Simplified residual structure and fast deep residual networks

doi:10.13229/j.cnki.jdxbgxb20210027

CIOMP OpenIR

	Simplified residual structure and fast deep residual networks
	H.-J. Yang; E.-S. Wang; Y.-X. Sui; F. Yan and Y. Zhou
	2022
发表期刊	Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)
ISSN	16715497
卷号	52 期号:6 页码:1413-1421
摘要	In order to address the problem of slow training of the current deep ResNets model, a novel residual structure is designed. Compared with the typical residual structure, the structure only contains a Batch Normalization and ReLU, which reduces training time and improves the training speed by reducing the amount of calculation in the network training process. The comparative experiments are carried out on the CIFAR10/100 image classification database. The classification error rate of 110 layers networks constructed by this method on CIFAR10 and CIFAR100 is 5.29% and 24.80%, respectively. The classification error rate of 110-ResNet is 5.75% and 26.02%, respectively. Training the network takes 133.47 (this method) and 208.26 (ResNet) seconds per epoch, increased by 35.91%. The results show that the network structure greatly improves the training speed while ensuring the classification performance, and has better practical value. 2022, Jilin University Press. All right reserved.
DOI	10.13229/j.cnki.jdxbgxb20210027
URL	查看原文
收录类别	ei
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/67079
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	H.-J. Yang,E.-S. Wang,Y.-X. Sui,et al. Simplified residual structure and fast deep residual networks[J]. Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition),2022,52(6):1413-1421.
APA	H.-J. Yang,E.-S. Wang,Y.-X. Sui,&F. Yan and Y. Zhou.(2022).Simplified residual structure and fast deep residual networks.Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition),52(6),1413-1421.
MLA	H.-J. Yang,et al."Simplified residual structure and fast deep residual networks".Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) 52.6(2022):1413-1421.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Simplified residual （1862KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载