CS7643 Quiz 5 - P2 questions and answers 2026\2027 A+
Grade
Discriminative vs. Generative Models
- correct answer 1. Discriminative models model the conditional distribution, probability of label given
input P(y|x)
- NN, SVM, etc.
- No way to handle unreasonable outputs (i.e. if trained on cats and dog images, will always output a
label of cat or dog)
2. Generative Models model distribution over input space P(x)
- Can parameterize our model as P(x, theta) and use Maximum Likelihood Estimation to optimize the
parameters
- Called generative because they can generate samples
- Can "reject" unreasonable inputs as being too unlikely
- Feature Learning without labels
Explicit vs Implicit Density
- correct answer Explicit: Explicitly define and solve for Pmodel(x|θ), given an explicit likelihood that can
be maximized
Implicit: Learn a parameterized generation model that can sample from the joint distribution
Pmodel(x|θ) without explicitly defining Pmodel(x|θ)
Tractable Density Estimation
- correct answer - Explicit Density
- Simplify joint distribution into factorized model of simpler components and optimize with respect to
simpler components
, - PixelRNN/PixelCNN
Approximate Density Estimation
- correct answer - Learn distributions that approximate true joint distribution
- Variational Autoencoder
- We don't model density itself, but can sample from the distribution
- GAN
Implicit Density Estimation
- correct answer - We don't model density itself, but can sample from the distribution
- GAN
Factorized Models for Images Downsides
- correct answer 1. Slow sequential generation process
2. Only considers few context pixels
PixelRNN
- correct answer Explicit & Tractable
Uses chain rule to decompose the likelihood of an image x into a product of 1-d distributions
Similar to language models
Requires ordering of variables!
Training: pixel depends implicitly on the pixels above and to the left.
Generating: Generates pixels one at a time, very slow, only considers the pixels immediately adjacent
when generating
Grade
Discriminative vs. Generative Models
- correct answer 1. Discriminative models model the conditional distribution, probability of label given
input P(y|x)
- NN, SVM, etc.
- No way to handle unreasonable outputs (i.e. if trained on cats and dog images, will always output a
label of cat or dog)
2. Generative Models model distribution over input space P(x)
- Can parameterize our model as P(x, theta) and use Maximum Likelihood Estimation to optimize the
parameters
- Called generative because they can generate samples
- Can "reject" unreasonable inputs as being too unlikely
- Feature Learning without labels
Explicit vs Implicit Density
- correct answer Explicit: Explicitly define and solve for Pmodel(x|θ), given an explicit likelihood that can
be maximized
Implicit: Learn a parameterized generation model that can sample from the joint distribution
Pmodel(x|θ) without explicitly defining Pmodel(x|θ)
Tractable Density Estimation
- correct answer - Explicit Density
- Simplify joint distribution into factorized model of simpler components and optimize with respect to
simpler components
, - PixelRNN/PixelCNN
Approximate Density Estimation
- correct answer - Learn distributions that approximate true joint distribution
- Variational Autoencoder
- We don't model density itself, but can sample from the distribution
- GAN
Implicit Density Estimation
- correct answer - We don't model density itself, but can sample from the distribution
- GAN
Factorized Models for Images Downsides
- correct answer 1. Slow sequential generation process
2. Only considers few context pixels
PixelRNN
- correct answer Explicit & Tractable
Uses chain rule to decompose the likelihood of an image x into a product of 1-d distributions
Similar to language models
Requires ordering of variables!
Training: pixel depends implicitly on the pixels above and to the left.
Generating: Generates pixels one at a time, very slow, only considers the pixels immediately adjacent
when generating
