Prospects and applications of photonic neural networks

Chaoran Huang; Volker J. Sorger; Mario Miscuglio; Mohammed Al-Qadasi; Avilash Mukherjee; Lutz Lampe; Mitchell Nichols; Alexander N. Tait; Thomas Ferreira de Lima; Bicky A. Marquez; Jiahui Wang; Lukas Chrostowski; Mable P. Fok; Daniel Brunner; Shanhui Fan; Sudip Shekhar; Paul R. Prucnal; Bhavin J. Shastri

doi:10.1080/23746149.2021.1981155

Prospects and applications of photonic neural networks

Chaoran Huang, Volker J. Sorger, Mario Miscuglio, Mohammed Al-Qadasi, Avilash Mukherjee, Lutz Lampe, Mitchell Nichols, Alexander N. Tait, Thomas Ferreira de Lima, Bicky A. Marquez, Jiahui Wang, Lukas Chrostowski, Mable P. Fok, Daniel Brunner, Shanhui Fan, Sudip Shekhar, Paul R. Prucnal, Bhavin J. Shastri

Research output: Contribution to journal › Review article › peer-review

120 Scopus citations

Abstract

Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on conventional computers that have separate memory and processor (and that operate sequentially) are limited in speed and energy efficiency. Neuromorphic engineering aims to build processors in which hardware mimics neurons and synapses in the brain for distributed and parallel processing. Neuromorphic engineering enabled by photonics (optical physics) can offer sub-nanosecond latencies and high bandwidth with low energies to extend the domain of artificial intelligence and neuromorphic computing applications to machine learning acceleration, nonlinear programming, intelligent signal processing, etc. Photonic neural networks have been demonstrated on integrated platforms and free-space optics depending on the class of applications being targeted. Here, we discuss the prospects and demonstrated applications of these photonic neural networks.

Original language	English (US)
Article number	1981155
Journal	Advances in Physics: X
Volume	7
Issue number	1
DOIs	https://doi.org/10.1080/23746149.2021.1981155
State	Published - 2022

All Science Journal Classification (ASJC) codes

General Physics and Astronomy

Keywords

Photonic neural networks
artificial intelligence
machine learning
neuromorphic computing
neuromorphic photonics
silicon photonics

Access to Document

10.1080/23746149.2021.1981155

Cite this

Huang, C., Sorger, V. J., Miscuglio, M., Al-Qadasi, M., Mukherjee, A., Lampe, L., Nichols, M., Tait, A. N., Ferreira de Lima, T., Marquez, B. A., Wang, J., Chrostowski, L., Fok, M. P., Brunner, D., Fan, S., Shekhar, S., Prucnal, P. R., & Shastri, B. J. (2022). Prospects and applications of photonic neural networks. Advances in Physics: X, 7(1), Article 1981155. https://doi.org/10.1080/23746149.2021.1981155

@article{29545aee1fd846c7b561309e5402f104,

title = "Prospects and applications of photonic neural networks",

abstract = "Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on conventional computers that have separate memory and processor (and that operate sequentially) are limited in speed and energy efficiency. Neuromorphic engineering aims to build processors in which hardware mimics neurons and synapses in the brain for distributed and parallel processing. Neuromorphic engineering enabled by photonics (optical physics) can offer sub-nanosecond latencies and high bandwidth with low energies to extend the domain of artificial intelligence and neuromorphic computing applications to machine learning acceleration, nonlinear programming, intelligent signal processing, etc. Photonic neural networks have been demonstrated on integrated platforms and free-space optics depending on the class of applications being targeted. Here, we discuss the prospects and demonstrated applications of these photonic neural networks.",

keywords = "Photonic neural networks, artificial intelligence, machine learning, neuromorphic computing, neuromorphic photonics, silicon photonics",

