Growing Neural Cellular Automata

Training an end-to-end differentiable, self-organising cellular automata model of morphogenesis, able to both grow and regenerate specific patterns.

Growing Neural Cellular Automata Distill Growing Neural Cellular Automata Differentiable Model of Morphogenesis Click or tap the image to erase the part of the pattern and see it regenerate. Double clicking places a new seed cell on the grid. Speed: Step ( step/s) Model type: Growing Persistent Regenerating Rotation [experiment 4] Growing models were trained to generate patterns, but don't know how to persist them. Some patterns explode, some decay, but some happen to be almost stable or even regenerate parts! [experiment 1] Persistent models are trained to make the pattern stay for a prolonge

saved by

• Yufei Xiao
• Pranav
• Karan MJ
• Claire Wang
• Freeman Jiang
• Shreya Mogulothu
• Aaron Pham
• surya
• Yudhister Joel Kumar
• Nathan Chen
• Jackson Mowatt Gok
• Mason Wang

related reading

• Learning Sensorimotor Capabilities in Cellular Automatadevelopmentalsystems.org
• [2506.22899] Neural Cellular Automata: From Cells to Pixelsarxiv.org
• Towards self-organized controlavariengien.github.io
• The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
• A Gentle Introduction to Graph Neural Networksdistill.pub
• Self-Assembly Gets Automated in Reverse of ‘Game of Life’ | Quanta Magazinequantamagazine.org
• Digital Ecosystems: Interactive Multi-Agent Neural Cellular Automatapub.sakana.ai
• Neural network training makes beautiful fractals | Jascha’s blogsohl-dickstein.github.io
• Lenia - Wikipediaen.wikipedia.org
• GitHub - jasonwebb/morphogenesis-resources: Resources on the topic of digital morphogenesis (creating form with code). Includes links to major articles, code repos, creative projects, books, software, and more.github.com
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Complexity Explorables | Get a life!chakazul.github.io