Birch_SPIE2020.pdf (211.47 kB)
Implementations and optimisations of optical Conv2D networks designs
conference contribution
posted on 2023-06-09, 22:27 authored by Phil BirchPhil Birch, Amir Rahimi, Peter Overbury, Rupert YoungRupert Young, Chris ChatwinChris ChatwinDeep 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.
History
Publication status
- Published
File Version
- Accepted version
Journal
Proceedings Volume 11356, Semiconductor Lasers and Laser Dynamics IXISSN
0277-786XPublisher
SPIEExternal DOI
Volume
11356Article number
a113561CEvent name
SPIE Photonics EuropeEvent location
Online Only, FranceEvent type
conferenceEvent date
6-10 April 2020Series
SPIE Photonics EuropeDepartment affiliated with
- Engineering and Design Publications
Research groups affiliated with
- Industrial Informatics and Signal Processing Research Group Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2020-12-15First Open Access (FOA) Date
2020-12-15First Compliant Deposit (FCD) Date
2020-12-14Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC