Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

Regularization theory presents a sound framework to solving supervised learning problems. However, there is a gap between the theoretical results and practical suitability of regularization networks (RN). Radial basis function networks (RBF) that can be seen as a special case of regularization networks have a rich selection of learning algorithms. In this work we study a relationship between RN and RBF, and show that theoretical estimates for RN hold for a concrete RBF applied to real-world data, to a certain degree. This can provide several recommendations for strategies on choosing number of units in RBF network.