NPTEL Online Certification Courses

Indian Institute of Technology Kharagpur

Deep Learning
Assignment- Week 8
TYPE OF QUESTION: MCQ/MSQ
Number of questions: 10 Total mark: 10 X 1 = 10
______________________________________________________________________________

QUESTION 1:
Which of the following functions can be used as an activation function in the output layer if we
wish to predict the probabilities of n classes such that sum of p over all n equals to 1?

a. Softmax
b. ReLU
c. Sigmoid
d. Tanh
Correct Answer: a

Detailed Solution:

Softmax function ensures that the summation of probabilities asserted over the k classes
equals to 1.
______________________________________________________________________________

QUESTION 2:
The input image has been converted into a matrix of size 256 X 256 and a kernel/filter of size
3x3 with a stride of 1 and no padding. What will be the size of the convoluted matrix?

a. 253x253
b. 3x3
c. 254x254
d. 256x256

Correct Answer: c

Detailed Solution:

The size of the convoluted matrix is given by CxC where C=((I-F+2P)/S)+1, where C is the
size of the Convoluted matrix, I is the size of the input matrix, F the size of the filter matrix
and P the padding applied to the input matrix. Here P=0, I=256, F=3 and S=1. There the
answer is 254x254.
______________________________________________________________________________
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 3:
The numerical output of a sigmoid node in a neural network is:

a. Bounded between 0 and 1

b. Bounded between -1 and 1
c. Bounded between -1 and 0
d. Unbounded

Correct Answer: a

Detailed Solution:

Answer is evident from the formula of a sigmoid function.

______________________________________________________________________________

QUESTION 4:
The figure below shows image of a face which is input to a convolutional neural net and the
other three images shows different levels of features extracted from the network. Can you
identify from the following options which one is correct?

a. Label 3: Low-level features, Label 2: High-level features, Label 1: Mid-level

features
b. Label 1: Low-level features, Label 3: High-level features, Label 2: Mid-level
features
c. Label 2: Low-level features, Label 1: High-level features, Label 3: Mid-level
features
d. Label 3: Low-level features, Label 1: High-level features, Label 2: Mid-level
features

Correct Answer: b

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

Convolutional NN will try to learn low-level features such as edges and lines in early layers
then parts of faces of people and then high-level representation of a face.

______________________________________________________________________________

QUESTION 5:
Suppose you have 5 convolutional kernel of size 3 x 3 with no padding and stride 1 in the first
layer of a convolutional neural network. You pass an input of dimension 228 x 228 x 3 through
this layer. What are the dimensions of the data which the next layer will receive?

a. 217 x 217 x 3
b. 217 x 217 x 8
c. 225 x 225 x 5
d. 225 x 225 x 3

Correct Answer: c

Detailed Solution:

The layer accepts a volume of size W1×H1×D1. In our case, 228x228x3

Requires four hyperparameters: Number of filters K=5, their spatial extent F=3, the stride
S=1, the amount of padding P=0.

Produces a volume of size W2×H2×D2 i.e. 225x225x256 where: W2=(W1−F+2P)/S+1

=(228−3)/1+1 =225, H2=(H1−F+2P)/S+1 =(228−3)/1+1 =225, (i.e. width and height are
computed equally by symmetry), D2= Number of filters K=5.

____________________________________________________________________________

QUESTION 6:
What is the mathematical form of the Leaky ReLU layer?

a. f(x)=max(0,x)
b. f(x)=min(0,x)
c. f(x)=min(0, αx), where α is a small constant
d. f(x)=1(x<0)(αx)+1(x>=0)(x), where α is a small constant

Correct Answer: d

Detailed Solution:

Option d comes from the direct formula.

 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

____________________________________________________________________________

QUESTION 7:
The input image has been converted into a matrix of size 224 x 224 and convolved with a
kernel/filter of size FxF with a stride of s and padding P to produce a feature map of dimension
222x222. Which among the following is true?

a. F=3x3, s=1, P=1

b. F=3x3, s=0, P=1
c. F=3x3, s=1, P=0
d. F=2x2, s=0, P=0

Correct Answer: c

Detailed Solution:

The size of the convoluted matrix is given by CxC, where C=((I-F+2P)/S)+1, where C is the
size of the convoluted matrix, I is the size of the input matrix, F the size of the filter matrix
and P the padding applied to the input matrix. Here C is given in the question and it is 222.
Therefore, P=0, I=224, F=3 and s=1. Thus option c is the answer.

______________________________________________________________________________

QUESTION 8:
For a transfer learning task, which layers according to you can be more generally transferred to
another task?

a. Higher layers
b. Lower layers
c. Task specific
d. Cannot comment

Correct Answer: b

Detailed Solution:

Lower layers are more general features (for eg: can be edge detectors) and thus can be
transferred well to other task. Higher layers on the other hand are task specific.

______________________________________________________________________________
 NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 9:
Statement 1: Adding more hidden layers will solve the vanishing gradient problem for a 2-layer
neural network

Statement 2: Making the network deeper will increase the chance of vanishing gradients.

a. Statement 1 is correct
b. Statement 2 is correct
c. Neither Statement 1 nor Statement 2 is correct
d. Vanishing gradient problem is independent of number of hidden layers of the
neural network.

Correct Answer: b

Detailed Solution:

As more layers using certain activation functions are added to neural networks, the
gradients of the loss function approaches zero, making the network hard to train. Thus
statement 2 is correct.

____________________________________________________________________________

QUESTION 10:
Which of the following activations can cause vanishing gradient problem?

a. ReLU
b. Leaky ReLU
c. Sigmoid
d. Linear

Correct Answer: c

Detailed Solution:

When the sigmoid function value is either too high or too low, the derivative becomes very
small i.e. << 1. This causes vanishing gradients and poor learning for deep networks.

______________________________________________________________________

______________________________________________________________________________

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