ICGA-97 Workshop on Test Problem Generators
This page and the associated repository is the result of the Workshop
on Test Problem Generators for Evolutionary Algorithms, which was held
at the The Seventh International Conference on Genetic Algorithms at
Michigan State University in July 1997.
Motivation for the Workshop and the Repository
In comparing and contrasting the performance of evolutionary
algorithms (EAs), there is currently an over-reliance on individual
problems and/or rigid test suites of problems. An alternative
approach is to create test problem generators in which random problems
with certain characteristics can be generated automatically and
methodically. Some example characteristics would be multimodality,
epistasis, the degree of deception, and problem size. Since problems
are randomly created within a certain class, it is often easier to
draw general conclusions about the behavior of an EA - the strengths
and weaknesses of the algorithms can be tied to specific problem
characteristics.
The format for this workshop was a series of talks (see schedule
below). Each talk was by a contributor who had a novel test
problem generator for the EA community. Click on the talks to see
the actual slides that were presented.
Schedule of Talks
These were the talks at the workshop.
Introduction (William Spears)
The De Jong Test Suite Considered Harmful (Kenneth De Jong)
Epistasis and Multimodality Generators (William Spears)
An NK-Landscape Generator (Mitchell Potter)
Graph Generators (Peter Ross)
Hyperplane Defined Functions (Ted Belding)
Polynomial Generators (Tom English)
For more information, please contact
William M. Spears.
Last modified: 07/29/99