This thesis recasts the debate between Michigan-style and Pitt-style classi er systems to a debate on appropriately sizing organizations within a learning classi er system. Motivated by the economic study of transaction costs, an organizational classi er system (OCS) combining explicit use of multiple reputation values and organization sizing operators better distinguishes parasitic (less than optimal) classi ers than a simple classi er system (SCS). The results show that by building a system that autonomously adjusts the degree of individual to collective behavior, it is possible for it to be both e cient and resilient to problem di culty. iii Acknowledgments I thank my parents, although no amount of thanks could su ciently repay their unfailing love and support. I thank Dr. David Goldberg, my adviser, for his input, support, and creative ideas. I thank Kevin Carmody and Je rey Horn for their friendship and support. I thank Rebecca Robinson for taking care of things while I worked on this thesis. Support for this work was provided by the U.S. Air Force O ce of Scienti c Research under Grant No. F49620-94-1-0103 and from the National Aeronautics and Space Administration with Grant No. NGT-50873. iv Table of
[1]
David E. Goldberg,et al.
Genetic Algorithms in Search Optimization and Machine Learning
,
1988
.
[2]
Ronald H. Coase,et al.
The Firm, the Market, and the Law
,
1990
.
[3]
Stephen F. Smith,et al.
A learning system based on genetic adaptive algorithms
,
1980
.
[4]
F. Hayek.
The economic nature of the firm: The use of knowledge in society
,
1945
.
[5]
Tom H. Westerdale.
A Defense of the Bucket Brigade
,
1989,
ICGA.
[6]
Joseph Culberson,et al.
GIGA Program Description and Operation
,
1992
.
[7]
John J. Grefenstette,et al.
Multilevel Credit Assignment in a Genetic Learning System
,
1987,
International Conference on Genetic Algorithms.
[8]
David E. Goldberg,et al.
A Critical Review of Classifier Systems
,
1989,
ICGA.
[9]
Rick L. Riolo,et al.
Bucket Brigade Performance: I. Long Sequences of Classifiers
,
1987,
ICGA.
[10]
Rick L. Riolo,et al.
Bucket Brigade Performance: II. Default Hierarchies
,
1987,
ICGA.