Learning and identifying finite state automata with recurrent high-order neural networks

Abstract

This paper presents neural network models for learning and identifying deterministic finite state automata (FSA). The proposed models are a class of high-order recurrent neural networks. The models are capable of representing FSA with the network size being smaller than the existing models proposed so far. We also propose an identification method of FSA from a given set of input and output data by training the proposed models of neural networks.