Machine learning is a branch of Artificial Intelligence(AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.
“Machine learning algorithms are software programs that learn from data and make predictions about future events.”  The term machine learning was coined in 1959 by Arthur Samuel, an IBM employee and pioneer in the field of computer gaming and artificial intelligence.

There are four types of machine learning:

1. Supervised Learning : It is based on supervision. In this, we train the machines using labelled dataset and based on the training the machine predicts the output.
2. Un-supervise Learning : It is different from the supervised learning techniques as its name suggest, there is no need of supervision. In un-supervised machine learning the machine is trained using the un-labelled dataset and machine predicts the output without any supervision.
3. Semi-supervise Learning : It is a type of machine learning algorithms that lies between supervised and un-supervise machine learning. It uses the combination of labelled and un-labelled datasets during the training period. To overcome the drawbacks of supervised learning and un-supervise learning, the concept of semi-supervise learning is introduced.
4. Reinforcement Learning : It works on a feedback-based process in which an AI agent   ( a software component) automatically explore its surrounding by hitting and trail, taking action, learning from experience and improving its performance.