Generative Adversarial Network (GAN): a general review on different variants of GAN and applications

Deep learning plays a very important role in the research area in the field of Artificial Intelligence (AI) and Machine Learning (ML) and many models have been developed based on GAN applications. Generative Adversarial Networks (GAN) is an unsupervised learning method which is based on a very popular logic known as zero-sum game theory for two players. The main objective of Generative Adversarial Networks is to calculate the distribution of original samples using discriminator and the work of Generator is to generate new samples from the real data samples. In current years, Generative Adversarial Networks (GAN) has made big development essentially withinside the area of computer vision, image classification, speech and language processing and so on. The paper explains about the basic introduction of GAN and different types of GAN were introduced with its applications. Original GAN version and its changed classical variations has been surveyed. The problems and limitations of GAN and the future work of GAN models were discussed.