计算机与现代化Issue(8)：66-70,5.DOI:10.3969/j.issn.1006-2475.2017.08.014
基于余弦相似度的边界样本选择方法
Boundary Sample Selection Method Based on Cosine Similarity
摘要
Abstract
The training of convolution neural network usually requires a lot of training samples, which causes the training time be too long.To solve this problem, this paper presents a boundary sample selection method based on cosine similarity.We select boundary samples as the training set of convolution neural network, and carry out example selection experiment on the MNIST, CIFAR10 and SVHN data sets.Then a convolutional neural network is used to carry out experiments.Experimental results show that this method can preserve the typical samples in the training set and eliminate redundant samples.Thereby, the number of training samples is reduced, the network training time is shortened and the learning efficiency of network is improved.关键词
深度学习/卷积神经网络/模式识别/边界数据/图像识别/样本选择Key words
deep learning/convolutional neural network/pattern recognition/boundary data/image recognition/sample selection分类
信息技术与安全科学引用本文复制引用
李春利,柳振东,惠康华..基于余弦相似度的边界样本选择方法[J].计算机与现代化,2017,(8):66-70,5.基金项目
中国民航大学科研启动基金资助项目(2010QD10X) （2010QD10X）
