Generative Adversarial Networks MCQs
1. What is the primary objective of a Generative Adversarial Network (GAN)?
a) Image classification
b) Image generation
c) Text summarization
d) Text translation
Answer: b) Image generation
2. What are the two main components of a GAN?
a) Generator and encoder
b) Discriminator and encoder
c) Generator and discriminator
d) Encoder and discriminator
Answer: c) Generator and discriminator
3. Which component of a GAN is responsible for generating synthetic samples?
a) Generator
b) Discriminator
c) Encoder
d) Decoder
Answer: a) Generator
4. Which component of a GAN is responsible for distinguishing between real and generated samples?
a) Generator
b) Discriminator
c) Encoder
d) Decoder
Answer: b) Discriminator
5. What is the training process in a GAN called?
a) Supervised learning
b) Reinforcement learning
c) Unsupervised learning
d) Adversarial learning
Answer: d) Adversarial learning
6. How does the generator component in a GAN learn to generate realistic samples?
a) By minimizing the loss function of the discriminator
b) By maximizing the loss function of the discriminator
c) By minimizing the loss function of the generator
d) By maximizing the loss function of the generator
Answer: c) By minimizing the loss function of the generator
7. How does the discriminator component in a GAN learn to distinguish between real and generated samples?
a) By minimizing the loss function of the generator
b) By maximizing the loss function of the generator
c) By minimizing the loss function of the discriminator
d) By maximizing the loss function of the discriminator
Answer: c) By minimizing the loss function of the discriminator
8. Which loss function is commonly used in GANs?
a) Cross-entropy loss
b) Mean squared error loss
c) Binary logistic loss
d) Kullback-Leibler divergence
Answer: c) Binary logistic loss
9. What is mode collapse in GANs?
a) When the generator produces limited variations of samples
b) When the discriminator fails to distinguish between real and generated samples
c) When the GAN training process becomes unstable
d) When the generator and discriminator achieve perfect equilibrium
Answer: a) When the generator produces limited variations of samples
10. What is the purpose of noise input in the generator component of a GAN?
a) To randomize the generation process and introduce variations
b) To control the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To randomize the generation process and introduce variations
11. What is the role of the discriminator in a GAN during the training process?
a) To provide feedback to the generator and help it improve
b) To generate synthetic samples
c) To adjust the learning rate during training
d) None of the above
Answer: a) To provide feedback to the generator and help it improve
12. Which technique can be used to stabilize GAN training and address mode collapse?
a) Wasserstein GAN
b) Conditional GAN
c) Progressive GAN
d) All of the above
Answer: d) All of the above
13. What is the purpose of the latent space in a GAN?
a) To represent the high-dimensional space of real samples
b) To control the diversity and characteristics of generated samples
c) To adjust the learning rate during training
d) None of the above
Answer
: b) To control the diversity and characteristics of generated samples
14. Which type of GAN is designed to generate samples conditioned on specific input information?
a) Unconditional GAN
b) Wasserstein GAN
c) Progressive GAN
d) Conditional GAN
Answer: d) Conditional GAN
15. What is the purpose of the reconstruction loss in a GAN with an encoder component?
a) To encourage the encoder to produce meaningful latent representations
b) To control the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To encourage the encoder to produce meaningful latent representations
16. Which GAN architecture uses a stack of generators and discriminators to progressively generate higher-resolution samples?
a) Unconditional GAN
b) Wasserstein GAN
c) Progressive GAN
d) Conditional GAN
Answer: c) Progressive GAN
17. How does the training process of a GAN typically work?
a) The generator and discriminator are trained alternately
b) The generator and discriminator are trained simultaneously
c) The generator is trained first, followed by the discriminator
d) The discriminator is trained first, followed by the generator
Answer: b) The generator and discriminator are trained simultaneously
18. Which technique can be used to improve stability and prevent vanishing gradients in GAN training?
a) Batch normalization
b) Dropout
c) Weight regularization
d) All of the above
Answer: d) All of the above
19. What is the purpose of the evaluation metrics in GANs?
a) To measure the quality and diversity of generated samples
b) To adjust the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To measure the quality and diversity of generated samples
20. Which technique can be used to generate high-quality images in GANs?
a) Style-based GAN
b) Deep Convolutional GAN (DCGAN)
c) Wasserstein GAN (WGAN)
d) All of the above
Answer: d) All of the above
21. What is the purpose of the Wasserstein distance in Wasserstein GANs?
a) To measure the similarity between real and generated samples
b) To adjust the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To measure the similarity between real and generated samples
22. Which loss function is commonly used in Wasserstein GANs?
a) Cross-entropy loss
b) Mean squared error loss
c) Wasserstein loss
d) Kullback-Leibler divergence
Answer: c) Wasserstein loss
23. What is the purpose of the feature matching technique in GANs?
a) To encourage the generator to match the statistics of real samples
b) To control the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To encourage the generator to match the statistics of real samples
24. Which GAN architecture uses a multi-level hierarchy of generators and discriminators?
a) StyleGAN
b) Deep Convolutional GAN (DCGAN)
c) Wasserstein GAN (WGAN)
d) All of the above
Answer: a) StyleGAN
25. What is the purpose of the conditional input in a conditional GAN?
a) To control the characteristics of generated samples
b) To adjust the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To
control the characteristics of generated samples
26. Which GAN architecture is known for its ability to generate realistic and diverse images?
a) Progressive GAN
b) StyleGAN
c) Wasserstein GAN (WGAN)
d) All of the above
Answer: d) All of the above
27. What is the purpose of the adversarial loss in GANs?
a) To encourage the generator to produce samples that deceive the discriminator
b) To control the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To encourage the generator to produce samples that deceive the discriminator
28. Which technique can be used to address the problem of mode collapse in GANs?
a) Gradient penalty
b) Batch normalization
c) Dropout
d) All of the above
Answer: a) Gradient penalty
29. What is the purpose of the discriminator regularization in GANs?
a) To prevent overfitting of the discriminator
b) To control the learning rate during training
c) To adjust the weights and biases of the generator
d) None of the above
Answer: a) To prevent overfitting of the discriminator
30. Which GAN architecture is designed for text generation tasks?
a) TextGAN
b) StyleGAN
c) Wasserstein GAN (WGAN)
d) All of the above
Answer: a) TextGAN