Editing Mating pool (section)

[[File:Mating pool process.jpg|thumb|Visual representation of the position of the mating pool during the genetic algorithm process.]]
'''Mating pool''' is a concept used in [[evolutionary algorithms]] and means a population of parents for the next population.<ref>{{cite journal |title=Evolutionary algorithms |journal=Computational Intelligence: Methods and Techniques |date=2008 |pages=265–347 |doi=10.1007/978-3-540-76288-1_7 |url=https://link.springer.com/chapter/10.1007/978-3-540-76288-1_7 |publisher=Springer |isbn=978-3-540-76287-4 |language=en|url-access=subscription }}</ref><ref name=":0">Regupathi, R. “Cost Optimization Of Multistoried Rc Framed Structure Using Hybrid Genetic Algorithm.”  ''International Research Journal of Engineering and Technology (IRJET)'', vol. 04, no. 07, July 2017, p. 890., www.irjet.net/archives/V4/i7/IRJET-V4I7211.pdf.</ref>

The mating pool is formed by candidate solutions that the [[Selection (genetic algorithm)|selection]] operators deem to have the highest fitness in the current population. Solutions that are included in the mating pool are referred to as parents. Individual solutions can be repeatedly included in the mating pool, with individuals of higher fitness values having a higher chance of being included multiple times. [[Crossover (genetic algorithm)|Crossover]] operators are then applied to the parents, resulting in recombination of genes recognized as superior. Lastly, random changes in the genes are introduced through [[Mutation (genetic algorithm)|mutation]] operators, increasing the genetic variation in the gene pool. Those two operators improve the chance of creating new, superior solutions. A new generation of solutions is thereby created, the children, who will constitute the next population. Depending on the selection method, the total number of parents in the mating pool can be different to the size of the initial population, resulting in a new population that’s smaller. To continue the algorithm with an equally sized population, random individuals from the old populations can be chosen and added to the new population.<ref name=":0" /><ref>{{Cite web|last=Schatten|first=Alexander|date=19 June 2002|title=Genetic Algorithms|url=https://web.cs.ucdavis.edu/~vemuri/classes/ecs271/Genetic%20Algorithms%20Short%20Tutorial.htm}}</ref><ref>{{Cite journal|last1=Mitchell|first1=Melanie|last2=Taylor|first2=Charles E.|date=November 1999|title=Evolutionary Computation: An Overview|url=http://www.annualreviews.org/doi/10.1146/annurev.ecolsys.30.1.593|journal=Annual Review of Ecology and Systematics|language=en|volume=30|issue=1|pages=593–616|doi=10.1146/annurev.ecolsys.30.1.593|bibcode=1999AnRES..30..593M |issn=0066-4162|url-access=subscription}}</ref>

At this point, the fitness value of the new solutions is evaluated. If the termination conditions are fulfilled, processes come to an end. Otherwise, they are repeated.

The repetition of the steps result in candidate solutions that evolve towards the most optimal solution over time. The genes will become increasingly uniform towards the most optimal gene, a process called [[Convergence of random variables|convergence]]. If 95% of the population share the same version of a gene, the gene has converged. When all the individual fitness values have reached the value of the best individual, i.e. all the genes have converged, population convergence is achieved.<ref name=":0" /><ref name=":1">Beasley, D., Bull, D. R., & Martin, R. R. (1993). An overview of genetic algorithms: Part 1, fundamentals. University computing, 15(2), 56-69.</ref>