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