Convergence of RBF Networks Regression Function Estimates and Classifiers

In the paper convergence of the RBF network regression estimates and classifiers with so-called regular radial kernels is investigated. The parameters of the network are trained by minimizing the empirical risk on the training data. We analyze MISE convergence by utilizing the machine learning theory techniques such as VC dimension and covering numbers and the error bounds involving them. The performance of the normalized RBF network regression estimates is also tested in simulations.