QuickRBF is an Efficient Construction of Radial Basis Function Networks with the Cholesky Decomposition
The QuickRBF package is a simple, easy-to-use, and efficient software package for Radial Basis Function Networks (RBFN). Also, the QuickRBF package use an efficient least mean square error method for constructing RBFN classifier based on the Cholesky decomposition.
The QuickRBF package performs in comparison with the state-of-art support vector machine (SVM) package, LIBSVM [Chang and Lin, 2001], in data classification and bioinformatics applications. The general observation is that the QuickRBF classifier is capable of delivering the same level of prediction accuracy as the SVM, while enjoying execution efficiency during the phase to construct the classifier.