Pre-processing for the RBF-NNs with flexible parameters for multi-dimensional data

This paper describes a solution to the optimization task of approximation by radial-basis-function (RBF) neural network. The proposed method is created for the teacher NNs for complex system and is addressed to the problem of variable shape parameters for data using the RBF. It involves the k-means algorithm, the RBF neural network, the ideas of the algorithm for placing new centers of neurons and the structure of the future deep learning complex neural network (NN).