<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD with OASIS Tables with MathML3 v1.4 20241031//EN" "https://jats.nlm.nih.gov/archiving/1.4/JATS-archive-oasis-article1-4-mathml3.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" dtd-version="1.4" article-type="research-article" xml:lang="en"><front><journal-meta><journal-title-group><journal-title xml:lang="ru">Право и управление</journal-title></journal-title-group><issn publication-format="print">2224-9133</issn></journal-meta><article-meta><article-id pub-id-type="doi">10.24412/2224-9133-2026-4-52-58</article-id><article-categories><subj-group><subject>Other</subject></subj-group></article-categories><title-group><article-title xml:lang="ru">ПРЕОБРАЗОВАНИЙ К ГЛУБОКОМУ ОБУЧЕНИЮ</article-title><trans-title-group xml:lang="en"><trans-title>FUNDAMENTALS OF CONSTRUCTING AND TRAINING FULLY CONNECTED NEURAL NETWORKS: FROM LINEAR TRANSFORMATIONS TO DEEP LEARNING</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Семенов</surname><given-names>Александр Александрович</given-names></name><name xml:lang="en"><surname>Semenov</surname><given-names>Aleksandr Aleksandrovich</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/><email>mail@law-books.ru</email></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Аветисян</surname><given-names>Карэн Рафаелович</given-names></name><name xml:lang="en"><surname>Avetisyan</surname><given-names>Karen Rafaelovich</given-names></name></name-alternatives><xref ref-type="aff" rid="aff3"/><xref ref-type="aff" rid="aff4"/><email>Karen-Avetisyan-1989@bk.ru</email></contrib><aff-alternatives id="aff1"><aff><institution xml:lang="en">Chief Researcher, Federal State Budgetary Institution “STIS”, of the Ministry of Internal Affairs of the Russian Federation</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="ru">научный сотрудник, ФКУ НПО «СТиС» МВД России</institution></aff></aff-alternatives><aff-alternatives id="aff3"><aff><institution xml:lang="en">Senior Lecturer, Department of Information Technology, and Cybercrime Investigation Organization, Moscow Academy of the Investigative Committee, of the Russian Federation named after A. Ya. Sukharev</institution></aff></aff-alternatives><aff-alternatives id="aff4"><aff><institution xml:lang="ru">старший преподаватель кафедры информационных технологий, и организации расследования киберпреступлений, Московская академия Следственного комитета, Российской Федерации имени А.Я. Сухарева</institution></aff></aff-alternatives></contrib-group><pub-date pub-type="epub" iso-8601-date="2026-05-14"><day>14</day><month>05</month><year>2026</year></pub-date><issue>4</issue><fpage>52</fpage><lpage>58</lpage><history><date date-type="received" iso-8601-date="2026-04-25"><day>25</day><month>04</month><year>2026</year></date><date date-type="accepted" iso-8601-date="2026-05-14"><day>14</day><month>05</month><year>2026</year></date></history><self-uri content-type="pdf" xlink:href="publication-7008bf91-215d-44ad-8d87-ea1f5e732320.pdf" xlink:title="PDF"/><abstract xml:lang="ru"><p>В работе рассматриваются базовые принципы построения нейросетей на примере полносвязной архитектуры. Показано, что использование только линейных преобразований недостаточно для моделирования сложных зависимостей, что обосновывает необходимость введения нелинейных функций активации. Описаны ключевые компоненты нейросети: полносвязные слои, функции активации, перцептрон и многослойные структуры. Рассмотрены особенности обучения с использованием градиентного спуска, включая функции потерь (кросс-энтропию) и нормализацию выходов с помощью softmax. Проанализированы ограничения полносвязных сетей и области их практического применения</p></abstract><abstract xml:lang="en" abstract-type="summary"><p>This paper examines the basic principles of constructing neural networks using a fully connected architecture as an example. It is shown that using linear transformations alone is insufficient for modeling complex dependencies, justifying the need to introduce nonlinear activation functions. Keycomponents of a neural network are described: fully connected layers, activation functions, perceptrons, and multilayer structures. The specifics of training using