The University of Southampton
University of Southampton Institutional Repository

Noise-resilient and high-speed deep learning with coherent silicon photonics

Noise-resilient and high-speed deep learning with coherent silicon photonics
Noise-resilient and high-speed deep learning with coherent silicon photonics

The explosive growth of deep learning applications has triggered a new era in computing hardware, targeting the efficient deployment of multiply-and-accumulate operations. In this realm, integrated photonics have come to the foreground as a promising energy efficient deep learning technology platform for enabling ultra-high compute rates. However, despite integrated photonic neural network layouts have already penetrated successfully the deep learning era, their compute rate and noise-related characteristics are still far beyond their promise for high-speed photonic engines. Herein, we demonstrate experimentally a noise-resilient deep learning coherent photonic neural network layout that operates at 10GMAC/sec/axon compute rates and follows a noise-resilient training model. The coherent photonic neural network has been fabricated as a silicon photonic chip and its MNIST classification performance was experimentally evaluated to support accuracy values of >99% and >98% at 5 and 10GMAC/sec/axon, respectively, offering 6× higher on-chip compute rates and >7% accuracy improvement over state-of-the-art coherent implementations.

2041-1723
5572
Mourgias-Alexandris, G.
44afb581-c021-4354-bcad-3112d33533da
Moralis-Pegios, M.
e6448ee5-e507-4989-99ad-9d16f7b4da0a
Tsakyridis, A.
58de829a-b1c8-4b1d-a416-3207381923e9
Simos, S.
9b7382b6-c156-42be-a8a6-c2242a8e7e5e
Dabos, G.
b5ea6c10-d366-40a8-9c4b-86c0fcbb045f
Totovic, A.
fcfddba1-c9e7-497f-8666-071a00ec7979
Passalis, N.
1894f976-e397-422d-bef8-c334114cace1
Kirtas, M.
2f570503-b88e-4f73-bfb8-d4965445c587
Rutirawut, T.
590101f7-65c8-4da3-9a5d-e3d2efd74349
Gardes, F. Y.
7a49fc6d-dade-4099-b016-c60737cb5bb2
Tefas, A.
79348442-4404-46bd-a2f2-aeb9530f36bd
Pleros, N.
bcf4688d-05c5-4b72-95fa-dee52e7a2bdf
Mourgias-Alexandris, G.
44afb581-c021-4354-bcad-3112d33533da
Moralis-Pegios, M.
e6448ee5-e507-4989-99ad-9d16f7b4da0a
Tsakyridis, A.
58de829a-b1c8-4b1d-a416-3207381923e9
Simos, S.
9b7382b6-c156-42be-a8a6-c2242a8e7e5e
Dabos, G.
b5ea6c10-d366-40a8-9c4b-86c0fcbb045f
Totovic, A.
fcfddba1-c9e7-497f-8666-071a00ec7979
Passalis, N.
1894f976-e397-422d-bef8-c334114cace1
Kirtas, M.
2f570503-b88e-4f73-bfb8-d4965445c587
Rutirawut, T.
590101f7-65c8-4da3-9a5d-e3d2efd74349
Gardes, F. Y.
7a49fc6d-dade-4099-b016-c60737cb5bb2
Tefas, A.
79348442-4404-46bd-a2f2-aeb9530f36bd
Pleros, N.
bcf4688d-05c5-4b72-95fa-dee52e7a2bdf

Mourgias-Alexandris, G., Moralis-Pegios, M., Tsakyridis, A., Simos, S., Dabos, G., Totovic, A., Passalis, N., Kirtas, M., Rutirawut, T., Gardes, F. Y., Tefas, A. and Pleros, N. (2022) Noise-resilient and high-speed deep learning with coherent silicon photonics. Nature Communications, 13 (1), 5572, [5572]. (doi:10.1038/s41467-022-33259-z).

Record type: Article

Abstract

The explosive growth of deep learning applications has triggered a new era in computing hardware, targeting the efficient deployment of multiply-and-accumulate operations. In this realm, integrated photonics have come to the foreground as a promising energy efficient deep learning technology platform for enabling ultra-high compute rates. However, despite integrated photonic neural network layouts have already penetrated successfully the deep learning era, their compute rate and noise-related characteristics are still far beyond their promise for high-speed photonic engines. Herein, we demonstrate experimentally a noise-resilient deep learning coherent photonic neural network layout that operates at 10GMAC/sec/axon compute rates and follows a noise-resilient training model. The coherent photonic neural network has been fabricated as a silicon photonic chip and its MNIST classification performance was experimentally evaluated to support accuracy values of >99% and >98% at 5 and 10GMAC/sec/axon, respectively, offering 6× higher on-chip compute rates and >7% accuracy improvement over state-of-the-art coherent implementations.

Text
s41467-022-33259-z (1) - Version of Record
Available under License Creative Commons Attribution.
Download (2MB)

More information

Accepted/In Press date: 9 September 2022
e-pub ahead of print date: 23 September 2022
Published date: 23 September 2022
Additional Information: © 2022. The Author(s).

Identifiers

Local EPrints ID: 471364
URI: http://eprints.soton.ac.uk/id/eprint/471364
ISSN: 2041-1723
PURE UUID: 6ec34d3f-f15c-4c3b-9f97-b5dcae6b0101
ORCID for F. Y. Gardes: ORCID iD orcid.org/0000-0003-1400-3272

Catalogue record

Date deposited: 03 Nov 2022 18:06
Last modified: 31 Jan 2024 02:43

Export record

Altmetrics

Contributors

Author: G. Mourgias-Alexandris
Author: M. Moralis-Pegios
Author: A. Tsakyridis
Author: S. Simos
Author: G. Dabos
Author: A. Totovic
Author: N. Passalis
Author: M. Kirtas
Author: T. Rutirawut
Author: F. Y. Gardes ORCID iD
Author: A. Tefas
Author: N. Pleros

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×