What is Supervise Learning?

Before understand Supervised learning we must be aware of the following terminologies:

What is Regression: This term is used for the goal, is to predict continuous real value,     such as “pound”, “weight”, “distance”, et cetera.

What is Classification: This tern is used for the goal to predicted output category, such as True/False, 1/0, Green/Yellow, spam/ not spam, Ill/Healthy

What is Labelled data: Data consisting of a set of training examples, where each example is a pair consisting of an input and a desired output value (also called the supervisory signal, labels, etc)

What is Supervise Learning?

The majority of practical machine-learning uses supervised learning algorithms, which is designed to learn by example, where you have input variables “x” and an output variable “Y” and we use an algorithm to learn the mapping function from the input to the output.

y = f(x)

Where “y” is the desired output of the input function value “x” based on a machine learning model during training.

Example:

NO.	SIZE	COLOR	SHAPE	NAME
1	Big	Red	Rounded shape with a depression at the top	Apple
2	Small	Reddish Yellow	Round shape	Apricot
3	Big/small	Green	Long cylinder with curve	Banana
4	Small	Black	Round to oval	Blackberry
5	Small	Green	Elliptical	Avocado

 

Let’s assume, we have taken a new fruit from the basket then we observe the size, colour and shape of that fruit.

 If size is Big, colour is Red, the shape is rounded shape with a depression at the top, you will confirm the fruit name is apple and you will put in apple group. And the same for the other fruits in the basket too.

Hence, in this way the task of grouping the fruits is completed successfully.

We can observe in the table that a column was labelled as “NAME” this is called "Response Variable".

 If we have learned the thing before from the training data and then applying that knowledge of the test data (for new fruit), this type of learning is called Supervised Learning.

The goal is to approximate the mapping function so well that when we have new input data (x) that we can predict the output variables (Y) for that data.

The term supervised learning came from the idea that an algorithm is learning from a training dataset

Training data for supervised learning includes a set of examples that are paired with input subjects and the desired output (which is also referred to as the supervisory signal). 

Common supervised machine learning algorithms are:

• Logistic regression
• Linear regression
• Linear discriminate analysis
• Decision trees
• Bayesian logic
• Support vector machines (SVM)
• Similarity learning
• Random forests
• Linear Classifiers
• Support Vector Machines
• K-Nearest Neighbors
• Random Forest

   
What is Unsupervised Learning?