Automatic classification of video using a scalable photonic neuro-inspired architecture

Damien Rontani; Piotr Antonik; Nicolas Marsal; Daniel Brunner

doi:10.1117/12.2551368

2 March 2020 Automatic classification of video using a scalable photonic neuro-inspired architecture

Damien Rontani, Piotr Antonik, Nicolas Marsal, Daniel Brunner

Proceedings Volume 11274, Physics and Simulation of Optoelectronic Devices XXVIII; 112740F (2020) https://doi.org/10.1117/12.2551368
Event: SPIE OPTO, 2020, San Francisco, California, United States

Abstract

We propose a physical alternative of software based approaches for advanced classification task by considering a photonic-based architecture implementing a recurrent neural network with up to 16,384 physical neurons. This architecture is realized with o↵-the-shelf components and can be scaled up to hundred thousand or millions of nodes while ensuring data-ecient training strategy thanks to the reservoir computing framework. We use this architecture to perform a challenging computer vision task: the classification of human actions from a video feed. For this task, we show for the first time that a physical architecture with a simple learning strategy, consisting of training one linear readout for each class, can achieve a >90% success rate in terms of classification accuracy. This rivals the deep-learning approaches in terms of level of performance and hence could pave the way towards novel paradigm for ecient real-time video processing at the physical layer using photonic systems.

Citation Download Citation

Damien Rontani, Piotr Antonik, Nicolas Marsal, and Daniel Brunner "Automatic classification of video using a scalable photonic neuro-inspired architecture", Proc. SPIE 11274, Physics and Simulation of Optoelectronic Devices XXVIII, 112740F (2 March 2020); https://doi.org/10.1117/12.2551368

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