Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

25/05/2018 Deep Learning For Visual Computing - - Unit 13 - Week 12

[email protected]

Courses » Deep Learning For Visual Computing

Announcements Course Ask a Question Progress Mentor

Unit 13 - Week 12

Course
outline Assignment 12
The due date for submitting this assignment has passed. Due on 2018-04-18, 23:59 IST.
How to access
the portal Submitted assignment

Week 1 1) Which of the following topology is true for RNN? 1 point

Week 2
Many to one

Week 3
Many to many
Week 4
One to many
Week 5
Any of the above
Week 6
No, the answer is incorrect.
Week 7 Score: 0
Accepted Answers:
Week 8 Any of the above

Week 9 2) Which of the following parameters are needed for RNN in addition to input transformation 1 point
weights (Wh,x,t )
Week 10

Wh,h,t
Week 11

Week 12
ht−1
Lecture 56 :
Understanding
Video Analysis
Both a and b

Lecture 57 :
None of the above
Recurrent
Neural No, the answer is incorrect.
Networks and
Score: 0
Long Short-
Term Memory Accepted Answers:
Both a and b
Lecture 58 :
Spatio-Temporal
3) Which of the following gates are used in LSTM? 1 point
Deep Learning
for Video
Input
Analysis
Forget
Lecture 59 :
Output
Activity
recognition All of the above
using 3D-CNN
No, the answer is incorrect.
Score: 0

https://onlinecourses.nptel.ac.in/noc18_ee08/unit?unit=16&assessment=142 1/3
25/05/2018 Deep Learning For Visual Computing - - Unit 13 - Week 12

Lecture 60 : Accepted Answers:


Activity All of the above
recognition
using CNN- 4) Given a sequence of T color images of size 224 x 224, how are they organized for tensor 1 point
LSTM processing ?
Feedback for
3 x T x 224 x 224
Week 12
T x 3 x 224 x 224
Quiz :
3xTxMxM
Assignment 12
None of the above
Week 12:
Lecture Slides No, the answer is incorrect.
Score: 0
DOWNLOAD
VIDEOS Accepted Answers:
3 x T x 224 x 224

5) Given a sequence of 100 color images of size 224 x 224 and kernel of size 3, no padding, 18 1 point
channels and single stride. What is the convolution output

18 x 100 x 222 x 222

18 x 98 x 222 x 222

18 x 98 x 224 x 224

None of the above

No, the answer is incorrect.


Score: 0
Accepted Answers:
18 x 98 x 222 x 222

6) For temporal learning which architecture is most preferable 1 point

Autoencoder
LSTM
CNN
None of the above

No, the answer is incorrect.


Score: 0
Accepted Answers:
LSTM

7) Which of the following hurdles of RNN were overcomed by LSTM 1 point

Learning long term dependencies


Exponential decay of learning rate along time
Both a and b
None of the above

No, the answer is incorrect.


Score: 0
Accepted Answers:
Both a and b

8) Which of the following commands create a LSTM with input dimension as 3 and output 1 point
dimension as 3 through nn module

nn.LSTM(3, 3)
nn.GRU(3, 3).LSTM
nn.RNN(3, 3).LSTM
None of the above

https://onlinecourses.nptel.ac.in/noc18_ee08/unit?unit=16&assessment=142 2/3
25/05/2018 Deep Learning For Visual Computing - - Unit 13 - Week 12
No, the answer is incorrect.
Score: 0
Accepted Answers:
nn.LSTM(3, 3)

9) How many variables are generated upon feed forwarding LSTM for 5 step 1 point

output variables
output and hidden variables
output, hidden and input storage variable
None

No, the answer is incorrect.


Score: 0
Accepted Answers:
output, hidden and input storage variable

10)How many variables are fed for lstm 1 point

Input
Input and previous hidden state
Input, previous hidden and previous output
None of the above

No, the answer is incorrect.


Score: 0
Accepted Answers:
Input and previous hidden state

Previous Page End

© 2014 NPTEL - Privacy & Terms - Honor Code - FAQs -


A project of In association with

Funded by

Powered by

https://onlinecourses.nptel.ac.in/noc18_ee08/unit?unit=16&assessment=142 3/3

You might also like