Silicon Integrated Photonic-Electronic Multiply-Accumulate Neurons

We experimentally demonstrate an EAM-based photonic-electronic multiply-accumulate neuron that performs inference in a health monitoring task with 1350 trainable parameters, achieving an f1 score of 85.9 % at 10 Gbaud compute rate.

Saved in:

Bibliographic Details
Published in:	2024 Conference on Lasers and Electro-Optics (CLEO) pp. 1 - 2
Main Authors:	Roumpos, I., De Marinis, L., Kincaid, P. S., Paolini, E., Kovaios, S., Tsakyridis, A., Moralis-Pegios, M., Berciano, M., Ferraro, F., Bode, D., Srinivasan, A., Pantouvaki, M., Contestabile, G., Vyrsokinos, K., Pleros, N.
Format:	Conference Proceeding
Language:	English
Published:	Optica 05-05-2024
Subjects:	Electro-optical waveguides Monitoring Neurons Photonics Silicon
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	We experimentally demonstrate an EAM-based photonic-electronic multiply-accumulate neuron that performs inference in a health monitoring task with 1350 trainable parameters, achieving an f1 score of 85.9 % at 10 Gbaud compute rate.