YPYurii Parzhyn

Yurii Parzhyn

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yurii Parzhyn has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Invariant structural learning: concept formation as hypergraph attractor dynamics

    by Mykyta Lapin, Yurii Parzhyn, Kostiantyn Bokhan, Kyrylo Perevoznyk, Tetiana Aleksandrova

    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

    Application of neural network technology for public opinion analysis

    by Kyrylo Perevoznyk, Yurii Parzhyn

    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.

  • Method For Binary Contour Images Vectorization Of Handwritten Characters For Recognition By Detector Neural Networks

    by Yuri Parzhin, Sergii Galkyn, Maksym Sobol

    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.