RGA-CNNs:convolutional neural networks based on reduced geometric algebra  

作　　者：Rui WANG Miaomiao SHEN Xiangyang WANG Wenming CAO 

机构地区：[1]School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China [2]College of Information Engineering,Shenzhen University,Shenzhen 518060,China

出　　处：《Science China(Information Sciences)》2021年第2期236-238,共3页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.61771299,61771322,61375015,61301027)。

摘　　要：Dear editor,Recently,convolutional neural networks(CNNs)have exhibited high performance particularly in object detection[1],face recognition[2],and image classification[3].However,there has been little work on CNN models for multidimensional data,such as the three-dimensional(3 D)data,which are typically presented as color images[4].Traditional real-valued CNN models[4]have achieved state-of-the-art results for gray-scale images.

关 键 词：NETWORKS NEURAL CNNS 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]