Limited Discriminator GAN using explainable AI model for overfitting problem

Data-driven learning is the most representative deep learning method. Generative adversarial networks (GANs) are designed to generate sufficient data to support such learning. The learning process of GAN models typically trains a generator and discriminator in turn. However, overfitting problems occ...

Full description

Bibliographic Details
Main Authors: Jiha Kim, Hyunhee Park
Format: Article
Language:English
Published: Elsevier 2023-04-01
Series:ICT Express
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S240595952100179X