Authors: | Beyer, Hans-Georg Kalyanmoy Deb |
Title: | On the Analysis of Self-Adaptive Evolutionary Algorithms |
Language (ISO): | en |
Abstract: | Due to the exibility in adapting to different fitness landscapes, self-adaptive evolutionary algorithms (SA-EAs) have been gaining popularity in the recent past. In this paper, we postulate the properties that SA-EA operators should have for successful applications. Specifically, population mean and variance of a number of SA-EA operators, such as various real-parameter crossover operators and self-adaptive evolution strategies, are calculated for this purpose. In every case, simulation results are shown to verify the theoretical calculations. The postulations and population variance calculations explain why self-adaptive GAs and ESs have shown similar performance in the past and also suggest appropriate strategy parameter values which must be chosen while applying and comparing different SA-EAs. |
Subject Headings: | blend crossover operator evolution strategies fuzzy recombination operator genetic algorithms population mean population variance self-adaptation simulated binary crossover |
URI: | http://hdl.handle.net/2003/5374 http://dx.doi.org/10.17877/DE290R-15381 |
Issue Date: | 2001-10-16 |
Provenance: | Universität Dortmund |
Appears in Collections: | Sonderforschungsbereich (SFB) 531 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ci69.pdf | DNB | 426.25 kB | Adobe PDF | View/Open |
ci69.ps | 474.16 kB | Postscript | View/Open |
This item is protected by original copyright |
This item is protected by original copyright rightsstatements.org