gradient descent are discussed, including loss functions (cross-entropy) and output normalization using softmax. The limitations of fully connected networks and their practical applications are analyzed</p></abstract><kwd-group xml:lang="ru"><kwd>конфиденс</kwd><kwd>линейные преобразования</kwd><kwd>нейросеть</kwd><kwd>полносвязный слой</kwd><kwd>функция активации</kwd><kwd>сигмоида</kwd><kwd>перцептрон</kwd><kwd>многослойный перцептрон</kwd><kwd>глубокое обучение</kwd><kwd>градиентный спуск</kwd><kwd>обратное распространение ошибки</kwd><kwd>кросс-энтропия</kwd><kwd>классификация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>neural network</kwd><kwd>fully connected layer</kwd><kwd>activation function</kwd><kwd>sigmoid</kwd><kwd>softmax</kwd><kwd>perceptron</kwd><kwd>multilayer perceptron</kwd><kwd>deep learning</kwd><kwd>gradient descent</kwd><kwd>backpropagation</kwd><kwd>cross-entropy</kwd><kwd>classification</kwd><kwd>confidence</kwd><kwd>linear transformations</kwd></kwd-group></article-meta></front><back><ref-list><ref id="ref1"><mixed-citation publication-type="other" xml:lang="ru">Chen Zhang, Joohee KimVideo object detection with two-path convolutional LSTM pyramid. 2016. URL: https://www.researchgate.net/ publication /343702579_Video_Object_Detection_ With_ Two-Path_ Convolutional_LSTM_ Pyramid/ fulltext/5f3b2658928 51cd302013482/Video-ObjectDetection-With-Two-Path-Convolutional-LSTMPyramid.pdf/ (дата обращения: 16.01.2026).</mixed-citation></ref><ref id="ref2"><mixed-citation publication-type="other" xml:lang="ru">Hanson A., Koutilya PNVR, Sanjukta Krishnagopal, Larry Davis Bidirectional Convolutional LSTM for the Detection of Violence in Videos. 2018. URL: https://openaccess.thecvf.com/content_ eccv_2018_workshops/w10 /html/Hanson_ Bidirectional_Convolutional_LSTM_or_the_ Detection_of_ Violence_in_ Videos_ ECCVW_2018_ paper.html (дата обращения: 15.01.2026).</mixed-citation></ref><ref id="ref3"><mixed-citation publication-type="other" xml:lang="ru">Howard A.G., Menglong Zhu, BoChen, Kalenichenko D. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. 2017. URL: https://arxiv.org/pdf/1704.04861/ (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref4"><mixed-citation publication-type="other" xml:lang="ru">Iandola F.N., Han S., Moskewicz M.W., Ashraf K., Dally W.J., Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and</mixed-citation></ref><ref id="ref5"><mixed-citation publication-type="other" xml:lang="ru">Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. 2015. URL: https://arxiv.org/ pdf/1502.03167/ (дата обращения: 13.01.2026).</mixed-citation></ref><ref id="ref6"><mixed-citation publication-type="other" xml:lang="ru">Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian SunDeep Residual Learning for Image Recognition. 2015. URL: https://arxiv.org/ pdf/1512.03385 (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref7"><mixed-citation publication-type="other" xml:lang="ru">Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian SunSpatial pyramid pooling in deep convolutional networks for visual recognition. 2015. URL: https://arxiv.org/pdf/1406.4729/ (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref8"><mixed-citation publication-type="other" xml:lang="ru">Krizhevsky I., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural networks. 2012. URL: https://proceedings. neurips.cc/paper_files/paper/2012/file/ c399862d3b9d6b76c8436e 924a68c45b-Paper.pdf (дата обращения: 12.01.2026).</mixed-citation></ref><ref id="ref9"><mixed-citation publication-type="other" xml:lang="ru">Lavin A., Scott Gray Fast Algorithms for Convolutional Neural Networks. 2015. URL: https:// arxiv.org/abs/1509.09308 (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref10"><mixed-citation publication-type="other" xml:lang="ru">Mikolov T., KaiChen, Corrado G., Jeffrey Dean Efficient Estimation of Word Representations in Vector Space. 2013. URL: https://arxiv.org/ abs/1301.3781 (дата обращения: 15.01.2026).