Wikipedia
Machine learning is a subfield of computer science (CS) and artificial intelligence (AI) that deals with the construction and study of systems that can learn from data, rather than follow only explicitly programmed instructions.
Standford Machine Learning course - Coursera
Machine learning is the science of getting computers to act without being explicitly programmed.
Data Mining - Ian H. Witten, Eibe Frank, Mark A. Hall
We interpret machine learning as the acquisition of structural descriptions from examples.
Bayesian Reasoning and Machine Learning - David Barber
Machine learning is a study of data-driven methods capable of mimicking, understanding and aiding human and biological information processing tasks.
Machine Learning: A Probabilistic Perspective - Kevin P. Murphy
In particular, we define machine learning as a set of methods that can automatically detect patterns in data, and then use the uncovered patterns to predict future data, or to perform other kinds of decision making under uncertainty (such as planning how to collect more data!).
Building Machine Learning Systems with Python - Willi Richert
Machine learning (ML) teaches machines how to carry out tasks by themselves.
Machine Learning for Hackers - Drew Conway, John Myles White
At the highest level of abstraction, we can think of machine learning as a set of tools and methods that attempt to infer patterns and extract insight from a record of the observable world.
Machine Learning: An Algorithmic Perspective - Stephen Marsland
Machine learning, then, is about making computers modify or adapt their actions (whether these actions are making predictions, or controlling a robot) so that these actions get more accurate, where accuracy is measured by how well the chosen actions reflect the correct ones.
Introduction to Machine Learning - Ethem Alpaydin
Machine learning is programming computers to optimize a performance criterion using example data or past experience.
Me
Machine learning: using computers (=machine) to run algorithms that estimate (=learn) parameters of some model.