Ensemble learning boosts the inference accuracy of diffractive neural networks

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

doi:10.1117/12.2593665

1 August 2021 Ensemble learning boosts the inference accuracy of diffractive neural networks

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

Proceedings Volume 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021; 118040E (2021) https://doi.org/10.1117/12.2593665
Event: SPIE Nanoscience + Engineering, 2021, San Diego, California, United States

Abstract

We improve the inference performance of diffractive deep neural networks (D2NN) for image classification by utilizing ensemble learning and feature engineering. Through a novel pruning algorithm, we designed an ensemble of e.g., N=14 D2NNs that collectively achieve a blind testing accuracy of 61.14% on the classification of CIFAR-10 images, which provides an improvement of >16% compared to the average performance of the individual D2NNs within the ensemble. These results constitute the highest inference accuracies achieved to date by any diffractive network design and would be broadly useful to create diffractive optical machine learning systems for various imaging and sensing needs.

Conference Presentation

Citation Download Citation

Md. Sadman Sakib Rahman, Jingxi Li, Deniz Mengu, Yair Rivenson, and Aydogan Ozcan "Ensemble learning boosts the inference accuracy of diffractive neural networks", Proc. SPIE 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021, 118040E (1 August 2021); https://doi.org/10.1117/12.2593665

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