Overview

Genetic algorithms are used to find approximate solutions to difficult optimization problems by 'evolving' a population of candidate solutions over many generations.

The Process

  1. Initialization: Create a random population of 'chromosomes' (potential solutions).
  2. Fitness Evaluation: Score each solution based on how well it solves the problem.
  3. Selection: Choose the best-performing individuals to be 'parents.'
  4. Crossover (Recombination): Combine parts of two parents to create 'offspring.'
  5. Mutation: Randomly alter parts of the offspring to maintain diversity.
  6. Repeat: The new population replaces the old one, and the process continues until a satisfactory solution is found.

Applications

  • Engineering design optimization.
  • Scheduling and logistics.
  • Training neural network architectures (Neuroevolution).

Related Terms