34
3

Reconstructing cellular automata rules from observations at nonconsecutive times

Abstract

Recent experiments by Springer and Kenyon have shown that a deep neural network can be trained to predict the action of tt steps of Conway's Game of Life automaton given millions of examples of this action on random initial states. However, training was never completely successful for t>1t>1, and even when successful, a reconstruction of the elementary rule (t=1t=1) from t>1t>1 data is not within the scope of what the neural network can deliver. We describe an alternative network-like method, based on constraint projections, where this is possible. From a single data item this method perfectly reconstructs not just the automaton rule but also the states in the time steps it did not see. For a unique reconstruction, the size of the initial state need only be large enough that it and the t1t-1 states it evolves into contain all possible automaton input patterns. We demonstrate the method on 1D binary cellular automata that take inputs from nn adjacent cells. The unknown rules in our experiments are not restricted to simple rules derived from a few linear functions on the inputs (as in Game of Life), but include all 22n2^{2^n} possible rules on nn inputs. Our results extend to n=6n=6, for which exhaustive rule-search is not feasible. By relaxing translational symmetry in space and also time, our method is attractive as a platform for the learning of binary data, since the discreteness of the variables does not pose the same challenge it does for gradient-based methods.

View on arXiv
Comments on this paper