Artificial intelligence

Abstract: The paper explores an important area of artificial intelligence — Generative Adversarial Networks (GANs), which are used to create high-quality artificial data samples. GANs have undergone significant development and application in various sectors, including the processing of graphical data. The report focuses on the practical use of GANs and their architecture. It discusses the fundamental principles of GAN operation, highlights the advantages and disadvantages, including issues with training, vanishing gradients, and convergence oscillations, and describes measures to overcome these problems. It also examines current research in the field of GANs and their applications in various domains, including cybersecurity, medicine, forensics, and computer vision. Practical results from the report's authors regarding their own GAN experiments, optimization, and architecture improvements are presented. The research aims to analyze the architectural features of GANs to enhance their training process.

Keywords: artificial intelligence, deep learning, neural networks, generative adversarial networks, image processing.

References:

1. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, J. (2014). “Generative Adversarial Networks,” Proceedings of the International Conference on Neural Information Processing Systems (NIPS), 2672-2680.
2. Aldausari, N., Sowmya, A., Marcus, N. and Mohammadi, G. (2022). Video Generative Adversarial Networks: A Review [Online]. Available at: https://doi.org/10.1145/3487891
3. Striuk, O.S., Kondratenko, Y.P. (2021). “Generative Adversarial Neural Networks and Deep Learning: Successful Cases and Advanced Approaches,” International Journal of Computing, vol. 20, issue 3, 339-349.
4. Striuk, O.S., Kondratenko, Y.P. (2023). Generative Adversarial Networks in Cybersecurity: Analysis and Response, in: Y. Kondratenko, V. Kreinovich, W. Pedrycz, A. Chilrii, A. M. Gil-Lafuente (Eds.), Artificial Intelligence in Control and Decisionmaking Systems: Dedicated to Prof. Janusz Kacprzyk. Studies in Computational Intelligence, vol. 1087, Springer, Cham, 373-388.
5. Arjovsky, M., Bottou, L. (2017). Towards Principled Methods for Training Generative Adversarial Networks [Online]. Available at: https://arxiv.org/abs/1701.04862
6. Striuk, O.S., Kondratenko, Y.P. (2023). “Optimization Strategy for Generative Adversarial Networks Design,” International Journal of Computing, vol. 22, issue 3, 292-301.
7. Ayari, R. (2020). Generative Adversarial Networks [Online]. Available at: https://bit.ly/3Uk4GBw
8. Borji, A. (2018). Pros and Cons of GAN Evaluation Measures [Online]. Available at: https://arxiv.org/abs/1802.03446
9. Brownlee, J. (2017). A Gentle Introduction to Transfer Learning for Deep Learning [Online]. Available at: https://bit.ly/3GTmdeC
10. Striuk, O., Kondratenko, Y., Sidenko, I., Vorobyova, A. (2020, November 27). “Generative Adversarial Neural Network for Creating Photorealistic Images,” Proceedings of 2020 IEEE 2nd International Conference on Advanced Trends in Information Theory, Kyiv, Ukraine, 368-371.
11. Lecun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998). “Gradient-based learning applied to document recognition,” in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, doi: 10.1109/5.726791.
12. Striuk, O. and Kondratenko, Y. (2021). “Adaptive Deep Convolutional GAN for Fingerprint Sample Synthesis,” 2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT), Lviv, Ukraine, 193-196. doi: 10.1109/AICT52120.2021.9628978.
13. Bécue A. and Champod, C. (2023). "Interpol review of fingermarks and other body impressions (2019–2022)," Forensic Science International: Synergy, vol. 6, 100304.
14. Striuk, O. And Kondratenko, Y. (2023). “Implementation of Generative Adversarial Networks in Mobile Applications for Image Data Enhancement,” Journal of Mobile Multimedia, vol. 19, 03, 823–838, doi: 10.13052/jmm1550-4646.1938.
15. Shehu, Y.I., Ruiz-Garcia, A., Palade, V., James, A. (2018). “Sokoto Coventry Fingerprint Dataset,” arXiv:1807.10609 [cs.CV], 1-3.
16. BIRDS 400 Dataset, [Online]. Available at: https://www.kaggle.com/datasets/gpiosenka/100-birdspecies.
17. Di Mattia F. et al. (2021). A Survey on GANs for Anomaly Detection [Online]. Available at: https://arxiv.org/abs/1906.11632