Orthogonal Features Extraction Method and Its Application in Convolution Neural Network

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.

Keywords

• convolution neural network
• feature redundancy
• orthogonality
• feature vector