In a standard GAN architecture, how many neural networks are used ?
2023
In a standard GAN architecture, how many neural networks are used ?
- A.
Two
- B.
One
- C.
Three
- D.
Four
Attempted by 96 students.
Show answer & explanation
Correct answer: A
The correct answer is Option A: Two. A standard Generative Adversarial Network (GAN) architecture consists of exactly two neural networks training simultaneously: the Generator, which creates realistic fake data from random noise, and the Discriminator, which evaluates the data to distinguish between real data and the generator's fake data.