Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (1): 27-46.DOI: 10.3778/j.issn.1673-9418.2008016

• Surveys and Frontiers • Previous Articles     Next Articles

Development and Application of Convolutional Neural Network Model

YAN Chunman ,WANG Cheng   

  1. College of Physics and Electronic Engineering , Northwest Normal University, Lanzhou 730070, China
  • Online:2021-01-01 Published:2021-01-07

卷积神经网络模型发展及应用

严春满王铖   

  1. 西北师范大学 物理与电子工程学院,兰州 730070

Abstract:

Deep learning is the latest trend of machine learning and artificial intelligence research. As a new field of rapid development in the past ten years, more and more researchers pay attention to it. Convolutional neural network (CNN) model is one of the most important classical structures in deep learning model, and its performance has been gradually improved in recent years. Since it can automatically learn the feature representation of sample data, convolutional neural network has been widely used in image classification, object detection, semantic segmentation and natural language processing. This paper first analyzes the model structure of typical convolutional neural network model, which increases the depth and width of the network in order to improve its performance, analyzes the network structure that uses attention mechanism to further improve the performance of the model, and then summarizes and analyzes the current special model structure. Finally, it summarizes and discusses the application of convolutional neural network in related fields, and the future research direction is prospected.

Key words: convolutional neural network (CNN) model, feature extraction, computer vision, natural language processing

摘要:

深度学习是机器学习和人工智能研究的最新趋势,作为一个十余年来快速发展的崭新领域,越来越受到研究者的关注。卷积神经网络(CNN)模型是深度学习模型中最重要的一种经典结构,其性能在近年来深度学习任务上逐步提高。由于可以自动学习样本数据的特征表示,卷积神经网络已经广泛应用于图像分类、目标检测、语义分割以及自然语言处理等领域。首先分析了典型卷积神经网络模型为提高其性能增加网络深度以及宽度的模型结构,分析了采用注意力机制进一步提升模型性能的网络结构,然后归纳分析了目前的特殊模型结构,最后总结并讨论了卷积神经网络在相关领域的应用,并对未来的研究方向进行展望。

关键词: 卷积神经网络(CNN)模型, 特征提取, 计算机视觉, 自然语言处理