Definition
In deep learning, a generative adversarial network (Generative Adversarial Network) is an architecture made up of two neural networks that compete against each other: a generator that creates synthetic data from random noise and a discriminator that tries to distinguish real data from generated data. Adversarial training drives the generator to produce increasingly realistic samples.
Relationships
types-of / more specific
—
Concepts linked to this one by a real relationship in the glossary. Hover over each one to see why it's related.