A study of automatic rule generation and adaption

This paper describes a rule-based learning system called CSM which acquires knowledge through trial-and-error interaction automatically and builds its knowledge base incrementally without human assistance. The development of CSM suggests a promising way to bridge the gap between general-purpose, low-level adaptive learning systems and specialized symbolic rule-based AI systems. To show the feasibility of this approach, CSM has been tested both in the robot navigation domain and letter extrapolation domain. The experimental results show that CSM is able to create appropriate rules from scratch to solve given tasks in an increasingly efficient and direct manner.

[1]  John J. Grefenstette,et al.  Technique For Automatic Motion Correction In Digital Subtraction Angiography , 1987 .

[2]  John H. Holland,et al.  COGNITIVE SYSTEMS BASED ON ADAPTIVE ALGORITHMS1 , 1978 .

[3]  Tom M. Mitchell,et al.  Generalization as Search , 2002 .

[4]  Stephen F. Smith,et al.  A learning system based on genetic adaptive algorithms , 1980 .

[5]  John H. Holland.  Genetic Algorithms and Classifier Systems: Foundations and Future Directions , 1987, ICGA.

[6]  John H. Holland,et al.  Escaping brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systems , 1995 .

[7]  Lashon B. Booker,et al.  Intelligent Behavior as an Adaptation to the Task Environment , 1982 .

[8]  Albert Donally Bethke,et al.  Genetic Algorithms as Function Optimizers , 1980 .

[9]  Stewart W. Wilson.  Quasi-Darwinian Learning in a Classifier System , 1987 .

[10]  Lashon B. Booker,et al.  Improving the Performance of Genetic Algorithms in Classifier Systems , 1985, ICGA.

[11]  H. Simon,et al.  Empirical tests of a theory of human acquisition of concepts for sequential patterns , 1973 .

[12]  John H. Holland,et al.  Cognitive systems based on adaptive algorithms , 1977, SGAR.

[13]  J. D. Schaffer,et al.  Some experiments in machine learning using vector evaluated genetic algorithms (artificial intelligence, optimization, adaptation, pattern recognition) , 1984 .

[14]  John J. Grefenstette,et al.  Csm: a genetic classifier system with memory for learning by analogy , 1987 .

[15]  Lawrence Davis,et al.  Job Shop Scheduling with Genetic Algorithms , 1985, ICGA.

[16]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[17]  Kenneth Alan De Jong,et al.  An analysis of the behavior of a class of genetic adaptive systems. , 1975 .

[18]  John H. Holland,et al.  Induction: Processes of Inference, Learning, and Discovery , 1987, IEEE Expert.