Concept
Generator
The generator is the neural network in a GAN that maps a random noise vector to a synthetic sample meant to pass as real. Think of it like a decoder in an autoencoder, except it is never shown real data directly and gets no reconstruction target.
The rest of “Generator” 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→