Образование и право

2076-1503

10.24412/2076-1503-2026-7-775-784

Other

Развитие и архитектурные особенности рекуррентных и спайковых нейросетей

Development and architectural features of recurrent and spiking neural networks

Семенов

Александр Александрович

Semenov

Alexander Alexandrovich

mail@law-books.ru

Гончар

Владимир Владимирович

Gonchar

Vladimir Vladimirovich

vg0778@bk.ru

Chief Researcher, Federal State Budgetary Institution “STIS” of the Ministry of Internal Affairs of Russia

научный сотрудник ФКУ НПО «СТиС» МВД России

Associate Professor, Department of Information Technology and Cybercrime Investigation Moscow Academy of the Investigative Committee of the Russian Federation named after A. Ya. Sukharev

доцент кафедры информационных технологий и организации расследования киберпреступлений Московская академия Следственного комитета Российской Федерации имени А.Я. Сухарева

10082026

77757840207202603082026

В статье рассматриваются альтернативные архитектуры нейросетей, включая спайковые и рекуррентные модели. Особое внимание уделяется механизмам памяти, обработке последовательных данных и проблемам обучения таких сетей. Описаны принципы работы LSTM и GRU, а также практические аспекты применения рекуррентных нейросетей в задачах анализа последовательностей.

This article examines alternative neural network architectures, including spiking and recurrent models. Particular attention is paid to memory mechanisms, processing of sequential data, and training issues of such networks. The operating principles of LSTM and GRU are described, as well as practical aspects of applying recurrent neural networks to sequence analysis problems.

нейросетирекуррентные нейросетиRNNLSTMGRUспайковые нейросетинейроморфные вычисленияпоследовательности данныхпамять нейросетиbackpropagation through time

neural networksrecurrent neural networksRNNLSTMGRUspiking neural networksneuromorphic computingdata sequencesneural network memorybackpropagation over time

Chen Zhang, Joohee Kim Video object detection with two-path convolutional LSTM pyramid. 2016. // Research Gate. – 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/ (дата обращения: 16.01.2026).

Hanson A., Koutilya PNVR, Sanjukta Krishnagopal, Larry Davis Bidirectional Convolutional LSTM for the Detection of Violence in Videos. 2018. // CVF Open Access. – 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).

Howard A.G., Menglong Zhu, Bo Chen, Kalenichenko D. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. 2017. // arXiv.org. – URL: https://arxiv.org/pdf/1704.04861/ (дата обращения: 11.01.2026).

Iandola F.N., Han S., Moskewicz M.W., Ashraf K., Dally W.J., Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size Recognition. 2016. Published as a conference paper at ICLR. 2015. // Research Gate. – URL: https://www. researchgate.net/publication/ 301878495_SqueezeNet_AlexNet-level_accuracy_ with_50x_fewer_ parameters_ and_05MB_model_ size (дата обращения: 10.01.2026).

Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. 2015. // arXiv.org. – URL: https://arxiv.org/pdf/1502.03167/ (дата обращения: 13.01.2026).

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun Deep Residual Learning for Image Recognition. 2015. // arXiv.org. – URL: https://arxiv. org/pdf/1512.03385 (дата обращения: 11.01.2026).

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun Spatial pyramid pooling in deep convolutional networks for visual recognition. 2015. // arXiv.org. – URL: https://arxiv.org/pdf/1406.4729/ (дата обращения: 11.01.2026).

Krizhevsky I., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural networks. 2012. // NeurIPS Proceedings. – URL: https:// proceedings.neurips.cc/paper_files/paper/2012/file/ c399862d3b9d6b76c8436e 924a68c45b-Paper.pdf (дата обращения: 12.01.2026).

Lavin A., Scott Gray Fast Algorithms for Convolutional Neural Networks. 2015. // arXiv. org. – URL: https://arxiv.org/abs/1509.09308 (дата обращения: 11.01.2026).

Mikolov T., Kai Chen, Corrado G., Jeffrey Dean Efficient Estimation of Word Representations in Vector Space. 2013. // arXiv.org. – URL: https://arxiv. org/abs/1301.3781 (дата обращения: 15.01.2026).

Norman P. Jouppi, Cliff Young, Nishant Patil and others In-Datacenter Performance Analysis of a Tensor Processing Unit. 2017. // arXiv.org. – URL: https://arxiv.org/pdf/1704.04760 (дата обращения: 11.01.2026).

Ronneberger O., Fischer Ph., Brox Th. U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015. // arXiv.org. – URL: https://arxiv. org/pdf/1505.04597/ (дата обращения: 13.01.2026).

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. // arXiv.org. – URL: https://arxiv.org/pdf/1409.4842 (дата обращения: 12.01.2026)

Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2015. Published as a conference paper at ICLR 2015. // arXiv.org. – URL: https://arxiv.org/ pdf/1409.1556 (дата обращения: 10.01.2026).

