In a Generative Adversarial Network (GAN), which component is trained to identify whether an image is real or synthetic?
Show answer
Discriminator
The discriminator acts as a binary classifier, while the generator tries to create data that the discriminator will mistake for real. The two networks are trained simultaneously in a minimax game until the generator produces realistic outputs.
Also asked as:
- In the context of a GAN, which network acts as a binary classifier to distinguish between real data and synthetic data produced by the generator?