| Literature DB >> 18267874 |
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.Year: 1994 PMID: 18267874 DOI: 10.1109/72.329697
Source DB: PubMed Journal: IEEE Trans Neural Netw ISSN: 1045-9227