Overview of Capsule Neural Networks

被引:5
|
作者
Sun, Zengguo [1 ,2 ]
Zhao, Guodong [2 ]
Scherer, Rafal [3 ]
Wei, Wei [4 ]
Wozniak, Marcin [5 ]
机构
[1] Minist Educ, Key Lab Modern Teaching Technol, Xian, Shaanxi, Peoples R China
[2] Shaanxi Normal Univ, Sch Comp Sci, Xian, Peoples R China
[3] Czestochowa Tech Univ, Dept Intelligent Comp Syst, Czestochowa, Poland
[4] Xian Univ Technol, Sch Comp Sci & Engn, Xian, Peoples R China
[5] Silesian Tech Univ, Fac Appl Math, Gliwice, Poland
来源
JOURNAL OF INTERNET TECHNOLOGY | 2022年 / 23卷 / 01期
基金
中国国家自然科学基金;
关键词
Capsule network; Dynamic routing Mechanism; Convolutional neural network; Deep learning; CLASSIFICATION; CAPSNET;
D O I
10.53106/160792642022012301004
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
As a vector transmission network structure, the capsule neural network has been one of the research hotspots in deep learning since it was proposed in 2017. In this paper, the latest research progress of capsule networks is analyzed and summarized. Firstly, we summarize the shortcomings of convolutional neural networks and introduce the basic concept of capsule network. Secondly, we analyze and summarize the improvements in the dynamic routing mechanism and network structure of the capsule network in recent years and the combination of the capsule network with other network structures. Finally, we compile the applications of capsule network in many fields, including computer vision, natural language, and speech processing. Our purpose in writing this article is to provide methods and means that can be used for reference in the research and practical applications of capsule networks.
引用
收藏
页码:33 / 44
页数:12
相关论文
共 50 条
  • [1] NEURAL NETWORKS - AN OVERVIEW
    JANSSON, PA
    ANALYTICAL CHEMISTRY, 1991, 63 (06) : A357 - A362
  • [2] AN OVERVIEW OF NEURAL NETWORKS
    GREENWOOD, D
    BEHAVIORAL SCIENCE, 1991, 36 (01): : 1 - 33
  • [3] A Receptor Skeleton for Capsule Neural Networks
    Chen, Jintai
    Yu, Hongyun
    Qian, Chengde
    Chen, Danny Z.
    Wu, Jian
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [4] Overview of recurrent neural networks
    Liu J.-W.
    Song Z.-Y.
    Kongzhi yu Juece/Control and Decision, 2022, 37 (11): : 2753 - 2768
  • [5] An overview on rough neural networks
    Hongmei Liao
    Shifei Ding
    Miaomiao Wang
    Gang Ma
    Neural Computing and Applications, 2016, 27 : 1805 - 1816
  • [6] ARTIFICIAL NEURAL NETWORKS - AN OVERVIEW
    PARKER, DB
    ANDREW SEYBOLDS OUTLOOK ON PROFESSIONAL COMPUTING, 1988, 6 (10): : 23 - 25
  • [7] Enhanced neural networks:: An overview
    Mingo, LF
    Díaz, MA
    Gisbert, F
    Carrillo, JD
    KNOWLEDGE-BASED INTELLIGENT INFORMATION ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, PTS 1 AND 2, 2001, 69 : 1170 - 1173
  • [8] Artificial Neural Networks: An Overview
    Micheli-Tzanakou, Evangelia
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2011, 22 (1-4) : 208 - 230
  • [9] Randomness in neural networks: an overview
    Scardapane, Simone
    Wang, Dianhui
    WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2017, 7 (02)
  • [10] A practical overview of neural networks
    Burke, L
    Ignizio, JP
    JOURNAL OF INTELLIGENT MANUFACTURING, 1997, 8 (03) : 157 - 165