论文信息 - Simultaneous Discovery of Reusable Detectors and Subroutines Using Genetic Programming

Simultaneous Discovery of Reusable Detectors and Subroutines Using Genetic Programming

This paper describes an approach for automatically decomposing a problem into subproblems and then automatically discovering reusable subroutines, and a way of assembling the results produced by these subroutines in order to solve a problem. The approach uses genetic programming with automatic function definition. Genetic programming provides a way to genetically breed a computer program to solve a problem. Automatic function definition enables genetic programming to define potentially useful subroutines dynamically during a run. The approach is applied to an illustrative problem. Genetic programming with automatic function definition reduced the computational effort required to learn a solution to the problem by a factor of 2.0 as compared to genetic programming without automatic function definition. Similarly, the average structural complexity of the solution was reduced by about 21%.

John R. Koza | J. Koza

[1] John R. Koza. Hierarchical Automatic Function Definition in Genetic Programming , 1992, FOGA.

[2] John R. Koza,et al. Performance improvement of machine learning via automatic discovery of facilitating functions as applied to a problem of symbolic system identification , 1993, IEEE International Conference on Neural Networks.

[3] John R. Koza,et al. Genetic Programming: The Movie , 1992 .

[4] John R. Koza,et al. Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[5] Arthur L. Samuel,et al. Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[6] John R. Koza. Simultaneous discovery of detectors and a way of using the detectors via genetic programming , 1993, IEEE International Conference on Neural Networks.

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