Symbolic Computation Using Cellular Automata-Based Hyperdimensional Computing

This letter introduces a novel framework of reservoir computing that is capable of both connectionist machine intelligence and symbolic computation. A 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 reservoir. The proposed framework is shown to be capable of long-term memory, and it requires orders of magnitude less computation compared to echo state networks. As the focus of the letter, we suggest that binary reservoir feature vectors can be combined using Boolean operations as in hyperdimensional computing, paving a direct way for concept building and symbolic processing. To demonstrate the capability of the proposed system, we make analogies directly on image data by asking, What is the automobile of air?

Inference of Automata by dialectic learning

SUMMARYAn algorithm for the inference of the external behaviour model of an automaton is given. It uses a sequential learning procedure based on induction-contradiction-correction concepts. The induction is a generalization of relationships between automaton state properties, and the correction consists in a more and more accurate discrimination of the automaton state properties. These properties are defined from the input/output contradictory sequences which are discovered after the observed contradictions between successive predictions and observations.