Neighborhood based Levenberg-Marquardt algorithm for neural network training
Top Cited Papers
- 7 November 2002
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 13 (5) , 1200-1203
- https://doi.org/10.1109/tnn.2002.1031951
Abstract
Although the Levenberg-Marquardt (LM) algorithm has been extensively applied 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 paper, the behavior of a recently proposed variation of this algorithm is studied. This new method is based on the application of the concept of neural neighborhoods to the LM algorithm. It is shown that, by performing an LM step on a single neighborhood at each training iteration, not only significant savings in memory occupation and computing effort are obtained, but also, the overall performance of the LM method can be increased.Keywords
This publication has 5 references indexed in Scilit:
- A quasi-local Levenberg-Marquardt algorithm for neural network trainingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Accelerating the convergence of the back-propagation methodBiological Cybernetics, 1988
- LINPACK Users' GuidePublished by Society for Industrial & Applied Mathematics (SIAM) ,1979
- 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