Advancing diffractive network-based image classification by ensemble learning

Md Sadman Sakib Rahman; Jingxi Li; Deniz Mengu; Yair Rivenson; Aydogan Ozcan

doi:10.1117/12.2608016

9 March 2022 Advancing diffractive network-based image classification by ensemble learning

Md Sadman Sakib Rahman, Jingxi Li, Deniz Mengu, Yair Rivenson, Aydogan Ozcan

Proceedings Volume PC12019, AI and Optical Data Sciences III; PC1201901 (2022) https://doi.org/10.1117/12.2608016
Event: SPIE OPTO, 2022, San Francisco, California, United States

Abstract

We report the use of ensemble learning to achieve significant improvements in the performance of diffractive optical classifiers on CIFAR-10 image dataset. We initially created a pool of 1252 diversely-trained diffractive network models; using a novel iterative pruning algorithm, we trimmed this down to an ensemble size of 14 diffractive networks to achieve a blind testing accuracy of 61.14% on CIFAR-10 image classification, which performs >16% higher in its inference accuracy compared to the average performance of the individual diffractive networks within the ensemble. These results signify a major advancement in all-optical inference and image classification capabilities of diffractive networks.

Conference Presentation

Citation Download Citation

Md Sadman Sakib Rahman, Jingxi Li, Deniz Mengu, Yair Rivenson, and Aydogan Ozcan "Advancing diffractive network-based image classification by ensemble learning", Proc. SPIE PC12019, AI and Optical Data Sciences III, PC1201901 (9 March 2022); https://doi.org/10.1117/12.2608016

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Image classification

Image filtering

Computer programming

Optical networks

Statistical inference

RELATED CONTENT

Example based automatic generation of image filters and classifiers based...
Proceedings of SPIE (March 04 2015)

Fourier spatial frequency analysis for image classification training the...
Proceedings of SPIE (April 06 2016)

Pre-processing techniques to improve HEVC subjective quality
Proceedings of SPIE (May 01 2017)

Ensemble learning boosts the inference accuracy of diffractive neural networks
Proceedings of SPIE (January 01 1900)

Local structure learning and prediction for efficient image compression
Proceedings of SPIE (January 19 2009)

Time-lapse image classification boosts diffractive optical network inference accuracy
Proceedings of SPIE (January 01 1900)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years