NPTEL Online Certification Courses

Indian Institute of Technology Kharagpur

Deep Learning
Assignment- Week 7
TYPE OF QUESTION: MCQ/MSQ
Number of questions: 10 Total mark: 10 X 1 = 10
______________________________________________________________________________

QUESTION 1:
What is the main advantage of layer-by-layer pre-training for deep autoencoders?

a. It reduces the total number of weights and simplifies the optimization process
b. It provides better initial weight values for the entire network
c. It allows for parallel training of different hidden layers.
d. It guarantees perfect reconstruction of the input data with minimal error.

Correct Answer: b

Detailed Solution:

Layer by layer training requires serial training, doesn’t reduces weights and doesn’t
guarantee minimal reconstruction error.

______________________________________________________________________________

QUESTION 2:
Select the correct option about Denoising autoencoders?

Statement A: The loss is between the original input and the reconstruction from a noisy version
of the input

Statement B: Denoising autoencoders can be used as a tool for feature extraction.

a. Both the statements are false

b. Statement A is false but Statement B is true
c. Statement A is true but Statement B is false
d. Both the statements are true

Correct Answer: d

Detailed Solution:

For denoising autoencoder, both statement 1 and 2 are true. Thus option (d) is correct
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

______________________________________________________________________________

QUESTION 3:
Which of the following is a linear operator?

a. Sigmoid
b. Rectified Linear Unit
c. Convolution function
d. None of the above

Correct Answer: c

Detailed Solution:

Convolution is a linear operator.

______________________________________________________________________________

QUESTION 4:
Which statement is TRUE about deep autoencoders?

a. They have a single hidden layer for representing the latent space.
b. They have few parameters compared to shallow autoencoders.
c. They excel at capturing complex relationships and features in high-dimensional
data.
d. They require supervised learning with labeled data for training.

Correct Answer: c

Detailed Solution:

Refer to classroom lecture.

 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 5:

Which of the following is false about autoencoder?

a. Autoencoders possesses generalization capabilities

b. Autoencoders are best suited for image captioning task
c. Its objective is to minimize the reconstruction loss so that output is similar to
input
d. It compresses the input into a latent space representation and then reconstruct
the output from it

Correct Answer: b

Detailed Solution:

Except option (b), rest all the options are true about autoencoders

____________________________________________________________________________

QUESTION 6:
Which of the following is true for Contractive Autoencoders?

a. penalizing instances where a small change in the input leads to a large change in
the encoding space
b. penalizing instances where a large change in the input leads to a small change in
the encoding space
c. penalizing instances where a small change in the input leads to a small change in
the encoding space
d. None of the above

Correct Answer: a

Detailed Solution:

Direct from definition of Contractive autoencoders

_____________________________________________________________________________
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 7:
Impulse response is the output of ________________system due to impulse input applied at
time=0. Fill in the blanks from the options below.

a. Linear
b. Time Varying
c. Time Invariant
d. Linear And Time Invariant

Correct Answer: d

Detailed Solution:

Impulse response is output of LTI system due to impulse input pplied at time t=0 or n=0.
Behaviour of an LTI system is characterized by its impulse response .

_________________________________________________________________________

QUESTION 8:
The Dirac delta function is ___ when t=0. Fill in the blanks.

a. 1
b. 0
c. Infinity
d. None of the above

Correct Answer: c

Detailed Solution:

Self-explainable from the definition of Dirac delta function

______________________________________________________________________________
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 9:
Given the image below where, Row 1: Original Input, Row 2: Noisy input, Row 3: Reconstructed
output. Choose one of the following variants of autoencoder that is most suited to get Row 3
from Row 2.

a. Stacked autoencoder
b. Sparse autoencoder
c. Denoising autoencoder
d. None of the above

Correct Answer: c

Detailed Solution:
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Reconstruction of original noise-free data from noisy input is the tasks of denoising
autoencoder

____________________________________________________________________________

QUESTION 10:
Which application of deep autoencoders utilizes the extracted latent space representation?

a. Anomaly detection by comparing data points to the known latent space

distribution.
b. Image segmentation by classifying individual pixels based on their latent
features.
c. Pre-training for other deep learning models like convolutional neural networks.
d. All of the above.

Correct Answer: d

Detailed Solution:

Direct from Lectures

______________________________________________________________________________

************END*******