Statistical Properties of Cellular Automata in the Context of Learning and Recognition: Part 1, Introduction.

摘要

In this lecture, the map from a cellular automaton to a sequence of analytical approximations called the local structure theory is described. Connections are drawn between cellular automata and neural network models. It is suggested that the process by which a cellular automaton holds particular probability measures invariant is an appropriate model for biological memory. 20 figs. (ERA citation 14:016867)