2 docs tagged with "gan"

GANs are famously hard to train, and the failure modes are specific and recognisable. Worse: the standard debugging instinct — watch the loss curve — actively misleads here.

Every generative model so far has needed an explicit loss function measuring "how good is this sample." GANs replace that explicit loss with a second trained network, whose entire job is to learn what "real" looks like — and the generator improves purely by trying to fool it.