Effects of moving the centers in an RBF network

Abstract

In Radial Basis Function Networks, placement of centers has been one of the problems addressed and is said to have a significant effect on the performance of the network. Supervised learning of center locations in some applications show that they are superior to the networks whose centers are located using unsupervised methods. But such networks can take the same training time as that of sigmoid networks. Supervised learning of centers seem to offset the advantages achieved by the two stage learning of the RBF networks. One way to overcome this may be to train the network with a set of centers selected by unsupervised methods and then to fine tune the centers. This can be done by first evalu..