cap6938 neuroevolution and artificial embryogeny evolutionary comptation n.
Download
Skip this Video
Download Presentation
CAP6938 Neuroevolution and Artificial Embryogeny Evolutionary Comptation

Loading in 2 Seconds...

play fullscreen
1 / 18

CAP6938 Neuroevolution and Artificial Embryogeny Evolutionary Comptation - PowerPoint PPT Presentation


  • 108 Views
  • Uploaded on

CAP6938 Neuroevolution and Artificial Embryogeny Evolutionary Comptation. Dr. Kenneth Stanley January 23, 2006. Main Idea. Natural selection can work on computers Selection: Picking the best parents Variation: Mutation and Mating Start with some really bad individuals

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'CAP6938 Neuroevolution and Artificial Embryogeny Evolutionary Comptation' - ailani


Download Now 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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
cap6938 neuroevolution and artificial embryogeny evolutionary comptation

CAP6938Neuroevolution and Artificial EmbryogenyEvolutionary Comptation

Dr. Kenneth Stanley

January 23, 2006

main idea
Main Idea
  • Natural selection can work on computers
    • Selection: Picking the best parents
    • Variation: Mutation and Mating
  • Start with some really bad individuals
  • Some are always better than others
  • Survival of the fittest leads to improvement
  • Progress occurs over generations
survival of the roundest
Survival of the Roundest

Gen 1

Select as parents

Gen 2

Select as parents

Gen 3

Champ!

several versions of ec
Several Versions of EC
  • Genetic Algorithms (Holland 1960s)
  • Evolution Strategies (Rechenberg 1965)
  • Evolution Programming (Fogel 1966)
  • Genetic Programming? (Smith 1980,Koza 1982)
  • The process is more important than the name
major concepts
Major Concepts
  • Genotype and Phenotype
  • Representation / mapping
  • Evaluation and fitness
  • Generations
  • Steady state
  • Selection
  • Mutation
  • Mating/Crossover/Recombination
  • Premature Convergence
  • Speciation
genotype and phenotype
Genotype and Phenotype
  • Genotype means the code (e.g. DNA) used to the describe an organism, i.e. the “blueprint”
  • Phenotype is the organism’s actual realization

10010110110

representation and mapping
Representation and Mapping
  • The genotype is a representation of the phenotype; how to represent information is a profound and deep issue
  • The process of creating the phenotype from the genotype is called the genotype to phenotype mapping
  • Mapping can happen in many ways
evaluation and fitness
Evaluation and Fitness
  • The phenotype is evaluated, not the genotype
  • The performance of the phenotype during evaluation is its fitness
  • Fitness tells us which genotypes are better than others
generations
Generations
  • Most GAs proceed generationally:
    • A whole population is evaluated one at a time
    • That is the current generation
    • They then are replaced en masse by their offspring
    • The replacements form the next generation
    • And so on…
steady state evolution
Steady State Evolution
  • Not all EC is generational
  • It is possible to replace only one individual at a time, i.e. steady state evolution
  • Common in Evolution Strategies (ES)
  • Also called real-time or online evolution
  • Another twist: Phenotypes can be evaluated simultaneously and asynchronously
selection
Selection
  • Selection means deciding who should be a parent and who should not
  • Selection is usually based on fitness
  • Methods of selection (see Mitchell p.166)
    • Roulette Wheel (probability based on fitness)
    • Truncation (random among top n%)
    • Rank selection (use rank instead of fitness)
    • Elitism (champs get to have clones)
mutation
Mutation
  • Mutation means changing the genotype randomly
  • Can vary from strong (every gene mutates) to weak (only one gene mutates)
  • May mean adding a new gene entirely
  • Mutation prevents fixation
  • Mutation is a source of diversity and discovery
mating
Mating
  • Combining one or more genomes
  • Many ways to implement crossover:
    • Singlepoint
    • Multipoint (Uniform)
    • Multipoint average (Linear)
  • How important is crossover?
  • What is it for?
premature convergence
Premature Convergence
  • When a single genotype dominates the population, it is converged
  • Convergence is premature if a suitable solution has not yet been found
  • Premature convergence is a significant concern in EC
  • Hence the need to maintain diversity
speciation
Speciation
  • A population can be divided into species
  • Can prevents incompatibles from mating
  • Can protects innovative concepts in niches
  • Maintains diversity
  • Many methods
    • Islands
    • Fitness sharing
    • Crowding
natural evolution is not just optimization
Natural Evolution is not Just Optimization
  • What is the optimum?
  • What is the space being searched?
  • What are the dimensions?
  • Herb Simon (1958): “Satisficing”
  • Is evolution even just a satisficer?
  • Evolution satisfices and complexifies
next class theoretical issues in ec
Next Class: Theoretical Issues in EC
  • The Schema Theorem
  • No Free Lunch

Homework:

Mitchell pp. 117-38, and ch.5 (pp. 170-177)

No Free Lunch Theorems for Optimization

by Wolpert and Macready (1996)

ad