</mixed-citation></ref><ref id="ref11"><mixed-citation publication-type="other" xml:lang="ru">Norman P. Jouppi, Cliff Young, Nishant Patil and others In-Datacenter Performance Analysis of a Tensor Processing Unit. 2017. URL: https://arxiv. org/pdf/1704.04760 (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref12"><mixed-citation publication-type="other" xml:lang="ru">Ronneberger O., Fischer Ph., Brox Th. U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015. URL: https://arxiv.org/ pdf/1505.04597/ (дата обращения: 13.01.2026).</mixed-citation></ref><ref id="ref13"><mixed-citation publication-type="other" xml:lang="ru">Szegedy C., Wei Liu, Chapel Hill, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich Going Deeper with Convolutions. 2014. URL: https://arxiv.org/pdf/1409.4842 (дата обращения: 12.01.2026)</mixed-citation></ref><ref id="ref14"><mixed-citation publication-type="other" xml:lang="ru">Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2015. Published as a conference paper at ICLR 2015. URL: https://arxiv.org/pdf/1409.1556 (дата обращения: 10.01.2026).</mixed-citation></ref><ref id="ref15"><mixed-citation publication-type="other" xml:lang="ru">Wei Liu, Anguelov D., Erhan D., Szegedy C., Reed S., Cheng-Yang Fu, Berg A.C. SSD: Single Shot MultiBox Detector. 2016. URL: https://arxiv.org/ pdf/1512.02325 (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref16"><mixed-citation publication-type="other" xml:lang="ru">Официальный сайт ONNX. URL: https:// onnx.ai/. (дата обращения: 11.01.2026).</mixed-citation></ref><ref id="ref17"><mixed-citation publication-type="other" xml:lang="ru">Основы технологий искусственного интеллекта: учебное пособие/ А.А. Семенов, В.В. Г ончар, А.С. Эрдниев. – Московский университет МВДРоссии имени В.Я, Кикотя, 2025. – 190с.</mixed-citation></ref><ref id="ref18"><mixed-citation publication-type="other" xml:lang="ru">Финансовый мониторинг: учебное пособие / В.И. Г лотов, А.У. Альбеков, О.Н. Тисен и др. – КноРус, 2022. – 198 с.</mixed-citation></ref><ref id="ref19"><mixed-citation publication-type="other" xml:lang="ru">Тисен О.Н. Противодействие современным приемам и способам вербовки в международные террористические организации // Российская юстиция. 2018, №9. С. 51-54.</mixed-citation></ref><ref id="ref20"><mixed-citation publication-type="other" xml:lang="ru">Г ончар В.В. О важности формирования единообразного понятийного аппарата необходимого для расследования преступлений в сфере компьютерной информации// Вестник Экономической безопасности. 2018. №1. С. 225-230.</mixed-citation></ref><ref id="ref21"><mixed-citation publication-type="other" xml:lang="ru">Орлова А.А., Г ончар В.В. Особенности расследования преступлений, совершаемых в сфере информационных технологий // Безопасность бизнеса. 2021. № 4. С. 25-29.</mixed-citation></ref><ref id="ref22"><mixed-citation publication-type="other" xml:lang="en">Chen Zhang, Joohee KimVideo object detection with two-path convolutional LSTM pyramid. 2016. URL: https://www.researchgate.net/publication/343702579_Video_Object_Detection_With_ Two-Path_ Convolutional_LSTM_ Pyramid/fulltext/5f3b2658928 51cd302013482/Video-Object-Detection-With-Two-Path-Convolutional-LSTM-Pyramid.pdf/ (access date: 01/16/2026).</mixed-citation></ref><ref id="ref23"><mixed-citation publication-type="other" xml:lang="en">Hanson A., Koutilya PNVR, Sanjukta Krishnagopal, Larry Davis Bidirectional Convolutional LSTM for the Detection of Violence in Videos. 2018. URL: https://openaccess.thecvf.com/content_ eccv_2018_workshops/w10 /html/Hanson_Bidirectional_Convolutional_LSTM_or_the_ Detection_of_ Violence_in_ Videos_ECCVW_2018_paper.html (accessed: 01/15/2026).</mixed-citation></ref><ref id="ref24"><mixed-citation publication-type="other" xml:lang="en">Howard A.G., Menglong Zhu, BoChen, Kalenichenko D. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. 2017. URL: https://arxiv.org/pdf/1704.04861/ (access date: 01/11/2026).</mixed-citation></ref><ref id="ref25"><mixed-citation publication-type="other" xml:lang="en">Iandola F.N., Han S., Moskewicz M.W., Ashraf K., Dally W.J., Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and</mixed-citation></ref><ref id="ref26"><mixed-citation publication-type="other" xml:lang="en">Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. 2015. URL: https://arxiv.org/ pdf/1502.03167/ (access date: 01/13/2026).