On the Levenberg-Marquardt training method for feed-forward neural networks
Author:
- 1 August 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (21579555) , 456-460
Abstract
The Levenberg-Marquardt (LM) training method is the most effective method for feed-forward neural networks with respect to the training precision. This method is well-known and popularly described in the neural networks literature. Nevertheless its implementation contains some difficulties because of the specific shape of the cost function and the large amount of variables. Here we give in sufficient details an example of a program implementation of the LM training method. This implementation (as a Matlab application) seems to work well with various examples.Keywords
This publication has 7 references indexed in Scilit:
- Numerical Optimization1999
- Iterative Methods for Optimization1999
- Forecasting exchange rates using feedforward and recurrent neural networksJournal of Applied Econometrics, 1995
- Neural Networks and Related Methods for ClassificationJournal of the Royal Statistical Society Series B: Statistical Methodology, 1994
- Theory of the backpropagation neural network1989
- An Algorithm for Least-Squares Estimation of Nonlinear ParametersJournal of the Society for Industrial and Applied Mathematics, 1963
- A method for the solution of certain non-linear problems in least squaresQuarterly of Applied Mathematics, 1944