GAN (Generative Adversarial Network)

A GAN consists of two neural networks: a generator and a discriminator. The generator creates synthetic data, while the discriminator attempts to distinguish generated examples from real ones. During training, both networks improve through competition, allowing the generator to gradually produce increasingly realistic outputs such as images, audio, or other forms of data.

GANs enable AI systems to generate highly realistic synthetic content and learn complex data distributions. They have played an important role in generative AI research and can help create additional training data when real-world data is limited, expensive, or difficult to obtain.