Code-First
Every concept has runnable Python. No hand-waving - you'll implement EC algorithms from scratch.
Just Enough Math
Clear explanations with KaTeX-rendered equations. Enough rigor to understand why things work.
Real-World Examples
From robot locomotion to portfolio optimization - see how evolutionary methods solve actual problems.
27 Modules, Zero to Mastery
A structured path through genetic algorithms, evolution strategies, swarm intelligence, neuroevolution, and beyond.
Introduction to EC
What is evolutionary computation, CI landscape, setup your lab
Optimization Foundations
Random search, hill climbing, fitness landscapes, No Free Lunch
Representation & Operators
Binary, real, permutation encodings; mutation, crossover, selection
GA Fundamentals
Holland's GA, binary encoding, crossover, schema theorem
GA Advanced
Real-coded GAs, SBX, adaptive operators, island models
The (1+1)-ES
Rechenberg's 1/5th rule, Gaussian mutation, step-size adaptation
Population-Based ES
(ยต,ฮป)-ES, (ยต+ฮป)-ES, self-adaptation
CMA-ES
Covariance matrix adaptation, rank-one/rank-mu updates
CMA-ES Advanced & NES
Restarts, large-scale variants, natural gradients, xNES
Genetic Programming
Tree-based GP, symbolic regression, bloat control
Differential Evolution
DE/rand/1, adaptive DE, SHADE, when DE beats CMA-ES
EDAs
PBIL, UMDA, BOA, CMA-ES as an EDA
Coevolution & Memetic
Competitive/cooperative coevolution, EA + local search
Particle Swarm (PSO)
Velocity update, topologies, inertia weight
Ant Colony (ACO)
Pheromone trails, TSP, routing problems
Other Swarm Methods
ABC, firefly, the metaphor problem in EC
Multi-Objective EA
Pareto fronts, NSGA-II, SPEA2, hypervolume
Many-Objective & MOEA/D
NSGA-III, decomposition, indicator-based methods
Quality-Diversity
MAP-Elites, novelty search, illumination algorithms
Neuroevolution
NEAT, HyperNEAT, evolving network topology
EC for NN Training
Weight evolution, NAS, hybrid gradient+evolution
ES for RL
OpenAI ES, shared noise tables, policy optimization
Constrained & Combinatorial
Penalty methods, scheduling, mixed-integer
Surrogate-Assisted
Expensive optimization, GP surrogates, Bayesian connection
LCS & Hyper-heuristics
Evolving rules, evolving heuristics, algorithm configuration
Benchmarking
BBOB/COCO, ECDF plots, statistical testing
Theory & Capstone
Runtime analysis, natural gradients, capstone project
Ready to evolve?
All you need is Python 3.13+ and a tolerance for watching fitness curves that take 500 generations to do anything interesting.
Get Started