Comparing population mean curves

B. Naudts; I. Landrieu    Department of Mathematics and Computer Science, University of Antwerpen (RUCA), Groenenborgerlaan 171, B-2020 Antwerpen, Belgium


One approach to the a posteriori classification of problem/algorithm combinations in the context of evolutionary algorithms (EAs), is to record and analyse a number of summary statistics of the evolution of the population. This paper discusses a necessary normalization of the population mean curve, i.e., the curve of the average fitness of the individuals in the population, plotted per generation. The normalization is based on a transformation w.r.t. the density of states (DoS) of the problem, the distribution ...

Get Foundations of Genetic Algorithms 2001 (FOGA 6) now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.