Deep Learning and Reinforcement Learning Week 8
Course Name: Deep Learning and Reinforcement Learning
Course Link: Deep Learning and Reinforcement Learning
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
Practice: Variational Autoencoders
Q1. (True/False) A common characteristic of both Autoencoders and Variational Autoencoders is that both have one neural network for encoding and another one for decoding.
True
False
Answer: True
Q2. These are all additional steps that you need to consider when using Variational Autoencoders, except:
Incorporate a logarithmic term into the loss function
Use binary crossentropy
Remove a KL loss function
Consider parameters within a distribution
Answer: Remove a KL loss function
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
Q3. Choose the right assertion in the context of comparing the reconstruction error of Autoencoders and Variational Autoencoders:
The reconstruction error of variational autoencoders can be higher because variational autoencoders are designed to maximize the interpretability of the latent space, not to minimize the reconstruction error.
The reconstruction error of variational autoencoders can be lower because variational autoencoders are designed to maximize the interpretability of the latent space, not to minimize the reconstruction error.
The reconstruction error of autoencoders can be lower because autoencoders are designed to maximize the interpretability of the latent space, not to minimize the reconstruction error.
The reconstruction error of autoencoders can be higher because autoencoders are designed to maximize the interpretability of the latent space, not to minimize the reconstruction error.
Answer: The reconstruction error of variational autoencoders can be higher because variational autoencoders are designed to maximize the interpretability of the latent space, not to minimize the reconstruction error.
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
Practice: Generative Adversarial Networks
Q1. The development of Generative Adversarial Networks was motivated, in part, by
the need for faster computation across multiple platforms.
the need to simultaneously generate differing types of output.
the vulnerability of standard Deep Learning approaches to input manipulation.
the inability of standard Deep Learning approaches to implement backpropagation.
Answer: the vulnerability of standard Deep Learning approaches to input manipulation.
Q2. (True/False) GANs are a way of training two neural networks simultaneously.
True
False
Answer: True
Q3. (True/False) GANs are probably behind some applications like FaceApp and applications that can make you look older.
True
False
Answer: True
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
Final Quiz
Q1. Select the right assertion:
Autoencoders learn from a compressed representation of the data, while variational autoencoders learn from a probability distribution representing the data.
Variational autoencoders learn from a compressed representation of the data, while autoencoders learn from a probability distribution representing the data.
Autoencoders and Principal Component Analysis can be used interchangeably.
Answer: Autoencoders learn from a compressed representation of the data, while variational autoencoders learn from a probability distribution representing the data.
Q2. (True/False) Variational autoencoders are generative models.
True
False
Answer: True
Q3. When comparing the results of Autoencoders and Principal Component Analysis, which approach might best improve the results from Autoencoders?
Add labels to the data
Add layers and epochs
Add a Variational Autoencoder
Reduce the dimensions of the data
Answer: Add layers and epochs
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
Q4. (True/False) KL loss is used in Variatoinal Autoencoders to represent the measure of the difference between two distributions.
True
False
Answer: True
Q5. A good way to compare the inputs and outputs of a Variational Autoencoder is to calculate the mean of a reconstruction function based on binary crossentropy.
True
False
Answer: True
Q6. The main parts of GANs architecture are:
loss error and random noise
generated and adversarial neurons
adversarial and non adversarial neurons
generator and discriminator
Answer: generator and discriminator
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
Q7. (True/False) One of the main advantages of GANs over other adversarial networks is that it does not spend any time evaluating whether an input or image is fake or real. It only computes probability of being fake.
True
False
Answer: True
These are answers of Deep Learning and Reinforcement Learning Week 8 Quiz
More Weeks of this course: Click Here
More Coursera Courses: http://progiez.com/coursera
| The content uploaded on this website is for reference purposes only. Please do it yourself first. |