Abstract
Genetic operators are primarily search operators in Evolution Strategies (ES). In fact, there are two important issues in the evolution process of the genetic search: exploration and exploitation. The analysis of the impact of the genetic operators in ES shows that the Classical Evolution Strategies (CES) relies on Gaussian mutation, whereas Fast Evolution Strategies (FES) selects Cauchy distribution as the primary mutation operator. With the analysis of the basic genetic operators of ES as well as their performances on a number of benchmark problems, this paper proposes an Improved Fast ES (IFES) which applies the search direction of global optimization into mutation operation to guide evolution process convergence, thus making the process quicker.
Extensive empirical studies have been carried out to evaluate the performances of IFES, FES and CES. The experimental results obtained from four widely used test functions show that IFES outperforms both FES and CES. It is therefore concluded that it is important to strike a balance between exploration and exploitation.
This is a preview of subscription content, log in via an institution to check access.
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
Baeck, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press, New York (1996)
Fogel, D.B.: An Introduction to Simulated Evolutionary Optimization. IEEE Trans. on Neural Networks 5(1), 3–4 (1994)
Baeck, T., Schwefel, H.-P.: Evolutionary Computation: An Overview. In: Proc. of the 1996 IEEE Int’l. Conf. on Evolutionary Computation (ICEC 1996), Nagoya, Japan, pp. 20–29. IEEE Press, New York (1996)
Yao, X., Liu, Y.: Fast Evolutionary Programming. In: Fogel, L.J., Angeline, P.J., Baeck, T. (eds.) Evolutionary Programming V: Proc. of the Fifth Annual Conference on Evolutionary Programming, pp. 257–266. The MIT Press, Cambridge (1996)
Yao, X., Lin, G., Liu, Y.: An Analysis of Evolutionary Algorithms Base on Neighborhood and Step Sizes. In: Angeline, P.J., McDonnell, J.R., Reynolds, R.G., Eberhart, R. (eds.) EP 1997. LNCS, vol. 1213, pp. 297–307. Springer, Heidelberg (1997)
Kappler, C.: Are Evolutionary Algorithms Improved by Large Mutations? In: Ebeling, W., Rechenberg, I., Voigt, H.-M., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 346–355. Springer, Heidelberg (1996)
Yao, X., Liu, Y.: Fast Evolutiona Strategies. Control and Cybernetics 26(3), 467–496 (1997)
Baeck, T., Gudolph, G., Schwefel, H.-P.: Evolutionary Programming and Evolution Strategies: Similarities and Differences. In: Fogel, D.B., Atmar, W. (eds.) Proc. of the Second Ann. Conf. on Evol. Prog., pp. 11–22. Evolutionary Programming Society, La Jolla
Davis, L.: Genetic Algorithms and Simulated Annealing, pp. 1–11. Morgan Kaufmann Publishers, Los Altos (1987)
Chellapilla, K.: Combining mutation operators in evolutionary programming. IEEE Trans. on Evolutionary Computation 2(3), 91–96 (1996)
Michalewicz, Z.: Genetic Algorithms + Data Structures = Evolution Programs, 3rd edn. Springer, Heidelberg (1996)
Schwefel, H.-P.: Evolution and Optimum Seeking. Sixth Generation Computer Technology Series. Wiley, Chichester (1995)
Guo, T.: Evolutionary Computation and Optimization. PhD thesis, Wuhan University, Wuhan (1999)
Guo, T., Kang, L.: A New Evolutionary Algorithm for Function Optimization. Wuhan University Journal of Natural Sciences 4(4), 404–419 (1999)
Lin, G., Kang, L., Chen, Y., McKay, B., Sarker, R.: A Self-adaptive Mutations with Multi-parent Crossover Evolutionary Algorithm for Solving Function Optimization Problems. In: Kang, L., Liu, Y., Zeng, S. (eds.) ISICA 2007. LNCS, vol. 4683, pp. 157–168. Springer, Heidelberg (2007)
Lin, G., Kang, L., Chen, Y., McKay, B., Sarker, R.: Comparing the Selective Pressure of Different Selection Operators Progress in Intelligence Computation and Applications, pp. 41–45 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lin, G., Lu, X., Kang, L. (2009). Search Direction Made Evolution Strategies Faster. In: Cai, Z., Li, Z., Kang, Z., Liu, Y. (eds) Computational Intelligence and Intelligent Systems. ISICA 2009. Communications in Computer and Information Science, vol 51. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04962-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-04962-0_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04961-3
Online ISBN: 978-3-642-04962-0
eBook Packages: Computer ScienceComputer Science (R0)