Neural Lindenmayer Systems
Christoph Walter Senn, Carmen Mei-Ling Frischknecht-Gruber, Mathias Sebastian Weyland, Rudolf Marcel Füchslin · 2024
Our work introduces the Neural Lindenmayer system, an innovative approach to learning Lindenmayer rules from string representations in the presence of noise. It demonstrates its effectiveness in the example of the dragon curve. By integrating a selection network with multiple rule networks, our system effectively captures the variability in rule lengths. This offers a promising direction for analyzing and generating complex patterns observed in nature.