Genetic Algorithms

Evolutionary and Population-Based Search

AI, Artificial and Computational Intelligence
AI, ACI, Genetic Algorithms, Ant Colony Optimisation, Neural Architecture Search, Neuroevolution

Evolutionary and Population-Based Search #

Population-based search explores with many candidate solutions at once. Genetic Algorithms evolve encoded solutions, Ant Colony Optimisation builds paths using collective pheromone signals, and neuroevolution applies evolutionary ideas to neural-network design.

  • Genetic Algorithm

  • Ant Colony Optimisation

  • Neural Architecture Search

  • Use case : Neuro Evolution - Evolutionary computation to design or train neural networks

Learning Objectives #

  • explain the purpose of population-based search
  • describe representation, fitness, selection, crossover and mutation
  • trace the core Genetic Algorithm loop and one numerical iteration
  • explain exploration and exploitation in Ant Colony Optimisation
  • interpret the main ACO transition and pheromone-update equations
  • distinguish NAS, NEAT, DeepNEAT and CoDeepNEAT

Big Picture #

flowchart TD
    P["Population-based search"] --> G["Genetic Algorithms"]
    P --> A["Ant Colony Optimisation"]
    G --> N["Neuroevolution"]
    N --> D["Deep network design"]

    style P fill:#E1F5FE
    style G fill:#C8E6C9
    style A fill:#FFF9C4
    style N fill:#EDE7F6
    style D fill:#C8E6C9

1. Why Use a Population? ☆ #

A single-state method follows one candidate through the search space. A population-based method maintains several candidates in parallel.