GANs

Generative Adversarial Networks are a type of neural network architecture invented in 2014 by Ian Goodfellow and his collaborators. GANs are foundational to much of today’s AI image generation.

A GAN is made of two neural networks that play a game:

ComponentRole
Generator (G)Tries to create fake data that looks like real data (e.g., fake images).
Discriminator (D)Tries to tell real from fake — it acts like a critic or detective.

They train together:

  1. The generator creates an image.
  2. The discriminator decides if it’s fake or real.
  3. Feedback from the discriminator helps the generator improve.
  4. Over time, the generator gets so good the discriminator can’t tell the difference.

This is why it’s called adversarial — the two networks are in a constant battle.

GANs are unsupervised (or self-supervised) learning models — they don’t need labeled data.

They learn the distribution of training data and generate new data from that distribution.

Many improved GANs have been developed since 2014, including:

VariantPurpose
DCGAN (2015)Deep Convolutional GAN — popular for image generation
StyleGAN (2018–2021)Introduced “style” control — used in “This Person Does Not Exist”
CycleGANImage-to-image translation (e.g., horses ↔ zebras)
BigGANHigh-quality, class-conditional image generation (from ImageNet)