Construction of a Correct Algorithm and Spatial Neural Network for Recognition Problems with Binary Data
- 1 October 2018
- journal article
- research article
- Published by Pleiades Publishing Ltd in Computational Mathematics and Mathematical Physics
- Vol. 58 (10) , 1673-1686
Abstract
Conditions under which it is possible to design a correct algorithm and a six-level spatial neural network reproducing the computations performed by this algorithm for recognition problems...Keywords
This publication has 10 references indexed in Scilit:
- Conditions of the correctness for the algebra of estimates calculation algorithms with μ-operators over a set of binary-data recognition problemsPattern Recognition and Image Analysis, 2017
- An approach to the solution of recognition problems using neural networksDoklady Mathematics, 2017
- Two-frequency self-oscillations in a FitzHugh–Nagumo neural networkComputational Mathematics and Mathematical Physics, 2017
- Deep learningNature, 2015
- On exact solutions of recognition problems based on the neural-network approachDoklady Mathematics, 2015
- Neural Network Method for Solving Linear Fractional Programming2010
- Algebra over estimation algorithms: Normalization with respect to the intervalComputational Mathematics and Mathematical Physics, 2009
- Subject independent facial expression recognition with robust face detection using a convolutional neural networkNeural Networks, 2003
- On the correctness of algebraic closures of recognition algorithms of the “tests” typeUSSR Computational Mathematics and Mathematical Physics, 1982
- Construction of recognition algorithms correct for a given control sampleUSSR Computational Mathematics and Mathematical Physics, 1979