标题：Understanding and Boosting of Deep Convolutional Neural Network Based on Sample Distribution
作者：Qinghe Zheng;Mingqiang Yang;Qingrui Zhang;Xinxin Zhang;Jiajie Yang;
作者机构：[Qinghe Zheng;Mingqiang Yang;Qingrui Zhang;Xinxin Zhang;Jiajie Yang]School of Information Science and Engineering, Shandong University;[Qinghe Zheng;M 更多
来源：Proceedings of 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2017)
关键词：deep convolutional neural network;sample distribution;feature boundary;penalty term
摘要：In order to improve the generalization ability of deep convolutional neural networks, an improved training strategy based on anomalous sample penalty term is introduced in this paper. We first establish an anomalous sample detection mechanism on the basis of preliminary neural network model, then we...