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).

▲

hidelooktropic a few seconds ago | parent | next [-]

Wow. That's fascinating. Thanks for that explanation. So these images come to be consequentially from initial state and weights...

▲

flir 7 hours ago | parent | prev [-]

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).

▲

esychology 7 hours ago | parent [-]

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.

▲

flir 7 hours ago | parent | next [-]

> The input to the NN is just the 3x3 neighborhood around a cell.

Well that sounds like black magic. Nice. Thanks for the reply.

▲

0xdeadbeefbabe 3 hours ago | parent | prev [-]

Is each image a NN or is it one NN for all the images?

	▲	esychology 44 minutes ago \| parent [-]
		One NN per pattern/image (instance based training).