GANs Introduction MCQ 15 Questions
Time: ~25 mins Advanced

GANs Introduction MCQ

Two networks play a game: one fakes data, the other judges—together they can synthesize realistic images.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Generator

z → image

Discriminator

Real vs fake

Min–max

Adversarial

Stability

Mode collapse

Generative adversarial networks

GANs train a generator G(z) to fool a discriminator D(x) that classifies real vs fake. The minimax objective leads to Nash equilibrium where samples match the data distribution at optimality (idealized). Practice requires balancing learning rates, architectures, and regularizers; mode collapse remains a classic failure mode.

The two-player game

D maximizes correct classification; G minimizes log(1−D(G(z))) or related objectives so fakes look real.

Key ideas

Generator

Maps noise z to samples in data space.

Discriminator

Scores real data high and fakes low.

Non-saturating G loss

Common reformulation so G gets stronger gradients early.

Mode collapse

G outputs limited variety; detectors see repeated patterns.

Training loop

Sample z → G(z) → update D on real/fake → update G to fool D

Pro tip: WGAN-GP, spectral norm, and progressive growing addressed many stability issues historically.