典型文献
Optimization of optical convolution kernel of optoelec-tronic hybrid convolution neural network
文献摘要：
To enhance the optical computation's utilization efficiency,we develop an optimization method for optical convolution kernel in the optoelectronic hybrid convolution neural network(OHCNN).To comply with the actual calculation pro-cess,the convolution kernel is expanded from single-channel to two-channel,containing positive and negative weights.The Fashion-MNIST dataset is used to test the network architecture's accuracy,and the accuracy is improved by 7.5％with the optimized optical convolution kernel.The energy efficiency ratio(EER)of two-channel network is 46.7％higher than that of the single-channel network,and it is 2.53 times of that of traditional electronic products.
文献关键词：
中图分类号：
作者姓名：
XU Xiaofeng;ZHU Lianqing;ZHUANG Wei;ZHANG Dongliang;LU Lidan;YUAN Pei
作者机构：
School of Electro-Optical Engineering,Changchun University of Science and Technology,Jilin 130022,China;Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument,Beijing Information Science and Technology University,Beijing 100192,China;Beijing Laboratory of Optical Fiber Sensing and System,Beijing Information Science and Technology University,Beijing 100016,China
文献出处：
引用格式：
[1]XU Xiaofeng;ZHU Lianqing;ZHUANG Wei;ZHANG Dongliang;LU Lidan;YUAN Pei-.Optimization of optical convolution kernel of optoelec-tronic hybrid convolution neural network)[J].光电子快报（英文版）,2022(03):181-186
A类：
OHCNN
B类：
Optimization,optical,convolution,kernel,hybrid,neural,network,To,enhance,computation,utilization,efficiency,develop,optimization,method,optoelectronic,comply,actual,calculation,cess,is,expanded,from,single,channel,containing,positive,negative,weights,Fashion,MNIST,dataset,used,test,architecture,accuracy,improved,by,optimized,energy,ratio,EER,higher,than,that,times,traditional,products
AB值：
0.486633
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
