Scribd
Upload
37 views3 pages

Deep Learning - IIT Ropar - Unit 9 - Week 6

Uploaded by

vmcse09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
37 views3 pages

Deep Learning - IIT Ropar - Unit 9 - Week 6

Uploaded by

vmcse09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

(https://swayam.gov.in) (https://swayam.gov.in/nc_details/NPTEL)

[email protected]

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

Course Week 6 : Assignment 6


outline The due date for submitting this assignment has passed.
Due on 2024-09-04, 23:59 IST.
About
NPTEL ()
Assignment submitted on 2024-08-31, 15:24 IST
How does an 1) We are given an autoencoder A. The average activation value of neurons in this 1 point
NPTEL network is 0.01. The given autoencoder is
online
course Contractive autoencoder
work? () Overcomplete neural network
Denoising autoencoder
Week 1 ()
Sparse autoencoder

Week 2 () Yes, the answer is correct.


Score: 1
Week 3 () Accepted Answers:
Sparse autoencoder

week 4 ()
2) If an under-complete autoencoder has an input layer with a dimension of 7, what 1 point
Week 5 () could be the possible dimension of the hidden layer?

6
Week 6 ()
8
Introduction to 0
Autoncoders
7
(unit?
unit=83&lesso 2
n=84) Yes, the answer is correct.
Score: 1
Link between
Accepted Answers:
PCA and
6
Autoencoders
(unit? 2

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=83&assessment=294 1/3
10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

unit=83&lesso 3) What type of autoencoder is it when the hidden layer’s dimensionality is less than 1 point
n=85) that of the input layer?
Regularization
Under-complete autoencoder
in
autoencoders Complete autoencoder
(Motivation) Overcomplete autoencoder
(unit?
Sparse autoencoder
unit=83&lesso
n=86) Yes, the answer is correct.
Score: 1
Denoising Accepted Answers:
Autoencoders Under-complete autoencoder
(unit?
unit=83&lesso
4) What is the purpose of a decoder in an autoencoder? 1 point
n=87)

Sparse To reconstruct the input data


Autoencoders To generate new data
(unit?
To compress the input data
unit=83&lesso
n=88) To extract features from the input data

Contractive Yes, the answer is correct.


Score: 1
Autoencoders
(unit? Accepted Answers:
unit=83&lesso To reconstruct the input data
n=89)
5) What are the advantages of using a denoising autoencoder? 1 point
Lecture
Material for Robustness to noisy input data
Week 6 (unit?
unit=83&lesso
Reduction of the risk of overfitting
n=90) Faster training time

Quiz: Week 6
It promotes sparsity in the hidden layer
: Assignment Yes, the answer is correct.
6 Score: 1
(assessment? Accepted Answers:
name=294) Robustness to noisy input data
Reduction of the risk of overfitting
Week 6
Feedback
Form: Deep 6) We are given an autoencoder A. The average activation value of neurons in this 1 point
Learning - IIT network is 0.06. The given autoencoder is:
Ropar (unit?
unit=83&lesso Contractive autoencoder
n=235) Overcomplete neural network

Week 7 () Sparse autoencoder


Denoising autoencoder
Week 8 () Yes, the answer is correct.
Score: 1
Week 9 () Accepted Answers:
Sparse autoencoder
week 10 ()
7) If the dimension of the input layer in an over-complete autoencoder is 5, what is the 1 point
Week 11 () possible dimension of the hidden layer?

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=83&assessment=294 2/3
10/27/24, 1:13 PM Deep Learning - IIT Ropar - - Unit 9 - Week 6

Week 12 () 4
2
Download 8
Videos ()
0

Books () Yes, the answer is correct.


Score: 1
Accepted Answers:
Text 8
Transcripts
() 8) What are the possible applications of autoencoders? 0 points

Problem Data Compression


Solving Extraction of important features
Session - Reducing noise
July 2024 ()
All of these

Yes, the answer is correct.


Score: 0
Accepted Answers:
All of these

9) Which of the following problems prevents us from using autoencoders for the task of1 point
Image compression?

Images are not allowed as input to autoencoders


Difficulty in training deep neural networks
Loss of image quality due to compression
Auto encoders are not capable of producing image output
Yes, the answer is correct.
Score: 1
Accepted Answers:
Loss of image quality due to compression

10) Which of the following is a potential advantage of using an overcomplete 1 point


autoencoder?

Reduction of the risk of overfitting


Ability to learn more complex and nonlinear representations
Faster training time
To compress the input data

Yes, the answer is correct.


Score: 1
Accepted Answers:
Ability to learn more complex and nonlinear representations

https://onlinecourses.nptel.ac.in/noc24_cs114/unit?unit=83&assessment=294 3/3

You might also like