Deep learning, a branch of machine learning, is a frontier for artificial intelligence, aiming to be closer to its primary goal—artificial intelligence. This paper mainly adopts the summary and the induction methods of deep learning. Firstly, it introduces the global development and the current situation of deep learning. Secondly, it describes the structural principle, the characteristics, and some kinds of classic models of deep learning, such as stacked auto encoder, deep belief network, deep Boltzmann machine, and convolutional neural network. Thirdly, it presents the latest developments and applications of deep learning in many fields such as speech processing, computer vision, natural language processing, and medical applications. Finally, it puts forward the problems and the future research directions of deep learning.

深度学习是机器学习的一个分支，是人工智能的前沿领域，旨在更接近其主要目标即人工智能。本文主要采用深度学习的总结和归纳方法。首先，介绍了深度学习的全球发展和现状。其次，描述了深度学习的结构原理，特征和一些经典模型，例如堆叠式自动编码器，深度置信网络，深度玻尔兹曼机和卷积神经网络。第三，它介绍了深度学习在语音处理，计算机视觉，自然语言处理和医疗应用等许多领域的最新发展和应用。最后，提出了深度学习存在的问题和未来的研究方向。