Data science becomes creative with generative adversarial networks (GANs) which have had a big success since theywere introduced in 2014 by Ian J. Goodfellow and co-authors. In technical term the GANs are based on the unsupervisedlearning of two artificial neural networks called Generator and Discriminator both trained under the adversarial learningidea. The major goal of GAN is to generate new samples that estimate the potential distribution of real data. Due to itshuge success, many modified versions have been proposed in the last two years. We summarize in this review paperGAN’s background, architecture and its application fields. Then, we discuss the different extensions of GAN over theoriginal model and provide a comparative analysis of these techniques.
展开▼
