Generative Adversarial Networks (GAN) is designed as an unsupervised learning model that refers to the process of automatically identifying and learning the regularities or patterns in input data, and then the model generates new examples from the original dataset. The primary function of GANs is to learn from the input training data and generate new data set with the same characteristics as the training data. The significance of GANs is the ability to model high-dimensional data, the capability of handling missing data, and the capacity to produce multi-modal outputs. The GAN model contains two sub-models include a generator model for generating new examples and a discriminator model for classifying whether generated examples are real from the domain or not. The training for both neural network models is performed simultaneously. The algorithm architecture of GAN contains two neural networks that are set against one another in order to generate new, false instances of data that can pass for real data. Types of GAN are categorized based on architectural optimization and objective function optimization. Such categories are Conditional GAN, Convolutional GAN, Autoencoders, Wasserstein GAN, and many more. GAN is an indirect training method due to discriminator, which is updated dynamically by itself. GANs consists of multiple discriminators and generator such as MD-GAN (Multiple Discriminator Generative Adversarial Network), SGAN (Semi-Supervised Adversarial Network), and many more. GAN automatically generates 3D models required in video games, animated movies, or cartoons. Other popular applications of GAN are image generation, image Image translation, Handwritten font generation, Voice generation, healthcare, Generation of new human poses and realistic photographs, Face aging, Image-to-Image Translation, Text-to-Image Translation, Semantic-Image-to-Photo Translation, Face Frontal View Generation. Future advancements of GANs are Steganalysis, information retrieval, Spatio-temporal data prediction, such as transportation, autonomous driving, speech enhancement, single-cell RNA-sequence imputation, and another new research direction is GANs for ethics in AI.