Deep learning with synthetic photonic lattices for equalization in optical transmission systems

Artem V. Pankov; Oleg S. Sidelnikov; Ilya D. Vatnik; Andrey A. Sukhorukov; Dmitriy V. Churkin

doi:10.1117/12.2537462

20 November 2019 Deep learning with synthetic photonic lattices for equalization in optical transmission systems

Artem V. Pankov, Oleg S. Sidelnikov, Ilya D. Vatnik, Andrey A. Sukhorukov, Dmitriy V. Churkin

Author Affiliations +

Proceedings Volume 11192, Real-time Photonic Measurements, Data Management, and Processing IV; 111920N (2019) https://doi.org/10.1117/12.2537462
Event: SPIE/COS Photonics Asia, 2019, Hangzhou, China

Abstract

In this work we propose a new physical realization of optical neural network (ONN) based on a recently appeared technological platform of synthetic photonic lattices (SPL), and demonstrate its capabilities for deep learning. The system operates with time series of optical pulses with ability to easily control their parameters and possesses the architecture that well suits the ONN paradigm. We have also shown that such an ONN can be potentially utilized for signal processing in optical communication lines for signal distortion compensation.

Citation Download Citation

Artem V. Pankov, Oleg S. Sidelnikov, Ilya D. Vatnik, Andrey A. Sukhorukov, and Dmitriy V. Churkin "Deep learning with synthetic photonic lattices for equalization in optical transmission systems", Proc. SPIE 11192, Real-time Photonic Measurements, Data Management, and Processing IV, 111920N (20 November 2019); https://doi.org/10.1117/12.2537462

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