NPTEL Online Certification Courses

Indian Institute of Technology Kharagpur

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

QUESTION 1:

Which of the following is False regarding batch-normalization??

a. Batch normalization prevents the problem of exploding

b. For an input x, Batch Normalization produces same output regardless of in
training mode or inference/test mode.
c. Batch normalization may prevent covariate shift
d. All of them

Correct Answer: b

Detailed Solution:
BN uses running exponential stats to estimate mean and standard deviation at test time, whereas
at training time it uses batch mean and standard deviation in it’s mathematical expression
QUESTION 2:

A neural network has 3 neurons in a hidden layer. Activations of the neurons for three batches
4 0 8
are[4] , [2] , [9] respectively. What will be the value of mean if we use batch normalization in
3 5 1
this layer?
4
a. [5]
3
2
b. [2]
5
1
c. [1]
1
0
d. [0]
0
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Correct Answer: a

Detailed Solution:
1 4 0 8 4
× ([4] + [2] + [9]) = [5]
3
3 5 1 3
______________________________________________________________________________

QUESTION 3:
How can we prevent underfitting?

a. Increase the number of data samples

b. Increase the number of parameters
c. Decrease the number of parameters
d. Decrease the number of data samples

Correct Answer: b

Detailed Solution:
Underfitting happens whenever models has less parameters to capture the data distribution. We
need to increase the parameters, so data can be fitted perfectly well.
______________________________________________________________________________

QUESTION 4:
How do we generally calculate mean and variance during testing?

a. Batch normalization is not required during testing

b. Mean and variance based on test image
c. Estimated mean and variance statistics during training
d. None of the above

Correct Answer: c

Detailed Solution:
We generally calculate batch mean and variance statistics during training and use the estimated
batch mean and variance during testing.
______________________________________________________________________________
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 5:
Which one of the following is an advantage of dropout?

a. Regularization
b. Prevent Overfitting
c. Improve Accuracy
d. All of Above

Correct Answer: d

Detailed Solution:
Dropout drops random features during training to prevent overfitting and over reliance on very
few features.
______________________________________________________________________________

QUESTION 6:
Which of the following is True regarding layer normalization and batch normalization?

a. Layer normalization normalizes over spatial and channel dimension whereas

Batch normalization normalizes over spatial and batch dimensions
b. Layer normalization normalizes over spatial and channel dimension whereas
Batch normalization normalizes over batch, spatial and channel dimension
c. Batch normalization normalizes over spatial and channel dimension whereas

Layer normalization normalizes over batch, spatial and channel dimension

d. None of these

Correct Answer: a

Detailed Solution:
See the lectures/lecture materials.
______________________________________________________________________________

QUESTION 7:
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Which one of the following regularization methods induces sparsity among the trained
weights?

a. 𝐿1 regularizer
b. 𝐿2 regularizer
c. Both 𝐿1 & 𝐿2
d. None of the above

Correct Answer: a
Detailed Solution:

https://developers.google.com/machine-learning/crash-course/regularization-for-sparsity/l1-
regularization

______________________________________________________________________________

QUESTION 8:
Which among the following is NOT a data augmentation technique?

a. Random horizontal and vertical flip of image

b. Random shuffle all the pixels of an image
c. Random color jittering
d. All the above are data augmentation techniques

Correct Answer: b

Detailed Solution:
Random shuffle of all the pixels of the image will distort the image and neural network will be
unable to learn anything. So, it is not a data augmentation technique.
______________________________________________________________________________

QUESTION 9:
Which of the following is true about model capacity (where model capacity means the ability of
neural network to approximate complex functions)?

a. As number of hidden layers increase, model capacity increases

b. As dropout ratio increases, model capacity increases
c. As learning rate increases, model capacity increases
d. None of these
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

Correct Answer: a

Detailed Solution:
Dropout and learning rate has nothing to do with model capacity. If hidden layers increase, it
increases the number of learnable parameter. Therefore, model capacity increases.
______________________________________________________________________________

QUESTION 10:
Two variant training schedule samples its minibatches in the following manner
Training Schedule 1

Mini batch 1=[Image1, Image2, Image3]

Mini batch 2=[Image4, Image5, Image6]

Training Schedule 2

Mini batch 1=[Image1, Image4 , Image3]

Mini batch 2=[Image2, Image 5, Image6]

The output activations of each corresponding image is compared across Training schedule 1 and
Training schedule 2 for a CNN with batch norm layers. Choose the correct statement

a. Activation outputs of corresponding image will be same across Training schedule

1 and Training schedule 2
b. Activation outputs of corresponding image will be different across Training
schedule 1 and Training schedule 2
c. Some activations outputs of corresponding images will be same but some will be
different
d. None of these.

Correct Answer: b

Detailed Solution:

As minibatch constructed are different across training scheme, The mini-batch statistics will
also be different and therefore activation outputs of corresponding images will be different.

____________________________________________________________________________

______________________________________________________________________________

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