You are on page 1of 6

NPTEL Online Certification Courses

Indian Institute of Technology Kharagpur

Deep Learning
Assignment- Week 6
TYPE OF QUESTION: MCQ/MSQ
Number of questions: 10 Total mark: 10 X 1 = 10
______________________________________________________________________________

QUESTION 1:

Which of the following is FALSE about PCA and Autoencoders?

a. PCA works well with non-linear data but Autoencoders are best suited for linear
data
b. Output of both PCA and Autoencoders is lossy
c. Both PCA and Autoencoders can be used for dimensionality reduction
d. None of the above

Correct Answer: a

Detailed Solution:

Options are self-explanatory

QUESTION 2:
Which of the following is not true for PCA? Tick all the options that are correct.

a. Rotates the axes to lie along the principal components


b. Is calculated from the covariance matrix
c. Removes some information from the data
d. Eigenvectors describe the length of the principal components

Correct Answer: d

Detailed Solution:

See the definition

Direct from classroom lecture


NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 3:
Consider the four sample points below, 𝑋𝑖 ∈ ℝ2 .

We want to represent the data in 1D using PCA. Compute the unit-length principal component
directions of X, and then choose from the options below which one the PCA algorithm would choose if
you request just one principal component.

a. [1/√2 1/√2]𝑇
b. [1/√2 −1/√2]𝑇
c. [−1/√2 1/√2]𝑇
d. [1/√2 1/√2]𝑇

Correct Answer: d

Detailed Solution:

Centering X,

The above matrix is 𝑿𝒄 . Now,


NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

𝟏𝟎 𝟔
𝟏
𝑿𝑻𝒄 𝑿𝒄 = [ ].
𝟒 𝟔 𝟏𝟎
Now eigen vector with eigen value 16 is [1/√2 1/√2]𝑇
Now eigen vector with eigen value 4 is [1/√2 −1/√2]𝑇

QUESTION 4:
Given input 𝑥 and linear autoencoder (no bias) with random weights (𝑊 for encoder and 𝑊 ′ for
decoder), what mathematical form is minimized to achieve optimal weights?

a. |𝑥 − (𝑊 ′ ∙ 𝑊 ∙ 𝑥)|
b. |𝑥 − (𝑊 ∙ 𝑊 ′ ∙ 𝑥)|
c. |𝑥 − (𝑊 ∙ 𝑊 ∙ 𝑥)|
d. |𝑥 − (𝑊 ′ ∙ 𝑊 ′ ∙ 𝑥)|

Correct Answer: a

Detailed Solution:

Output 𝒚 = 𝑾′ ∙ 𝑾 ∙ 𝒙

We have to minimize the error between input and output.

So, mathematical form that need to be minimized is |𝒙 − 𝒚| = |𝒙 − 𝑾′ ∙ 𝑾 ∙ 𝒙|

QUESTION 5:
Suppose a neural network has 3 input nodes, a, b, c. There are 2 neurons, X and F. X = a+ 2b+4c
and F = 2X + 1. What is the output F when input (a, b, c) = (-6, 1, 2).
a. 5
b. 4
c. 9
d. 8

Correct Answer: c

Detailed Solution:

𝑿 = 𝒂 + 𝟐𝒃 + 𝟒𝒄 = −𝟔 + 𝟐 + 𝟖 = 𝟒
𝑭 = 𝟐𝑿 + 𝟏 = 𝟗
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

QUESTION 6:
Suppose a neural network has 3 input nodes, a, b, c. There are 2 neurons, X and F. X = a+ 2b+4c
and F = 2X + 1. What is the gradient of F with respect to a, b and c? Assume, (a, b, c) = (-6, 1, 2).
a. (2, 4, 8)
b. (1, 2, 4)
c. (-1, -2, -4)
d. (2, 2, 4)

Correct Answer: a

Detailed Solution:

𝝏𝑭 𝝏𝑭 𝝏𝑿
𝑭 = 𝟐𝑿 + 𝟏, = ∗ =𝟐∗𝟏=𝟐
𝝏𝒂 𝝏𝑿 𝝏𝒂
𝝏𝑭 𝝏𝑭
Same follows for and 𝝏𝒄
𝝏𝒃

QUESTION 7:
A single hidden and no-bias autoencoder has 100 input neurons and 10 hidden neurons. What
will be the number of parameters associated with this autoencoder?

a. 1000
b. 2000
c. 2110
d. 1010

Correct Answer: b

Detailed Solution:

As single hidden layer and no-bias autoencoder,

Input neurons = 100, Hidden neurons = 10. So Output neurons = 100

Total number of parameters = 100*10+10*100=2000

QUESTION 8:
𝑑𝑦 𝑑𝑦
𝑦 = min(𝑎, 𝑏) and 𝑎 > 𝑏. What is the value of and ?
𝑑𝑎 𝑑𝑏

a. 1, 0
b. 0, 1
NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

c. 0, 0
d. 1, 1

Correct Answer: b

Detailed Solution:

𝑦 = min(𝑎, 𝑏) and 𝑎 > 𝑏.


𝑑𝑦 𝑑𝑦
Now 𝑦 = 𝑏. So = 0 and =1
𝑑𝑎 𝑑𝑏

QUESTION 9:
When 𝑡𝑎𝑛ℎ(𝑥) = 𝑇 and 𝑠𝑖𝑔𝑚𝑜𝑖𝑑(𝑥) = 𝑆 which of the following satisfies their relationship?
2𝑆+1
a. 𝑇 =
2𝑆 2 −2𝑆+1
2𝑆+1
b. 𝑇 =
2𝑆 2 +2𝑆+1
2𝑆−1
c. 𝑇 =
2𝑆 2 −2𝑆+1
2𝑆−1
d. 𝑇 =
2𝑆 2 +1

Correct Answer: c

Detailed Solution:

QUESTION 10:
Which of the following two vectors can form the first two principal components?

a. {2; 3; 1} and {3; 1; −9}


NPTEL Online Certification Courses
Indian Institute of Technology Kharagpur

b. {2; 4; 1} and {−2; 1; −8}


c. {2; 3; 1} and {−3; 1; −9}
d. {2; 3; −1} and {3; 1; −9}

Correct Answer: a

Detailed Solution:

Only in option (a), the vectors are orthogonal

______________________________________________________________________________

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

You might also like