kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университетkaz29-245Research ArticleРАЗРАБОТКА ПРОГРАММНОГО ОБЕСПЕЧЕНИЯ И ИНЖЕНЕРИЯ ЗНАНИЙSOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERINGНЕЙРОННЫЕ СЕТИ ДЛЯ СВЕРТОЧНЫХ НЕЙРОННЫХ СЕТЕЙ: РАСШИРЕНИЕ И ПОДРОБНОЕ ОБЪЯСНЕНИЕNEURAL NETWORKS TO CONVOLUTIONAL NEURAL NETWORKS: EXPANSION AND DETAILED EXPLANATIONЯкуфудзянА.YakufujiangA.

Азати Якуфудзян, магистрант

 Azati Yakufujiang

МаликоваФ.MalikovaF.

PhD

ТемирбековA.TemirbekovA.

PhD

КенжегуловаС.KenzhegulovaS.

ст. преп.

Казахский Национальный университет им. аль-ФарабиКазахстанAl-Farabi Kazakh National UniversityKazakhstanКазахский Национальный университет им. аль-Фараби; Алматинский университет энергетики и связиКазахстанAl-Farabi Kazakh National University; Almaty University of Power Engineering and TelecommunicationsKazakhstanУниверситет Международного бизнесаКазахстанUniversity of International BusinessKazakhstan2019131120211635560Copyright © Якуфудзян А., Маликова Ф., Темирбеков A., Кенжегулова С., 20212021Якуфудзян А., Маликова Ф., Темирбеков A., Кенжегулова С.Yakufujiang A., Malikova F., Temirbekov A., Kenzhegulova S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/245

Эта статья в основном посвящена оценке нейронных сетей, от нейронных сетей до сверточных нейронных сетей, сверточного слоя, слоя объединения. В прошлом веке ученые обнаружили несколько визуальных неврологических функций. Зрительный нерв имеет локальное рецептивное поле. Распознавание целого изображения состоит из нескольких локальных точек распознавания. Различные нейроны обладают способностью распознавать различные формы, а зрительный нерв обладает способностью суперпозиции.

In the last century, scientists discovered several visual neurological features. The optic nerve has a local receptive field. The recognition of a whole picture is composed of multiple local recognition points. Different neurons have the ability to recognize different shapes, and the optic nerve has superposition ability. The pattern can be composed of low-level simple lines. Later, people found that after the operation of the concatenation, the process of optic nerve processing calculation can be well reflected. The LeNet-5, which was invented by LeCun in 1998 [1], can greatly enhance the recognition effect. This article mainly focuses on the neural network evaluation, from neural networks to convolutional neural networks, convolutional layer, the pooling layer, and the overall CNN structure.

NNCNNPythonкомпьютерное зрениемашинное обучениеNNCNNPythonComputer VisionMachine LearningReferencesLeCun, Y., & Bengio, Y. (1998). Convolution Networks for Images, Speech, and Time-Series. Igarss 2014. URL: http://yann.lecun.com/exdb/publis/pdf/lecun-bengio-95a.pdfLeCun, Y., & Bengio, Y. (1998). Convolution Networks for Images, Speech, and Time-Series. Igarss 2014. URL: http://yann.lecun.com/exdb/publis/pdf/lecun-bengio-95a.pdfHe, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (n. d.). Bag of Tricks for Image Classification with Convolutional Neural Networks.He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (n. d.). Bag of Tricks for Image Classification with Convolutional Neural Networks.Cheng, J., Wang, P., Li, G., Hu, Q., & Lu, H. (2018). A Survey on Acceleration of Deep Convolutional Neural Networks. Retrieved from https://arxiv.org/pdf/1802.00939.pdfCheng, J., Wang, P., Li, G., Hu, Q., & Lu, H. (2018). A Survey on Acceleration of Deep Convolutional Neural Networks. Retrieved from https://arxiv.org/pdf/1802.00939.pdfBenton, T., Staab, J., & Evans, D. L. (2007). Medical Co-Morbidity in Depressive Disorders. Annals of Clinical Psychiatry, 19, 289-303. https://doi.org/10.1080/10401230701653542Benton, T., Staab, J., & Evans, D. L. (2007). Medical Co-Morbidity in Depressive Disorders. Annals of Clinical Psychiatry, 19, 289-303. https://doi.org/10.1080/10401230701653542Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2016). Image-to-Image Translation with Conditional Adversarial Networks. Retrieved from http://arxiv.org/abs/1611.07004Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2016). Image-to-Image Translation with Conditional Adversarial Networks. Retrieved from http://arxiv.org/abs/1611.07004Nielsen, M. A. (2015). Neural Networks and Deep Learning. Retrieved from http://neuralnetworksanddeeplearning.com/Nielsen, M. A. (2015). Neural Networks and Deep Learning. Retrieved from http://neuralnetworksanddeeplearning.com/He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (n. d.). Bag of Tricks for Image Classification with Convolutional Neural Networks. Retrieved from https://github.com/dmlc/gluon-cvHe, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (n. d.). Bag of Tricks for Image Classification with Convolutional Neural Networks. Retrieved from https://github.com/dmlc/gluon-cvBishop, C. M. (2006). Pattern Recognition and Machine Learning. In M. Jordan, J. Kleinberg, & B. Scholkopf (Eds.), Pattern Recognition. https://doi.org/10.1117/1.2819119Bishop, C. M. (2006). Pattern Recognition and Machine Learning. In M. Jordan, J. Kleinberg, & B. Scholkopf (Eds.), Pattern Recognition. https://doi.org/10.1117/1.2819119

The authors declare that there are no conflicts of interest present.