Implementations and optimisations of optical Conv2D networks designs

Philip Birch; Navid Rahimi; Peter Overburry; Rupert Young; Chris Chatwin

doi:10.1117/12.2554021

1 April 2020 Implementations and optimisations of optical Conv2D networks designs

Philip Birch, Navid Rahimi, Peter Overburry, Rupert Young, Chris Chatwin

Proceedings Volume 11356, Semiconductor Lasers and Laser Dynamics IX; 113561C (2020) https://doi.org/10.1117/12.2554021
Event: SPIE Photonics Europe, 2020, Online Only

Abstract

Deep learning for object detection offers the advantage of very low electrical power requirements but with the potential of a very large computation bandwidth due to the ability of Fraunhofer diffraction to perform correlation operations. However, many of the current designs of deep learning networks are not easily implemented in the optical domain. In this paper we develop a modified version of the deep learning library, Keras, that can accurately model optical systems. This allows the discovery of the optimal weights by calculating them on a realistic optical system. Noise sources, speckle models, and calibration errors can be accounted for. The effect of using readily realisable filters such as nematic liquid crystal phase only spatial light modulators is investigated. The effect of multiplexing a number of correlations in order to replicate the Conv2D multiple channel input is assessed. The effect of an optically implementable bias and activation functions are examined and compared to the state-of-the-art software implementations. We show that object recognition can be achieved using spatial light modulator technology and give comparable results to digital implementations.

Conference Presentation

Citation Download Citation

Philip Birch, Navid Rahimi, Peter Overburry, Rupert Young, and Chris Chatwin "Implementations and optimisations of optical Conv2D networks designs", Proc. SPIE 11356, Semiconductor Lasers and Laser Dynamics IX, 113561C (1 April 2020); https://doi.org/10.1117/12.2554021

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