What is Machine Learning?

Have you ever wondered what is machine learning? This article will answer your question.

Let’s start with origin, this definition comes from Arthur Samuel, who was one of the first to coin the term machine learning. He defined machine learning as:

Field of study that gives computers the ability to learn without being explicitly programmed.

-Samuel Arthur, IBM, 1959

This is a decent definition, but it is a little vague and it glosses over some of the key concept in machine learning.

We can define machine learning as follow:

Machine learning is fitting a function to examples and using that function to generalize and make predictions about new examples.

Let us discuss a little this definition. You can see that we now highlight the fact that machine learning model is based on data that you feed it, as it learns from fitting on examples. And then it comes the general role which is used to the learned model to make prediction about the new examples. This new definition underlines the key concept of machine learning.

In other words, machine learning used past data to learn trends, then uses those trends to make prediction in the future data.