Learning Cellular Automaton Dynamics with Neural Networks

Part of Advances in Neural Information Processing Systems 5 (NIPS 1992)

Bibtex Metadata Paper


N. Wulff, J A. Hertz


We have trained networks of E - II units with short-range connec(cid:173) tions to simulate simple cellular automata that exhibit complex or chaotic behaviour. Three levels of learning are possible (in decreas(cid:173) ing order of difficulty): learning the underlying automaton rule, learning asymptotic dynamical behaviour, and learning to extrap(cid:173) olate the training history. The levels of learning achieved with and without weight sharing for different automata provide new insight into their dynamics.