Skip to main content
SpringerLink
Log in

A Class of Asymptotically Stable Algorithms for Learning-Rate Adaptation

  • Published:
Algorithmica Aims and scope Submit manuscript

Abstract.

A stability criterion for learning is given. In the case of learning-rate adaptation of backpropagation, a class of asymptotically stable algorithms is presented and studied, including a convergence proof. Simulations demonstrate relevance and limitations.

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

Author information

Authors and Affiliations

  1. Department of Computing, Imperial College of Science, Technology and Medicine, 180 Queen's Gate, London SW7 2BZ, England. s.rueger@doc.ic.ac.uk, http://www-ala.doc.ic.ac.uk/~smr3., , , , , , UK

    S. M. Rüger

Authors
  1. S. M. Rüger
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Received January 29, 1997; revised June 19, 1997.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Rüger, S. A Class of Asymptotically Stable Algorithms for Learning-Rate Adaptation . Algorithmica 22, 198–210 (1998). https://doi.org/10.1007/PL00013830

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/PL00013830

Search

Navigation