A case for codons in evolutionary algorithms

Authors:
Joshua Gilbert;Maggie Eppstein
Affiliations:
Dept. of Computer Science, University of Vermont, Burlington, VT;Dept. of Computer Science, University of Vermont, Burlington, VT
Venue:
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Year:
2003

Citing 6
Cited 0

Nonstationary function optimization using genetic algorithm with dominance and diploidy

Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Practical Handbook of Genetic Algorithms: New Frontiers

Practical Handbook of Genetic Algorithms: New Frontiers
The Darwinian Genetic Code: An Adaptation for Adapting?

Genetic Programming and Evolvable Machines
Genotype-Phenotype-Mapping and Neutral Variation - A Case Study in Genetic Programming

PPSN III Proceedings of the International Conference on Evolutionary Computation. The Third Conference on Parallel Problem Solving from Nature: Parallel Problem Solving from Nature
The Influence Of Binary Representations Of Integers On The Performance Of Selectorecombinative Genetic Algorithms

GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Genetic programming using genotype-phenotype mapping from linear genomes into linear phenotypes

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new method is developed for representation and encoding in population-based evolutionary algorithms. The method is inspired by the biological genetic code and utilizes a many-to-one, codon-based, genotype-to-phenotype translation scheme. A genetic algorithm was implemented with this codon-based representation using three different codon translation tables, each with different characteristics. A standard genetic algorithm is compared to the codon-based genetic algorithms on two difficult search problems; a dynamic knapsack problem and a static problem involving many suboptima. Results on these two problems indicate that the codon-based representation may promote rapid adaptation to changing environments and the ability to find global minima in highly non-convex problems.