À suivreGuide suivant
Réseaux de neurones graphiques
Fondamentaux
GUIDE des fondamentaux
Generative adversarial networks train a generator against a discriminator.
Écoutez ce guideNarré par l'IA · ~3 min
The generator produces synthetic samples while the discriminator learns to distinguish generated samples from training examples; successful learning is not guaranteed by this competition.
Ian Goodfellow and colleagues introduced the GAN framework in 2014. In the original unconditional formulation, a generator maps sampled latent noise into synthetic data. A discriminator receives real training examples and generated samples, learning to distinguish their origins. The generator receives gradients through the discriminator and aims to make its outputs harder to distinguish. This original setup should not be generalized into a claim that every GAN generator is forbidden from receiving real images. Conditional and image-to-image formulations can provide other inputs: the pix2pix research, for example, learns mappings from input images to target images with paired training data. Practical GAN training can be difficult. Mode collapse describes inadequate variety when a generator concentrates on a limited range of outputs; realistic individual samples do not establish that the intended distribution is represented. The original theoretical analysis describes an ideal distribution-matching equilibrium. When the generator distribution matches the data distribution, the optimal discriminator assigns probability one-half to either origin. That result depends on the theoretical setup and does not guarantee convergence of a finite trained system. Conditioning adds another distinction. In the conditional GAN formulation by Mirza and Osindero, information such as a class label can be supplied to both generator and discriminator. It specifies the condition being modeled, while the generated content can still vary. A conventional feed-forward generator can produce a sample in one forward evaluation, but comparisons of latency or quality with another model must identify the actual architecture and workload.
Studying an unconditional generator that maps sampled latent noise into images.
Training a conditional GAN with class information supplied to both networks.
Using paired input and target images in an image-to-image translation experiment.
Comparing the diversity of generated samples with the intended data distribution.
Adversarial objectives can be investigated alongside other generative approaches for particular tasks. Evaluation should measure both sample quality and variety, and explain the data and conditioning used. A one-pass generator can be compared with an iterative sampler on a specified device and output size, while neither the network family nor the number of evaluations alone establishes universal speed or quality superiority. Research can examine training behavior and conditional control without treating plausible samples as proof of faithful distribution coverage.
Newsletter gratuite
Trois histoires d'IA vérifiées chaque matin de la semaine, écrites dans un anglais simple. Gratuit pour toujours, sans publicité.
Un e-mail chaque jour de la semaine. Désabonnez-vous en un clic. Nous ne vendons ni ne partageons jamais votre adresse.
Testez-vous
Commentaires instantanés sur chaque réponse et un certificat partageable avec une pièce d'identité vérifiable une fois que vous avez réussi un cours.
Soutenez l’enseignement gratuit de l’IA. AI Understanding est une organisation à but non lucratif 501(c)(3) : pas de publicité, pas de paywall, jamais. Faire un don
Generative adversarial networks train a generator against a discriminator. The generator produces synthetic samples while the discriminator learns to distinguish generated samples from training examples; successful learning is not guaranteed by this competition.
Un GAN associe un générateur, qui crée de faux échantillons, à un discriminateur, qui tente de distinguer les données réelles des faux du générateur.
The original unconditional generator maps a sampled latent variable into generated data; conditional variants can receive additional inputs.
Differentiating through the discriminator supplies a generator learning signal; other inputs and losses are possible in later GAN variants.
L'effondrement des modes se produit lorsque le générateur trouve quelques sorties qui trompent le discriminateur et continue de les produire, perdant ainsi de la diversité.
The original paper lists Goodfellow and coauthors and was submitted in 2014.
Continuez à apprendre
Plus de guides sélectionnés pour ce sujet
À suivreGuide suivant
Réseaux de neurones graphiques
Fondamentaux