Interactive demonstrations of artificial intelligence concepts. From genetic algorithms simulating natural evolution to neural networks learning patterns, these demos explore the fundamental building blocks of machine learning.
Ant colony optimization in action — watch virtual ants lay pheromone trails to discover shortest paths through emergent swarm intelligence
CreaturesWatch virtual organisms evolve through natural selection — genetic mutations shape body structure, speed, and survival strategies over generations
Curve DrawerDraw any freehand curve on the canvas and watch a genetic algorithm discover the matching mathematical equation in real time
Decision Tree ClassifierInteractive decision tree classifier that visualizes how machine learning algorithms split data points into categories with real-time training
Equation SolverDiscover polynomial equations through genetic evolution — a population of candidate formulas competes to best fit your data points
Genetic DriftInteractive genetic drift simulation where evolving creatures navigate toward a target through mutation, crossover, and natural selection
Image EvolutionWatch a genetic algorithm recreate any image using translucent polygons — evolution progressively refines shape, color, and position
Neural Network PlaygroundTrain neural networks interactively and visualize decision boundaries in real time — experiment with layers, activation functions, and datasets
Neuroevolution (dqn)Neuroevolution demo where neural networks learn to cross a busy road — deep Q-learning trains digital frogs to dodge traffic
Neuroevolution (NEAT)NEAT neuroevolution demo where neural networks evolve through natural selection to master a Flappy Bird-style obstacle course
Particle Swarm OptimizationParticle swarm optimization demo where a collective of agents cooperates to find optimal solutions across complex fitness landscapes
PerceptronDraw digits on the canvas and watch a neural network recognize them in real time — interactive MNIST handwritten digit classification demo
Q-LearningWatch a Q-learning agent discover optimal paths through a grid world — reinforcement learning builds a value map from rewards and penalties
Travelling SalesmanSolve the Travelling Salesman Problem with genetic algorithms — watch evolution find the shortest route through dozens of cities in real time