Skip to main content
SpringerLink
Log in

Adaptive online learning for nonstationary problems

  • Part III: Learning: Theory and Algorithms
  • Conference paper
  • First Online:
Book cover Artificial Neural Networks — ICANN'97 (ICANN 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1327))

Included in the following conference series:

Abstract

An adaptation algorithm for online training is examined. For stationary tasks it can reduce the learning rate to reach the best convergence. Instead of simple annealing, it keeps the learning rate flexible, such that it can also adapt to nonstationary tasks. Different tasks, abrupt or gradual changes, and different guidance measures are discussed.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Amari S. (1997), in NIPS 9, MIT Press, in press.

    Google Scholar 

  2. Opper M. (1996), Phys. Rev. Lett. 77, p. 4671–4674.

    Google Scholar 

  3. Sompolinsky H., Barkai N. & Seung H.S. (1995), in Neural Networks: The Statistical Mechanics Perspective, World Scientific, p. 105–130.

    Google Scholar 

  4. Bös S. (1995), in ICANN'95, p. 111-116, and to be submitted.

    Google Scholar 

  5. Bös S. (1996), in ICANN'96, Springer LNCS 1112, p. 89–94.

    Google Scholar 

  6. Bös S., Murata N., Amari S., & Müller K.-R. (1997), submitted.

    Google Scholar 

  7. Murata N., Bös S., Amari S., & Müller K.-R. (1997), in preparation.

    Google Scholar 

  8. Murata N., Müller K.-R., Ziehe A., & Amari S. (1997), in NIPS 9, MIT Press, in press.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Information Representation Lab, FRP, RIKEN, 351-01, Wako-shi, Saitama, Japan

    Siegfried Bös

Authors
  1. Siegfried Bös
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Wulfram Gerstner Alain Germond Martin Hasler Jean-Daniel Nicoud

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Bös, S. (1997). Adaptive online learning for nonstationary problems. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020172

Download citation

  • DOI: https://doi.org/10.1007/BFb0020172

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63631-1

  • Online ISBN: 978-3-540-69620-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation