Local message passing interaction through Sobel/Laplace kernel gradient instead of Dense layer
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.
https://distill.pub/2020/growing-ca/
Self-classifying MNIST Digits
Training an end-to-end differentiable, self-organising cellular automata for classifying MNIST digits.
https://distill.pub/2020/selforg/mnist/
Self-Organising Textures
Neural Cellular Automata learn to generate textures, exhibiting surprising properties.
https://distill.pub/selforg/2021/textures/
Thread: Differentiable Self-organizing Systems
Thread: Differentiable Self-organizing Systems
A collection of articles and comments with the goal of understanding how to design robust and general purpose self-organizing systems.
https://distill.pub/2020/selforg/

Seonglae Cho