Re:Growing Neural Cellular Automata: A Differentiable Model ...
by caetris1 on Tuesday February 11, 2020 @07:55PM
(#22304688)
This is because the center point of your models do not expect a foreground/background boundary. By putting a hole at the center, the boundaries seek to stabilize the system by bubbling outward. The best way to put it is that there is no stable state where a doughnut hole exists at the center. An interference pattern ripples outward and destroys the system.
Interactions will play out very differently at different speeds because you are interacting with a sped-up/slowed down version of the CA.
2. We haven’t done any rigorous studies of regenerative capability, although this is certainly on our to-do list. From empirically playing with them, models seem to be more susceptible to damage to the centre of their bodies than to limbs, likely as a result of “growing” outwards.