The application of the second most popular artificial neural networks (ANN), namely the radial basis function networks, has been developed for obtaining sufficient quantitative structureretention relationships (QSRR) with improved accuracy. The present study examined a dataset of 25 substances as solutes to two different stationary phases (silica and alumina). The solutes were analyzed to their structural descriptors and related to their retention behavior, as expressed by their capacity factors, using radial basis function (RBF) and generalized regression neural networks (GRNN) as function approximation systems.The proposed methods led to substantial gain in both the prediction ability and the computation speed of the resulting models 2239 compared to regression models. Furthermore, the results were compared with that produced from classical linear and nonlinear multivariate regression such as principal components regression (PCR) and nonlinear (polynomial) partial least squares regression (PLS). Some of the proposed ANN models diminished the number of outliers, during their implementation to unseen data (solutes), to zero.