In recent years, deep learning has achieved great success in many fields, such as face recognition, computer vision, natural language processing, autonomous cars and so on. Deep learning has a strong learning ability and can use datasets more efficiently for feature extraction compared to traditional machine learning. Because of this, deep learning becomes more and more popular for many researchers to do their research work. In this paper, we will mainly introduce deep learning, hardware implementation for deep learning and their applications. Besides, we will also discuss the limitations and the future of deep learning expected by the professionals. Lastly, we will give our suggestions and predictions for the future of deep learning.