In contemporary computer sciences, machine learning is one of the areas. A lot of research has been carried out to make machines intelligent. Learning is an important feature of computers as well as normal human behavior. Different approaches have been developed in several fields of operation for the same. Conventional machine learning algorithms have been introduced. Researchers have worked hard to develop the exactness of these learning algorithms. They have thought of another level contributing to a broad definition of learning. Deep study is a machine learning subset. Few deep learning implementations have been researched until now. This would undoubtedly resolve concerns in many new areas of application, sub-domains that use profound learning. This paper illustrates a study of historical and future areas, sub-domains and implementations for computer learning.