NONPARAMETRIC ALGORITHMS OF PATTERN RECOGNITION AND MODELS OF STOCHASTIC DEPENDENCE IN SMALL SAMPLES CONDITIONS
Considered is the technique for constructing linear and nonlinear nonparametric collectives of decision functions in pattern recognition and restoration of stochastic dependences problems. The proposed systems provide efficient processing of information of high dimensionality. The results of computational experiments are presented.
Keywords: nonparametric statistics, pattern recognition, nonparametric models, probability density, small samples
