计算机应用研究2024，Vol.41Issue(4)：961-969,9.DOI:10.19734/j.issn.1001-3695.2023.06.0347
卷积神经网络的正则化方法综述
Survey on regularization methods for convolutional neural network
摘要
Abstract
In recent years,convolutional neural networks have been widely used in various fields of computer vision and achieved remarkable results.Regularization method is an important part of convolutional neural network,which helps to avoid the overfitting phenomenon of convolutional neural network in the process of model training.There are fewer reviews on regularization methods for convolutional neural networks,and most of them lack a summary of the newly proposed regularization methods.Firstly,this paper conducted a detailed summary of the literature on regularization methods in convolutional neural networks,and classified the regularization methods into parameter regularization,data regularization,label regularization and combinatorial regularization.After that,on the public datasets such as ImageNet,it compared and analyzed the advantages and disadvantages of different regularization methods based on evaluation indexes such as top-1 accuracy and top-5 accuracy.Finally,it discussed the future research trends and work directions of regularization methods for convolutional neural network.关键词
卷积神经网络/正则化方法/过拟合/泛化Key words
convolutional neural network/regularization method/overfitting/generalization分类
信息技术与安全科学引用本文复制引用
陈琨,王安志..卷积神经网络的正则化方法综述[J].计算机应用研究,2024,41(4):961-969,9.基金项目
国家自然科学基金地区基金资助项目(62162013) （62162013）
贵州师范大学学术新苗基金资助项目(黔师新苗[2022]30号) （黔师新苗[2022]30号）
