Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP
This study explores optimizing hyperparameters in Generative Adversarial Networks (GANs) using the Gaussian Analytical Hierarchy Process (Gaussian AHP). By integrating machine learning techniques and multi-criteria decision methods, the aim is to enhance the performance and efficiency of GAN models....
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10804166/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563389424304128 |
|---|---|
| author | Thiago Serafim Rodrigues Placido Rogerio Pinheiro |
| author_facet | Thiago Serafim Rodrigues Placido Rogerio Pinheiro |
| author_sort | Thiago Serafim Rodrigues |
| collection | DOAJ |
| description | This study explores optimizing hyperparameters in Generative Adversarial Networks (GANs) using the Gaussian Analytical Hierarchy Process (Gaussian AHP). By integrating machine learning techniques and multi-criteria decision methods, the aim is to enhance the performance and efficiency of GAN models. It trains GAN models using the Fashion MNIST dataset. It applies Gaussian AHP to optimize hyperparameters based on multiple performance criteria, such as the quality of generated images, training stability, and training time. Iterative experiments validate the methodology by automatically adjusting hyperparameters based on the obtained scores, thereby maximizing the model’s efficiency and quality. Results indicate significant improvements in image generation quality and computational efficiency. The study highlights the effectiveness of combining Gaussian AHP with GANs for systematic hyperparameter optimization, providing insights into achieving higher performance in image generation tasks. Future research could extend this approach to other neural network architectures and diverse datasets, further demonstrating the versatility of this optimization technique. This method’s potential applications extend across various domains, including data augmentation and anomaly detection, indicating its broad applicability and impact. |
| format | Article |
| id | doaj-art-b66d44b9809b40afa3519d3cfb80d8f1 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b66d44b9809b40afa3519d3cfb80d8f12025-01-03T00:01:31ZengIEEEIEEE Access2169-35362025-01-011377078810.1109/ACCESS.2024.351897910804166Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHPThiago Serafim Rodrigues0https://orcid.org/0009-0003-5695-599XPlacido Rogerio Pinheiro1https://orcid.org/0000-0002-1718-1712Graduate Program in Applied Informatics, University of Fortaleza, Fortaleza, BrazilGraduate Program in Applied Informatics, University of Fortaleza, Fortaleza, BrazilThis study explores optimizing hyperparameters in Generative Adversarial Networks (GANs) using the Gaussian Analytical Hierarchy Process (Gaussian AHP). By integrating machine learning techniques and multi-criteria decision methods, the aim is to enhance the performance and efficiency of GAN models. It trains GAN models using the Fashion MNIST dataset. It applies Gaussian AHP to optimize hyperparameters based on multiple performance criteria, such as the quality of generated images, training stability, and training time. Iterative experiments validate the methodology by automatically adjusting hyperparameters based on the obtained scores, thereby maximizing the model’s efficiency and quality. Results indicate significant improvements in image generation quality and computational efficiency. The study highlights the effectiveness of combining Gaussian AHP with GANs for systematic hyperparameter optimization, providing insights into achieving higher performance in image generation tasks. Future research could extend this approach to other neural network architectures and diverse datasets, further demonstrating the versatility of this optimization technique. This method’s potential applications extend across various domains, including data augmentation and anomaly detection, indicating its broad applicability and impact.https://ieeexplore.ieee.org/document/10804166/Generative adversarial networkshyperparameter optimizationgaussian analytical hierarchy processmulticriteria decision-makingmachine learning |
| spellingShingle | Thiago Serafim Rodrigues Placido Rogerio Pinheiro Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP IEEE Access Generative adversarial networks hyperparameter optimization gaussian analytical hierarchy process multicriteria decision-making machine learning |
| title | Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP |
| title_full | Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP |
| title_fullStr | Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP |
| title_full_unstemmed | Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP |
| title_short | Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP |
| title_sort | hyperparameter optimization in generative adversarial networks gans using gaussian ahp |
| topic | Generative adversarial networks hyperparameter optimization gaussian analytical hierarchy process multicriteria decision-making machine learning |
| url | https://ieeexplore.ieee.org/document/10804166/ |
| work_keys_str_mv | AT thiagoserafimrodrigues hyperparameteroptimizationingenerativeadversarialnetworksgansusinggaussianahp AT placidorogeriopinheiro hyperparameteroptimizationingenerativeadversarialnetworksgansusinggaussianahp |