Variable projections neural network training

V. Pereyra, G. Scherer and F. Wong

Mathematics and Computers in Simulation (MATCOM), 2006, vol. 73, issue 1, 231-243

Abstract: The training of some types of neural networks leads to separable non-linear least squares problems. These problems may be ill-conditioned and require special techniques. A robust algorithm based on the Variable Projections method of Golub and Pereyra is designed for a class of feed-forward neural networks and tested on benchmark examples and real data.

Keywords: Neural networks; Variable projection algorithm (search for similar items in EconPapers)
Date: 2006
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378475406001753
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:matcom:v:73:y:2006:i:1:p:231-243

DOI: 10.1016/j.matcom.2006.06.017

Access Statistics for this article

Mathematics and Computers in Simulation (MATCOM) is currently edited by Robert Beauwens

More articles in Mathematics and Computers in Simulation (MATCOM) from Elsevier
Bibliographic data for series maintained by Catherine Liu ().