QUESTION BANK

Course Name : Machine Learning

Corse Code : CS603C
Regulation : R21

Group-A
(Multiple Choice Questions)
Question No. Questions Marks Module CO BT
No. No. Level
1. Application of machine learning methods to 1 M1 CO4 BT5
large databases is called
A. data mining.
B. artificial intelligence
C. big data computing
D. internet of things
2. If machine learning model output involves 1 M1 CO2 BT4
target variable then that model is called as
A. descriptive model
B. predictive model
C. reinforcement learning
D. all of the above
3. In what type of learning labelled training data 1 M1 CO1 B2
is used
A. unsupervised learning
B. supervised learning
C. reinforcement learning
D. active learning
4. In following type of feature selection method 1 M3 CO2 BT2
we start with empty feature set
A. forward feature selection
B. backward feature selection
C. both A and B
D. none of the above
5. SVM can be used to solve ___________ 1 M1 CO3 BT3
problems
A. Classification
B. Regression
C. Clustering
D. Both Classification and Regression
 QUESTION BANK

6. Which of the following is a disadvantage of 1 M3 CO3 BT4

decision tree?
A. Factor Analysis
B. Decision Trees are robust to outliners
C. Decision Trees are prone to overfit
D. None of the above
7. Which of the following is the best machine 1 M2 CO3 BT3
learning method?
A. scalable
B. accuracy
C. fast
D. all of the above
8. What characterize unlabeled examples in 1 M1 CO1 BT2
machine learning?
A. there is no prior knowledge
B. there is no confusing knowledge
C. there is prior knowledge
D. there is plenty of confusing knowledge
9. What does dimensionality reduction reduce? 1 M2 CO2 BT1
A. stochastics
B. collinerity
C. performance
D. entropyne
10. Data used to build a data mining model. 1 M2 CO3 BT3
A. training data
B. validation data
C. test data
D. hidden data
11. The problem of finding hidden structure in 1 M1 CO1 BT3
unlabeled data is called…
A. supervised learning
B. unsupervised learning
C. reinforcement learning
D. none of the above
12. Of the Following Examples, Which would 1 M1 CO3 BT5
you address using an supervised learning
Algorithm?
A. given email labeled as spam or not
spam, learn a spam filter.
B. given a set of news articles found on
 QUESTION BANK

the web, group them into set of articles about

the same story.
C. given a database of customer data,
automatically discover market segments and
group customers into different market
segments.
D. find the patterns in market basket
analysis.
13. You are given reviews of few netflix series 1 M1 CO4 BT5
marked as positive, negative and neutral.
Classifying reviews of a new netflix series is
an example of
A. supervised learning
B. unsupervised learning
C. semisupervised learning
D. reinforcement learning
14. Which of the following is a good test dataset 1 M2 CO3 BT3
characteristic?
A. large enough to yield meaningful
results
B. is representative of the dataset as a
whole
C. both A and B
D. None of the above
15. Following are the types of supervised learning 1 M1 CO3 BT2
A. classification
B. regression
C. subgroup discovery
D. all of the above
16. Type of matrix decomposition model is 1 M2 CO2 BT2
A. descriptive model
B. predictive model
C. logical model
D. none of the above
17. The output of training process in machine 1 M1 CO4 BT4
learning is
A. machine learning model
B. machine learning algorithm
C. null
D. accuracy
18. A feature F1 can take certain value: A, B, C, 1 M3 CO3 BT4
 QUESTION BANK

