Diffractive neural networks with improved expressive power for gray-scale image classification  

作　　者：MINJIA ZHENG WENZHE LIU LEI SHI JIAN ZI 

机构地区：[1]State Key Laboratory of Surface Physics,Key Laboratory of Micro-and Nano-Photonic Structures(Ministry of Education)and Department of Physics,Fudan University,Shanghai 200433,China [2]Institute for Nanoelectronic Devices and Quantum Computing,Fudan University,Shanghai 200433,China [3]Collaborative Innovation Center of Advanced Microstructures,Nanjing University,Nanjing 210093,China [4]Shanghai Research Center for Quantum Sciences,Shanghai 210315,China

出　　处：《Photonics Research》2024年第6期1159-1166,共8页光子学研究（英文版）

基　　金：Major Program of National Natural Science Foundation of China(T2394481);Science and Technology Commission of Shanghai Municipality(2019SHZDZX01,21DZ1101500,22142200400,23DZ2260100);National Key Research and Development Program of China(2022YFA1404800,2023YFA1406900);National Natural Science Foundation of China(12234007,12221004,12321161645)

摘　　要：In order to harness diffractive neural networks(DNNs)for tasks that better align with real-world computer vision requirements,the incorporation of gray scale is essential.Currently,DNNs are not powerful enough to accomplish gray-scale image processing tasks due to limitations in their expressive power.In our work,we elucidate the relationship between the improvement in the expressive power of DNNs and the increase in the number of phase modulation layers,as well as the optimization of the Fresnel number,which can describe the diffraction process.To demonstrate this point,we numerically trained a double-layer DNN,addressing the prerequisites for intensitybased gray-scale image processing.Furthermore,we experimentally constructed this double-layer DNN based on digital micromirror devices and spatial light modulators,achieving eight-level intensity-based gray-scale image classification for the MNIST and Fashion-MNIST data sets.This optical system achieved the maximum accuracies of 95.10%and 80.61%,respectively.

关 键 词：process MIRROR LIMITATIONS 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]