Concept
Discriminator
The discriminator is a classifier trained to distinguish real data from synthetic data produced by a generator. In the original GAN paper it is one half of the adversarial pair: D takes a sample and outputs a scalar probability that the sample came from the real…
The rest of “Discriminator” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→