A SELF-ADAPTIVE QUANTUM RADIAL BASIS FUNCTION NETWORK FOR CLASSIFICATION APPLICATIONS

In this paper, a self-adaptive quantum radial basis function network (QRBFN) is proposed for classification applications. The QRBFN model is with three layers, while the hidden layer contains quantum function nenurons (QENs), equipped with multilevel activation functions. Each QFN is composed of the sum of sigmoid functions shifted by sonic specific quantum intervals. A self-adaptive learning algorithm consisting of the self-clustering algorithm (SCA) and the backpropagation algorithm is proposed. The proposed SCA method is a fast, one-pass approach for a dynamic estimation of the number of clusters in the given input data space. The back-propagation algorithm is used to tune the adjustable parameters. Simulation results on the three well-known bench-marking classification applications show that lite proposed model outperforms to other relative approaches, in term of higher classification accuracies.