Share Email Print

Proceedings Paper

Diffractive optical neural networks designed by deep learning (Conference Presentation)
Author(s): Aydogan Ozcan

Paper Abstract

We introduce a physical mechanism to perform machine learning by demonstrating a Diffractive Deep Neural Network architecture that can all-optically implement various functions following the deep learning-based design of passive layers that work collectively. We created 3D-printed diffractive networks that implement classification of images of handwritten digits and fashion products as well as the function of an imaging lens at terahertz spectrum. This passive diffractive network can perform, at the speed of light, various complex functions that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that perform unique tasks using diffractive networks.

Paper Details

Date Published: 9 September 2019
Proc. SPIE 11080, Metamaterials, Metadevices, and Metasystems 2019, 110802J (9 September 2019); doi: 10.1117/12.2525245
Show Author Affiliations
Aydogan Ozcan, Univ. of California, Los Angeles (United States)

Published in SPIE Proceedings Vol. 11080:
Metamaterials, Metadevices, and Metasystems 2019
Nader Engheta; Mikhail A. Noginov; Nikolay I. Zheludev, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?