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

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

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.

Y. Kuroe

[1] Noga Alon,et al. Efficient simulation of finite automata by neural nets , 1991, JACM.

[2] C. Lee Giles,et al. Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[3] Marios M. Polycarpou,et al. High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[4] Marvin Minsky,et al. Computation : finite and infinite machines , 2016 .

[5] Yasuaki Kuroe,et al. Neural network representation and identification of finite state automata , 2003, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).

[6] Padhraic Smyth,et al. Learning Finite State Machines With Self-Clustering Recurrent Networks , 1993, Neural Computation.

[7] C. Lee Giles,et al. Constructive learning of recurrent neural networks: limitations of recurrent cascade correlation and a simple solution , 1995, IEEE Trans. Neural Networks.

[8] Yasuaki Kuroe,et al. Identification of nonlinear dynamical systems by recurrent high-order neural networks , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[9] P. Peretto,et al. Long term memory storage capacity of multiconnected neural networks , 2004, Biological Cybernetics.