Training Feedforward Networks with the Marquardt Algorithm

  • Hagan M
  • Menhaj M
  • 580


    Mendeley users who have this article in their library.
  • 4.3k


    Citations of this article.


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.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text


  • Martin T. Hagan

  • Mohammad B. Menhaj

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free