Artificial neural networks were used in the solution of many problems in the field of machine learning. However, in the period called "AI Winter", studies in this area have come to a halt due to especially hardware limitations and other problem. Artificial neural networks, which started to become a popular area at beginning of the 2000's, have switched from shallow networks to deep networks thanks to GPU developments. This approach has been successfully used in a wide range of fields from image processing to natural language processing, from medical applications to activity identification. In this study, it is described the history of the deep learning, methods and the implementations separated by the application areas. In addition, information has been given to the libraries used in recent years and working groups focused on deep learning. The aim of this study both explains the developments in deep learning to researchers and provides possible fields study with deep learning.