1 / 17

Genetic Algorithms

Genetic Algorithms. Vida Movahedi November 2006. Contents. What are Genetic Algorithms? From Biology … Evolution … To Genetic Algorithms Demo. What are Genetic Algorithms?. A method of solving Optimization Problems Exponentially large set of solutions Easy to compute cost or value

ford
Télécharger la présentation

Genetic Algorithms

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Genetic Algorithms Vida Movahedi November 2006

  2. Contents • What are Genetic Algorithms? • From Biology … • Evolution • … To Genetic Algorithms • Demo

  3. What are Genetic Algorithms? • A method of solving Optimization Problems • Exponentially large set of solutions • Easy to compute cost or value • Search algorithm (looking for the optimum) • Very similar to random search?! • Population- based • We start with a set of possible solutions (initial population) and evolve it to get to the optimum • Also called Evolutionary Algorithms • Based on evolution in biology

  4. Can we use the same idea to get an optimal solution? From Biology … • Charles Darwin (1859) • Natural selection , “survival of the fittest” • Improvement of species

  5. Evolution To implement optimization as evolution, We need • Mapping features to genes, showing each individual with a chromosome • An initial population • Have a function to measure fitness  same as what we want to optimize • Implement and apply Reproduction • Replace offspring in old generation • Have an exit condition for looping over generations

  6. Initial Population • Representation of possible solutions as chromosomes • Binary • Real • etc. • Random initial population • If not random  stuck in local optima

  7. Recombination (crossover) • Random crossover points • Inheriting genes from one parent

  8. Mutation • Random Mutation Point • Changing gene value to a random value

  9. … to Genetic Algorithms BEGIN /* genetic algorithm*/ Generate initial population ;Compute fitness of each individual ; LOOP Select individuals from old generations for mating ; Create offspring by applying recombination and/or mutation to the selected individuals ; Compute fitness of the new individuals ; Kill old individuals ,insert offspring in new generation ; IF Population has converged THEN exit loop; END LOOP END

  10. Simple Example

  11. Example • http://www.rennard.org/alife/english/gavgb.html

  12. References • [1] Hue, Xavier (1997), “Genetic Algorithms for Optimisation: Background and Applications”, http://www.epcc.ed.ac.uk/overview/publications/training_material/tech_watch/97_tw/techwatch-ga/ • [2] Whitely, Darell (1995), “A Genetic Algorithm Tutorial”, http://samizdat.mines.edu/ga_tutorial/

  13. Questions?

More Related