All-optical output layer in photonic extreme learning machines

Vicente Rocha; Tiago D. Ferreira; Nuno A. Silva

doi:10.1117/12.3021888

18 June 2024 All-optical output layer in photonic extreme learning machines

Vicente Rocha, Tiago D. Ferreira, Nuno A. Silva

Proceedings Volume 13017, Machine Learning in Photonics; 1301714 (2024) https://doi.org/10.1117/12.3021888
Event: SPIE Photonics Europe, 2024, Strasbourg, France

Conference Poster

Abstract

Lately, the field of optical computing resurfaced with the demonstration of a series of novel photonic neuromorphic schemes for autonomous and inline data processing promising parallel and light-speed computing. We emphasize the Photonic Extreme Learning Machine (PELM) as a versatile configuration exploring the randomness of optical media and device production to bypass the training of the hidden layer. Nevertheless, the implementation of this framework is limited to having the output layer performed digitally. In this work, we extend the general PELM implementation to an all-optical configuration by exploring the amplitude modulation from a spatial light modulator (SLM) as an output linear layer with the main challenge residing in the training of the output weights. The proposed solution explores the package pyTorch to train a digital twin using gradient descent back-propagation. The trained model is then transposed to the SLM performing the linear output layer. We showcase this methodology by solving a two-class classification problem where the total intensity reaching the camera predicts the class of the input sample.

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

Citation Download Citation

Vicente Rocha, Tiago D. Ferreira, and Nuno A. Silva "All-optical output layer in photonic extreme learning machines", Proc. SPIE 13017, Machine Learning in Photonics, 1301714 (18 June 2024); https://doi.org/10.1117/12.3021888

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