Neataptic (Neuro-evolution Playground)
A collection of articles showing how neural networks can be improved across generations. Demos include target-seeking agents, an Agar.io-style game AI, and color classification, so you can watch performance improve through selection and mutation rather than ordinary training.
How to try it
Pick 'Target-seeking AI', 'Agar.io AI', 'Classify colors', or 'Playground' from the list on the left, and the simulation runs inside the article page. Watch how the agents' movement changes as generations pass, while the text explains the network structure and the genetic algorithm settings. The articles and interface are in English only.