深度学习及其在目标和行为识别中的新进展

深度学习是机器学习中的一个新的研究领域。通过深度学习的方法构建深度网络来抽取特征是目前目标和行为识别中得到关注的研究方向。为引起更多计算机视觉领域研究者对深度学习进行探索和讨论，并推动目标和行为识别的研究，本文对深度学习及其在目标和行为识别中的新进展给予了概述。本文先介绍深度学习领域研究的基本状况、主要概念和原理；然后介绍近期利用深度学习在目标和行为识别应用中的一些新进展；最后阐述了深度学习与神经网络之间的关系，深度学习的优缺点，以及目前深度学习理论需要解决的主要问题。这对拟将深度学习应用于目标和行为识别的研究人员应有所帮助。

Deep learning and its new progress in object and behavior recognition

Deep learning is a new research area in machine learning. Currently, extracting features via deep learning for visual object recognition and behavior recognition capture many attentions. To draw more attention from research community about deep learning, and to push forward the research frontier of object and behavior recognition, this paper gives a general progress overview for deep learning and its application to visual object and behavior recognition. This paper first gives a general introduction to deep learning, including the basic situation, main concepts and principle. Then, some new progresses on using deep learning in visual object recognition and behavior recognition are presented. At last, a discussion about the differences between deep learning and neural network as well as the advantage and disadvantage of deep learning are given, the main existing problems that should be solved for deep learning theory are pointed. This should provide some help for the research community on applying the deep learning to the visual object and behavior recognition.