“Mircea cel Batran” Naval Academy Scientific Bulletin, Volume XVI – 2013 – Issue 1 Published by “Mircea cel Batran” Naval Academy Press, Constanta, Romania TRAINING OF RBF NEURAL NETWORKS: A COMPARATIVE OVERVIEW

According to literature, it is well-known that the training algorithm of RBF neural networks depends a lot by the specific way to obtain the positioning of RBF centers over the input data space, and to fit the neural weights to the output layer, respectively. Having as starting point a real pattern recognition task belonging to video imagery to solve, this paper presents a comparative analysis of some standard and advanced approaches used to assure a high-quality training process of RBF neural networks. Key-words: connexionist models, RBF neural network, pattern recognition