Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP
TL;DR
This study optimizes GAN hyperparameters using Gaussian AHP, combining machine learning and multi-criteria methods to improve model performance on the Fashion MNIST dataset.
Hyperparameter Optimization in Generative Adversarial Networks (GANs) Using Gaussian AHP
Thiago Serafim Rodrigues; Plácido Rogério Pinheiro
https://doi.org/10.1109/ACCESS.2024.3518979
Volume 13
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 hyperpara...