Differentiable cellular automata
Discrete Mathematics
2017-09-01 v1 Cellular Automata and Lattice Gases
Abstract
We describe a class of cellular automata (CAs) that are end-to-end differentiable. DCAs interpolate the behavior of ordinary CAs through rules that act on distributions of states. The gradient of a DCA with respect to its parameters can be computed with an iterative propagation scheme that uses previously-computed gradients and values. Gradient-based optimization over DCAs could be used to find ordinary CAs with desired properties.
Keywords
Cite
@article{arxiv.1708.09546,
title = {Differentiable cellular automata},
author = {Carlos Martin},
journal= {arXiv preprint arXiv:1708.09546},
year = {2017}
}