DCGAN: Deep Convolutional Generative Adversarial Network

GAN is Generative Adversarial Network having two neural networks: Generator and Discriminator that are pitted against each other and are simultaneously trained by an adversarial process. Generator: learns to generate plausible data that is very similar to the training data. Data generated from the Generator should be indistinguishable from the real data. Discriminator: the key objective is to distinguish between the generator's fake data from the real data and is a simple classification network. The Generator acts like a forger trying to trick the Discriminator by generating fake data.