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.

Issue Section:
General Conference: Accepted oral presentations
This content is only available as a PDF.
© 2024 Massachusetts Institute of Technology Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license
2024
Massachusetts Institute of Technology
This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. For a full description of the license, please visit https://creativecommons.org/licenses/by/4.0/legalcode.
Issue Section:
General Conference: Accepted oral presentations