Russian Federation
The paper compares the most popular architectures of convolutional neural networks, their advantages and disadvantages, and areas of application. Neural networks such as ALEX NET, ZF NET, VG, GOOGLENET, RESET are analyzed.
Convolutional neural network, machine learning, filter, subsample, activation function
1. Sikorskiy, O.S. Obzor svertochnyh neyronnyh setey dlya zadachi klassifikacii izobrazheniy / O.S. Sikorskiy // Novye informacionnye tehnologii v avtomatizirovannyh sistemah. – 2017. – № 20. – S. 37-42.
2. Marshalko, D.A. Arhitektura svertochnyh neyronnyh setey / D.A. Marshalko, O.V. Kubanskih // Uchenye zapiski Bryanskogo gosudarstvennogo universiteta. – 2019. - № 4. – S. 10-13.
3. Svertochnaya neyronnaya set', chast' 1: struktura, topologiya, funkcii aktivacii i obuchayuschee mnozhestvo. – URL: https://habr.com/ru/articles/348000/ (data obrascheniya: 12.03.2025).
4. Saymon, H. Neyronnye seti: polnyy kurs / H. Saymon. – M. : Izdatel'skiy dom «Vil'yams», 2019. – 1104 s.
5. Makarov, M.A. Iskusstvennyy intellekt v promyshlennoy infor-matike : uchebnoe posobie / M.A. Makarov, I.Yu. Zaycev. – M. : MIREA – RTU, 2024. – 118 s.
6. Zhou, L. Design and Implementation of AlexNet Flower Classification System from the Perspective of Deep Learning / L. Zhou // International Journal of Computer Science and Information Technology. – 2024. – Vol. 3(3). – Pp. 292-299.
7. Evolyuciya arhitektur neyrosetey v komp'yuternom zrenii: klassifikaciya izobrazheniy. – URL: https://habr.com/ru/companies/slsoft/articles/855602/ (data obrascheniya: 12.03.2025).
8. Face Images Classification using VGG-CNN / I.N.G.A. Astawa, M.L. Radhitya, I.W.R. Ardana, F.A. Dwiyanto // Knowledge Engineering and Data Science. – 2021. – Vol. 4(1). – Pp. 49-54.
9. Dong, H. Investigations on Convolutional Neural Network Based on Im-age Recognition / H. Dong // Highlights in Science, Engineering and Technology. – 2025. – Vol. 124. – Pp. 208-215.
10. Chzhu, I. Issledovanie ostatochnoy neyronnoy seti RESNET / I. Chzhu, T.P. Novikova, S.A. Evdokimova // Modelirovanie informacionnyh sistem i tehnologiy : materialy Mezhdunarodnoy nauchno-prakticheskoy konferencii, Voronezh, 27 oktyabrya 2022 g. – Voronezh, 2022. – S. 343-349.
11. Deep Residual Learning for Image Recognition / K. He [et al.] // Pro-ceedings of the IEEE Conference on Computer Vision and Pattern Recognition. – 2016. – Pp. 770-778.
