Advertisement

Abstract

It has long been recognized that mutation is a key ingredient in genetic algorithms (GAs) and the choice of suitable mutation probability will have a significant effect on the performance of genetic search. In this paper, a statistics-based adaptive non-uniform mutation (SANUM) is presented within which the probability that each gene will subject to mutation is learnt adaptively over time and over the loci. As a search algorithm based on mechanisms abstracted from population genetics, GAs implicitly maintain the statistics about the search space through the population. SANUM explicitly makes use of the statistics information of the allele distribution in each gene locus to adaptively adjust the mutation probability of that locus. To test the performance of SANUM, it is compared to traditional bit mutation operator with a number of “standard” fixed mutation probabilities suggested by other researchers over a range of typical test problems. The results demonstrate that SANUM performs persistently well over the range of test problems while the performance of traditional mutation operators with fixed mutation probabilities greatly depends on the problem under consideration. SANUM represents a robust adaptive mutation operator that needs no prior knowledge about the fitness landscape of the problem being solved.

Keywords

Genetic Algorithm Test Problem Mutation Operator Mutation Probability Fitness Landscape 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [l]
    D. H. Ackley (1987). A Connectionist Machine for Genetic Hillclimbing. Boston, MA: Kluwer Academic Publishers.CrossRefGoogle Scholar
  2. [2]
    J. E. Baker (1987). Reducing bias and inefficiency in the selection algorithms. In J. J. Grefenstelle (ed.), Proc. 2nd Int. Conf. on Genetic Algorithms, 14–21. Lawrence Erlbaum Associates.Google Scholar
  3. [3]
    T. Bäck (1992). Self-Adaptation in Genetic Algorithms. In F. J. Varela and P. Bourgine (eds.), Proc. of the 1st European Conf. on Artificial Life, 263–271. MIT Press.Google Scholar
  4. [4]
    T. Bäck (1997). Mutation Parameters. In T. Bäck, D. B. Fogel, and Z. Michalewicz (eds.), Handbook of Evolutionary Computation, E1.2.1–E1.2.7. Oxford University Press.Google Scholar
  5. [5]
    D. Come, P. Ross and H.-L. Fang (1994). GA Research Note 7: Fast Practical Evolutionary Timetabling. Technical Report, Department of Artificial Intelligence, University of Edinburgh, UK.Google Scholar
  6. [6]
    L. Davis (1989). Adapting operator probabilities in genetic algorithms. In D. Schaffer (ed.), Proc. of the 3rd Int. Conf. on Genetic Algorithms, 60–69. San Mateo CA: Morgan Kaufmann Publishers.Google Scholar
  7. [7]
    K. A. De Jong (1975). An Analysis of the Behavior of a Class of Genetic Adaptive Systems. PhD Thesis, Department of Computer and Communication Sciences, University of Michigan, Ann Abor.Google Scholar
  8. [8]
    K. A. De Jong, M. A. Potter and W. M. Spears (1997). Using problem generators to explore the effects of epistasis. In T. Back (ed.), Proc. of the 7th Int. Conf. on Genetic Algorithms, 338–345. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar
  9. [9]
    A. E. Eiben, R. Hinterding and Z. Michalewicz (1999). Parameter control in evolutionary algorithms. IEEE 1hlns. on Evolutionary Computation 3(2):124–141.CrossRefGoogle Scholar
  10. [10]
    T. C. Fogarty (1989). Varying the Probability of Mutation in the Genetic Algorithm. In J. D. Schaffer (ed.), Proc. of the Srd Int. Conf. on Genetic Algorithms, 104–109. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar
  11. [11]
    J. J. Grefenstette (1986). Optimization of Control Parameters for Genetic Algorithms. IEEE 1hlns. on Systems, Man and Cybernetics, 16(1): 122–128.CrossRefGoogle Scholar
  12. [12]
    D. E. Goldberg (1989). Genetic Algorithms in Search, Optimization, and Machine Learning. Reading, MA: Addison-Wesley.MATHGoogle Scholar
  13. [13]
    D. E. Goldberg, B. Korb and K. Deb (1989). Messy Genetic Algorithms: Motivation, Analysis, and First Results. Complex Systems, 4: 415–444.MathSciNetGoogle Scholar
  14. [14]
    J. Hesser and R. Männer (1991). Towards an Optimal Mutation Probability in Genetic Algorithms. In H.-P. Schwefel, R. Männer(eds.), Proc. of the 1st Conf. on Parallel Problem Solving from Nature, 23–32.Google Scholar
  15. [15]
    J. H. Holland (1975). Adaptation in Natural and Artificial Systems. Ann Arbor, University of Michigan Press.Google Scholar
  16. [16]
    B. Julstrom (1995). What have you done for me lately? adapting operator probabilities in a steady-state genetic algorithm. In L. J. Eshelman (ed.), Proc. of the 6th Int. Conf. on Genetic Algorithms, 81–87. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar
  17. [17]
    J. Levenick (1995). Metabits: Genetic Endogenous Crossover Control. In L. J. Eshelman (ed.), Proc. of the 6th Int. Conf. on Genetic Algorithms, 88–95. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar
  18. [18]
    M. Mitchell, S. Forrest and J. H. Holland (1992). The Royal Road for Genetic Algorithms: Fitness Landscapes and GA Performance. In F. J. Varela and P. Bourgine (eds.), Proc. of the 1st European Conference on Artificial Life, 245–254. Cambridge, MA: MIT Press.Google Scholar
  19. [19]
    H. Mühlenbein (1992). How Genetic Algorithms Really Work: I. Mutation and Hillclimbing. In R. Männer and B. Manderick (eds.), Proc. of the 2nd Conf. on Parallel Problem Solving from Nature, 15–29.Google Scholar
  20. [20]
    J. D. Schaffer, R. A. Caruana, L. J. Eshelman, and R. Das (1989). A Study of Control Parameters Affecting Online Performance of Genetic Algorithms for Function Optimization. In J. D. Schaffer (ed.), Proc. of the 3rd Int. Conf. on Genetic Algorithms, 51–60. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar
  21. [21]
    H-P. Schwefel (1981). Numerical Optimization of Computer Models. Wiley, Chichester.MATHGoogle Scholar
  22. [22]
    J. E. Smith and T. C. Fogarty (1996). Self-adaptation of Mutation Rates in a Steady-State Genetic Algorithm. In Proc. of the 3rd IEEE Conf. on Evolutionary Computation, 318–323. IEEE Press.Google Scholar
  23. [23]
    W. Spears (1992). Crossover or Mutation. In L. D. Whitley (Ed.), Foundations of Genetic Algorithms 2. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar
  24. [24]
    A. Tuson and P. Ross (1998). Adapting Operator Settings in Genetic Algorithms. Evolutionary Computation, 6(2): 161–184.CrossRefGoogle Scholar
  25. [25]
    L. D. Whitley (1991). Fundamental Principles of Deception in Genetic Search. In G. J. E. Rawlins (ed.), Foundations of Genetic Algorithms 1, 221–241. San Mateo, CA: Morgan Kaufmann Publishers.Google Scholar

Copyright information

© Springer-Verlag London 2004

Authors and Affiliations

  • Shengxiang Yang
    • 1
  1. 1.Department of Computer ScienceUniversity of LeicesterLeicesterUK

Personalised recommendations