Referenced Items are not available for this document.
Bounding ellipsoid (BE) algorithms offer an attractive alternative to traditional training algorithms for neural networks, for example, backpropagation and least squares methods. The benefits include high computational efficiency and fast convergence speed. In this paper, we propose an ellipsoid propagation algorithm to train the weights of recurrent neural networks for nonlinear systems identification. Both hidden layers and output layers can be updated. The stability of the BE algorithm is proven.
Published in:
Neural Networks, IEEE Transactions on
(Volume:20
,
Issue:
6
)
Date of Publication: June 2009
- Page(s):
- 983 - 991
- ISSN :
- 1045-9227
- INSPEC Accession Number:
- 10713262
- Digital Object Identifier :
- 10.1109/TNN.2009.2015079
- Product Type:
- Journals & Magazines
- Date of Publication :
- 15 May 2009
- Date of Current Version :
- 02 June 2009
- Issue Date :
- June 2009
- Sponsored by :
- IEEE Computational Intelligence Society
- PubMed ID :
- 19447727
About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2013 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
