The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World

the results by voting.

The next step is to turn it into an algorithm.

Overfitting happens when you have too many hypotheses and not enough data to tell them apart.

Like the Hydra, the complexity monster has many heads. One of them is space complexity: the number of bits of information an algorithm needs to store in the computer’s memory. If the algorithm needs more memory than the computer can provide, it’s useless and must be discarded. Then there’s the evil sister, time complexity: how long the algorithm ta

What we need is an algorithm that will spontaneously group together similar objects, or different images of the same object. This is the problem of clustering, and it’s one of the most intensively studied in machine learning.

The most important question in any analogical learner is how to measure similarity.

Robby has a Naïve Bayes classifier and needs to figure out the class of a new object, all he needs to do is apply the classifier and compute the probability of each class given the object’s attributes. (Small, fluffy, brown, bear-like, with big eyes, and a bow tie? Probably a toy but possibly an animal.)

Control of data and ownership of the models learned from it is what many of the twenty-first century’s battles will be about—between governments, corporations, unions, and individuals.

Machine learning is what you get when the unreasonable effectiveness of mathematics meets the unreasonable effectiveness of data. Biology and sociology will never be as simple as physics, but the method by which we discover their truths can be.