) 上海交通大学 电子信息与电气工程学院,上海 200240
收稿日期:2020-09-08出版日期:2021-10-28发布日期:2021-11-01通讯作者:李建勋E-mail:lijx@sjtu.edu.cn作者简介:李 辰(1990-),男,陕西省汉中市人,硕士生,工程师,主要从事神经网络及效能评估研究.基金资助:国家自然科学基金(61673265);国家重点研发计划(2020YFC1512203);民机专项科研项目(MJ-2017-S-38)Orthogonal Features Extraction Method and Its Application in Convolution Neural Network
LI Chen, LI Jianxun() School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Received:2020-09-08Online:2021-10-28Published:2021-11-01Contact:LI Jianxun E-mail:lijx@sjtu.edu.cn摘要/Abstract
摘要： 针对卷积神经网络中存在的特征冗余问题,将正交性向量的概念引入特征中,从强化特征之间差异性的角度,提出一种适用于卷积神经网络的正交性特征提取方法.通过搭建并列的卷积神经网络支路结构,设计正交损失函数,从而促使卷积核提取出相互正交的样本特征,丰富特征多样性,消除特征冗余,提升特征用于分类识别的效果.在一维样本数据集上的实验结果表明,相比于普通的卷积神经网络,所提方法能够监督不同卷积核,挖掘出更为全面的正交性特征信息,进而提升卷积神经网络的性能效率,为后续模式识别和紧凑型神经网络的研究奠定基础.
关键词: 卷积神经网络, 特征冗余, 正交性, 特征向量
Abstract: In view of feature redundancy in the convolutional neural network, the concept of orthogonal vectors is introduced into features. Then, a method for orthogonal features extraction of convolutional neural network is proposed from the perspective of enhancing the differences between features. By building the structure of parallel branches and designing the orthogonal loss function, the convolution kernels can extract the orthogonal features, enrich the feature diversity, eliminate the feature redundancy, and improve the results of classification. The experiment results on one-dimensional sample dataset show that compared with the traditional convolution neural network, the proposed method can supervise the convolution kernels with different sizes to mine more comprehensive information of orthogonal features, which improves the efficiency of convolutional neural network and lays the foundation for subsequent researches on pattern recognition and compact neural network.
Key words: convolution neural network, feature redundancy, orthogonality, feature vector
PDF全文下载地址:
点我下载PDF
