Design considerations for optical deep learning networks

Birch, Phil, Young, Rupert and Chatwin, Chris (2021) Design considerations for optical deep learning networks. In: ICAEM 21, 30-31st Aug 2021, Pakistan.

Full text not available from this repository.


Performing deep learning in the optical domain is attractive due to the very low electrical power requirements when compared to running networks on a GPU. Since a single positive lens can perform a Fourier transform, correlation operations are relatively simple to implement and they have the potential of a very large computational bandwidth. However, many of the current designs of deep learning networks are not easily implemented in the optical domain. In this paper we develop a python framework for simulating optical deep learning using Pytorch. 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 readily realisable filters such as nematic liquid crystal phase only spatial light modulators is investigated. Key differences still exist such as activation functions and the ability to modulate the signal is limited.

Item Type: Conference or Workshop Item (Other)
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Related URLs:
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 20 Sep 2021 14:41
Last Modified: 04 Oct 2021 16:19
📧 Request an update