Mixing, Control Maps, and Genetic Algorithm Success

  • David E. Goldberg
Part of the Genetic Algorithms and Evolutionary Computation book series (GENA, volume 7)


On the face of it, the previous chapter would seem like good news. After all, solution accuracy and reliability were predictably controlled using nothing more than appropriate (sub- or near-linear) population sizing. Moreover, this happy circumstance appeared to occur on both easy and hard problems. But closer scrutiny of the presented results shows that all is not necessarily well. In the last chapter, and in previous works on population sizing, when difficult problems were tested, tight linkage was assumed. That is, alleles contributing to a difficult building block were assumed to be physically close to one another, and crossover operators such as single-point crossover were used to facilitate the necessary exchange of intact building blocks with high probability.


Building Block Crossover Operator Hard Problem Good Individual Easy Problem 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media Dordrecht 2002

Authors and Affiliations

  • David E. Goldberg
    • 1
  1. 1.University of Illinois at Urbana-ChampaignUSA

Personalised recommendations