# Deep Learning | Week 1

Course Name: Deep Learning

#### Q1) From a pack of 52 cards, two cards are drawn together at random. What is the probability of both the cards being kings?a. 1/15b. 25/57c. 35/256d. 1/221

Q2) For a two class problem Bayes minimum error classifier follows which of following rule? (The two different classes are w₁ and w2, and input feature vector is x)
a. Choose w₁ if P(w₁/x) > P(w2/x)
b. Choose w₁ if P(w₁)>P(w2)
c. Choose w2 if P(w₁)<P(w2)
d. Choose w2 if P(w₁/x) > P(w2/x)

Answer: a. Choose w₁ if P(w₁/x) > P(w2/x)

#### These are NPTEL Deep Learning Week 1 Assignment 1 Answers

Q3) The texture of the region provides measure of which of the following properties?
a. Smoothness alone
b. Coarseness alone
c. Regularity alone
d. Smoothness, coarseness and regularity

Answer: d. Smoothness, coarseness and regularity

Q4) Why convolution neural network is taking off quickly in recent times? (Check the options that are true.)
a. Access to large amount of digitized data
b. Integration of feature extraction within the training process.
c. Availability of more computational power
d. All of the above.

Answer: d. All of the above.

These are NPTEL Deep Learning Week 1 Assignment 1 Answers

Q5) The bayes formula states :
a. posterior = likelihood*prior/evidence
b. posterior = likelihood*evidence/prior
c. posterior = likelihood * prior
d. posterior = likelihood * evidence

Answer: a. posterior = likelihood*prior/evidence

Q6) Suppose Fourier descriptor of a shape has K coefficient, and we remove last few coefficient and use only first m (m<K) number of coefficient to reconstruct the shape. What will be effect of using truncated Fourier descriptor on the reconstructed shape?
a. We will get a smoothed boundary version of the shape.
b. We will get only the fine details of the boundary of the shape.
c. Full shape will be reconstructed without any loss of information.
d. Low frequency component of the boundary will be removed from contour of the shape.

Answer: a. We will get a smoothed boundary version of the shape.

These are NPTEL Deep Learning Week 1 Assignment 1 Answers

Q7) The plot of distance of the different boundary point from the centroid of the shape taken at various direction is known as
a. Signature descriptor
b. Polygonal descriptor
c. Fourier descriptor.
d. Convex Hull

Answer: a. Signature descriptor

Q8) If the larger values of gray co-occurrence matrix are concentrated around the main diagonal, then which one of the following will be true?
a. The value of element difference moment will be high.
b. The value of inverse element difference moment will be high.
c. The value of entropy will be very low.
d. None of the above.

Answer: b. The value of inverse element difference moment will be high.

These are NPTEL Deep Learning Week 1 Assignment 1 Answers

Q9) Which of the following is a Co-occurrence matrix based descriptor
a. Entropy
b. Uniformity
c. Signature
d. Inverse Element difference moment.
e. All of the above.

Answer: e. All of the above.

These are NPTEL Deep Learning Week 1 Assignment 1 Answers

Q10) Consider two class Bayes’ Minimum Risk Classifier. Probability of classes W1 and W2 are, P (w₁) =0.3 and P (w₂) =0.7 respectively. P(x) = 0.55, P (x| w₁) = 0.75, P (x| w2) =0.45 and the loss matrix values are

Find the Risk R (α₂|x).
a. 0.42
b. 0.61
c. 0.48
d. 0.39