Advertisement

Parallelization of Algorithms with Recurrent Neural Networks

  • João Pedro Neto
  • Fernando Silva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6593)

Abstract

Neural networks can be used to describe symbolic algorithms like those specified in high-level programming languages. This article shows how to translate these network description of algorithms into a more suitable format in order to feed an arbitrary number of parallel processors to speed-up the computation of sequential and parallel algorithms.

Keywords

Neural Networks Parallelization Symbolic Computing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Carnell, A., Richardson, D.: Parallel computation in spiking neural nets. Theoretical Computer Science 386(1-2), 57–72 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Gruau, F., Ratajszczak, J., Wibe, J.: A neural compiler. Theoretical Computer Science 141, 1–52 (1995)CrossRefzbMATHGoogle Scholar
  3. 3.
    Herz, A., Goltisch, T., Machens, C., Jaeger, D.: Modelling Single-Neuron Dynamics and Computations: A Balance of Detail and Abstraction. Science 314, 80–85 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Neto, J., Siegelmann, H., Costa, J.: On the Implementation of Programming Languages with Neural Nets. In: First International Conference on Computing Anticipatory Systems, vol. 1, pp. 201–208 (1998)Google Scholar
  6. 6.
    Neto, J., Costa, J., Siegelmann, H.: Symbolic Processing in Neural Networks. Journal of Brazilian Computer Society 8(3), 58–70 (2003)CrossRefGoogle Scholar
  7. 7.
    Neto, J.: A Virtual Machine for Neural Computers. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 525–534. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Siegelmann, H., Sontag, E.: Analog Computation via Neural Networks. Theoretical Computer Science 131, 331–360 (1994)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Siegelmann, H.: Neural Networks and Analog Computation, Beyond the Turing Limit. Birkhäuser, Basel (1999)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • João Pedro Neto
    • 1
  • Fernando Silva
    • 1
  1. 1.Dept. Informatics, Faculty of SciencesUniversity of LisbonPortugal

Personalised recommendations