Quotes from John Paul Mueller

The central idea is that you can represent reality using a mathematical function that the algorithm doesn't know in advance but can guess after having seen some data. You can express reality and all its challenging complexity in terms of unknown mathematical functions that machine learning algorithms find and make advantageous. This concept is the core idea for all kinds of machine learning algorithms.

You need to distinguish between regression problems, whose target is a numeric value, and classification problems, whose target is a qualitative variable, such as a class or a tag.

leaving to the algorithm to determine the data patterns on its own. This type of algorithm tends to restructure the data into something else, such as new features that may represent a class or a new series of uncorrelated values.

As a kind of learning, it resembles the methods humans use to figure out that certain objects or events are from the same class, such as by observing the degree of similarity between objects.

accompany an example with positive or negative feedback according to the solution the algorithm proposes. Reinforcement learning is connected to applications for which the algorithm must make decisions (so the product is prescriptive, not just descriptive, as in unsupervised learning), and the decisions bear consequences. In the human world, it is just like learning by trial and error.

To survive, a technology must prove useful. In fact, it must prove more than useful; it must meet perceived needs in a manner that existing technologies don't as well as build a base of adherents who provide a monetary reason to continue investing in the technology.