Caesar AI Atlas

Discriminator

Caesar AI Atlas Definition

A discriminator is a system or model component that distinguishes real examples from generated or fake examples. In a generative adversarial network, it evaluates outputs from the generator and provides a training signal that helps improve generated samples.

Other Definitions

Discriminator Source

A system that determines whether examples are real or fake. Alternatively, the subsystem within a generative adversarial network that determines whether the examples created by the generator are real or fake. See The discriminator in the GAN course for more information.

Related Terms

Generative Adversarial NetworkGeneratorOutputsWasserstein LossAdversarial LearningGenerative Model