PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Convolution Neural Networks are one of the pillars of the Machine Learning revolution over the last years. However, convolution operation is associated with a high computational cost. Here, we present a compact and high-speed solution to perform convolution leveraging optics on a chip, with the potential to reach over 350 TOPS/W.
Conference Presentation
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Nicola Peserico, Shurui Li, Hangbo Yang, Hamed Dalir, Puneet Gupta, Volker J. Sorger, "PhotoFourier: silicon photonics joint transfer correlator for convolution neural network," Proc. SPIE 12673, Optics and Photonics for Information Processing XVII, 1267307 (4 October 2023); https://doi.org/10.1117/12.2678666