Li Yiming, Zheng Zexi, Li Ran, Chen Quan, Luan Haitao, Yang Hui, Zhang Qiming, Gu Min
Opt Express. 2022 Sep 26;30(20):36700-36710. doi: 10.1364/OE.468648.
As an all-optical learning framework, diffractive deep neural networks (DNNs) have great potential in running speed, data throughput, and energy consumption. The depth of networks and the misalignment of layers are two problems to limit its further development. In this work, a robust all-optical network framework (multiscale diffractive U-Net, MDUNet) based on multi-scale features fusion has been proposed. The depth expansion and alignment robustness of the network can be significantly improved by introducing sampling and skip connections. Compared with common all-optical learning frameworks, MDUNet achieves the highest accuracy of 98.81% and 89.11% on MNIST and Fashion-MNIST respectively. The testing accuracy of MNIST and Fashion-MNIST can be further improved to 99.06% and 89.86% respectively by using the ensemble learning method to construct the optoelectronic hybrid neural network.
作为一种全光学习框架，衍射深度神经网络（DNNs）在运行速度、数据吞吐量和能耗方面具有巨大潜力。网络深度和层间失准是限制其进一步发展的两个问题。在这项工作中，提出了一种基于多尺度特征融合的稳健全光网络框架（多尺度衍射U-Net，MDUNet）。通过引入采样和跳跃连接，可以显著提高网络的深度扩展和对齐鲁棒性。与常见的全光学习框架相比，MDUNet在MNIST和Fashion-MNIST上分别达到了98.81%和89.11%的最高准确率。通过使用集成学习方法构建光电混合神经网络，MNIST和Fashion-MNIST的测试准确率可分别进一步提高到99.06%和89.86%。
