Machine Learning is a branch of artificial intelligence (AI) to learn the data, identify the pattern and to make decisions with minimal human intervention.

Different types of machine learning are Supervised, Unsupervised and Semi-supervised and Reinforcement method. Supervised learning algorithm is trained for labelled input data set. This uses many classification and regression algorithms. Unsupervised learning will not have explicit labels associated with the training dataset. Semi-Supervised learning is sub class of supervised learning. This learning method can use small amount of unlabelled and large amount of labelled data. Reinforcement learning has software agent for optimal control and decision making.
In recent years deep reinforcement learning method gained attention in various domains. Deep learning is a machine learning approach for analysing the data. The term “deep” refers to multiple layers are used to extract the new feature. Each successive layer takes the output of the previous layer and feeds the result to the next layer.
Each layer learns the input dataset and produces the output, which will be the input to the next layer. Each successive layer takes the output from the previous layer and feeds the result to the next layer. This allows classifying and extracting the feature in each layer. Deep learning is used in speech recognition, natural language processing, image recognition, pattern matching task, vision recognition, medical diagnosis so on.