Share Email Print

Proceedings Paper

Automatic classification of video using a scalable photonic neuro-inspired architecture
Author(s): Damien Rontani; Piotr Antonik; Nicolas Marsal; Daniel Brunner
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 2 March 2020
PDF: 6 pages
Proc. SPIE 11274, Physics and Simulation of Optoelectronic Devices XXVIII, 112740F (2 March 2020);
Show Author Affiliations
Damien Rontani, CentraleSupélec & Univ. de Lorraine (France)
Piotr Antonik, CentraleSupélec & Univ. de Lorraine (France)
Nicolas Marsal, CentraleSupélec & Univ. de Lorraine (France)
Daniel Brunner, CNRS & Univ. Bourgogne Franche-Comté (France)

Published in SPIE Proceedings Vol. 11274:
Physics and Simulation of Optoelectronic Devices XXVIII
Bernd Witzigmann; Marek Osiński; Yasuhiko Arakawa, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?