In computing, machine learning is a method of teaching computers to learn from data, without being explicitly programmed.
Machine learning is a branch of artificial intelligence (AI) that deals with the construction and study of algorithms that can learn from and make predictions on data. Such algorithms operate by building a model from example inputs in order to make data-driven predictions or decisions, rather than following strictly static program instructions.
Machine learning can be considered a subfield of AI since it builds upon mathematical foundations as well as general purpose heuristics like optimization methods from statistics and information theory. Machine learning also intersects with statistics, control theory, signal processing, and other areas.
At its core, machine learning involves using algorithms to parse data and find patterns within it. These patterns can then be used to make predictions about new, unseen data. So, for instance, if you were trying to build a program that could identify dogs in pictures, you might feed it thousands of photos of different dogs (and cats), until the algorithm learned what characteristics define a “dog”. Then, given a new photo (of a dog or anything else), the algorithm could reasonably predict whether or not it contains a dog.