计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (3): 33-43.DOI: 10.3778/j.issn.1002-8331.2009-0209

• 热点与综述 • 上一篇    下一篇

胶囊神经网络研究现状与未来的浅析

贺文亮,朱敏玲   

  1. 北京信息科技大学 计算机学院,北京 100101
  • 出版日期:2021-02-01 发布日期:2021-01-29

Research Status and Future Analysis of Capsule Neural Network

HE Wenliang, ZHU Minling   

  1. Computer School, Beijing Information Science & Technology University, Beijing 100101, China
  • Online:2021-02-01 Published:2021-01-29

摘要:

当今时代的人工智能技术迅速发展,推动了社会的巨大进步。深度学习作为人工智能领域重要的一部分,具有非常广阔的应用前景,近年来,越来越多的专家学者开始研究深度学习领域相关技术,比较典型的两个方向就是自然语言处理和计算机视觉,其中计算机视觉的发展大力引领着深度学习领域的进步。介绍了卷积神经网络的经典模型和深度学习中新型神经网络模型——胶囊网络以及其动态路由算法,并对比了二者的优劣性。对胶囊网络的应用给予综述,以图像和文本两方面来阐述胶囊网络的应用领域和优势所在。最后进行概括总结,并展望了胶囊网络可能的改进方向。

关键词: 深度学习, 胶囊网络, 卷积神经网络, 图像识别, 文本分类

Abstract:

Nowadays, the rapid development of artificial intelligence technology has promoted the great progress of society. As an important part of artificial intelligence, deep learning has a very broad application prospect. In recent years, more and more experts and scholars have begun to study the related technologies in the field of deep learning. Two typical directions are natural language processing and computer vision. Among them, the development of computer vision strongly leads the progress in the field of deep learning. The application of convolutional neural network and a new neural network model in deep learning?capsule network and its dynamic routing algorithm are introduced, and their advantages and disadvantages are compared. Then, the application of capsule network is reviewed, and the application fields and advantages of capsule network are described in terms of image and text. Finally, the paper summarizes and looks forward to the possible improvement direction of capsule network.

Key words: deep learning, capsule network, Convolutional Neural Network(CNN), image recognition, text classification