Continuous Optimization by Evolving Probability Density Functions with a Two-Island Model
The work presents a new evolutionary algorithm designed for continuous optimization. The algorithm is based on evolution of probability density functions, which focus on the most promising zones of the domain of each variable. Several mechanisms are included to self-adapt the algorithm to the feature of the problem. By means of an experimental study, we have observed that our algorithm obtains good results of precision, mainly in multimodal problems, in comparison with some state-of-the-art evolutionary methods.
KeywordsLocal Search Local Optimum Basic Algorithm Memetic Algorithm Simplex Algorithm
Unable to display preview. Download preview PDF.
- 2.Deb, K., Corne, D., Michalewicz, Z.: Special Session on Real-parameter Optimization. In: IEEE Congress on Evolutionary Computation 2005, Edimburgh, UK (September 2005)Google Scholar
- 3.Larrañaga, P., Lozano, J.A. (eds.): Estimation of distribution algorithms. A new tool for evolutionary computation. Kluwer Academic Publishers, Dordrecht (2001)Google Scholar
- 4.Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C. The Art of Scientific Computing, 2nd edn. Cambridge University Press, CambridgeGoogle Scholar