N. M. Novikova, V. G. Lyalikova

The signals detection in random noise is a most important problem of the theory and technics of communication and radar systems. This problem is decided with statistical methods, but the neural networks are quite capable of doing it. The analysis of the articles, in which the problem of signals detection with neural network is considered, has been realized. The articles aim is comparative analysis of characteristics statistical and neural networks algorithms of signals detectors. Bayesian method has been used for modeling optimal statistical detector. Algorithms of education Hamming neural network, Kohonen neural network, RBF neural network and two-layer perceptron have been used for modeling signals neural detectors. The architecture of neural network RBF has been considered in this article. The algorithm of effective education RBF neural network has been received by authors. Quasideterministic signal in random noise has been used for computing experiment realization. The detection probability and false-alarm probability have been received in the computing experiments. The comparative analysis of the experimental results has been realized. In this article has shown, that the decided topology of the RBF neural network has provided with such characteristics of signals detection as Bayesian algorithm.