2021
DOI: 10.1038/s41377-020-00446-w
|View full text |Cite|
|
Sign up to set email alerts
|

Ensemble learning of diffractive optical networks

Abstract: A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning. Specifically, there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization, power efficiency and computation speed. Diffractive deep neural networks (D2NNs) form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
51
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9

Relationship

4
5

Authors

Journals

citations
Cited by 105 publications
(61 citation statements)
references
References 47 publications
0
51
0
Order By: Relevance
“…S2. A Fresnel lens was designed to have a focal length (f ) of 145.6 λ and a pupil diameter of 104 λ [88]. The transmission profile of the lens t L was formulated as: where x and y denote the distance from the center of the lens in lateral coordinates.…”
Section: Lens-based Imaging System Simulationmentioning
confidence: 99%
“…S2. A Fresnel lens was designed to have a focal length (f ) of 145.6 λ and a pupil diameter of 104 λ [88]. The transmission profile of the lens t L was formulated as: where x and y denote the distance from the center of the lens in lateral coordinates.…”
Section: Lens-based Imaging System Simulationmentioning
confidence: 99%
“…The parameters embedded in diffractive layers were iteratively tuned throughout the error backpropagation learning process. As a result, the classification accuracy of optical D 2 NN reached 93.39% (seven layers) for digits dataset (Modified National Institute of Standards and Technology, MNIST) and In follow-up studies, a set of groups continued to improve the system performance of D 2 NN by several meanings [127][128][129][130]. For acceleration of D 2 NN training speed, Zhou et al [123] conducted the backpropagation algorithm for in situ training of both linear and nonlinear optical networks.…”
Section: Optical Diffractive Neural Networkmentioning
confidence: 99%
“…In this work, the training process of ONNs is still completed by an electronic computer to update parameters, and each diffractive layer is fabricated by 3D printing technology. In 2021, Rahman et al applied a pruning algorithm to further improve the image classification accuracy of D 2 NNs [ 23 ]. On the image classification of the CIFAR-10 dataset released by Canadian Institute For Advanced Research, whose test images are more complicated than MNIST and Fashion-MNIST, the D 2 NN architecture combined with the pruning algorithm provides an inference improvement of more than 16% compared to the average performance.…”
Section: Mplc Matrix Corementioning
confidence: 99%