Silicon Photonic Neuromorphic Computing with 16 GHz Input Data and Weight Update Line Rates

Apostolos Tsakyridis; George Giamougiannis; George Mourgias-Alexandris; Angelina Totovic; George Dabos; Nikolaos Passalis; Manos Kirtas; Anastasios Tefas; Miltiadis Moralis-Pegios; Nikos Pleros

doi:10.1364/CLEO_SI.2022.STh5G.1

Conference on Lasers and Electro-Optics
Technical Digest Series (Optica Publishing Group, 2022),
paper STh5G.1
•https://doi.org/10.1364/CLEO_SI.2022.STh5G.1

Silicon Photonic Neuromorphic Computing with 16 GHz Input Data and Weight Update Line Rates

Apostolos Tsakyridis, George Giamougiannis, George Mourgias-Alexandris, Angelina Totovic, George Dabos, Nikolaos Passalis, Manos Kirtas, Anastasios Tefas, Miltiadis Moralis-Pegios, and Nikos Pleros

CLEO: Science and Innovations 2022

San Jose, California United States
15–20 May 2022
ISBN: 978-1-957171-05-0

From the session
Neuromorphic Photonics (STh5G)

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
A. Tsakyridis, G. Giamougiannis, G. Mourgias-Alexandris, A. Totovic, G. Dabos, N. Passalis, M. Kirtas, A. Tefas, M. Moralis-Pegios, and N. Pleros, "Silicon Photonic Neuromorphic Computing with 16 GHz Input Data and Weight Update Line Rates," in Conference on Lasers and Electro-Optics, Technical Digest Series (Optica Publishing Group, 2022), paper STh5G.1.

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Get Video
Citation alert
Save article

Abstract

We experimentally demonstrate a silicon photonic neuron that supports on-chip input-data and weight update rates at 16GHz. Its computational performance is evaluated via the classification of the MNIST dataset achieving a mean accuracy of 99.18%.

PDF Article | Presentation Video

More Like This

DDOS attack identification via a silicon photonic Deep Neural Network with 50 GHz input and weight update

Apostolos Tsakyridis, George Giamougiannis, Miltiadis Moralis-Pegios, George Mourgias-Alexandris, Angelina R. Totovic, George Dabos, Manos Kirtas, Nikolaos Passalis, Anastasios Tefas, Dimitrios Kalavrouziotis, Dimitris Syrivelis, P. Bakopoulos, E. Mentovich, and Nikos Pleros
W3G.1 Optical Fiber Communication Conference (OFC) 2023

High-speed analog photonic computing with tiled matrix multiplication and dynamic precision capabilities for DNNs

George Giamougiannis, Apostolos Tsakyridis, Miltiadis Moralis-Pegios, Christos Pappas, Manos Kirtas, Nikolaos Passalis, David Lazovsky, Anastasios Tefas, and Nikos Pleros
We5.20 European Conference and Exhibition on Optical Communication (ECOC) 2022

Photonic Neuromorphic Computing: Architectures, Technologies, and Training Models

Miltiadis Moralis-Pegios, Angelina Totovic, Apostolos Tsakyridis, George Giamougiannis, George Mourgias-Alexandris, George Dabos, Nikolaos Passalis, Manos Kirtas, Anastasios Tefas, and Nikos Pleros
M1G.4 Optical Fiber Communication Conference (OFC) 2022

Previous Article Next Article

Presentation Video

Presentation video access is available to:

Optica Publishing Group subscribers
Technical meeting attendees
Optica members who wish to use one of their free downloads. Please download the article first. After downloading, please refresh this page.

Contact your librarian or system administrator
or
Log in to access Optica Member Subscription or free downloads

More Like This

DDOS attack identification via a silicon photonic Deep Neural Network with 50 GHz input and weight update

High-speed analog photonic computing with tiled matrix multiplication and dynamic precision capabilities for DNNs

Photonic Neuromorphic Computing: Architectures, Technologies, and Training Models