Please use this identifier to cite or link to this item:
https://dspace.chmnu.edu.ua/jspui/handle/123456789/1307
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Striuk, O. | - |
dc.contributor.author | Kondratenko, Y. | - |
dc.date.accessioned | 2023-10-19T11:28:07Z | - |
dc.date.available | 2023-10-19T11:28:07Z | - |
dc.date.issued | 2023 | - |
dc.identifier.issn | 17276209 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173639757&doi=10.47839%2fijc.22.3.3223&partnerID=40&md5=6decdDOI: 10.47839/ijc.22.3.3223 | - |
dc.identifier.uri | https://computingonline.net/files/journals/1/archieve/IJC_2023_22_3_02.pdf | - |
dc.identifier.uri | https://dspace.chmnu.edu.ua/jspui/handle/123456789/1307 | - |
dc.description | Striuk, O., & Kondratenko, Y. (2023). Optimization Strategy for Generative Adversarial Networks Design. International Journal of Computing, 22(3), 292-301. doi: 10.47839/ijc.22.3.3223 | uk_UA |
dc.description.abstract | Generative Adversarial Networks (GANs) are a powerful class of deep learning models that can generate realistic synthetic data. However, designing and optimizing GANs can be a difficult task due to various technical challenges. The article provides a comprehensive analysis of solution methods for GAN performance optimization. The research covers a range of GAN design components, including loss functions, activation functions, batch normalization, weight clipping, gradient penalty, stability problems, performance evaluation, mini-batch discrimination, and other aspects. The article reviews various techniques used to address these challenges and highlights the advancements in the field. The article offers an up-to-date overview of the state-of-the-art methods for structuring, designing, and optimizing GANs, which will be valuable for researchers and practitioners. The implementation of the optimization strategy for the design of standard and deep convolutional GANs (handwritten digits and fingerprints) developed by the authors is discussed in detail, the obtained results confirm the effectiveness of the proposed optimization approach. | uk_UA |
dc.language.iso | en | uk_UA |
dc.publisher | Research Institute of Intelligent Computer Systems | uk_UA |
dc.subject | artificial intelligence | uk_UA |
dc.subject | deep learning | uk_UA |
dc.subject | design | uk_UA |
dc.subject | generative adversarial network | uk_UA |
dc.subject | loss function | uk_UA |
dc.subject | machine learning | uk_UA |
dc.subject | optimization | uk_UA |
dc.title | Optimization Strategy for Generative Adversarial Networks Design | uk_UA |
dc.type | Article | uk_UA |
Appears in Collections: | Публікації науково-педагогічних працівників ЧНУ імені Петра Могили у БД Scopus |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Striuk, O., Kondratenko, Y..pdf | 63.22 kB | Adobe PDF | View/Open | |
Optimization Strategy for Generative.pdf | 1.15 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.