基于10.6微米全光深度神经网络衍射光栅的设计与实现  

Design and implementation of diffraction grating based on 10.6μm all-optical depth neural network

作　　者：牛海莎 于明鑫 祝博飞 姚齐峰 张乾坤 鹿利单 钟国舜[3] 祝连庆[1] NIU Hai-Sha;YU Ming-Xin;ZHU Bo-Fei;YAO Qi-Feng;ZHANG Qian-Kun;LU Li-Dan;ZHONG Guo-Shun;ZHU Lian-Qing(Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument,Beijing Information Science&Technology University,Beijing 100192,China;Beijing ZX Intelligent Chip Technology Co.,Ltd.,Beijing 100876,China;The 11th Research Institute of China Electronic Science&Technology Group Inc.,Beijing 100015,China)

机构地区：[1]光电测试技术与仪器教育部重点实验室,北京信息科技大学,北京100192 [2]北京紫溪智芯科技有限公司,北京100876 [3]中国电子科技集团公司第十一研究所,北京100015

出　　处：《红外与毫米波学报》2020年第1期13-18,共6页Journal of Infrared and Millimeter Waves

基　　金：高等学校学科创新引智计划(D17021);国家自然科学基金重点项目(51535002);促进高校内涵发展项目(5211910905)~~

摘　　要：光子人工智能芯片以光速执行运算,且具有低功耗、延迟低、抗电磁干扰的优势。小型化与集成化是实现这一技术革新的关键步骤。本文将光刻技术运用于衍射光栅的制作,提出一种基于10.6微米激光的全光衍射深度学习神经网络光栅设计及实现方法。由于光源波长由毫米波向微米波进化,神经元的特征尺度缩小至20微米,与现有光衍射神经网络相比,深度学习神经网络特征尺寸缩小了80倍,为进一步实现光子计算芯片大规模集成奠定了基础。The photonic artificial intelligent chip performs calculations at the speed of light,and has the advantages of low power consumption,low delay,and anti-electromagnetic interference.Miniaturization and integration are the key steps to realize this technological innovation.In this paper,lithography is applied to the fabrication of diffraction gratings.A design and implementation method of all-optics diffraction deep learning neural network grating based on 10.6 micron laser is proposed.Since the wavelength of the light source evolved from the millimeter wave to micrometer wave,the characteristic scale of the neuron are reduced to 20 micrometers.Compared with the existing optical computing neural network,the feature size of the deep learning neural network is reduced by 80 times,which laid the foundation for further large-scale integration of photonic computing chips.

关 键 词：光子芯片 衍射光栅 深度学习 神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]