GenAIWiki
Deep Learning

generative-adversarial-networks

A class of machine learning frameworks that generate new data samples via adversarial training.

Expanded definition

Generative Adversarial Networks (GANs) consist of two neural networks, a generator and a discriminator, that compete against each other in a game-theoretic framework. The generator creates new data samples, while the discriminator evaluates their authenticity. This framework excels in generating realistic images, text, and audio. A misconception is that GANs can only generate realistic images; they can also be used for diverse applications including video generation and data augmentation.

Related terms

Explore adjacent ideas in the knowledge graph.

generative-adversarial-networks FAQ

What is generative-adversarial-networks?

A class of machine learning frameworks that generate new data samples via adversarial training.

How is generative-adversarial-networks used in AI systems?

Generative Adversarial Networks (GANs) consist of two neural networks, a generator and a discriminator, that compete against each other in a game-theoretic framework. The generator creates new data samples, while the discriminator evaluates their authenticity. This framework excels in generating realistic images, text, and audio. A misconception is that GANs can only generate realistic images; th...

Related

Comparisons, tools, and models that connect to this idea.