Generative Adversarial Networks (GANs) is a type of deep neural network architecture that utilizes unsupervised machine learning to generate data. They were presented in 2014, in a paper by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. This paper will introduce the core components of GANs. This will take you through how every part function and the significant ideas and innovation behind GANs. It will likewise give a short outline of the advantages and downsides of utilizing GANs, comparison of architectures of various GANs and knowledge into certain true applications.