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 all-optically process information as the input light diffracts through these passive layers. D2NNs have demonstrated success in various tasks, including object classification, the spectral encoding of information, optical pulse shaping and imaging. Here, we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble learning. After independently training 1252 D2NNs that were diversely engineered with a variety of passive input filters, we applied a pruning algorithm to select an optimized ensemble of D2NNs that collectively improved the image classification accuracy. Through this pruning, we numerically demonstrated that ensembles of N = 14 and N = 30 D2NNs achieve blind testing accuracies of 61.14 ± 0.23% and 62.13 ± 0.05%, respectively, on the classification of CIFAR-10 test images, providing an inference improvement of >16% compared to the average performance of the individual D2NNs within each ensemble. These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.

Computational imaging without a computer: seeing through random diffusers at the speed of light

“…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.…”

Intelligent designs in nanophotonics: from optimization towards inverse creation

“…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.…”

Photonic Matrix Computing: From Fundamentals to Applications

“…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.…”