On Logical Correction of Neural Network Algorithms for Pattern Recognition

The paper is devoted to the description of hybrid pattern recognition method developed by research groups from Russia, Armenia and Spain. The method is based upon logical correction over the set of conventional neural networks. Output matrices of neural networks are processed according to the potentiality principle which allows increasing of recognition reliability.

Suboptimal Multistage Nonparametric Hypotheses Test

2000 Mathematics Subject Classification: 62L10, 62L15.