Evolving Logic Programs to Classify Chess-Endgame Positions
In this paper, an algorithm is presented for learning concept classification rules. It is a hybrid between evolutionary computing and inductive logic programming (ILP). Given input of positive and negative examples, the algorithm constructs a logic program to classify these examples. The algorithm has several attractive features including the ability to explicitly use background (user-supplied) knowledge and to produce comprehensible output. We present results of using the algorithm to tackle the chess-endgame problem (KRK). The results show that using fitness proportionate selection to bias the population of ILP learners does not significantly increase classification accuracy. However, when rules are exchanged at intermediate stages in learning, in a manner similar to crossover in Genetic Programming, the predictive accuracy is frequently improved.
KeywordsGenetic Algorithm Evolutionary Algorithm Logic Program Predictive Accuracy Inductive Logic Programming
Unable to display preview. Download preview PDF.
- 1.L. Davis. Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York, 1991.Google Scholar
- 2.Kenneth A. DeJong and William M. Spears. Using genetic algorithms to solve NP-complete problems. In International Conference on Genetic Algorithms, pages 124–132, 1989.Google Scholar
- 4.T. G. Dietterich. Machine learning research: Four current directions. AI Magazine, 18(4):97–136, 1997.Google Scholar
- 5.A. Giordana and L. Saitta. Regal: an integrated system for learning relations using genetic algorithms. In Proceedings of 2nd International Workshop on Multistrategy Learning, pages 234–249. Morgan Kaufmann, 1993.Google Scholar
- 6.David E. Goldberg. Genetic and evolutionary algorithms come of age. Communications of the ACM, Vol. 37:113–119, March 1994.Google Scholar
- 7.William E. Hart and Richard K. Belew. Optimization with genetic algorithm hybrids that use local search. In Richard K. Belew and Melanie Mitchell, editors, Adaptive Individuals in Evolving Populations: Models and Algorithms., volume 26, chapter 27, pages 483–496. SFI Studies in the Sciences of Complexity, 1996.Google Scholar
- 8.S. H. Muggleton, M. Bain, J. Hayes-Michie, and D. Michie. An experimental comparison of human and machine learning formalisms. In Proc. Sixth International Workshop on Machine Learning, pages 113–118, San Mateo, CA, 1989. Morgan Kaufmann.Google Scholar
- 10.Stephen Muggleton. Inverse Entailment and Progol. New Generation Computing, 13, 1995.Google Scholar
- 11.Philip Reiser. EVIL1: a learning system to evolve logical theories. In Proc. Workshop on Logic Programming and Multi-Agent Systems (International Conference on Logic Programming), pages 28–34, July 1997.Google Scholar
- 12.A. C. Schultz and J. J. Grefenstette. Improving tactical plans with genetic algorithms. In Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence, number IEEE Cat. No. 90CH2915-7, pages 328–334, Herndon, VA, 6—9 Nov 1990. IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
- 13.Man Leung Wong and Kwong Sak Leung. Inductive logic programming using genetic algorithms. In J.W. Brahan and G.E. Lasker, editors, Advances in Artificial Intelligence — Theory and Application II, pages 119–124, 1994.Google Scholar