A new hybrid fuzzy ARTMAP and radial basis function neural network with online pruning strategy

Abstract

In this paper, a new online learning algorithm is proposed to learn a data sample in hybrid mode. This new algorithm is developed and referred as Growing and Pruning - Fuzzy ARTMAP-radial basis function (GAP-FAM-RBF) neural network. In this algorithm, fuzzy ARTMAP (FAM) network learns from training samples and radial basis function (RBF) network provides viable solutions. The GAP-FAM-RBF that proposed is able to learn online from the first data samples. The insignificant hidden neurons will be pruned. The performance of this algorithm is evaluated on regression applications. © 2016 IEEE.