2/28/25, 11:54 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

Assessment submitted.
(https://swayam.gov.in) (https://swayam.gov.in/nc_details/NPTEL)
X

rohit.ece.21@nitap.ac.in 

NPTEL (https://swayam.gov.in/explorer?ncCode=NPTEL) » Deep Learning - IIT Ropar (course)


Click to register
for Certification
exam
Thank you for taking the Week 6 :
Assignment 6.
(https://examform.nptel.ac.in/2025_01/exam_form/dashboard)

If already
registered, click
to check your
Week 6 : Assignment 6
payment status Your last recorded submission was on 2025-02-28, 23:53 Due date: 2025-03-05, 23:59 IST.
IST

1) What is/are the primary advantages of Autoencoders over PCA? 1 point

Course
outline Autoencoders are less prone to overfitting than PCA.
Autoencoders are faster and more efficient than PCA.
About Autoencoders require fewer input data than PCA.
NPTEL () Autoencoders can capture nonlinear relationships in the input data.

How does an 2) Which of the following is a potential advantage of using an overcomplete 1 point
NPTEL autoencoder?
online
course Reduction of the risk of overfitting
work? ()
Faster training time
Ability to learn more complex and nonlinear representations
Week 0 ()
To compress the input data
Week 1 ()
3) We are given an autoencoder A. The average activation value of neurons in this 1 point
Week 2 () network is 0.015. The given autoencoder is

Contractive autoencoder
Week 3 ()
Sparse autoencoder
week 4 () Overcomplete neural network
Denoising autoencoder
Week 5 ()
4) Suppose we build a neural network for a 5-class classification task. Suppose for a single
Week 6 () training example, the true label is [0 1 0 0 1] while the predictions by the neural network are [0.4

https://onlinecourses.nptel.ac.in/noc25_cs21/unit?unit=83&assessment=315 1/4
 2/28/25, 11:54 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

Introduction to 0.25 0.2 0.1 0.6]. What would be the value of cross-entropy loss for this example? (Answer up to
Assessment submitted. two decimal places, Use base 2 for log-related calculations)
Autoncoders
X (unit?
unit=83&lesso 2.74
n=84) 1 point

Link between 5) If an under-complete autoencoder has an input layer with a dimension of 5, what 1 point
PCA and could be the possible dimension of the hidden layer?
Autoencoders
(unit? 5
unit=83&lesso
4
n=85)
2
Regularization
0
in
autoencoders 6
(Motivation)
(unit? 6) Which of the following networks represents an autoencoder? 1 point
unit=83&lesso
n=86)

Denoising
Autoencoders
(unit?
unit=83&lesso
n=87)

Sparse
Autoencoders
(unit?
unit=83&lesso
n=88)

Contractive
Autoencoders
(unit?
unit=83&lesso
n=89)

Lecture
Material for
Week 6 (unit?
unit=83&lesso
n=90)

Week 6
Feedback
Form:Deep
Learning - IIT
Ropar!! (unit?
unit=83&lesso
n=235)

Quiz: Week 6
: Assignment
6
(assessment?
name=315)

https://onlinecourses.nptel.ac.in/noc25_cs21/unit?unit=83&assessment=315 2/4
 2/28/25, 11:54 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

Week
Assessment 7 ()
submitted.
X
Download
Videos ()

Books ()

Text
Transcripts
()

Problem
Solving
Session -
Jan 2025 ()

7) What is the primary reason for adding corruption to the input data in a denoising 1 point
autoencoder?

To increase the complexity of the model.

To improve the model's ability to generalize to unseen data.
To reduce the size of the training dataset.
To increase the training time.

8) Suppose for one data point we have features x 1 , x 2 , x 3 , x 4 , x 5 as 1 point

−4, 6, 2.8, 0, 17.3 then, which of the following function should we use on the output
layer(decoder)?

Linear
Logistic
Relu
Tanh

9) Which of the following statements about overfitting in overcomplete autoencoders is 1 point

true?

Reconstruction error is very high while training

Reconstruction error is very low while training
Network fails to learn good representations of input
Network learns good representations of input

https://onlinecourses.nptel.ac.in/noc25_cs21/unit?unit=83&assessment=315 3/4
 2/28/25, 11:54 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

Assessment submitted. 10) What is the purpose of a decoder in an autoencoder? 1 point

X
To reconstruct the input data
To generate new data
To compress the input data
To extract features from the input data

You may submit any number of times before the due date. The final submission will be
considered for grading.
Submit Answers

https://onlinecourses.nptel.ac.in/noc25_cs21/unit?unit=83&assessment=315 4/4