A Generative Adversarial Network (GAN) is a type of artificial intelligence model used to generate new data that resembles existing data. It consists of two main components: a generator that creates new samples and a discriminator that evaluates them. The generator tries to produce data that is indistinguishable from real data, while the discriminator attempts to differentiate between real and generated data. The two components work in opposition, hence the term "adversarial." As the generator improves its ability to create realistic data, the discriminator also becomes better at identifying fakes. This process continues until the generator produces high-quality outputs, making GANs useful in various applications, including image generation and data augmentation.