Improving evolutionary algorithms with scouting

Authors:
Konstantinos Bousmalis;Gillian M. Hayes;Jeffrey O. Pfaffmann
Affiliations:
Department of Informatics, The University of Edinburgh, Edinburgh, UK;Institute of Perception, Action and Behaviour, Department of Informatics, The University of Edinburgh, Edinburgh, UK;Department of Computer Science, Lafayette College, Easton, PA
Venue:
EPIA'07 Proceedings of the aritficial intelligence 13th Portuguese conference on Progress in artificial intelligence
Year:
2007

Citing 5
Cited 1

Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator

ACM Transactions on Modeling and Computer Simulation (TOMACS) - Special issue on uniform random number generation
The theory of evolution strategies

The theory of evolution strategies
Scouting Context-Sensitive Components

EH '01 Proceedings of the The 3rd NASA/DoD Workshop on Evolvable Hardware
GNU Scientific Library Reference Manual - 2nd Edition

GNU Scientific Library Reference Manual - 2nd Edition
Fitness uniform optimization

IEEE Transactions on Evolutionary Computation

Improving Evolutionary Algorithms with Scouting: High---Dimensional Problems

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The goal of an Evolutionary Algorithm(EA) is to find the optimal solution to a given problem by evolving a set of initial potential solutions. When the problem is multi-modal, an EA will often become trapped in a suboptimal solution(premature convergence). The Scouting-Inspired Evolutionary Algorithm(SEA) is a relatively new technique that avoids premature convergence by determining whether a subspace has been explored sufficiently, and, if so, directing the search towards other parts of the system. Previous work has only focused on EAs with point mutation operators and standard selection techniques. This paper examines the effect of scouting on EA configurations that, among others, use crossovers and the Fitness-Uniform Selection Scheme(FUSS), a selection method that was specifically designed as means to avoid premature convergence. We will experiment with a variety of problems and show that scouting significantly improves the performance of all EA configurations presented.