SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-gan-generator-discriminator

Which two models compete in a generative adversarial network?

A generator competes with a discriminator.

Start playing free

  1. An encoder and tokenizer
  2. Two identical optimizers
  3. A generator and discriminator ✔

Why: The generator produces samples intended to resemble the data. The discriminator estimates whether a sample came from real training data or from the generator.

Huh, didn't know that: The generator is trained to increase the discriminator's mistakes, creating a two-player minimax game.

The dad joke
The generator made art, and the discriminator became a tough critic.
Like this card?
Play the game

References

Answer: A generator and discriminator. The generator produces samples intended to resemble the data. The discriminator estimates whether a sample came from real training data or from the generator.

  1. Generative Adversarial Nets papers.nips.cc/paper/2014/hash/f033ed80deb0234979a61f95710dbe25-Abstract.html
    a generative model G that captures the data distribution, and a discriminative model D
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceHow do AI, machine learning and deep learning fit together?Artificial IntelligenceWhat did Alan Turing call his 1950 test of machine intelligence?Artificial IntelligenceTuring predicted that by about 2000, judges would ID the machine at most what percent of the time?

That's stuff everyone should know.