基于10.6μm波长的小型化非线性全光衍射深度神经网络建模方法  

Modeling Method of Miniaturized Nonlinear All-Optical Diffraction Deep Neural Network Based on 10.6μm Wavelength

作　　者：孙一宸 董明利[1] 于明鑫 夏嘉斌[1] 张旭 白雨晨 鹿利单 祝连庆[1] Sun Yichen;Dong Mingli;Yu Mingxin;Xia Jiabin;Zhang Xu;Bai Yuchen;Lu Lidan;Zhu Lianqing(Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument,Beijing Information Science and Technology University,Beijing 100192,China)

机构地区：[1]北京信息科技大学光电测试技术及仪器教育部重点实验室,北京100192

出　　处：《激光与光电子学进展》2021年第8期395-406,共12页Laser & Optoelectronics Progress

基　　金：北京市自然基金-市教委联合基金(KZ201911232044);高等学校学科创新引智计划(先进光电子器件与系统学科创新引智基地)(D17021)。

摘　　要：提出了一种基于10.6μm波长的小型化非线性全光衍射深度神经网络建模方法。采用波长为10.6μm的二氧化碳(CO2)激光光源,其对应的神经网络物理尺寸为1mm×1mm,依据相关的光学物理参数特性,构建了基于10.6μm波长的非线性全光衍射深度神经网络模型框架,使用网格搜索法确定最优的神经网络模型超参数,并选择交叉熵损失函数和Adam优化器对神经网络进行了优化。分别在MNIST手写数字数据集和Fashion-MNIST数据集上对该方法进行了测试,其分类结果分别达到了0.9630和0.8743。所提方法为制备小型化的全光衍射光栅提供了理论参考。One method used for modeling a miniaturized nonlinear all-optical diffraction deep neural network based on 10.6μm wavelength is proposed.First,a carbon dioxide(CO2)laser light source with a wavelength of 10.6μm is used,and the corresponding physical size of the neural network is 1 mm×1 mm.Second,the model framework of the nonlinear all-optical diffraction deep neural network based on 10.6μm wavelength is constructed according to the characteristics of relevant optical physical parameters.Finally,the grid search method is used to determine the hyper-parameters of the optimal neural network model,and the cross entropy loss function and the Adam optimizer are selected to optimize the neural network.The proposed method is tested on the MNIST handwritten digital dataset and the Fashion-MNIST dataset,respectively,and the classification results reach 0.9630 and 0.8743,respectively.The proposed method provides theoretical reference for the preparation of miniaturized all-optical diffraction gratings.

关 键 词：光计算 非线性全光衍射深度神经网络 激活函数 10.6μm 深度学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]