Skip to main content
SpringerLink
Log in

The Power of Extra Analog Neuron

  • Conference paper
Theory and Practice of Natural Computing (TPNC 2014)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 8890))

Included in the following conference series:

Abstract

In the effort to refine the analysis of computational power of neural nets between integer and rational weights we study a hybrid binary-state network with an extra analog unit. We introduce a finite automaton with a register which is shown to be computationally equivalent to such a network. The main result is a sufficient condition for a language accepted by this automaton to be regular which is based on the new concept of a quasi-periodic power series. These preliminary results suggest an interesting connection with the active research field on the expansions of numbers in non-integer bases which seems to be a fruitful area for further research including many important open problems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Adamczewski, B., Frougny, C., Siegel, A., Steiner, W.: Rational numbers with purely periodic β-expansion. Bulletin of The London Mathematical Society 42(3), 538–552 (2010)

    Article  MATH  MathSciNet  Google Scholar 

  2. Allouche, J.P., Clarke, M., Sidorov, N.: Periodic unique beta-expansions: The Sharkovskiĭ ordering. Ergodic Theory and Dynamical Systems 29(4), 1055–1074 (2009)

    Article  MATH  MathSciNet  Google Scholar 

  3. Alon, N., Dewdney, A.K., Ott, T.J.: Efficient simulation of finite automata by neural nets. Journal of the ACM 38(2), 495–514 (1991)

    Article  MATH  MathSciNet  Google Scholar 

  4. Balcázar, J.L., Gavaldà, R., Siegelmann, H.T.: Computational power of neural networks: A characterization in terms of Kolmogorov complexity. IEEE Transactions on Information Theory 43(4), 1175–1183 (1997)

    Article  MATH  Google Scholar 

  5. Chunarom, D., Laohakosol, V.: Expansions of real numbers in non-integer bases. Journal of the Korean Mathematical Society 47(4), 861–877 (2010)

    Article  MATH  MathSciNet  Google Scholar 

  6. Dassow, J., Mitrana, V.: Finite automata over free groups. International Journal of Algebra and Computation 10(6), 725–738 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  7. Glendinning, P., Sidorov, N.: Unique representations of real numbers in non-integer bases. Mathematical Research Letters 8(4), 535–543 (2001)

    Article  MATH  MathSciNet  Google Scholar 

  8. Hare, K.G.: Beta-expansions of Pisot and Salem numbers. In: Proceedings of the Waterloo Workshop in Computer Algebra 2006: Latest Advances in Symbolic Algorithms, pp. 67–84. World Scientific (2007)

    Google Scholar 

  9. Horne, B.G., Hush, D.R.: Bounds on the complexity of recurrent neural network implementations of finite state machines. Neural Networks 9(2), 243–252 (1996)

    Article  Google Scholar 

  10. Ibarra, O.H., Sahni, S., Kim, C.E.: Finite automata with multiplication. Theoretical Computer Science 2(3), 271–294 (1976)

    Article  MATH  MathSciNet  Google Scholar 

  11. Indyk, P.: Optimal simulation of automata by neural nets. In: Mayr, E.W., Puech, C. (eds.) STACS 1995. LNCS, vol. 900, pp. 337–348. Springer, Heidelberg (1995)

    Chapter  Google Scholar 

  12. Kambites, M.E.: Formal languages and groups as memory. Communications in Algebra 37(1), 193–208 (2009)

    Article  MATH  MathSciNet  Google Scholar 

  13. Kilian, J., Siegelmann, H.T.: The dynamic universality of sigmoidal neural networks. Information and Computation 128(1), 48–56 (1996)

    Article  MATH  MathSciNet  Google Scholar 

  14. Koiran, P.: A family of universal recurrent networks. Theoretical Computer Science 168(2), 473–480 (1996)

    Article  MATH  MathSciNet  Google Scholar 

  15. Komornik, V., Loreti, P.: Subexpansions, superexpansions and uniqueness properties in non-integer bases. Periodica Mathematica Hungarica 44(2), 197–218 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  16. Minsky, M.: Computations: Finite and Infinite Machines. Prentice-Hall, Englewood Cliffs (1967)

