Abstract
This paper presents a line of research in genetic algorithms (GAs), called building-block identification. The building blocks (BBs) are common structures inferred from a set of solutions. In simple GA, crossover operator plays an important role in mixing BBs. However, the crossover probably disrupts the BBs because the cut point is chosen at random. Therefore the BBs need to be identified explicitly so that the solutions are efficiently mixed. Let S be a set of binary solutions and the solution s = b 1 ... b ℓ, b i ∈ {0, 1}. We construct a symmetric matrix of which the element in row i and column j, denoted by m ij , is the chi-square of variables b i and b j . The larger the m ij is, the higher the dependency is between bit i and bit j. If m ij is high, bit i and bit j should be passed together to prevent BB disruption. Our approach is validated for additively decomposable functions (ADFs) and hierarchically decomposable functions (HDFs). In terms of scalability, our approach shows a polynomial relationship between the number of function evaluations required to reach the optimum and the problem size. A comparison between the chi-square matrix and the hierarchical Bayesian optimization algorithm (hBOA) shows that the matrix computation is 10 times faster and uses 10 times less memory than constructing the Bayesian network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aporntewan, C., Chongstitvatana, P.: Simultaneity matrix for solving hierarchically decomposable functions. In: Proceedings of the Genetic and Evolutionary Computation, pp. 877–888. Springer, Heidelberg (2004)
Goldberg, D.E.: The Design of Innovation: Lessons from and for Competent Genetic Algorithms. Kluwer Academic Publishers, Boston (2002)
Harik, G.R.: Learning linkage. In: Foundation of Genetic Algorithms, vol. 4, pp. 247–262. Morgan Kaufmann, San Francisco (1997)
Harik, G.R.: Linkage learning via probabilistic modeling in the ECGA. Technical Report 99010, Illinois Genetic Algorithms Laboratory, University of Illinois at Urbana-Champaign, Champaign, IL (1999)
Holland, J.H.: Building blocks, cohort genetic algorithms, and hyperplane-defined functions. Evolutionary Computation 8(4), 373–391 (2000)
Kargupta, H., Park, B.: Gene expression and fast construction of distributed evolutionary representation. Evolutionary Computation 9(1), 43–69 (2001)
Munetomo, M., Goldberg, D.E.: Linkage identification by non-monotonicity detection for overlapping functions. Evolutionary Computation 7(4), 377–398 (1999)
Pelikan, M., Goldberg, D.E., Lobo, F.: A survey of optimization by building and using probabilistic models. Computational Optimization and Applications 21(1), 5–20 (1999)
Pelikan, M.: Bayesian optimization algorithm: From single level to hierarchy. Doctoral dissertation, University of Illinois at Urbana-Champaign, Champaign, IL (2002)
Thierens, D.: Scalability problems of simple genetic algorithms. Evolutionary Computation 7(4), 331–352 (1999)
Watson, R.A., Pollack, J.B.: Hierarchically consistent test problems for genetic algorithms. In: Proceedings of Congress on Evolutionary Computation, pp. 1406–1413. IEEE Press, Piscataway (1999)
Yu, T., Goldberg, D.E.: Dependency structure matrix analysis: off-line utility of the dependency structure matrix genetic algorithm. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 355–366. Springer, Heidelberg (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aporntewan, C., Chongstitvatana, P. (2004). Chi-Square Matrix: An Approach for Building-Block Identification. In: Maher, M.J. (eds) Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making. ASIAN 2004. Lecture Notes in Computer Science, vol 3321. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30502-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-30502-6_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-24087-7
Online ISBN: 978-3-540-30502-6
eBook Packages: Computer ScienceComputer Science (R0)