Generative Adversarial Networks

E59296

deep generative model machine learning model architecture

Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.

Aliases (5)

Statements (62)

Predicate	Object
instanceOf	deep generative model → machine learning model architecture →
abbreviation	GANs →
application	anomaly detection → data augmentation → domain adaptation → image synthesis → image-to-image translation → speech synthesis → style transfer → super-resolution → text-to-image generation → video generation →
basedOn	adversarial training →
challenge	mode collapse → non-convergence → training instability →
discriminatorGoal	distinguish real from fake samples →
ethicalConcern	deepfakes → synthetic media misuse →
evaluationMetric	FID → Fréchet Inception Distance → Inception Score →
field	artificial intelligence → deep learning → machine learning →
generatorGoal	fool the discriminator →
hasComponent	discriminator network → generator network →
inputToDiscriminator	generated samples → real samples →
inputToGenerator	random noise vector →
inspiredBy	game theory → two-player zero-sum games →
introducedAtConference	NeurIPS 2014 →
introducedBy	Ian Goodfellow →
introducedInPublication	Generative Adversarial Nets →
introducedInYear	2014 →
lossFunction	adversarial loss →
notableVariant	Conditional GAN → CycleGAN → DCGAN → Deep Convolutional GAN → Progressive GAN → StyleGAN → WGAN → Wasserstein GAN → cGAN →
objective	generate realistic synthetic samples → learn data distribution →
optimizationMethod	minimax game → stochastic gradient descent →
outputOfGenerator	synthetic sample →
representation	latent space →
subfieldOf	generative modeling →
trainingType	self-supervised learning → unsupervised learning →
typicalDataType	audio → images → text → video →
uses	neural networks →

Referenced by (7)

Subject (surface form when different)	Predicate
Ian Goodfellow → Ian Goodfellow ("GANs") →	knownFor
Generative Adversarial Networks ("DCGAN") → Generative Adversarial Networks ("cGAN") →	notableVariant
Generative Adversarial Networks ("GANs") →	abbreviation
Generative Adversarial Networks ("Generative Adversarial Nets") →	introducedInPublication
Ian Goodfellow ("Generative Adversarial Network") →	notableConcept