Learning algorithms are said to be algorithms that improve automatically with experience. The study and use of such algorithms with inanimate machines and systems is called machine learning. Herbert A. Simon, one of the founders of the field, described it thus: "Learning denotes changes in a system that ... enable a system to do the same task more efficiently the next time." Learning algorithms are therefore an important tool and part of artificial intelligence, but in many senses they are more than that--their study may have quite important implications in the social sciences and humanities as well as in the solution of traditional computing problems.

There are many reasons to study learning algorithms. One of the obvious benefits is that study of learning algorithms may also expose the structure of the human cognitive function, itself, and thus shed new light on the nature of human knowledge. Simon...