AIExplainer

What is generative adversarial network?

A type of artificial intelligence algorithm that generates new data by competing with itself

Stands for: GAN

A generative adversarial network is a type of AI algorithm that consists of two parts: a generator and a discriminator. The generator creates new data, such as images or music, while the discriminator tries to distinguish between the generated data and real data. Through this competition, the generator improves and can produce highly realistic data.

Imagine a counterfeiter trying to create fake money, and a detective trying to detect the fake money. The counterfeiter gets better at making fake money, and the detective gets better at detecting it. Eventually, the counterfeiter can make fake money that is almost indistinguishable from real money.

The AI-generated portrait 'Edmond de Belamy' was created using a generative adversarial network and sold at Christie's auction house for $432,500.

Generative adversarial networks are used in a variety of applications, including generating realistic images and videos, creating new music and art, and even generating text.

Some people think that generative adversarial networks are only used for creating fake or misleading content, but they can also be used for positive applications such as generating new ideas for art, music, and design.

Generative adversarial networks were first introduced in a 2014 paper by Ian Goodfellow and his colleagues.

adversarial network neural network generator deep generative model

Three products for different needs — explore what’s relevant to you.