A quasi-local Levenberg-Marquardt algorithm for neural network training
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (10987576) , 2242-2246
- https://doi.org/10.1109/ijcnn.1998.687209
Abstract
Although the Levenberg-Marquardt algorithm has been extensively used as a neural network training method, it suffers from being very expensive, both in memory and number of operations required, when the network to be trained has a significant number of adaptive weights. In this work we propose a modification of this method that considers the concept of neural neighbourhoods. It is shown that, by performing a Levenberg-Marquardt step to a single neighbourhood at each iteration, significant savings in computing effort and memory occupation are obtained, without efficiency loss.Keywords
This publication has 4 references indexed in Scilit:
- Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weightsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Accelerating the convergence of the back-propagation methodBiological Cybernetics, 1988
- 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