D, E, & F and represents grade of students

from a college. Here feature type is
A. nominal
B. ordinal
C. categorical
D. Boolean
19. Supervised learning and unsupervised 1 M1 CO3 BT3
clustering both require which is correct
according to the statement.
A. output attribute.
B. hidden attribute.
C. input attribute.
D. categorical attribute
20. What characterize is hyper plane in 1 M6 CO3 BT4
geometrical model of machine learning?
A. a plane with 1 dimensional fewer than
number of input attributes.
B. a plane with 2 dimensional fewer than
number of input attributes.
C. a plane with 1 dimensional more than
number of input attributes.
D. a plane with 2 dimensional more than
number of input attributes.
21. K-Nearest Neighbors (KNN) is classified as 1 M3 CO1 BT2
what type of machine learning algorithm?
a) Instance-based learning
b) Parametric learning
c) Non-parametric learning
d) Model-based learning
22. Which of the following is not a supervised 1 M3 CO1 BT2
machine learning algorithm?
a) K-means
b) Naïve Bayes
c) SVM for classification problems
d) Decision tree
23. What’s the key benefit of using deep learning 1 M6 CO4 BT5
for tasks like recognizing images?
a) They need less training data than other
methods.
b) They’re easier to explain and understand
than other models.
 QUESTION BANK

c) They can learn complex details from the

data on their own.
d) They work faster and are more efficient
computationally.
24. Which algorithm is best suited for a binary 1 M3 CO2 BT3
classification problem?
a) K-nearest Neighbors
b) Decision Trees
c) Random Forest
d) Linear Regression
25. Which of the following statements is true 1 M6 CO1 BT2
about AdaBoost?
a) It is particularly prone to overfitting on
noisy datasets
b) Complexity of the weak learner is
important in AdaBoost
c) It is generally more prone to overfitting
d) It improves classification accuracy
26. Which one of the following models is a 1 M5 CO2 BT3
generative model used in machine learning?
a) Support vector machines
b) Naïve Bayes
c) Logistic Regression
d) Linear Regression
27. An artificially intelligent car decreases its 1 M6 CO3 BT4
speed based on its distance from the car in
front of it. Which algorithm is used?
a) Naïve-Bayes
b) Decision Tree
c) Linear Regression
d) Logistic Regression
28. Which of the following statements is false 1 M3 CO2 BT2
about Ensemble learning?
a) It is a supervised learning algorithm
b) It is an unsupervised learning algorithm
c) More random algorithms can be used to
produce a stronger ensemble
d) Ensembles can be shown to have more
flexibility in the functions they can represent
29. Decision tree uses the inductive learning 1 M1 CO3 BT3
machine learning approach.
 QUESTION BANK

a) False
b) True
30. Which of the following statements is not true 1 M3 CO2 BT2
about boosting?
a) It mainly increases the bias and the
variance
b) It tries to generate complementary base-
learners by training the next learner on the
mistakes of the previous learners
c) It is a technique for solving two-class
classification problems
d) It uses the mechanism of increasing the
weights of misclassified data in preceding
classifiers
31. In which category does linear regression 1 M1 CO1 BT1
belong to?
a) Neither supervised nor unsupervised
learning
b) Both supervised and unsupervised learning
c) Unsupervised learning
d) Supervised learning
32. The learner is trying to predict housing prices 1 M1 CO4 BT3
based on the size of each house. What type of
regression is this?
a) Multivariate Logistic Regression
b) Logistic Regression
c) Linear Regression
d) Multivariate Linear Regression
33. The learner is trying to predict housing prices 1 M1 CO3 BT4
based on the size of each house. The variable
“size” is ___________
a) dependent variable
b) label set variable
c) independent variable
d) target variable
34. The learner is trying to predict the cost of 1 M1 CO2 BT3
papaya based on its size. The variable “cost”
is __________
a) independent variable
b) target Variable
c) ranked variable
 QUESTION BANK

d) categorical variable
35. The independent variable is represented along 1 M2 CO3 BT3
_________
a) Either X-axis or Y-axis, it doesn’t matter
b) Y axis
c) X axis
d) Depends on the dataset
36. The learner is trying to predict the price of a 1 M1 CO2 BT3
house based on the length and width of the
house.
x1 = length and x2 = width. What is a better
hypothesis?
a) h(X) = t0 + t1x1
b) h(X) = t0 + t1x1+ t2x2
c) h(X) = t0 + t2x2
d) h(X) = t0 + t1X, where area of the house: X
= x1 * x2
37. A drawback of Polynomial Regression is 1 M6 CO2 BT3
handling of features with a different priority.
a) True
b) False
38. h(x) = y. What is the cost (h(x), y)? 1 M2 CO3 BT3
a) -infinite
b) infinite
c) 0
d) always h(x)
39. Let m be the number of training instances. 1 M6 CO3 BT2
What is the summation of cost function
multiplied by to get the gradient descent?
a) 1/m
b) m
c) 1 + m
d) 1 – m
40. The cost function is minimized by 1 M6 CO4 BT4
__________
a) Linear regression
b) Polynomial regression
c) PAC learning
d) Gradient descent
41. What is the minimum number of parameters 1 M2 CO1 BT1
 QUESTION BANK

of the gradient descent algorithm?

