University of Sussex
Browse

File(s) not publicly available

Design considerations for optical deep learning networks

presentation
posted on 2023-06-10, 00:51 authored by Phil BirchPhil Birch, Rupert YoungRupert Young, Chris ChatwinChris Chatwin
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.

History

Publication status

  • Published

Journal

International Conference on Applied and Engineering Mathematics

Publisher

IEEE

Presentation Type

  • other

Event name

ICAEM 21

Event location

Pakistan

Event type

conference

Event date

30-31st Aug 2021

Department affiliated with

  • Engineering and Design Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2021-09-20

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC