If you're familiar with CAs (e.g. Conway's Game of Life), you can think of a NeuralCA as a CA where the update rule is given by a neural network. Here we optimize the neural net weights so that it behaves a certain way (e.g. grow a lizard from a single seed).
Wow. That's fascinating. Thanks for that explanation. So these images come to be consequentially from initial state and weights...
What are the inputs to the NN? The whole grid, or just nearby cells? What happens if two NNs overlap on the same grid? (Gonna go read the paper).
The input to the NN is just the 3x3 neighborhood around a cell. We can overlap two NNs on the same grid (through interpolation). Checkout https://meshnca.github.io to see the effect. When the brush is in graft mode, it basically allows you to paint some regions that will follow a different NN rule.
> The input to the NN is just the 3x3 neighborhood around a cell.
Well that sounds like black magic. Nice. Thanks for the reply.
Is each image a NN or is it one NN for all the images?
One NN per pattern/image (instance based training).