Abstract: Deep learning is a hot research topic in the field of artificial intelligence, and it is an inevitable trend to use deep learning to support the research of artificial intelligence. Its performance advantages have been demonstrated in the fields of image, voice and text. Based on the analysis of deep learning related literature, this paper reviews the application of the current deep learning model, involves the concept and method framework of deep learning, analyzes the bottlenecks to be broken currently, and points out the future research direction of deep learning.

Key words: deep learning, Convolutional Neural Network（CNN）, modeling, face recognition

摘要： 深度学习是人工智能领域的研究热点，利用深度学习支持人工智能的研究工作已经是必然趋势，在图像、语音、文本等领域已经展现出性能优势。对深度学习相关文献进行了分析研究，介绍了深度学习的概念和方法框架，综述了当前深度学习模型及其应用情况，分析了深度学习需要突破的瓶颈，指出了深度学习未来的研究方向。

关键词: 深度学习, 卷积神经网络（CNN）, 建模, 人脸识别