Supervised Machine Learning

 Types of Machine Learning

There are four types of machine learning, i.e.,

1)   Supervised Learning – Learning from labeled data (input + output)

2)   Unsupervised Learning – Learning from unlabeled data (only input)

3)   Semi-Supervised Learning – Learning from partially labeled data

4)   Reinforcement Learning – Learning through reward and punishment

Machine learning is all about learning from data and getting trained on it.

1) Supervised Machine Learning.

In data, there are inputs and outputs, which are called labeled data. When we identify the relationship between the input and the output, so that, for a new input, the output can be obtained it is called Supervised Machine Learning.

******************** >< ********************

Types of Data:

1.   Numerical Data – Data in the form of numbers
Example: Age, Marks, CGPA, Package, weight etc.

2.   Categorical Data – Data in the form of categories or labels
Example: Gender, Placement (Yes/No), Department, Nationality etc.

 

******************** >< ********************

1.1 Supervised Machine Learning:

           I.  Regression :

Regression is a supervised machine learning technique used to find the relationship between input and output when the output is a numerical value.

Regression is used when the output is a number, such as marks or salary.

 

Example:

Input		Output
IQ	CGPA	Package (LPA)
110	8.5	6.5
120	9.1	9.0
100	7.8	4.8
115	8.8	8.2
105	8.0	5.5

            I.  Classification :

Classification is a supervised machine learning technique used to find the relationship between input and output when the output is categorical (class or label).

Classification is used when the output is a category, such as Placed / Not Placed, Yes / No, or Spam / Not Spam.

 

Example:

Input		Output
IQ	CGPA	Placement
110	8.5	Y
95	7.2	N
120	9.1	Y
85	6.5	N
100	7.8	Y

******************** >< ********************