Non-destructive depth-dependent crossover for genetic programming
In our previous paper , a depth-dependent crossover was proposed for GP. The purpose was to solve the difficulty of the blind application of the normal crossover, i.e., building blocks are broken unexpectedly. In the depth-dependent crossover, the depth selection ratio was varied according to the depth of a node. However, the depth-dependent crossover did not work very effectively as generated programs became larger. To overcome this, we introduce a non-destructive depth-dependent crossover, in which each offspring is kept only if its fitness is better than that of its parent. We compare GP performance with the depth-dependent crossover and that with the non-destructive depth-dependent crossover to show the effectiveness of our approach. Our experimental results clarify that the non-destructive depth-dependent crossover produces smaller programs than the depth-dependent crossover.
Unable to display preview. Download preview PDF.
- 1.Aho, A., Hopcroft, J. and Ullman, J. The Design and Analysis of Computer Algorithms, Addison-Wesley, 1974Google Scholar
- 2.Angeline, J. Subtree Crossover: Building Block Engine or Macromutation?, In Koza, J., Deb, K., Dorigo, M., Fogel, D. Garzon, M., Iba, H. and Riolo, R. editors, Proceedings of the Second Annual Conference Genetic Programming 1997 (GP97), pages 9–17, MIT Press, 1997Google Scholar
- 3.Iba, H., deGaris, H. and Sato, T. Genetic Programming using a Minimum Description Length Principle, In Kinnear, Jr. K. editor, Advances in Genetic Programming, pages 265–284, MIT Press, 1994Google Scholar
- 4.Ito, T. and Iba, H. and Kimura, M. Robustness of Robot Programs Generated by Genetic Programming, In Koza, J., Goldberg, D., Fogel, D. and Riolo, R. editors, Proceedings of the First Annual Conference Genetic Programming 1996 (GP96), pages 321–326, MIT Press, 1996Google Scholar
- 5.Ito, T. and Iba, H. and Sato, S. Depth-Dependent Crossover for Genetic Programming, In Proceedings of the 1998 IEEE International Conference on Evolutionary Computation (ICEC’98), 1998Google Scholar
- 6.Kinnear, Jr. K. Generality and Difficulty in Genetic Programming: Evolving a Sort, In Proceedings of 5th International Joint Conference on Genetic Algorithms MIT press, 1993Google Scholar
- 7.Koza, J. Genetic Programming: On the Programming of Computers by Natural Selection, MIT press, 1992Google Scholar
- 8.Rudolf, F. and Wilson, W. Statistical Methods, Academic Press, Inc. 1992Google Scholar
- 9.Slavov, V and Nikolaev, N Fitness Landscapes and Inductive Genetic Programming, In Smith, G. editor, Third International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA’97), Springer-Verlag, Vienna, 1997Google Scholar
- 10.Soule, T., Foster, J. and Dickinson, J. Code Growth in Genetic Programming, In Koza, J., Goldberg, D., Fogel, D. and Riolo, R. editors, Proceedings of the First Annual Conference Genetic Programming 1996 (GP96), pages 215–223, MIT Press, 1996Google Scholar
- 11.Soule, T. and Foster, J. Code Size and Depth Flows in Genetic Programming, In Koza, J., Deb, K., Dorigo, M., Fogel, D. Garzon, M., Iba, H. and Riolo, R. editors, Proceedings of the Second Annual Conference Genetic Programming 1997 (GP97), pages 313–320, MIT Press, 1997Google Scholar