DocumentCode
1190601
Title
Training feedforward networks with the Marquardt algorithm
Author
Hagan, Martin T. ; Menhaj, Mohammad B.
Volume
5
Issue
6
fYear
1994
fDate
11/1/1994 12:00:00 AM
Firstpage
989
Lastpage
993
Abstract
The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the other techniques when the network contains no more than a few hundred weights
Keywords
backpropagation; feedforward neural nets; function approximation; least squares approximations; Marquardt algorithm; backpropagation; feedforward network training; feedforward neural networks; function approximation; learning; nonlinear least squares; Acceleration; Approximation algorithms; Backpropagation algorithms; Convergence; Feedforward neural networks; Function approximation; Least squares approximation; Least squares methods; Neural networks; Testing;
fLanguage
English
Journal_Title
Neural Networks, IEEE Transactions on
Publisher
ieee
ISSN
1045-9227
Type
jour
DOI
10.1109/72.329697
Filename
329697
Link To Document