    Google Scholar 

  17. Mitrana, V., Stiebe, R.: Extended finite automata over groups. Discrete Applied Mathematics 108(3), 287–300 (2001)

    Article  MATH  MathSciNet  Google Scholar 

  18. Orponen, P.: Computing with truly asynchronous threshold logic networks. Theoretical Computer Science 174(1-2), 123–136 (1997)

    Article  MATH  MathSciNet  Google Scholar 

  19. Parry, W.: On the β-expansions of real numbers. Acta Mathematica Hungarica 11(3), 401–416 (1960)

    Article  MATH  MathSciNet  Google Scholar 

  20. Rényi, A.: Representations for real numbers and their ergodic properties. Acta Mathematica Academiae Scientiarum Hungaricae 8(3-4), 477–493 (1957)

    Article  MATH  MathSciNet  Google Scholar 

  21. Salehi, Ö., Yakaryılmaz, A., Say, A.C.C.: Real-time vector automata. In: Gąsieniec, L., Wolter, F. (eds.) FCT 2013. LNCS, vol. 8070, pp. 293–304. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  22. Schmidt, K.: On periodic expansions of Pisot numbers and Salem numbers. Bulletin of the London Mathematical Society 12(4), 269–278 (1980)

    Article  MATH  MathSciNet  Google Scholar 

  23. Sidorov, N.: Expansions in non-integer bases: Lower, middle and top orders. Journal of Number Theory 129(4), 741–754 (2009)

    Article  MATH  MathSciNet  Google Scholar 

  24. Siegelmann, H.T.: Recurrent neural networks and finite automata. Journal of Computational Intelligence 12(4), 567–574 (1996)

    Article  Google Scholar 

  25. Siegelmann, H.T.: Neural Networks and Analog Computation: Beyond the Turing Limit. Birkhäuser, Boston (1999)

    Google Scholar 

  26. Siegelmann, H.T., Sontag, E.D.: Analog computation via neural networks. Theoretical Computer Science 131(2), 331–360 (1994)

    Article  MATH  MathSciNet  Google Scholar 

  27. Siegelmann, H.T., Sontag, E.D.: On the computational power of neural nets. Journal of Computer System Science 50(1), 132–150 (1995)

    Article  MATH  MathSciNet  Google Scholar 

  28. Šíma, J.: Analog stable simulation of discrete neural networks. Neural Network World 7(6), 679–686 (1997)

    Google Scholar 

  29. Šíma, J.: Energy complexity of recurrent neural networks. Neural Computation 26(5), 953–973 (2014)

    Article  MathSciNet  Google Scholar 

  30. Šíma, J., Orponen, P.: General-purpose computation with neural networks: A survey of complexity theoretic results. Neural Computation 15(12), 2727–2778 (2003)

    Article  MATH  Google Scholar 

  31. Šíma, J., Wiedermann, J.: Theory of neuromata. Journal of the ACM 45(1), 155–178 (1998)

    Article  MATH  MathSciNet  Google Scholar 

  32. Šorel, M., Šíma, J.: Robust RBF finite automata. Neurocomputing 62, 93–110 (2004)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Computer Science, Academy of Sciences of the Czech Republic, P.O. Box 5, 18207, Prague 8, Czech Republic

    Jiří Šíma

Authors
  1. Jiří Šíma
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Research Group on Mathematical Linguistics (GRLMC), Rovira i Virgili University, Avinguda Catalunya, 35, 43002, Tarragona, Spain

    Adrian-Horia Dediu  & Carlos Martín-Vide  & 

  2. E.T.S. de Ingenierías Informática y de Telecomunicación, DECSAI, University of Granada, C/Periodista Daniel Saucedo Aranda s/n, 18071, Granada, Spain

    Manuel Lozano

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Šíma, J. (2014). The Power of Extra Analog Neuron. In: Dediu, AH., Lozano, M., Martín-Vide, C. (eds) Theory and Practice of Natural Computing. TPNC 2014. Lecture Notes in Computer Science, vol 8890. Springer, Cham. https://doi.org/10.1007/978-3-319-13749-0_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-13749-0_21

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-13748-3

  • Online ISBN: 978-3-319-13749-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation