Algorithms are an exacting standard. It’s often said that you don’t really understand something until you can express it as an algorithm.

Learning algorithms are the seeds, data is the soil, and the learned programs are the grown plants.

the two main subproblems in analogical reasoning: figuring out how similar two things are and deciding what else to infer from their similarities.

Notice that we’re only saying that fever and cough are independent given that you have the flu, not overall.

Although it is less well known, many of the most important technologies in the world are the result of inventing a unifier, a single mechanism that does what previously required many.

with SVMs, we can learn smooth frontiers,

These examples are called support vectors because they’re the vectors that “hold up” the frontier: remove one, and a section of the frontier slides to a different place.

a company without machine learning can’t keep up with one that uses it.

The Master Algorithm is for induction, the process of learning, what the Turing machine is for deduction. It can learn to simulate any other algorithm by reading examples of its input-output behavior. Just as there are many models of computation equivalent to a Turing machine, there are probably many different equivalent formulations of a universal