Flappy Bird Neuroevolution
Trains neural networks to play Flappy Bird using NEAT, evolving topology and weights from minimal structure. Includes a browser-based replay viewer for stepping through generations.
Selected Work & Case Studies
03 Projects
Trains neural networks to play Flappy Bird using NEAT, evolving topology and weights from minimal structure. Includes a browser-based replay viewer for stepping through generations.
Predicts F1 fantasy points using a machine learning pipeline trained on historical race data, then solves optimal team selection as an integer programme under budget and roster constraints.
A browser-based procedural music sequencer that uses Markov chains to generate melodic patterns. Features a visual step-sequencer interface with real-time waveform visualisation and MIDI export capabilities.