Highly Influential

# Conditions of the correctness for the algebra of estimates calculation algorithms with μ-operators over a set of binary-data recognition problems

@article{Dyusembaev2017ConditionsOT, title={Conditions of the correctness for the algebra of estimates calculation algorithms with μ-operators over a set of binary-data recognition problems}, author={Anuar Dyusembaev and Mikhail Grishko}, journal={Pattern Recognition and Image Analysis}, year={2017}, volume={27}, pages={166-174} }

- Published 2017 in Pattern Recognition and Image Analysis
DOI:10.1134/S1054661817020043

This paper is aimed to show that specialized neural networks can be useful for finding exact solutions of the recognition problems involving binary data. For this purpose, as an original subclass, we take the subclass of estimates calculation algorithms (ECAs) in which all algorithms correspond to three-level multilayer neural networks (μ-blocks). The correctness conditions are defined that allow a correct algorithm to be constructed in the algebra over this ECA subclass for each Ω-regular… CONTINUE READING