Wei Liu, Anguelov D., Erhan D., Szegedy C., Reed S., Cheng-Yang Fu, Berg A.C. SSD: Single Shot MultiBox Detector. 2016. // arXiv.org. – URL: https://arxiv.org/pdf/1512.02325 (дата обращения: 11.01.2026).

Официальный сайт ONNX. – URL: https://onnx.ai/ (дата обращения: 11.01.2026).

Основы технологий искусственного интеллекта: учебное пособие/ А.А. Семенов, В.В. Гончар, А.С. Эрдниев. – Московский университет МВД России имени В.Я, Кикотя, 2025. – 190с.

Финансовый мониторинг: учебное пособие / В.И. Глотов, А.У. Альбеков, О.Н. Тисен и др. – КноРус, 2022. – 198 с.

Тисен О.Н. Противодействие современным приемам и способам вербовки в международные террористические организации // Российская юстиция. 2018, №9. С. 51-54.

Овчинский А.С., Аветисян К.Р. Аудиальные воздействия на участников массовых мероприятий как объект административно-правового регулирования// Вестник Московского университета МВД. 2015. № 1-. С. 293-297.

Зиборов О.В., Аветисян К.Р. Комплексный подход при противоборстве организации массовых беспорядков// Вестник Московского университета МВД. 2023. № 7. С. 100-104.

Howard A.G., Menglong Zhu, Bo Chen, Kalenichenko D. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. 2017. // arXiv.org. - URL: https://arxiv.org/pdf/1704.04861/ (access date: 11.01.2026).

Ioffe S., Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. 2015. // arXiv.org. - URL: https://arxiv.org/pdf/1502.03167/ (access date: 13.01.2026).

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun Deep Residual Learning for Image Recognition. 2015. // arXiv.org. - URL: https://arxiv. org/pdf/1512.03385 (access date: 11.01.2026).

Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun Spatial pyramid pooling in deep convolutional networks for visual recognition. 2015. // arXiv.org. - URL: https://arxiv.org/pdf/1406.4729/ (access date: 11.01.2026).

Krizhevsky I., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural networks. 2012. // NeurIPS Proceedings. - URL: https://proceedings.neurips.cc/paper_ files/paper/2012/file/c399862d3b9d6b76c8436e 924a68c45b-Paper.pdf (accessed on: 12.01.2026).

Lavin A., Scott Gray Fast Algorithms for Convolutional Neural Networks. 2015. // arXiv.org. - URL: https://arxiv.org/abs/1509.09308 (access date: 11.01.2026).

Mikolov T., Kai Chen, Corrado G., Jeffrey Dean Efficient Estimation of Word Representations in Vector Space. 2013. // arXiv.org. - URL: https://arxiv. org/abs/1301.3781 (access date: 15.01.2026).

Norman P. Jouppi, Cliff Young, Nishant Patil and others In-Datacenter Performance Analysis of a Tensor Processing Unit. 2017. // arXiv.org. - URL: https://arxiv.org/pdf/1704.04760 (access date: 11.01.2026).

Ronneberger O., Fischer Ph., Brox Th. U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015. // arXiv.org. - URL: https://arxiv. org/pdf/1505.04597/ (access date: 13.01.2026).

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. // arXiv.org. - URL: https://arxiv.org/pdf/1409.4842 (accessed on: 12.01.2026)

Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2015. Published as a conference paper at ICLR 2015. // arXiv.org. - URL: https://arxiv.org/ pdf/1409.1556 (access date: 10.01.2026).

Wei Liu, Anguelov D., Erhan D., Szegedy C., Reed S., Cheng-Yang Fu, Berg A.C. SSD: Single Shot MultiBox Detector. 2016. // arXiv.org. - URL: https://arxiv.org/pdf/1512.02325 (access date: 11.01.2026).

ONNX official website. - URL: https:// onnx.ai/ (access date: 11.01.2026).

Fundamentals of artificial intelligence technologies: a textbook/A.A. Semenov, V.V. Gonchar, A.S. Erdniev. - Moscow University of the Ministry of Internal Affairs of Russia named after V.Ya, Kikotya, 2025. - 190s.

Financial monitoring: training manual/V.I. Glotov, A.U. Albekov, O.N. Tisen et al. - KnoRus, 2022. - 198 s.

Tisen O.N. Countering modern methods and methods of recruitment to international terrorist organizations//Russian Justice. 2018, №9. S. 51-54.

Ovchinsky A.S., Avetisyan K.R. Audio effects on participants of mass events as an object of administrative and legal regulation//Bulletin of the Moscow University of the Ministry of Internal Affairs. 2015. № 1-. S. 293-297.

Ziborov O.V., Avetisyan K.R. An integrated approach to confronting the organization of mass riots//Bulletin of the Moscow University of the Ministry of Internal Affairs. 2023. № 7. S. 100-104.