Deep Learning Generative Models 2

Question 1

What is an autoencoder and what are its two main components?

Accepted Answer

A neural network that compresses input to a low-dimensional latent code and reconstructs it; encoder and decoder

Answer

An autoencoder maps input to a compressed latent representation via the encoder and reconstructs the input from that representation via the decoder, learning compact data representations.

Question 2

What is the Wasserstein GAN (WGAN) designed to address?

Accepted Answer

Training instability and mode collapse by using the Wasserstein distance as a more stable loss

Answer

WGAN replaces the standard GAN loss with the Wasserstein distance (Earth Mover's distance), providing more meaningful gradients even when generator and real distributions don't overlap.

Question 3

What is conditional generation in generative models?

Accepted Answer

Conditioning the generative process on a label or other input to control the attributes of generated samples

Answer

Conditional generation feeds class labels, text prompts, or other conditioning signals to the generative model, enabling control over the category or attributes of generated outputs.

Question 4

What is latent space interpolation in generative models?

Accepted Answer

Smoothly traversing the latent space between two encoded points to generate intermediate samples

Answer

Latent space interpolation linearly or spherically blends two latent vectors and decodes the intermediate points, producing samples that smoothly transition between the two originals.

Question 5

What is the key property of flow-based generative models such as RealNVP?

Accepted Answer

They learn invertible transformations allowing exact likelihood computation and efficient sampling in both directions

Answer

Flow-based models use a series of invertible (bijective) transformations with tractable Jacobians, enabling exact log-likelihood evaluation and straightforward sampling by inverting the flow.

Deep Learning Practice Test

Deep Learning Practice Test

Deep Learning Generative Models 2