# Deep Rooted Introduction to the Machine Learning

D

## What Is A Machine Learning?

The term machine learning leaves us with the plenty of different meanings and definitions. So, picking up one definition of Machine Learning out of the heap is a bit tricky job. But, if we compile all the relevant definitions than we can say that the machine learning means learning from the experiences and examples instead of programs.

In machine learning, the machine itself is trained to solve task with the utilization of the past experiences and examples. There is no need of generating codes for each and every task as the machine is capable to work itself. In short machine learning means making the machine self-efficient.

According to Tom M. Mitchell ” A computer program is said to learn from experience E with some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.”

## Elaboration of Definition in Context to the Game of Chess

E – the experience of playing chess games

T – the task of playing chess

P – the probability of winning the next game

Why Do We Need Machine Learning?

Well, always remember that the need of every invention occurs because of the limitations of another technology. In the case of machine learning, we can say that the limitations of Artificial Intelligence bring the need for machine learning.

In AI, we want to create one intelligent machine, but apart from few easy tasks like measuring the distance from point A to B, it doesn’t offer us more. So, thus the machine learning comes into the existence, where big data is used to make a machine intelligent.

In the machine learning, the machine is trained to find a pattern in the data, so that it can automatically work according to the change in the trend of the data. The algorithms used in the machine learning are really cool and today machine learning technology is being used everywhere. That’s why to learn the tricks of machine learning immediately enroll in the

## Types of Machine Learning Algorithms

1. ### Supervised Learning –

In this learning, the system tries to learn from the previously used examples. This learning is highly used in the machine learning. The mathematical expression of supervised learning is  Y = f(X).

2. ### Unsupervised Learning –

When algorithms are left alone to figure out the pattern in data, then it is called unsupervised learning. Mathematically, unsupervised learning is when you only have input data (X) and no corresponding output variables.

3. ### Reinforcement Learning –

In this situation, the machine is left alone to learn in the given environment. The machine has to learn from the old method of try and error as no algorithms are provided to the machine.

## Where Is Machine Learning?

Well, guys, machine learning technology is everywhere around us today.  Such as:

• Face Detection
• Weather Forecast
• Email Filtering
• Medical Diagnosis etc.

You see people, we are surrounded by the data infused machine learning technology today. So, young developers we highly recommend, you to at least learn the basic features of the machine learning for your better future.