MCQ Question

NPTEL Online Certification Courses Indian
Institute of Technology Kharagpur
Introduction to
Machine Learning
Assignment- Week 2
TYPE OF QUESTION: MCQ
Number of questions: 8 Total mark: 8 X 2 = 16
MCQ Question
QUESTION 1:
Identify whether the following statement is true or false?
“Overfitting is more likely when the set of training data is small”
A. True
B. False
Correct Answer : A.True
Detailed Solution : With a small training dataset, it’s easier to find a hypothesis to fit the training
data exactly,i.e., overfit.
______________________________________________________________________________
QUESTION 2:
Which of the following criteria is typically used for optimizing in linear regression.
A. Maximize the number of points it touches.
B. Minimize the number of points it touches.
C. Minimize the squared distance from the points.
D. Minimize the maximum distance of a point from a line.
Correct Answer : C. Minimize the squared distance from the points.
Detailed Solution : Loss function of linear regression is squared distance from the points.
______________________________________________________________________________
QUESTION 3:
Which of the following is false?
A. Bias is the true error of the best classifier in the concept class
B. Bias is high if the concept class cannot model the true data distribution well
C. High bias leads to overfitting
D. For high bias both train and test error will be high
Correct Answer : C. High bias leads to overfitting
Detailed Solution : High bias leads to underfitting.
______________________________________________________________________________
QUESTION 4:
The following dataset will be used to learn a decision tree for predicting whether a person
is happy (H) or sad (S), based on the color of shoes, whether they wear a wig and the
number of ears they have.
Color Wig Num. Ears Emotion (Output)
G Y 2 S
G N 2 S
G N 2 S
B N 2 S
B N 2 H
R N 2 H
R N 2 H
R N 2 H
R Y 3 H
Which attribute should you choose as the root of the decision tree?
A. Color
B. Wig
C. Number of ears
D. Any one of the previous three attributes
Correct Answer : A. Color
Detailed Solution : We have to compute Information Gain w.r.t. each of these 4 attributes and the
attribute with highest information gain will be chosen as the root of the decision tree.
______________________________________________________________________________
QUESTION 5:
Consider applying linear regression with the hypothesis as ℎθ(𝑥) = θ0 + θ1𝑥.The training data is
given in the table.
X Y
6 7
5 4
10 9
3 4
𝑚
2
The cost function is 𝐽(θ) =
1
2𝑚 ( )
∑ (ℎθ 𝑥𝑖 − 𝑦𝑖)
𝑖=1
What is the value of 𝐽(θ)when θ = (2, 1) ?
A. 0
B. 1
C. 2
D. 2.5
Correct Answer: D. 2.5
Detailed Solution : Substitute θ0 by 2 and θ1 by 1 and compute 𝐽(θ).

______________________________________________________________________________
QUESTION 6:
In a binary classification problem, out of 64 data points 29 belong to class I and 35 belong to
class II. What is the entropy of the data set?
A. 0.97
B. 0
C. 1
D. 0.99
Correct Answer : D. 0.99
Detailed Solution : We can compute Entropy as

𝐸𝑁𝑇𝑅𝑂𝑃𝑌(𝑝 +, 𝑝−) = − 𝑝+𝑙𝑜𝑔2𝑝+ − 𝑝−𝑙𝑜𝑔2𝑝− , here
𝑝+ = 29/64 𝑎𝑛𝑑 𝑝− = 35/64
______________________________________________________________________________
QUESTION 7:
Decision trees can be used for the following type of datasets:
I. The attributes are categorical

II. The attributes are numeric valued and continuous
III. The attributes are discrete valued numbers
A. In case I only
B. In case II only
C. In cases II and III only
D. In cases I, II and III
Correct Answer : D. In cases I, II and III
Detailed Solution : Decision trees can be applied in all 3 cases.

______________________________________________________________________________
QUESTION 8:
What is true for Stochastic Gradient Descent?

A. In every iteration, model parameters are updated for multiple training samples
B. In every iteration, model parameters are updated for one training sample
C. In every iteration, model parameters are updated for all training samples
D. None of the above
Correct Answer : B. In every iteration model parameters are updated for one training
sample.
Detailed Solution : In batch gradient descent, multiple training samples are used and in
stochastic gradient descent, one training sample is used to update parameters.
_____________________________________________________________________________
*****END*****

MCQ Question

Uploaded by

Copyright:

Available Formats

MCQ Question

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

MCQ Question

Uploaded by

Copyright:

Available Formats

NPTEL Online Certification Courses Indian

Institute of Technology Kharagpur

Identify whether the following statement is true or false?

“Overfitting is more likely when the set of training data is small”

Correct Answer : A.True

Correct Answer : C. Minimize the squared distance from the points.

Which of the following is false?

Correct Answer : C. High bias leads to overfitting

Detailed Solution : High bias leads to underfitting.

Color Wig Num. Ears Emotion (Output)

Detailed Solution : Substitute θ0 by 2 and θ1 by 1 and compute 𝐽(θ).

Correct Answer : D. 0.99

Detailed Solution : We can compute Entropy as

Decision trees can be used for the following type of datasets:

I. The attributes are categorical

Correct Answer : D. In cases I, II and III

Detailed Solution : Decision trees can be applied in all 3 cases.

What is true for Stochastic Gradient Descent?

You might also like