Skip to content
BENIBIX Learn

Generative Adversarial Network (GAN)

AI📈 Machine LearningNeural Networks

Also known as GAN

Two networks in a contest. One makes fakes, the other tries to catch them.

Think of it like

Think of it like a cop and a fake coin maker. The coins get better until the cop is fooled.

Example

A game studio trains a GAN on 50,000 photos of stone walls. The generator learns to make new wall patterns that never existed.

Why it matters

GANs were the first method to make truly lifelike fake images. They showed what generative AI could do.

Definition

A generative adversarial network is two neural networks that train by competing. One, the generator, makes fake examples, like fake photos of faces. The other, the discriminator, tries to tell fake from real. Each time one wins, the other learns from it. In the end, the fakes look real.
The generator makes a fake. The discriminator judges it next to real photos. Both learn from the result.

Common mistake

Expecting training to go smoothly. The two networks can get stuck, and the generator may make only a few kinds of output.

Key takeaways

  1. 1
    Two networks. A maker and a judge.
  2. 2
    They compete. Each learns from the other.
  3. 3
    Fakes get real. Until the judge is fooled.

Compare

Learn it properly