Verification the Related Data Base by the Layered Radial-Basis Neural Network

Abstract

The verification method of the information in the related data bases by the theory of layered radial-basis neural networks given in this article. The method consists of three levels: clustering the data by Kohonen network, learning and usage of radial-basis neuron network, marking the reliability of the rows in the table of data base. The software worked out by the invers method in the basis of radial-neuron basis. The suggested data base by the method of verification gives opportunity to work out the models of integrated informational systems, algorithms and software.