Optoelectronic convolutional neural networks based on time-stretch method  

作　　者：Yubin ZANG Minghua CHEN Sigang YANG Hongwei CHEN 

机构地区：[1]Beijing National Research Center for Information Science and Technology(BNRist),Department of Electronic Engineering,Tsinghua University,Beijing 100084,China

出　　处：《Science China(Information Sciences)》2021年第2期176-187,共12页中国科学（信息科学）（英文版）

基　　金：supported by National Key Research and Development Program of China(Grant No.2019YFB1803501);National Natural Science Foundation of China(Grant No.61771284);Beijing Natural Science Foundation(Grant No.L182043)。

摘　　要：In this paper, a new architecture of optoelectronic convolutional neural networks(CNNs) based on time-stretch method is proposed. In this loop-shaped structure mainly composed of fiber optical and electronic devices, computations of data from each layer of CNN which are carried by light pulses with high repetition rate can be accomplished in a serial way. Therefore, a 5-layer CNN with two convolution layers,two mean pooling layers and one fully-connected layer are implemented. Under the test of handwriting digit recognition, its accuracy can reach up to 95% under ideal circumstances. Tests under different relative noise levels have been conducted and analyzed as well.

关 键 词：convolutional neural networks time-stretch method artificial intelligence 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN29[自动化与计算机技术—控制科学与工程]