Representation and Identification of Finite State Automata by Recurrent Neural Networks

  • Yasuaki Kuroe
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)


This paper presents a new architecture of neural networks for representing deterministic finite state automata. The proposed model is capable of strictly representing FSA with the network size being smaller than the existing models proposed so far. We also discuss an identification method of FSA from a given set of input and output data by training the proposed neural networks. We apply the genetic algorithm to determine the parameters of the neural network such that its input and output relation becomes equal to those of a target FSA.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Minsky, M.L.: Computation:Finite and Infinite Machines. Prentice-Hall, New York (1967)zbMATHGoogle Scholar
  2. 2.
    Alon, N., Dewdney, A.K., Ott, T.J.: Efficient Simulation of Automata by Neural Nets. Journal of Association for Computing Machinery 38(2), 495–514 (1991)zbMATHMathSciNetGoogle Scholar
  3. 3.
    Giles, C.L., Miller, C.B., Chen, D., Chen, H.H., Sun, G.Z., Lee, Y.C.: Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks. Neural Computation 4, 393–405 (1992)CrossRefGoogle Scholar
  4. 4.
    Zegn, Z., Goodman, R.M., Smyth, P.: Learning Finite State Machines with Self- Clustering Recurrent Networks. Neural Computation 5, 976–990 (1993)CrossRefGoogle Scholar
  5. 5.
    Giles, C.L., Chen, D., Sun, G., Chen, H., Lee, Y., Goudreau, W.: Constructive Learning of Recurrent Neural Networks: Limitations of Recurrent Casade Correlation and a Simple Solution. IEEE Trans. on Neural Networks 6(4), 829–836 (1995)CrossRefGoogle Scholar
  6. 6.
    Kuroe, Y., Kimura, I.: Modeling of Unsteady Heat Conduction Field by Using Composite Recurrent Neural Networks. In: Proc. of IEEE International Conference on Neural Networks, vol. 1, pp. 323–328 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yasuaki Kuroe
    • 1
  1. 1.Center for Information ScienceKyoto Institute of TechnologyKyotoJapan

Personalised recommendations