Optical neural networks trained in situ with reinforcement learning

Oliver Neill; Daniele Faccio

doi:10.1117/12.3021870

18 June 2024 Optical neural networks trained in situ with reinforcement learning

Oliver Neill, Daniele Faccio

Proceedings Volume 13017, Machine Learning in Photonics; 130170L (2024) https://doi.org/10.1117/12.3021870
Event: SPIE Photonics Europe, 2024, Strasbourg, France

Abstract

Optical neural networks enable massively parallel and energy-efficient computing, making them a promising candidate for future sustainable computing architectures. However, the non-differentiability of these systems prohibits gradient-based optimisation, making training these networks a significant challenge. We introduce a meta-learning scheme that employs reinforcement learning to generate a gradient-free optimiser capable of training physical networks on various tasks in situ. The learned optimiser can improve training time and final accuracy compared to existing gradient-free methods when training a diffractive optical network on a variety of image classification tasks, providing a new option for gradient-free training general neuromorphic systems in situ.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Oliver Neill and Daniele Faccio "Optical neural networks trained in situ with reinforcement learning", Proc. SPIE 13017, Machine Learning in Photonics, 130170L (18 June 2024); https://doi.org/10.1117/12.3021870

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