典型文献
Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components
文献摘要：
One of the pressing issues for optical neural networks (ONNs) is the performance degradation introduced by parameter uncertainties in practical optical components. Hereby, we propose a novel two-step ex situ training scheme to configure phase shifts in a Mach–Zehnder-interferometer-based feedforward ONN, where a stochastic gradient descent algorithm followed by a genetic algorithm considering four types of practical imprecisions is employed. By doing so, the learning process features fast convergence and high computational efficiency, and the trained ONN is robust to varying degrees and types of imprecisions. We investigate the effectiveness of our scheme by using practical machine learning tasks including Iris and MNIST classifications, showing more than 23% accuracy improvement after training and accuracy (90.8% in an imprecise ONN with three hidden layers and 224 tunable thermal-optic phase shifters) comparable to the ideal one (92.0%).
文献关键词：
中图分类号：
作者姓名：
Rui Shao;Gong Zhang;Xiao Gong
作者机构：
Department of Electrical & Computer Engineering, National University of Singapore, Singapore, Singapore;e-mail: zhanggong@nus.edu.sg;e-mail: elegong@nus.edu.sg
文献出处：
引用格式：
[1]Rui Shao;Gong Zhang;Xiao Gong-.Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components)[J].光子学研究（英文）,2022(08):1868
A类：
imprecisions
B类：
Generalized,robust,training,scheme,using,genetic,algorithm,optical,neural,networks,imprecise,components,One,pressing,issues,ONNs,performance,degradation,introduced,parameter,uncertainties,practical,Hereby,propose,novel,step,ex,situ,configure,phase,shifts,Mach,Zehnder,interferometer,feedforward,where,stochastic,gradient,descent,followed,considering,four,types,employed,By,doing,so,learning,process,features,fast,convergence,high,computational,efficiency,trained,varying,degrees,We,investigate,effectiveness,machine,tasks,including,Iris,MNIST,classifications,showing,more,than,accuracy,improvement,after,three,hidden,layers,tunable,thermal,shifters,comparable,ideal
AB值：
0.624109
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。
