Abstract | ||
---|---|---|
The takeover time is the expected number of it- erations of some selection method until a popu- lation consists entirely of copies of the best in- dividual under the assumption that only one best individual is contained in the initial population. This quantity is often used to assess the behav- ior of selection methods in evolutionary algo- rithms. Here, takeover times and probabilities are analytically determined for some popular non- generational selection rules. Moreover, a novel classification number that aggregates additional information about the selection method is pro- posed. |
Year | Venue | Field |
---|---|---|
2000 | GECCO | Population,Mathematical optimization,Evolutionary algorithm,Computer science,Expected value,Artificial intelligence,Selection (genetic algorithm),Machine learning |
DocType | Citations | PageRank |
Conference | 2 | 0.44 |
References | Authors | |
3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Günter Rudolph | 1 | 219 | 48.59 |
Fachbereich Informatik | 2 | 113 | 12.60 |