当前位置: X-MOL 学术Light Sci. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Ensemble learning of diffractive optical networks
Light: Science & Applications ( IF 19.4 ) Pub Date : 2021-01-11 , DOI: 10.1038/s41377-020-00446-w
Md Sadman Sakib Rahman , Jingxi Li , Deniz Mengu , Yair Rivenson , Aydogan Ozcan

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.



中文翻译:

衍射光网络的综合学习

借助机器学习的力量,光学和光子学领域已出现了大量研究进展。特别地,由于光学计算硬件在并行化,功率效率和计算速度方面对机器学习任务的潜在优势,因此人们对光学计算硬件的兴趣正在复苏。衍射深度神经网络(D 2 NN )形成了这样一种光学计算框架,它受益于基于深度学习的连续衍射层设计,可在输入光通过这些无源层进行衍射时全光学处理信息。第2天NN已在各种任务中证明了成功,包括对象分类,信息的光谱编码,光脉冲整形和成像。在这里,我们使用特征工程和集成学习大大提高了衍射光网络的推理性能。在独立训练了1252个D 2 NN后,这些D 2 NN使用各种无源输入滤波器进行了多种工程设计,我们应用了修剪算法来选择D 2 NN的优化集合,从而共同提高了图像分类的准确性。通过该修剪,我们数值证明了N  = 14和N  = 30 D 2的合奏在CIFAR-10测试图像的分类上,NN分别达到61.14±0.23%和62.13±0.05%的盲测精度,与每个集合中单个D 2 NN的平均性能相比,推理提高了> 16%。这些结果构成了迄今为止在同一数据集上进行任何衍射光学神经网络设计所获得的最高推理精度,并且可能为扩展衍射光学图像分类和机器视觉系统的应用空间提供重大飞跃。

更新日期:2021-01-11
down
wechat
bug