a) 1
b) 2
c) 3
d) 4
42. What happens when the learning rate is low? 1 M3 CO2 BT3
a) It always reaches the minima quickly
b) It reaches the minima very slowly
c) It overshoots the minima
d) Nothing happens
43. Gradient descent tries to _____________ 1 M2 CO1 BT2
a) maximize the cost function
b) minimize the cost function
c) minimize the learning rate
d) maximize the learning rate.
44. Feature scaling can be used to simplify 1 M2 CO3 BT3
gradient descent for multivariate linear
regression.
a) True
b) False
45. On which factor is the updating of each 1 M3 CO2 BT2
parameter dependent on?
a) The number of training examples
b) Target variable
c) The learning rate and the target variable
d) The learning rate
46. What is updated by gradient descent after 1 M2 CO3 BT3
each iteration?
a) The learning rate
b) Independent variables
c) Target variable
d) The number of training examples
47. Mean normalization can be used to simplify 1 M2 CO2 BT2
gradient descent for multivariate linear
regression.
a) True
b) False
48. What is the objective of backpropagation 1 M6 CO3 BT2
algorithm?
a) to develop learning algorithm for multilayer
 QUESTION BANK

feed forward neural network

b) to develop learning algorithm for single
layer feed forward neural network
c) to develop learning algorithm for multilayer
feed forward neural network, so that network
can be trained to capture the mapping
implicitly
d) none of the mentioned
49. What are general limitations of back 1 M6 CO4 BT3
propagation rule?
a) local minima problem
b) slow convergence
c) scaling
d) all of the mentioned
50. There is feedback in final stage of back 1 M6 CO1 BT2
propagation algorithm?
a) yes
b) no
* Please don’t add any column in the above table. However, you may add rows as per requirement.
Group-B
(Short Answer Type Questions)
Question No. Questions Marks Module CO BT
No. No. Level
1. Compare Traditional Programming Model and 5 M1 CO1 BT1
Machine Learning Model with suitable
diagram.

2. Consider the confusion matrix: 5 M2 CO1 BT3

Actual Values

Yes No
Predicted Yes 12 3
Values
No 1 9

Compute algorithm training accuracy.

3. Define machine learning. Briefly describe 1+4 M1 CO2 BT1

different types of machine learning with
 QUESTION BANK

suitable example.

4. Compare between machine learning and deep 5 M1 CO1 BT2

learning.

5. Differentiate between supervised and 3+2 M1 CO1 BT2

unsupervised learning. What is Reinforcement
Learning? Give suitable example.

6. Calculate entropy of a single attribute ‘Playing 5 M1 CO3 BT3

Golf’ problem when the following data is
given:

Playing Golf

Yes No

9 5

7. Calculate the Gini Index when the following 5 M2 CO4 BT3

data is given:

ID Loan Amount Loan Status

1 100 Bad

2 200 Good

3 250 Bad

4 150 Good

5 300 Bad

8. Explain KNN Algorithm. 5 M2 CO3 BT3

9. a) Why do we perform normalization? 2 M2 CO2 BT3

b) What is the difference between precision and 3 M1 CO2 BT2

recall?

10. How can you conclude about the model’s 5 M1 CO3 BT4
performance using the confusion matrix?

11. What is the difference between L1 and L2 2+3 M2 CO2 BT2

regularization? What is their significance?

12. a) Does the accuracy score always a good metric 3 M2 CO4 BT4
to measure the performance of a classification
 QUESTION BANK

model?

b) What is the purpose of splitting a given 2 M2 CO2 BT3

dataset into training and validation data?

