Opt Lett. 2019 Nov 1;44(21):5186-5189. doi: 10.1364/OL.44.005186.
An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can work only under coherent light illumination, and the precision requirement in practical experiments is quite high. This Letter proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity, and can be easily programmable.
一种光学衍射神经网络 (DNN) 可以通过级联相位掩模结构来实现。与光学计算机类似，该系统可以以全光方式执行数字识别等机器学习任务。然而，该系统只能在相干光照明下工作，并且实际实验中的精度要求相当高。本信提出了一种基于单像素成像 (MLSPI) 的光学机器学习框架。该 MLSPI 系统可以执行与 DNN 相同的线性模式识别任务。此外，它可以在非相干照明条件下工作，具有较低的实验复杂性，并且易于编程。
