Iterated Function Systems Optimization with Genetic Algorithms
| Citations: | 1 - 0 self |
BibTeX
@MISC{Lankhorst_iteratedfunction,
author = {Marc M. Lankhorst and Marc M. Lankhorst},
title = {Iterated Function Systems Optimization with Genetic Algorithms},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper presents a genetic algorithm used to infer Iterated Function Systems (IFSs) for approximation of 1D and 2D data sets. First, we give an introduction to IFSs. Secondly, we discuss the encoding of 1D and 2D IFSs in the form of chromosomes, and present genetic operators to work upon these representations. The performance of the genetic algorithm is evaluated on four 1D and two 2D test sets. Particularly in the 2D case, the algorithm turns out to perform quite poorly. We give a theoretical explanation for these results, and provide empirical support for this explanation. 1 Introduction Genetic algorithms (GAs) are probabilistic search techniques inspired by the "survival of the fittest" principle of the neo-Darwinian theory of natural evolution (Dawkins, 1986) , and the mechanisms of natural genetics. In every generation, a new set of artificial "creatures" is created using bits and pieces of the fittest members of the previous generation, and occasionally, new parts are tried....
Keyphrases
genetic algorithm function system optimization artificial creature new part theoretical explanation iterated function system present genetic operator natural genetics test set data set empirical support probabilistic search technique introduction genetic algorithm new set previous generation natural evolution neo-darwinian theory
