Cognitive Economy in Artificial Intelligence Systems

Abstract

Intelligent system, can explore only tiny subsets of their potential external and conceptual worlds. To increase their effective capacities, they must develop efficient forms of representation, access, and operation. In this paper we develop several techniques which do not sacrifice expressibility, yet enable programs to (semi-)automatically improve themselves and thus increase their productivity. The basic source of power is the ability to predict the way that the program will be used in the future, and to tailor the program to expedite such UBEB. Caching, abstraction, and expectation-simplified processing are principal examples of such techniques. We discuss the use of these and other economic principles for modern AI systems. Our analysis leads to some counterintuitive ideas (e.g., favoring redundancy over minimal storage in inheritance hierarchies).