Verifying Properties of Neural Networks

  • Pedro Rodrigues
  • J. Félix Costa
  • Hava T. Siegelmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2084)

Abstract

In the beginning of nineties, Hava Siegelmann proposed a new computational model, the Artificial Recurrent Neural Network (ARNN), and proved that it could perform hypercomputation. She also established the equivalence between the ARNN and other analog systems that support hypercomputation, launching the foundations of an alternative computational theory. In this paper we contribute to this alternative theory by exploring the use of formal methods in the verification of temporal properties of ARNNs. Based on the work of Bradfield in verification of temporal properties of infinite systems, we simplify his tableau system, keeping its expressive power, and show that it is suitable to the verification of temporal properties of ARNNs.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bradfield, J.: Verifying Temporal Properties of Systems with Applications to Petri Nets, PhD thesis, University of Edinburgh (1991)Google Scholar
  2. 2.
    Bradfield, J.: Proving Temporal Properties of Petri Nets. In Rozenberg, G. (eds.): Advances in Petri Nets 1991. Lecture Notes in Computer Science, Vol. 524. Springer-Verlag, Berlin (1991) 29–47CrossRefGoogle Scholar
  3. 3.
    Bradfield, J., Stirling, C.:,Local Model Checking for Infinite State Spaces. Theoretical Computer Science, Vol. 96. (1992) 157–174MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Emerson, E. A., Lei, C.-L.: Efficient Model Checking in Fragments of the Propositional Mucalculus. Proceedings of the 1st IEEE Symposium on Logic in Computer Science, (1986) 267–278Google Scholar
  5. 5.
    Gilles, C., Miller, C., Chen, D., Chen, H., Sun, G., Lee, Y.: Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks. Neural Computation, Vol. 4 3 (1992) 393–405CrossRefGoogle Scholar
  6. 6.
    Gruau, F., Ratajszczak, J., Wiber, G.: A neural compiler. Theoretical Computer Science, Vol. 141(1-2) (1995) 1–52MATHCrossRefGoogle Scholar
  7. 7.
    Neto, J. P., Siegelmann, H. T., Costa, J. F.: On the Implementation of Programming Languages with Neural Nets. In First International Conference on Computing Anticipatory Systems (CASYS’97). CHAOS, 1 (1998) 201–208Google Scholar
  8. 8.
    Neto, J. P., Siegelmann, H. T., Costa, J. F.: Building Neural Net Software. submitted, (1999)Google Scholar
  9. 9.
    Pollack, J.: On Connectionism Models of Natural Language Processing. PhD thesis. University of Illinois, Urbana (1987)Google Scholar
  10. 10.
    Siegelmann, H. T.: On NIL: the Software Constructor of Neural Networks. Parallel Processing Letters. Vol. 6 4, World Scientific Publishing Company (1996) 575–582CrossRefGoogle Scholar
  11. 11.
    Siegelmann, H. T.: Neural Networks and Analog Computation: beyond the Turing limit. Birkhäuser, Boston (1999)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Pedro Rodrigues
    • 1
  • J. Félix Costa
    • 2
  • Hava T. Siegelmann
    • 3
  1. 1.Departamento de InformáticaFaculdade de Cix00EA;ncias da Universidade de LisboaLisboaPortugal
  2. 2.Departamento de MatemáticaInstituto Superior Técnico, Lisbon University of TechnologyLisboaPortugal
  3. 3.Faculty of Industrial Engineering and ManagementTechnion CityHaifaIsrael

Personalised recommendations