Physics-aware-trained diffractive deep neural networks

Kohei Yamamoto; Hiroyuki Yanagisawa

doi:10.1117/12.2675468

28 September 2023 Physics-aware-trained diffractive deep neural networks

Kohei Yamamoto, Hiroyuki Yanagisawa

Proceedings Volume 12655, Emerging Topics in Artificial Intelligence (ETAI) 2023; 126550F (2023) https://doi.org/10.1117/12.2675468
Event: SPIE Nanoscience + Engineering, 2023, San Diego, California, United States

Abstract

We have applied physics aware training (PAT) to diffractive deep neural networks (D2NN) consisting of multiple spatial light modulators (SLMs) to close the reality gap between the simulation model and the physical system. Compared to conventional training methods using only simulation models, PAT improves classification accuracy in the experiment. In this method, an analytic expression for backpropagation is based on Rayleigh-Sommerfeld diffraction integral as conventional, but the backpropagated error values are replaced by the measured values.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Kohei Yamamoto and Hiroyuki Yanagisawa "Physics-aware-trained diffractive deep neural networks", Proc. SPIE 12655, Emerging Topics in Artificial Intelligence (ETAI) 2023, 126550F (28 September 2023); https://doi.org/10.1117/12.2675468

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available