author = "Chaoran Huang and Sorger, {Volker J.} and Mario Miscuglio and Mohammed Al-Qadasi and Avilash Mukherjee and Lutz Lampe and Mitchell Nichols and Tait, {Alexander N.} and {Ferreira de Lima}, Thomas and Marquez, {Bicky A.} and Jiahui Wang and Lukas Chrostowski and Fok, {Mable P.} and Daniel Brunner and Shanhui Fan and Sudip Shekhar and Prucnal, {Paul R.} and Shastri, {Bhavin J.}",

note = "Publisher Copyright: {\textcopyright} 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.",

year = "2022",

doi = "10.1080/23746149.2021.1981155",

language = "English (US)",

volume = "7",

journal = "Advances in Physics: X",

issn = "2374-6149",

publisher = "Taylor and Francis Ltd.",

number = "1",

}

Huang, C, Sorger, VJ, Miscuglio, M, Al-Qadasi, M, Mukherjee, A, Lampe, L, Nichols, M, Tait, AN, Ferreira de Lima, T, Marquez, BA, Wang, J, Chrostowski, L, Fok, MP, Brunner, D, Fan, S, Shekhar, S, Prucnal, PR & Shastri, BJ 2022, 'Prospects and applications of photonic neural networks', Advances in Physics: X, vol. 7, no. 1, 1981155. https://doi.org/10.1080/23746149.2021.1981155

TY - JOUR

T1 - Prospects and applications of photonic neural networks

AU - Huang, Chaoran

AU - Sorger, Volker J.

AU - Miscuglio, Mario

AU - Al-Qadasi, Mohammed

AU - Mukherjee, Avilash

AU - Lampe, Lutz

AU - Nichols, Mitchell

AU - Tait, Alexander N.

AU - Ferreira de Lima, Thomas

AU - Marquez, Bicky A.

AU - Wang, Jiahui

AU - Chrostowski, Lukas

AU - Fok, Mable P.

AU - Brunner, Daniel

AU - Fan, Shanhui

AU - Shekhar, Sudip

AU - Prucnal, Paul R.

AU - Shastri, Bhavin J.

PY - 2022

Y1 - 2022

N2 - Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on conventional computers that have separate memory and processor (and that operate sequentially) are limited in speed and energy efficiency. Neuromorphic engineering aims to build processors in which hardware mimics neurons and synapses in the brain for distributed and parallel processing. Neuromorphic engineering enabled by photonics (optical physics) can offer sub-nanosecond latencies and high bandwidth with low energies to extend the domain of artificial intelligence and neuromorphic computing applications to machine learning acceleration, nonlinear programming, intelligent signal processing, etc. Photonic neural networks have been demonstrated on integrated platforms and free-space optics depending on the class of applications being targeted. Here, we discuss the prospects and demonstrated applications of these photonic neural networks.

AB - Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on conventional computers that have separate memory and processor (and that operate sequentially) are limited in speed and energy efficiency. Neuromorphic engineering aims to build processors in which hardware mimics neurons and synapses in the brain for distributed and parallel processing. Neuromorphic engineering enabled by photonics (optical physics) can offer sub-nanosecond latencies and high bandwidth with low energies to extend the domain of artificial intelligence and neuromorphic computing applications to machine learning acceleration, nonlinear programming, intelligent signal processing, etc. Photonic neural networks have been demonstrated on integrated platforms and free-space optics depending on the class of applications being targeted. Here, we discuss the prospects and demonstrated applications of these photonic neural networks.

KW - Photonic neural networks

KW - artificial intelligence

KW - machine learning

KW - neuromorphic computing

KW - neuromorphic photonics

KW - silicon photonics

UR - http://www.scopus.com/inward/record.url?scp=85118783026&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85118783026&partnerID=8YFLogxK

U2 - 10.1080/23746149.2021.1981155

DO - 10.1080/23746149.2021.1981155

M3 - Review article

AN - SCOPUS:85118783026

SN - 2374-6149

VL - 7

JO - Advances in Physics: X

JF - Advances in Physics: X

IS - 1

M1 - 1981155

ER -

Prospects and applications of photonic neural networks

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this