Robust Optimal-Size Implementation of Finite State Automata with Synfire Ring-Based Neural Networks

摘要

Synfire rings are important neural circuits capable of conveying synchronous, temporally precise and self-sustained activities in a robust manner. We describe a robust and optimal-size implementation of finite state automata with neural networks composed of synfire rings. More precisely, given any finite automaton, we build a corresponding neural network partly composed of synfire rings and capable of simulating it. The synfire ring activities encode the successive states of the automaton throughout its computation. The robustness of the network results from its architecture, which involves synfire rings and duplicated core components. We finally show that the network's size is asymptotically optimal: for an automaton with n states, the network has θ() cells.