A photonic artificial intelligence chip is based on an optical neural network (ONN), low power consumption, low delay, and strong antiinterference ability. The all-optical diffractive deep neural network has recently demonstrated its inference capabilities on the image classification task. However, the size of the physical model does not have miniaturization and integration, and the optical nonlinearity is not incorporated into the diffraction neural network. By introducing the nonlinear characteristics of the network, complex tasks can be completed with high accuracy. In this study, a nonlinear all-optical diffraction deep neural network (N-D²NN) model based on 10.6 μm wavelength is constructed by combining the ONN and complex-valued neural networks with the nonlinear activation function introduced into the structure. To be specific, the improved activation function of the rectified linear unit (ReLU), i.e., Leaky-ReLU, parametric ReLU (PReLU), and randomized ReLU (RReLU), is selected as the activation function of the N-D²NN model. Through numerical simulation, it is proved that the N-D²NN model based on 10.6 μm wavelength has excellent representation ability, which enables them to perform classification learning tasks of the MNIST handwritten digital dataset and Fashion-MNIST dataset well, respectively. The results show that the N-D²NN model with the RReLU activation function has the highest classification accuracy of 97.86% and 89.28%, respectively. These results provide a theoretical basis for the preparation of miniaturized and integrated N-D²NN model photonic artificial intelligence chips.

中文翻译：

---

波长为10.6μm的非线性全光衍射深层神经网络用于图像分类

光子人工智能芯片基于光神经网络（ONN），功耗低，时延低，抗干扰能力强。全光学衍射深层神经网络最近证明了其在图像分类任务中的推理能力。但是，物理模型的大小没有小型化和集成化，并且光学非线性没有被纳入衍射神经网络。通过引入网络的非线性特性，可以高精度地完成复杂的任务。在这项研究中，非线性全光衍射深层神经网络（ND ² NN）模型基于10.6  μm波长是通过将ONN和复值神经网络与引入结构的非线性激活函数相结合而构造的。具体而言，将经整流的线性单元（ReLU）的改进的激活函数，即Leaky-ReLU，参数化ReLU（PReLU）和随机化的ReLU（RReLU），选择为ND ² NN模型的激活函数。通过数值模拟，它证明了ND ²基于10.6 NN模型 μ米波长具有优良的表现能力，这使得它们能够执行MNIST手写数字数据集和时尚-MNIST数据集的分类学习任务以及分别。结果表明，ND ²具有RReLU激活功能的NN模型具有最高的分类精度，分别为97.86％和89.28％。这些结果为制备小型化，集成化的ND ² NN模型光子人工智能芯片提供了理论基础。