Title :
Improvement of the neighborhood based Levenberg-Marquardt algorithm by local adaptation of the learning coefficient
Author :
Toledo, A. ; Pinzolas, M. ; Ibarrola, J.J. ; Lera, G.
Author_Institution :
Dept. Tecnologia Electron., Univ. Politecnica de Cartagena, Spain
fDate :
7/1/2005 12:00:00 AM
Abstract :
In this letter, an improvement of the recently developed neighborhood-based Levenberg-Marquardt (NBLM) algorithm is proposed and tested for neural network (NN) training. The algorithm is modified by allowing local adaptation of a different learning coefficient for each neighborhood. This simple add-in to the NBLM training method significantly increases the efficiency of the training episodes carried out with small neighborhood sizes, thus, allowing important savings in memory occupation and computational time while obtaining better performance than the original Levenberg-Marquardt (LM) and NBLM methods.
Keywords :
learning (artificial intelligence); neural nets; computational time; learning coefficient; local adaptation; memory occupation; neighborhood based Levenberg-Marquardt algorithm; neural network training; Approximation algorithms; Calculus; Jacobian matrices; Learning systems; Neural networks; Optimization methods; System testing; Learning algorithms; neural networks (NNs); Algorithms; Computer Simulation; Models, Statistical; Neural Networks (Computer);
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2005.849849