Is the idea of crossover only restricted to Genetic Algorithms ? Are there any other evolutionary algorithms that uses crossover(even under another name ) ? If an algorithm uses crossover but does not utilize selection or mutation , should we call it a genetic algorithm ?
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
0
Crossover is a way of recombining solutions and is not limited to genetic algorithms. Scatter search is an example of a widely used meta-heuristic that recombines solutions systematically. A specific form of solution recombination is path relinking and Evolutionary GRASP is an example of a meta-heuristic based on it. Similar to a genetic algorithm it maintains a pool of good solutions and repeatedly recombines them by path relinking to find better solutions.
It may also be interesting to have a look at Evolution strategies, a subclass of evolutionary algorithms using mutation only.
