1 / 25

Evolutionary Computation

Evolutionary Computation. Biologically inspired algorithms. BY: Andy Garrett YE Ziyu. What is Evolutionary Computation. A subfield of artificial intelligence which mimics biology Used in optimization of black box problems Parallel processing. Types of Evolutionary Computation.

varen
Télécharger la présentation

Evolutionary Computation

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. Evolutionary Computation Biologically inspired algorithms BY: Andy Garrett YE Ziyu

  2. What is Evolutionary Computation • A subfield of artificial intelligence which mimics biology • Used in optimization of black box problems • Parallel processing

  3. Types of Evolutionary Computation • Evolutionary programing • Genetic algorithms • Evolutionary strategies • Genetic programing • Genetic algorithms • Swarm intelligence

  4. GeneticAlgorithms

  5. Genetic Algorithm——what is gene? Biology: A certain DNA sequence at a certain position of the chromosome. A certain element (an allele) of the solution (the chromosome) Genetic Algorithm : A certain value of a certain element of the solution. Three alternative values (genes)

  6. Genetic Algorithm——what is gene? Biology Genetic Algorithm Genes Genes constitute constitute Chromosome Solution determines determines Performance of a solution in the problem. (Fitness) Fitness of a individual In the environment

  7. Genetic Algorithm——what is gene? In Genetic Algorithm, genes (values of elements of the solution) determine the fitness (performance) of a solution. To solve a problem = To find the combination of genes that provides the best fitness (performance)

  8. X Genetic Algorithm——Initiation To conduct evolution, We need a set of solutions. (A population) Initially, the population is generated randomly. This is the first generation. Y A two-dimension search space dotted by randomly generated solutions (each solution consists of two elements, x and y)

  9. Genetic Algorithm——Reproduction: Crossover Crossover is how we create new individuals from the existing ones. Two solutions somehow be selected as “parents” Randomly select one (or more) point Apply cross (Recombine the two solutions) Finish! These will be two Individuals in the next generation

  10. Genetic Algorithm——Reproduction: Selection • Individuals with higher fitness have a higher probabilityto be chosen as parents of thecrossover operation. • Survival of the fittest

  11. Genetic Algorithm——Reproduction: Selection What’s the effect? Genes associated with high fitness are more likely to be passed to the new generation. After some generations, the average fitness of the population gets improved!

  12. Genetic Algorithm——Reproduction: Selection In a graphic view: (use our two-dimension example) The population gathers around the optimal solution. It’s like that the population is climbing the hill. Problem solved? X Y

  13. Genetic Algorithm——Mutation Problem: What if we have multiple hills in the searching space? The individuals may climb onto a hill that is not the highest. Thus, they may gather around a local optimum. X (Global optimum) (Local optimum) Y Y

  14. Genetic Algorithm——Mutation According to the crossover operation, genes in the new generation only come from the previous generation. Thus, once the solutions gather around a local optimum, they will be constrained in its vicinity! They won’t find the global optimum. X (Constraining region) Y

  15. Genetic Algorithm——Mutation Mutation: Make random changes to some genes in each generation. NEW genes are created! Solutions can jump out of the region. After some generations, they may probably gather around the global optimum. X Y

  16. Genetic Algorithm——Scenario Step 1: Initiation(Randomly generate the first generation); Step 2: Mutation; Step 3: Fitnessevaluation; Step 4: Reproduction: Selection; Crossover; Step 5: Go back to step 2, repeat this loop until a sufficiently good solution is found.

  17. Swarm intelligence

  18. Swarm Intelligence Swarm intelligence = cognition of individuals + communication Application in optimization problems: Particle Swarm Optimization (PSO)

  19. Swarm Intelligence——Initiation Randomly generate a set of solutions (called a swarm of particles), their initial positions, and their initial speeds. X V2o V3o V1o Y

  20. Swarm Intelligence——Travelling Two forces are exerted on each particle: X pbest2(gbest) 1. Force pointing to the best solution this particle has ever passed through (pbest) pbest3 2. Force pointing to the best solution any particle has ever passed through(gbest) pbest1 Y pbest gbest

  21. Swarm Intelligence——Travelling Forces pointing to pbests: Fp1, Fp2, Fp3 These forces result from the cognition of individual particles. X Fp2 Fp3 Fp1 Y

  22. Swarm Intelligence——Travelling Forces pointing to gbests: Fg1, Fg2, Fg3 These forces result from the communication among the particles. X Fg3 Fg2 Fg1 Y

  23. Swarm Intelligence——Travelling After some time, the particles would probably find some solutions that are sufficiently close the global optimum. X Fp2 Fg3 Fg2 Fg1 Fp3 Fp1 Y https://www.youtube.com/watch?v=j028fsZZZI4

  24. Evolutionary Computation • Time complexity is not generally considered • Number of iterations required for convergence

  25. Questions?

More Related