Yurii Parzhyn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yurii Parzhyn has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Kyrylo Perevoznyk
Educational and Scientific Institute of Computer Science and Information Technology of National Technical University "Kharkiv Polytechnic Institute", Kharkiv
2 shared publications - Kostiantyn Bokhan
Samsung R&D Institute Ukraine (SRK), 57, L'va Tolstogo Str., Kyiv, 01032, Ukraine
1 shared publication - Maksym Sobol
Національний технічний університет «Харківський політехнічний інститут
1 shared publication - Mykyta Lapin
Department of System Analysis and Information and Analytical Technologies National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine
1 shared publication - Sergii Galkyn
National Technical University Kharkiv Polytechnic Institute,Department of Computer Science and Intellectual Property,Kharkiv,Ukraine
1 shared publication - Tetiana Aleksandrova
National Technical University «Kharkiv Polytechnic Institute», Kharkiv
1 shared publication
Latest Publications
- Open Access
- 27 June 2026
- Published by Kharkiv National University of Radioelectronics in Innovative technologies and scientific solutions for industries
- No. 2(36),p. 70-94
Invariant structural learning: concept formation as hypergraph attractor dynamics
Subject of study. The subject of study is the formation of object-class concepts in machine-learning systems as a process of structural and parametric reduction of hypergraph representations, rather than as the optimization of a loss function. Objective. To construct an alternative learning framework for artificial neural networks – without an error functional (back-propagation) – that realizes invariant structural learning, where a class concept is defined as a structural attractor (the fixed point of a monotone reduction operator on a partially ordered space of hypergraphs), and to validate this theory on the recognition of handwritten digits. Objectives. 1) Formalize the framework with axioms of segmentation stability, strict reductivity, positive-only training, and locality of attention; 2) prove convergence and uniqueness of the attractor; 3) establish order-invariance of learning; 4) decompose the attractor into structural and parametric levels; 5) evaluate the transfer on a complete-contour subset of MNIST. Methods. Hypergraphs are obtained by skeletonizing binary contours (Growing Neural Gas + Ramer–Douglas–Peucker); concept attractors form via graph reduction over critical-point anchors. Classification uses a graph-edit-distance comparator with property costs and a complexity-adjusted log prior. The training set consists of 76 hand-picked MNIST originals, augmented (rotation ±10°, shift ±10%) to 805 instances. Results. The transfer learns 13 concept-attractors with node counts ranging from 3 to 15. Of 8,707 admissible complete-contour MNIST images, 8,685 yielded valid skeletal graphs; on this valid set, the transfer achieves an accuracy of 85.80%, weighted precision of 89.31%, recall of 85.80%, and an F1-score of 86.66%. The error structure is interpretable per concept – every misclassification traces back to a named attractor and feature range. Conclusions. The reported performance, achieved without a loss function and using three to nine originals per concept-attractor, supports the claim that learning consists of constructing a structural attractor rather than minimizing an error functional. The framework offers a principled approach to interpretable few-shot classification and a constructive alternative to gradient-based learning.
- 27 June 2026
- Published by Kharkiv National University of Radioelectronics in Innovative technologies and scientific solutions for industries
- No. 2(36),p. 70-94
Open AccessInvariant structural learning: concept formation as hypergraph attractor dynamics
Subject of study. The subject of study is the formation of object-class concepts in machine-learning systems as a process of structural and parametric reduction of hypergraph representations, rather than as the optimization of a loss function. Objective. To construct an alternative learning framework for artificial neural networks – without an error functional (back-propagation) – that realizes invariant structural learning, where a class concept is defined as a structural attractor (the fixed point of a monotone reduction operator on a partially ordered space of hypergraphs), and to validate this theory on the recognition of handwritten digits. Objectives. 1) Formalize the framework with axioms of segmentation stability, strict reductivity, positive-only training, and locality of attention; 2) prove convergence and uniqueness of the attractor; 3) establish order-invariance of learning; 4) decompose the attractor into structural and parametric levels; 5) evaluate the transfer on a complete-contour subset of MNIST. Methods. Hypergraphs are obtained by skeletonizing binary contours (Growing Neural Gas + Ramer–Douglas–Peucker); concept attractors form via graph reduction over critical-point anchors. Classification uses a graph-edit-distance comparator with property costs and a complexity-adjusted log prior. The training set consists of 76 hand-picked MNIST originals, augmented (rotation ±10°, shift ±10%) to 805 instances. Results. The transfer learns 13 concept-attractors with node counts ranging from 3 to 15. Of 8,707 admissible complete-contour MNIST images, 8,685 yielded valid skeletal graphs; on this valid set, the transfer achieves an accuracy of 85.80%, weighted precision of 89.31%, recall of 85.80%, and an F1-score of 86.66%. The error structure is interpretable per concept – every misclassification traces back to a named attractor and feature range. Conclusions. The reported performance, achieved without a loss function and using three to nine originals per concept-attractor, supports the claim that learning consists of constructing a structural attractor rather than minimizing an error functional. The framework offers a principled approach to interpretable few-shot classification and a constructive alternative to gradient-based learning.
- Open Access
- 25 December 2024
- Published by Igor Sikorsky Kyiv Polytechnic Institute in System research and information technologies
- No. 4,p. 97-106
Application of neural network technology for public opinion analysis
The research is devoted to studying and using neural network technologies, in particular algorithms and methods of natural language processing, to increase the efficiency of studying and analyzing public opinion of Ukraine’s partner countries regarding the war in Ukraine. The research involved analyzing and processing databases consisting of messages about the war in Ukraine on the social network Twitter. The resulting datasets were used to train several neural network models. The best classification results were obtained with the GPT-3.5-turbo model. For a deeper understanding of the results of the public opinion analysis, we created their visualization. The results of the study have shown the high efficiency of the selected solutions. They may be of great practical importance for improving methods of analyzing public opinion and making informed decisions based on a deep understanding of global feedback.
- 25 December 2024
- Published by Igor Sikorsky Kyiv Polytechnic Institute in System research and information technologies
- No. 4,p. 97-106
Open AccessApplication of neural network technology for public opinion analysis
The research is devoted to studying and using neural network technologies, in particular algorithms and methods of natural language processing, to increase the efficiency of studying and analyzing public opinion of Ukraine’s partner countries regarding the war in Ukraine. The research involved analyzing and processing databases consisting of messages about the war in Ukraine on the social network Twitter. The resulting datasets were used to train several neural network models. The best classification results were obtained with the GPT-3.5-turbo model. For a deeper understanding of the results of the public opinion analysis, we created their visualization. The results of the study have shown the high efficiency of the selected solutions. They may be of great practical importance for improving methods of analyzing public opinion and making informed decisions based on a deep understanding of global feedback.
- 3 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Method For Binary Contour Images Vectorization Of Handwritten Characters For Recognition By Detector Neural Networks
This paper describes the developed method for binary contour images vectorization of handwritten characters for recognition by detector neural networks. A description of the software that implements the developed method is given.
- 3 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Method For Binary Contour Images Vectorization Of Handwritten Characters For Recognition By Detector Neural Networks
This paper describes the developed method for binary contour images vectorization of handwritten characters for recognition by detector neural networks. A description of the software that implements the developed method is given.