A silicon photonic coherent neuron with 10GMAC/sec processing line-rate
A silicon photonic coherent neuron with 10GMAC/sec processing line-rate
We demonstrate a novel coherent Si-Pho neuron with 10Gbaud on-chip input-data vector generation capabilities. Its performance as a hidden layer within a neural network has been experimentally validated for the MNIST data-set, yielding 96.19% accuracy.
Mourgias-Alexandris, George
57c31ebb-de8d-4d7e-b17e-8be4ec646318
Moralis-Pegios, Miltiadis
ed2f6e60-508e-4307-a692-620fad3aa31e
Simos, Stelios
9b7382b6-c156-42be-a8a6-c2242a8e7e5e
Dabos, George
b5ea6c10-d366-40a8-9c4b-86c0fcbb045f
Passalis, Nikos
1894f976-e397-422d-bef8-c334114cace1
Kirtas, Manos
cd8891ae-f270-423d-bc40-9d624003986c
Rutirawut, Teerapat
590101f7-65c8-4da3-9a5d-e3d2efd74349
Gardes, Frederic
7a49fc6d-dade-4099-b016-c60737cb5bb2
Tefas, Anastasios
b88c667d-2147-4efc-8138-8dfe142457d1
Pleros, Nikos
31745dfe-bbc5-490a-bd49-0384f573f353
6 June 2021
Mourgias-Alexandris, George
57c31ebb-de8d-4d7e-b17e-8be4ec646318
Moralis-Pegios, Miltiadis
ed2f6e60-508e-4307-a692-620fad3aa31e
Simos, Stelios
9b7382b6-c156-42be-a8a6-c2242a8e7e5e
Dabos, George
b5ea6c10-d366-40a8-9c4b-86c0fcbb045f
Passalis, Nikos
1894f976-e397-422d-bef8-c334114cace1
Kirtas, Manos
cd8891ae-f270-423d-bc40-9d624003986c
Rutirawut, Teerapat
590101f7-65c8-4da3-9a5d-e3d2efd74349
Gardes, Frederic
7a49fc6d-dade-4099-b016-c60737cb5bb2
Tefas, Anastasios
b88c667d-2147-4efc-8138-8dfe142457d1
Pleros, Nikos
31745dfe-bbc5-490a-bd49-0384f573f353
Mourgias-Alexandris, George, Moralis-Pegios, Miltiadis, Simos, Stelios, Dabos, George, Passalis, Nikos, Kirtas, Manos, Rutirawut, Teerapat, Gardes, Frederic, Tefas, Anastasios and Pleros, Nikos
(2021)
A silicon photonic coherent neuron with 10GMAC/sec processing line-rate.
In 2021 Optical Fiber Communications Conference and Exhibition (OFC).
(doi:10.1364/OFC.2021.Tu5H.1).
Record type:
Conference or Workshop Item
(Paper)
Abstract
We demonstrate a novel coherent Si-Pho neuron with 10Gbaud on-chip input-data vector generation capabilities. Its performance as a hidden layer within a neural network has been experimentally validated for the MNIST data-set, yielding 96.19% accuracy.
This record has no associated files available for download.
More information
Published date: 6 June 2021
Identifiers
Local EPrints ID: 457344
URI: http://eprints.soton.ac.uk/id/eprint/457344
PURE UUID: a14e2ae3-e207-4197-b423-ee19647f84b3
Catalogue record
Date deposited: 01 Jun 2022 16:44
Last modified: 17 Mar 2024 03:26
Export record
Altmetrics
Contributors
Author:
George Mourgias-Alexandris
Author:
Miltiadis Moralis-Pegios
Author:
Stelios Simos
Author:
George Dabos
Author:
Nikos Passalis
Author:
Manos Kirtas
Author:
Teerapat Rutirawut
Author:
Frederic Gardes
Author:
Anastasios Tefas
Author:
Nikos 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