The article discusses generative adversarial networks for obtaining high quality images. Models, architecture and comparison of network operation are presented. The features of building deep learning models in the process of performing the super-resolution task, as well as methods associated with improving performance, are considered.
neuralnetwork, highresolution, generation, deeplearning, images
1. Aggarwal, Ch. Neural networks and deep learning: course English [Text] / Ch. Aggarwal. – SPb: LLC “Dialectic”, 2020. – 752p. - ISBN 978-5-907203-01-3.
2. Zhadaev, D. S. Features neural network analysis of level of preparation of students in the process of adaptive testing of their professional competence [Text] / D. S. Zhadaev, A. A. Kuzmenko, V. V. Spasennov // Bulletin of the Bryansk state technical University. – 2019. - №2 (75). – P. 90-98.
3. Nikolenko, S. Deep learning. Immersion in the world of neural networks [Text] / S. Nikolenko, A. Kadurin, E. Arkhangelskaya. - SPb.: Publishing house "Peter", 2018. – 482 p.
4. Patent RU 2309457 Model of the neural network IPCG06N3/06 / K. N. Shevchenko, N. V. Shevchenko, B. V. Shulgin Priority 06.05.2006, published 27.10.2007, BI. no. 30.
5. Goodfellow, I. J. Generative competitive networks, in: Advances in neural information processing systems [Text] / I. J. Goodfellow, J. Pouge-Abadi, M. Mirza, B. Xu, D. Ward-Farley, S. Ozer, A. S. Courville, Y. Benjio // 27th annual conference on neural systems. - 2014. – P. 2672-2680.
6. Box, J. Analysis of time series: forecasting and control [Text] / J. Box, D. M. Jenkins // Journal of Time. - No. 31. – 1976. – C. 238-242.
7. Ding, X. Deep learning for predicting stocks based on events, in: Proceedings of the Twenty-fourth International joint conference on artificial intelligence [Text] / H. Ding, Yu. Zhang, T. Liu, J. Duan // IJCAI, 2015. – P. 2327-2333.
8. Sinyu, Zhi, Stock market forecast. High-frequency data using generative adversarial networks [Text] / Zh. Sinyu, P. Zhixun, H. Guyu, T. Siqi, Ch. Zhao // Mathematical problem. Engineering. – 2018. – P. 7-10.
9. Razer, A.M. Recurrent neural network and hybrid model for predicting stock returns [Text] / A.M. Razer, A. Agarwal, V. N. Sastri // Expert system. Appl., - №42. – 2015. - P. 3234-3241
10. Tsantekidis, A. Forecasting stock prices from the book of limit orders using convolutional neural networks [Text] / A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbudzh, A. Iosifidis // 19-e. IEEE conference on business Informatics, CBI 2017. – P. 7-12.
11. Zeiler, M. Visualising and understanding convolution networks. European Conference on Computer Vision [Electronic resource] / M. Zeiler, R. Fergus. – URL: https://arxiv.org/pdf/1311.2901.pdf (accessed 29.09.2020).
12. Zhang, H. Character-level convolutional networks for text classification [Text] / H. Zhang, J. Zhao, Y. Le Cun // NIPS Conference. – 2015. - C. 649-657.