A New Adaptive Crossover Operator for the Preservation of Useful Schemata.

Conference Paper · January 2005with6 Reads
Source: DBLP
Conference: Advances in Machine Learning and Cybernetics, 4th International Conference, ICMLC 2005, Guangzhou, China, August 18-21, 2005, Revised Selected Papers
  • [Show abstract] [Hide abstract] ABSTRACT: Most real-coded genetic algorithm research has focused on developing effective crossover operators, and as a result, many different types of crossover operators have been proposed. Some forms of crossover operators are more suitable to tackle certain problems than others, even at the different stages of the genetic process in the same problem. For this reason, techniques that combine multiple crossovers, called hybrid crossover operators, have been suggested as alternative schemes to the common practice of applying only one crossover model to all the elements in the population. On the other hand, there are operators with multiple offsprings, more than two descendants from two parents, which present a better behavior than the operators with only two descendants, and achieve a good balance between exploration and exploitation. © 2009 Wiley Periodicals, Inc.
    Full-text · Article · May 2009
  • [Show abstract] [Hide abstract] ABSTRACT: Making theoretical has been a hard task for researchers in the field of Evolutionary Dynamic Optimization (EDO), as only a few approaches have appeared in recent years. In EDO, problems change over time, requiring from the solver, an Evolutionary Algorithm (EA), to continuously adapt to new conditions. Mathematical tools such as the takeover time models, extensively used to characterize and compare EAs in static problems, become much more difficult to understand when the problem changes over time. A preliminary takeover time model have been recently introduced for tournament selection and diversity-generating approaches. In this article, we propose a new enhanced model that takes into account important scenarios that were not initially considered. We use predictive modeling to describe the EAs performance and statistical analysis to validate our equations. Finally, we show how these theoretical models can be used to build novel techniques in EDO.
    Article · Jan 2015