Coevolutionary, distributed search for inducing concept descriptions

  • C. Anglano
  • A. Giordana
  • G. Lo Bello
  • L. Saitta
Genetic Algorithms
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1398)


This paper presents a highly parallel genetic algorithm, designed for concept induction in propositional and first order logics. The parallel architecture is an adaptation for set covering problems, of the diffusion model developed for optimization.

The algorithm exhibits other two important methodological novelties related to Evolutionary Computation. First, it combines niches and species formation with coevolution, in order to learn multimodal concepts. This is done by integrating the Universal Suffrage selection operator with the coevolution model recently proposed in the literature. Second, it makes use of a new set of genetic operators, which maintain diversity in the population.

The experimental comparison with previous systems, not using coevolution and based on traditional genetic operators, shows a substantial improvement in the effectiveness of the genetic search.


Concept Learning Parallel Genetic Algorithms Coevolution 


  1. 1.
    Augier, S., Venturini, G., and Kodratoff, Y. Learning First Order Logic Rules with a Genetic Algorithm. In Proc. Of the First International Conference on Knowledge Discovery and Data Mining (1995).Google Scholar
  2. 2.
    DeJong, K., Spears, W., and Gordon, F. Using genetic algorithms for concept learning. Machine Learning Journal, 13 (1993), 161–188.CrossRefGoogle Scholar
  3. 3.
    Giordana, A., and Neri, F. Search-intensive concept induction. Evolutionary Computation Journal (1996), Winter, 1995.Google Scholar
  4. 4.
    Goldberg, D.Genetic Algorithms. Addison-Wesley, Reading, MA, 1989.Google Scholar
  5. 5.
    Goldberg, D., and Richardson, J. Genetic algorithms with sharing for multimodal function optimization. In Int. Conf. on Genetic Algorithms (Cambridge, MA, 1987), Morgan Kaufmann, pp. 41–49.Google Scholar
  6. 6.
    Greene, D., and Smith, S. Competition-based induction of decision models from examples. Machine Learning Journal, 13 (1993), 229–258.CrossRefGoogle Scholar
  7. 7.
    Husbands, P., and Mill, F. Co-evolving parasites improve simulated evolution as an optimization procedure. In 4th Int. Conf. on Genetic Algorithms (Fairfax, VA, 1991), Morgan Kaufmann, pp. 264–270.Google Scholar
  8. 8.
    Janikow, C. A knowledge intensive genetic algorithm for supervised learning. Machine Learning Journal, 13 (1993), 198–228.Google Scholar
  9. 9.
    Michalski, R. A theory and methodology of inductive learning. In Machine Learning: An AI Approach (Los Altos, CA, 1983), J. C. R. Michalski and T. Mitchell, Eds., Morgan Kaufmann, pp. 83–134.Google Scholar
  10. 10.
    Potter, M., DeJong, K., and Grefenstette, J. A coevolutionary approach to learning sequential decision rules. In Int. Conf. on Genetic Algorithms (Pittsburgh, PA, 1995), Morgan Kaufmann, pp. 366–372.Google Scholar
  11. 11.
    Syswerda, G. Uniform crossover in genetic algorithms. In 3th Int. Conf. on Genetic Algorithms (Fairfax, VA, 1989), Morgan Kaufmann, pp. 2–9.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • C. Anglano
    • 1
  • A. Giordana
    • 1
  • G. Lo Bello
    • 1
  • L. Saitta
    • 1
  1. 1.Dipartimento di InformaticaUniversità di TorinoTorinoItaly

Personalised recommendations