</mixed-citation></ref><ref id="ref27"><mixed-citation publication-type="other" xml:lang="en">Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian SunDeep Residual Learning for Image Recognition. 2015. URL: https://arxiv.org/pdf/1512.03385 (access date: 01/11/2026).</mixed-citation></ref><ref id="ref28"><mixed-citation publication-type="other" xml:lang="en">Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian SunSpatial pyramid pooling in deep convolutional networks for visual recognition. 2015. URL: https://arxiv.org/pdf/1406.4729/ (access date: 01/11/2026).</mixed-citation></ref><ref id="ref29"><mixed-citation publication-type="other" xml:lang="en">Krizhevsky I., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural networks. 2012. URL: https://proceedings.neurips. cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e 924a68c45b-Paper.pdf (access date: 01/12/2026).</mixed-citation></ref><ref id="ref30"><mixed-citation publication-type="other" xml:lang="en">Lavin A., Scott Gray Fast Algorithms for Convolutional Neural Networks. 2015. URL: https:// arxiv.org/abs/1509.09308 (access date: 01/11/2026).</mixed-citation></ref><ref id="ref31"><mixed-citation publication-type="other" xml:lang="en">Mikolov T., KaiChen, Corrado G., Jeffrey Dean Efficient Estimation of Word Representations in Vector Space. 2013. URL: https://arxiv.org/ abs/1301.3781 (accessed: 15.01.2026).</mixed-citation></ref><ref id="ref32"><mixed-citation publication-type="other" xml:lang="en">Norman P. Jouppi, Cliff Young, Nishant Patil and others. In-Datacenter Performance Analysis of a Tensor Processing Unit. 2017. URL: https://arxiv. org/pdf/1704.04760 (accessed: 11.01.2026).</mixed-citation></ref><ref id="ref33"><mixed-citation publication-type="other" xml:lang="en">Ronneberger O., Fischer Ph., Brox Th. U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015. URL: https://arxiv.org/ pdf/1505.04597/ (accessed: 13.01.2026).</mixed-citation></ref><ref id="ref34"><mixed-citation publication-type="other" xml:lang="en">Szegedy C., Wei Liu, Chapel Hill, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich Going Deeper with Convolutions. 2014. URL: https://arxiv.org/pdf/1409.4842 (accessed: 12.01.2026)</mixed-citation></ref><ref id="ref35"><mixed-citation publication-type="other" xml:lang="en">Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2015. Published as a conference paper at ICLR 2015. URL: https://arxiv.org/pdf/1409.1556 (accessed: 10.01.2026).</mixed-citation></ref><ref id="ref36"><mixed-citation publication-type="other" xml:lang="en">Wei Liu, Anguelov D., Erhan D., Szegedy C., Reed S., Cheng-Yang Fu, Berg A.C. SSD: Single Shot MultiBox Detector. 2016. URL: https://arxiv.org/ pdf/1512.02325 (accessed: 11.01.2026).</mixed-citation></ref><ref id="ref37"><mixed-citation publication-type="other" xml:lang="en">Official website of ONNX. URL: https:// onnx.ai/. (accessed: 11.01.2026).</mixed-citation></ref><ref id="ref38"><mixed-citation publication-type="other" xml:lang="en">Fundamentals of Artificial Intelligence Technologies: a tutorial / A.A. Semenov, V.V. Gonchar, A.S. Erdniev. - Moscow University of the Ministry of Internal Affairs of Russia named after V. Ya, Kikot, 2025. - 190 p.</mixed-citation></ref><ref id="ref39"><mixed-citation publication-type="other" xml:lang="en">Financial Monitoring: a tutorial / V.I. Glotov, A.U. Albekov, O.N. Tisen, et al. – KnoRus, 2022. – 198 p.</mixed-citation></ref><ref id="ref40"><mixed-citation publication-type="other" xml:lang="en">O.N. Tisen. Counteracting Modern Techniques and Methods of Recruitment into International Terrorist Organizations // Russian Justice. 2018, No. 9. pp. 51-54.</mixed-citation></ref><ref id="ref41"><mixed-citation publication-type="other" xml:lang="en">V.V. Gonchar. On the Importance of Forming a Uniform Conceptual Apparatus Necessary for Investigating Crimes in the Sphere of Computer Information // Bulletin of Economic Security. 2018. No. 1. pp. 225-230.</mixed-citation></ref><ref id="ref42"><mixed-citation publication-type="other" xml:lang="en">A.A. Orlova, V.V. Gonchar. Features of Investigating Crimes Committed in the Sphere of Information Technology // Business Security. 2021. No. 4. pp. 25-29.</mixed-citation></ref></ref-list></back></article>
