A generative model is trained to match a data distribution by competing in a minimax game against a discriminator, reaching an equilibrium where the generator recovers the true distribution and the discriminator outputs 1/2 everywhere.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2014 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Generative Adversarial Networks
A generative model is trained to match a data distribution by competing in a minimax game against a discriminator, reaching an equilibrium where the generator recovers the true distribution and the discriminator outputs 1/2 everywhere.