The Open UniversitySkip to content
 

A class of asymptotically stable algorithms for learning-rate adaptation

Rüger, Stefan (1998). A class of asymptotically stable algorithms for learning-rate adaptation. Algorithmica, 22(1-2) pp. 198–210.

DOI (Digital Object Identifier) Link: http://dx.doi.org/10.1007/PL00013830
Google Scholar: Look up in Google Scholar

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.

Item Type: Journal Article
Copyright Holders: 1998 Springer-Verlag
ISSN: 1432-0541
Keywords: convex optimization; neural learning; learning-rate adaptation; line search; stability criterion
Academic Unit/Department: Knowledge Media Institute
Item ID: 11955
Depositing User: Users 8580 not found.
Date Deposited: 08 Oct 2008 13:13
Last Modified: 19 Mar 2014 15:33
URI: http://oro.open.ac.uk/id/eprint/11955
Share this page:

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk