CS7643 – Deep Learning Quiz 7 Exam (2026) GRADED A+
Study Guide
Description:
Comprehensive A+ study guide for CS7643 Quiz 7 Exam (2026). Covers advanced deep
learning topics including transfer learning, generative models (GANs, VAEs), attention
mechanisms, and reinforcement learning basics. Includes concise summaries, key formulas, and
solved examples to help you fully understand and review core concepts. Perfect for mastering the
material and achieving top marks.
Tags: CS7643, Deep Learning, Quiz 7, 2026, GRADED A+, Machine Learning, Neural
Networks, Study Guide, Exam Preparation, College Notes
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 ✔✔✔✔✔ - Explicit
Density
- Learn distributions that approximate true joint distribution
- Variational Autoencoder
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
Pixel CNN - CORRECT ANSWER ✔✔✔✔✔ Idea: Represent conditional
distribution as a convolution layer
- Considers larger context (receptive field)
- Practically can be implemented by applying a mask, zeroing out "future" pixels
Disadvantages:
- Faster training, but still slow generation
- Limited to smaller images
PixelRNN and PixelCNN Recap - CORRECT ANSWER ✔✔✔✔✔ Explicit
density model, optimizes exact likelihood, good samples. But inefficient
sequential generation
Implicit Generative Models - CORRECT ANSWER ✔✔✔✔✔ - Don't learn an
explicit model for p(x)
- Instead learn to generate samples from p(x)
a. Learn good feature representations
b. Perform data augmentation
c. Learn world models (a simulator) for RL
How?
1. Learn to sample from a NN output
2. Adversarial Training that uses one network's prediction to train the other
(dynamic loss function)
Generative Adversarial Networks - CORRECT ANSWER ✔✔✔✔✔ 1. A
generator transforms a vector of random numbers to an image p(x)
2. A discriminator takes p(x) and a series of fake images and attempts to
determine if it's real or fake
Study Guide
Description:
Comprehensive A+ study guide for CS7643 Quiz 7 Exam (2026). Covers advanced deep
learning topics including transfer learning, generative models (GANs, VAEs), attention
mechanisms, and reinforcement learning basics. Includes concise summaries, key formulas, and
solved examples to help you fully understand and review core concepts. Perfect for mastering the
material and achieving top marks.
Tags: CS7643, Deep Learning, Quiz 7, 2026, GRADED A+, Machine Learning, Neural
Networks, Study Guide, Exam Preparation, College Notes
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 ✔✔✔✔✔ - Explicit
Density
- Learn distributions that approximate true joint distribution
- Variational Autoencoder
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
Pixel CNN - CORRECT ANSWER ✔✔✔✔✔ Idea: Represent conditional
distribution as a convolution layer
- Considers larger context (receptive field)
- Practically can be implemented by applying a mask, zeroing out "future" pixels
Disadvantages:
- Faster training, but still slow generation
- Limited to smaller images
PixelRNN and PixelCNN Recap - CORRECT ANSWER ✔✔✔✔✔ Explicit
density model, optimizes exact likelihood, good samples. But inefficient
sequential generation
Implicit Generative Models - CORRECT ANSWER ✔✔✔✔✔ - Don't learn an
explicit model for p(x)
- Instead learn to generate samples from p(x)
a. Learn good feature representations
b. Perform data augmentation
c. Learn world models (a simulator) for RL
How?
1. Learn to sample from a NN output
2. Adversarial Training that uses one network's prediction to train the other
(dynamic loss function)
Generative Adversarial Networks - CORRECT ANSWER ✔✔✔✔✔ 1. A
generator transforms a vector of random numbers to an image p(x)
2. A discriminator takes p(x) and a series of fake images and attempts to
determine if it's real or fake
