Advertisement

Interactive Evolving Recurrent Neural Networks Are Super-Turing Universal

  • Jérémie Cabessa
  • Alessandro E. P. Villa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8681)

Abstract

Understanding the dynamical and computational capabilities of neural models represents an issue of central importance. In this context, recent results show that interactive evolving recurrent neural networks are super-Turing, irrespective of whether their synaptic weights are rational or real. We extend these results by showing that interactive evolving recurrent neural networks are not only super-Turing, but also capable of simulating any other possible interactive deterministic system. In this sense, interactive evolving recurrent neural networks represents a super-Turing universal model of computation, irrespective of whether their synaptic weights are rational or real.

Keywords

evolving recurrent neural networks neural computation interactive computation analog computation Turing machines with advice super-Turing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cabessa, J.: Interactive evolving recurrent neural networks are super-Turing. In: ICAART 2012, pp. 328–333. SciTePress (2012)Google Scholar
  2. 2.
    Cabessa, J., Siegelmann, H.T.: Evolving recurrent neural networks are super-turing. In: IJCNN 2011, pp. 3200–3206. IEEE (2011)Google Scholar
  3. 3.
    Cabessa, J., Siegelmann, H.T.: The computational power of interactive recurrent neural networks. Neural Computation 24(4), 996–1019 (2012)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Cabessa, J., Villa, A.E.P.: The expressive power of analog recurrent neural networks on infinite input streams. Theor. Comput. Sci. 436, 23–34 (2012)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    Cabessa, J., Villa, A.E.P.: The super-turing computational power of interactive evolving recurrent neural networks. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 58–65. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  6. 6.
    Copeland, B.J.: Hypercomputation. Minds Mach. 12(4), 461–502 (2002)CrossRefzbMATHGoogle Scholar
  7. 7.
    Goldin, D., Wegner, P.: Principles of interactive computation. In: Goldin, D., Smolka, S.A., Wegner, P. (eds.) Interactive Computation, pp. 25–37. Springer (2006)Google Scholar
  8. 8.
    Kleene, S.C.: Representation of events in nerve nets and finite automata. In: Shannon, C., McCarthy, J. (eds.) Automata Studies, pp. 3–41. Princeton University Press (1956)Google Scholar
  9. 9.
    McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysic 5, 115–133 (1943)CrossRefzbMATHMathSciNetGoogle Scholar
  10. 10.
    Minsky, M.L.: Computation: finite and infinite machines. Prentice-Hall, Inc. (1967)Google Scholar
  11. 11.
    von Neumann, J.: The computer and the brain. Yale University Press (1958)Google Scholar
  12. 12.
    Siegelmann, H.T.: Neural networks and analog computation: beyond the Turing limit. Birkhauser Boston Inc. (1999)Google Scholar
  13. 13.
    Siegelmann, H.T., Sontag, E.D.: Analog computation via neural networks. Theor. Comput. Sci. 131(2), 331–360 (1994)CrossRefzbMATHMathSciNetGoogle Scholar
  14. 14.
    Siegelmann, H.T., Sontag, E.D.: On the computational power of neural nets. J. Comput. Syst. Sci. 50(1), 132–150 (1995)CrossRefzbMATHMathSciNetGoogle Scholar
  15. 15.
    Síma, J., Orponen, P.: General-purpose computation with neural networks: A survey of complexity theoretic results. Neural Comput. 15(12), 2727–2778 (2003)CrossRefzbMATHGoogle Scholar
  16. 16.
    Turing, A.M.: On computable numbers, with an application to the Entscheidungsproblem. Proc. London Math. Soc. 2(42), 230–265 (1936)MathSciNetGoogle Scholar
  17. 17.
    Turing, A.M.: Intelligent machinery. Technical report, National Physical Laboratory, Teddington, UK (1948)Google Scholar
  18. 18.
    van Leeuwen, J., Wiedermann, J.: Beyond the Turing limit: Evolving interactive systems. In: Pacholski, L., Ružička, P. (eds.) SOFSEM 2001. LNCS, vol. 2234, pp. 90–109. Springer, Heidelberg (2001)Google Scholar
  19. 19.
    van Leeuwen, J., Wiedermann, J.: The Turing machine paradigm in contemporary computing. In: Engquist, B., Schmid, W. (eds.) Mathematics Unlimited - 2001 and Beyond, pp. 1139–1155. Springer (2001)Google Scholar
  20. 20.
    van Leeuwen, J., Wiedermann, J.: A theory of interactive computation. In: Goldin, D., Smolka, S.A., Wegner, P. (eds.) Interactive Computation, pp. 119–142. Springer (2006)Google Scholar
  21. 21.
    Wiedermann, J., van Leeuwen, J.: How we think of computing today. In: Beckmann, A., Dimitracopoulos, C., Löwe, B. (eds.) CiE 2008. LNCS, vol. 5028, pp. 579–593. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  22. 22.
    Wegner, P.: Interactive foundations of computing. Theor. Comput. Sci. 192, 315–351 (1998)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jérémie Cabessa
    • 1
    • 2
  • Alessandro E. P. Villa
    • 2
  1. 1.Laboratory of Mathematical Economics (LEMMA)University of Paris 2 – Panthéon-AssasParisFrance
  2. 2.Neuroheuristic Research Group, Department of Information SystemsUniversity of LausanneLausanneSwitzerland

Personalised recommendations