Abstract
Many Artificial Intelligence programs exhibit behavior that can be meaningfully compared against the performance of another system, e.g. against a human. A satisfactory understanding of such a program must include an analysis of the behavior of the program and the reasons for that behavior in terms of the program's structure. The primary goal of this thesis is to analyze carefully the performance of the Technology Chess Program as a paradigm for analysis of other complex AI performance programs. The analysis uses empirical, analytical, and statistical methods.

This publication has 0 references indexed in Scilit: