A definitions of Machine Learning

A lately, I read a lot of books, articles and papers about Machine Learning to find out what is Machine Learning?

As part of my learning journey, I thought it is a good idea for me to know the story behind it. It turns out that Machine Learning is like the others scientific discipline it always starts with a problem or question to address.

In 1959, Arthur Samuel described machine learning as a

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

He wrote a checkers playing program that can beat a  human players. It was a historic moment.

Then Tom Mitchel offered another definition of machine learning on his  book as a

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

An example with playing checker program the E is the experience of playing many games of checkers, T is the task of playing checkers and P is the probability that the program will win the next game. The definition by Tom Mitchel is widely used nowdays.