphic computing, neuromorphic photonics, optoelectronics, photonic integrated circuits (PICs), recurrent network, semiconductor lasers, spiking neural networks (SNNs), wavelength-divison multiplexing (WDM)",

author = "Peng, {Hsuan Tung} and Nahmias, {Mitchell A.} and {De Lima}, {Thomas Ferreira} and Tait, {Alexander N.} and Shastri, {Bhavin J.} and Prucnal, {Paul R.}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.",

year = "2018",

month = nov,

day = "1",

doi = "10.1109/JSTQE.2018.2840448",

language = "English (US)",

volume = "24",

journal = "IEEE Journal of Selected Topics in Quantum Electronics",

issn = "0792-1233",

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

number = "6",

}

TY - JOUR

T1 - Neuromorphic Photonic Integrated Circuits

AU - Peng, Hsuan Tung

AU - Nahmias, Mitchell A.

AU - De Lima, Thomas Ferreira

AU - Tait, Alexander N.

AU - Shastri, Bhavin J.

AU - Prucnal, Paul R.

PY - 2018/11/1

Y1 - 2018/11/1

N2 - This paper reviews some recent progress in the field of neuromorphic photonics, with a particular focus on scalability. We provide a framework for understanding the underlying models, and demonstrate a neuron-like processing device - an excitable laser - that has many favorable properties for integration with emerging photonic integrated circuit platforms. On a systems level, we compare several proposed interconnection frameworks that allow for fully tunable networks of photonic neurons.

AB - This paper reviews some recent progress in the field of neuromorphic photonics, with a particular focus on scalability. We provide a framework for understanding the underlying models, and demonstrate a neuron-like processing device - an excitable laser - that has many favorable properties for integration with emerging photonic integrated circuit platforms. On a systems level, we compare several proposed interconnection frameworks that allow for fully tunable networks of photonic neurons.

KW - Bifurcation

KW - excitability

KW - multiple-accumulate (MAC)

KW - neural networks

KW - neuromorphic computing

KW - neuromorphic photonics

KW - optoelectronics

KW - photonic integrated circuits (PICs)

KW - recurrent network

KW - semiconductor lasers

KW - spiking neural networks (SNNs)

KW - wavelength-divison multiplexing (WDM)

UR - http://www.scopus.com/inward/record.url?scp=85047653860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047653860&partnerID=8YFLogxK

U2 - 10.1109/JSTQE.2018.2840448

DO - 10.1109/JSTQE.2018.2840448

M3 - Article

AN - SCOPUS:85047653860

SN - 0792-1233

VL - 24

JO - IEEE Journal of Selected Topics in Quantum Electronics

JF - IEEE Journal of Selected Topics in Quantum Electronics

IS - 6

M1 - 8364605

ER -

Neuromorphic Photonic Integrated Circuits

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this