liveBook · Manning

Genetic diversity

As explained in Optimization Algorithms: AI techniques for design, planning, and control problems

The degree of variation among individuals in an evolutionary algorithm population.

Genetic diversity is the variation among individuals in a genetic algorithm population. Preserving it keeps exploration active and reduces premature convergence on suboptimal solutions. section 7.3.3

Selection choices directly affect diversity:

  • High selective pressure decreases diversity quickly, while lower pressure better preserves exploration. section 7.3.3
  • Elitism preserves top-performing individuals but reduces succeeding-generation diversity as more individuals are retained. section 7.3.3
  • Fitness-proportionate selection favors fitter individuals through probabilities proportional to fitness; rank-based selection, stochastic universal sampling, and tournament selection provide alternatives. section 7.3.3

Ticket pricing population

For candidate solutions x1–x5, x4 is best and x3 is second-best, so elitist selection chooses them as parents. Fitness-proportionate probabilities range from 0.03 for x1 to 0.39 for x4, concentrating selection on fitter candidates. section 7.3.3

How Optimization Algorithms: AI techniques for design, planning, and control problems covers it

How deep it goes
Explains how selection pressure and elitism reduce diversity, then illustrates effects through ranked candidates and selection probabilities.
Examples
Uses a ticket pricing population, binary-coded candidates, objective values, rankings, and roulette-wheel selection probabilities.
What it assumes
Assumes familiarity with genetic algorithm populations, individuals, fitness, parent selection, crossover, and mutation.
What you can do after
Evaluate selection operators by their pressure on diversity and choose alternatives that retain exploration.
How it connects
Connects genetic diversity with selective pressure, exploration, premature convergence, elitism, fitness-proportionate selection, and rank-based selection.
Cover of Optimization Algorithms: AI techniques for design, planning, and control problems
liveBookmanning.com
Read Optimization Algorithms: AI techniques for design, planning, and control problems on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Optimization Algorithms: AI techniques for design, planning, and control problems. The section links point to the parts of the book it draws on.