Skip to main content
SpringerLink
Log in

Autonomous learning by simple dynamical systems with a discrete-time formulation

  • Regular Article
  • Published:
The European Physical Journal B Aims and scope Submit manuscript

Abstract

We present a discrete-time formulation for the autonomous learning conjecture. The main feature of this formulation is the possibility to apply the autonomous learning scheme to systems in which the errors with respect to target functions are not well-defined for all times. This restriction for the evaluation of functionality is a typical feature in systems that need a finite time interval to process a unit piece of information. We illustrate its application on an artificial neural network with feed-forward architecture for classification and a phase oscillator system with synchronization properties. The main characteristics of the discrete-time formulation are shown by constructing these systems with predefined functions.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. P. Kaluza, A.S. Mikhailov, Phys. Rev. E 90, 030901 (2014)

    Article  ADS  Google Scholar 

  2. R. Rojas, Neural networks: a systematic introduction (Springer-Verlag, Berlin, New-York, 1996)

  3. P. Kaluza, E. Urdapilleta, Eur. Phys. J. B 87, 236 (2014)

    Article  ADS  Google Scholar 

  4. M. Inoue, K. Kaneko, PLoS Comput. Biol. 9, e1003001 (2013)

    Article  ADS  Google Scholar 

  5. P. Kaluza, M. Inoue, Eur. Phys. J. B 89, 156 (2016)

    Article  ADS  Google Scholar 

  6. P. Kaluza, A.S. Mikhailov. Eur. Phys. J. B 85, 129 (2012)

    Article  ADS  Google Scholar 

  7. A. Schuster, Int. J. Comput. Intell. 4, 88 (2008)

    Google Scholar 

  8. S. Bornholdt, K. Sneppen, Proc. R. Soc. Lond. B 267, 1459 (2000)

    Article  Google Scholar 

  9. P. Kaluza, M. Ipsen, M. Vingron, A.S. Mikhailov. Phys. Rev. E 75, 015101 (2007)

    Article  ADS  Google Scholar 

  10. T. Yanagita, A.S. Mikhailov, Phys. Rev. E 81, 031901 (2010)

    Article  ADS  Google Scholar 

  11. Y. Kuramoto, Chemical Oscillations, Waves and Turbulence (Springer, New York, 1984)

  12. R. Urbanczik, W. Senn, Nat. Neurosci. 12, 250 (2009)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Facultad de Ciencias Exactas y Naturales, Universidad Nacional de Cuyo, Padre Contreras 1300, 5500, Mendoza, Argentina

    Agustín M. Bilen & Pablo Kaluza

  2. Instituto de Investigaciones Físicas de Mar del Plata (IFIMAR), CONICET – Universidad Nacional de Mar del Plata, Funes 3350, 7600, Mar del Plata, Argentina

    Agustín M. Bilen

  3. Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Godoy Cruz 2290 (C1425FQB) , CABA, Argentina

    Pablo Kaluza

Authors
  1. Agustín M. Bilen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pablo Kaluza
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pablo Kaluza.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bilen, A.M., Kaluza, P. Autonomous learning by simple dynamical systems with a discrete-time formulation. Eur. Phys. J. B 90, 94 (2017). https://doi.org/10.1140/epjb/e2017-70714-7

Download citation

  • Received:

  • Revised:

  • Published:

  • DOI: https://doi.org/10.1140/epjb/e2017-70714-7

Keywords

Search

Navigation