Machine learning
It is a subset of artificial learning which provides the ability to learn automatically and improve from experiences without being explicitly programmed
a) Supervise: in this, we teach the machine by using labeled data
Problem types: classification and regression
Type of data: labeled data
Training: external supervision 
Aim: forecast
Approach: map labeled output to the known output
Popular algorithm: 
Applications: 
b) un supervised: in this, we teach the machine by using unlabeled data and it perform grouping function to give output
Problem type: association and clustering
Types of data: 
Training: 
Aim: 
Approach: 
Popular algorithm:
Applications: 
c) Reinforcement: in reinforcement, an agent interacts with its environment by producing actions and recovering errors and rewards
Types of problems:
types of data: no predefined data
training: no supervision
aim: learn a series of Afton
approach: follow trial and error method
popular algorithm:
applications: 
