As a result, when having any model learn to produce textures or patterns, we want it to learn a generative process for the pattern. First, reaching and maintaining a static state in an NCA appears to be non-trivial in comparison to a dynamic one, so much so that in Growing CA a pool of NCA states at various iteration times had to be maintained and sampled as starting states to simulate loss being applied after a time period longer than the NCAs iteration period, to achieve a static stability. In the same way that cells form eye patterns on the wings of butterflies to excite neurons in the brains of predators, our NCA’s population of cells has learned to collaborate to produce a pattern that excites certain neurons in an external neural network.