Machine learning is a field of computer science that uses statistical techniques to give computer systems the ability to “learn” by progressively thus improving performance to complete a specific task without actually being programmed to complete said task. One example is when online services/sites such as Spotify, Netflix, and Amazon make recommendations for music to listen to, what to watch, or buy.
When you’ve logged onto a website and been asked to identify street signs, bicycles, or cars by clicking on images (or type in a word or two) in a thing called a CAPTCHA? Then you have participated in machine learning.
First coined in 1959 by American pioneer in the field of computer gaming and artificial intelligence Arthur Samuel, machine learning has evolved from the study of pattern recognition and computational to a theory that artificial intelligence can learn from and make predictions on data by using a series of complete algorithms.
Algorithms are “rules” that are designed to solve a type of problem, you might remember them in school as formulas.
Machine learning like computational statistics uses computers to focuses on prediction-making. Unlike data mining where data s used for analysis by using pre-determined criteria, this is more of an automated form of learning.
Often referred to as prediction analysis, machine learning is a form of computer modeling of “what ifs” in the hope of providing reliable data based off on historical data, trend analysis, and relationships.