Testing the robustness of the genetic algorithm on the floating building block representation

Authors:
Robert K. Lindsay;Annie S. Wu
Affiliations:
Mental Health Research Institute, University of Michigan, Ann Arbor, MI;Artificial Intelligence Laboratory, University of Michigan, Ann Arbor, MI
Venue:
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Year:
1996

Citing 2
Cited 3

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Non-coding DNA and floating building blocks for the genetic algorithm

Non-coding DNA and floating building blocks for the genetic algorithm

Evolutive Introns: A Non-Costly Method of Using Introns in GP

Genetic Programming and Evolvable Machines
Introducing Start Expression Genes to the Linkage Learning Genetic Algorithm

PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Tightness time for the linkage learning genetic algorithm

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent studies on a floating building block representation for the genetic algorithm (GA) suggest that there are many advantages to using the floating representation. This paper investigates the behavior of the GA on floating representation problems in response to three different types of pressures: (1) a reduction in the amount of genetic material available to the GA during the problem solving process, (2) functions which have negative-valued building blocks, and (3) randomizing non-coding segments. Results indicate that the GA's performance on floating representation problems is very robust. Significant reductions in genetic material (genome length) may be made with relatively small decrease in performance. The GA can effectively solve problems with negative building blocks. Randomizing non-coding segments appears to improve rather than harm GA performance.