Learning Using Cellular Automata Based Feature Expansion and Reservoir Computing
In this paper, we introduce a novel framework of cellular automata based computing that is capable of long short-term memory. Cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the feature vector. The proposed framework requires orders of magnitude less computation compared to Echo State Networks. We prove that cellular automaton reservoir holds a distributed representation of attribute statistics, which provides a more effective computation than local representation. It is possible to estimate the kernel for linear cellular automata via metric learning, that enables a much more efficient distance computation in support vector machines framework.
Keywords: Cellular automata, distributed representation, metric learning, kernel methods, reservoir computing