liveBook · Manning

Population size

As explained in Evolutionary Deep Learning: Genetic algorithms and neural networks

Population size is the number of individuals simulated in each generation of an evolutionary algorithm.

Population size is the number of individuals simulated in each generation of an evolutionary algorithm. It controls how many candidate solutions participate in selection, reproduction, mutation, and evaluation at every iteration. section 2.5.9 section 2.6

Larger or more complex chromosomes generally require larger populations to make evolution effective. Population size is balanced against the number of generations: a larger population may be paired with fewer generations, while a smaller population may require more iterations. section 2.5.9

Inspect population size experimentally by changing it alongside related evolutionary settings:

  • Increase or decrease the population and rerun the evolutionary example to observe its effect on solution quality and evolutionary progress. section 3.2.1
  • Change population size in a NEAT experiment and compare how evolution behaves with different values. section 10.1.1
  • Test very small populations while varying speciation settings to examine their effect on the number of species. section 10.5.2

How Evolutionary Deep Learning: Genetic algorithms and neural networks covers it

How deep it goes
Defines the parameter, relates it to chromosome complexity and generations, and stops short of prescribing a universal value.
Examples
Exercises vary population size in genetic-algorithm and NEAT notebooks, including tests of very small populations and resulting speciation.
What it assumes
Assumes familiarity with genetic-algorithm operators while defining population size alongside generations, crossover, mutation, and evaluation.
What you can do after
Practice tuning population size by rerunning evolutionary experiments and comparing effects on evolution, results, and speciation.
How it connects
Connects population size with chromosomes, generations, selection, crossover, mutation, fitness evaluation, and NEAT speciation.
Cover of Evolutionary Deep Learning: Genetic algorithms and neural networks
liveBookmanning.com
Read Evolutionary Deep Learning: Genetic algorithms and neural networks on liveBook Get the book at manning.com

Also explained in

Compare how 2 books explain population size →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Evolutionary Deep Learning: Genetic algorithms and neural networks. The section links point to the parts of the book it draws on.