A parameter-less genetic algorithm

9 years 5 months ago
A parameter-less genetic algorithm
From the user’s point of view, setting the parameters of a genetic algorithm (GA) is far from a trivial task. Moreover, the user is typically not interested in population sizes, crossover probabilities, selection rates, and other GA technicalities. He is just interested in solving a problem, and what he would really like to do, is to hand-in the problem to a blackbox algorithm, and simply press a start button. This paper explores the development of a GA that fulfills this requirement. It has no parameters whatsoever. The development of the algorithm takes into account several aspects of the theory of GAs, including previous research work on population sizing, the schema theorem, building block mixing, and genetic drift.
Georges R. Harik, Fernando G. Lobo
Added 04 Aug 2010
Updated 04 Aug 2010
Type Conference
Year 1999
Authors Georges R. Harik, Fernando G. Lobo
Comments (0)