13. a) What is the difference between k-means and 3 M2 CO2 BT2

the KNN algorithm?

b) What is Linear Discriminant Analysis? 2 M6 CO1 BT1

14. a) What is the null hypothesis in linear 3 M6 CO1 BT2

regression problem?

b) Can SVMs be used for both classification and 2 M1 CO4 BT4

regression tasks?

15. What are the assumptions behind the K-means 2+3 M2 CO4 BT5
algorithm? How do these assumptions affect
the results?

16. How does Random Forest ensure diversity 5 M3 CO3 BT4

among the trees in the model?

17. What is the concept of information gain in 2+3 M1 CO2 BT3

decision trees? How does it guide the creation
of the tree structure?

18. How does the independence assumption affect 5 M5 CO4 BT5

the accuracy of a Naive Bayes classifier?

19. Why does PCA maximize the variance in the 5 M2 CO2 BT2
data?

20. How do you evaluate the effectiveness of a 3+2 M6 CO4 BT5

machine learning model in an imbalanced
dataset scenario? What metrics would you use
instead of accuracy?

* Please don’t add any column in the above table. However, you may add rows as per requirement.
Group-C
(Long Answer Type Questions)
Questio Questions Mar Modu C BT
n No. ks le No. O Lev
No. el
1. a Explain Decision Tree Algorithm. 5 M1 CO BT3
) 3
 QUESTION BANK

b) Apply ID3 algorithm for constructing decision tree for the 10 M2 CO BT5
following Play Tennins.csv dataset 4

Day Outlook Temp Humidity Windy Play

Day 1 Sunny Hot High False No
Day 2 Sunny Hot High True No

Day 3 Overcast Hot High False Yes

Day 4 Rainy Mild High False Yes

Day 5 Rainy Cool Normal False Yes

Day 6 Rainy Cool Normal True No

Day 7 Overcast Cool Normal True Yes

Day 8 Sunny Mild High False No

Day 9 Sunny Cool Normal False Yes

Day 10 Rainy Mild Normal False Yes

Day 11 Sunny Mild Normal True Yes

Day 12 Overcast Mild High True Yes

Day 13 Overcast Hot Normal False Yes

Day 14 Rainy Mild High True No

2. a Describe Support Vector Machine and Non-Linear Support 7 M1 CO BT1

) Vector Machine in detail. 1

b) What is Ensemble modeling? Discuss about Bagging, 8 M2 CO BT2

Boosting and Stacking. 2

3. a Compare Entropy and Information Gain in ID3 with an 5 M2 CO BT4

) example. 3

b) Use K-means algorithm to create two clusters of the 10 M2 CO BT5

following dataset. 4

Data point Coordinate(x,y)

A 2,2

B 3,2

C 1,1

D 3,1
 QUESTION BANK

E 1.5,0.5

4. a What is overfitting and underfiting? 5 M3 CO BT1

) 2

b) Discuss cross validation. 5 M3 CO BT2

1

c Define Sparse Modeling. 5 M4 CO BT3

) 2

5. a Explain Support Vector Machine (SVM). 5 M1 CO BT2

) 2

b) Explain non linear SVM and kernel function. 5 M1 CO BT3

2

c Explain polynomial regression. 5 M6 CO BT2

) 2

6. Write Short Note. (any three) 3x5

a Naïve Bayes Classification 5 M6 CO BT1
) 2

b) Reinforcement Learning 5 M5 CO BT2

1

c Sparse Modeling 5 M4 CO BT3

) 1

d) Performance metrics to evaluate an ML model 5 M1 CO BT5

4

e Clustering 5 M2 CO BT4
) 3

7. a Explain the various issues in Decision tree Learning 5 M1 CO BT2

) 2

b What do you mean by Gradient Descent? What are the 2+3 M3 CO BT5
) conditions in which Gradient Descent is applied? 4

c Differentiate between Gradient Descent and Stochastic 5 M3 CO BT2

) Gradient Descent. 2

8. a Explain the concept of Bayes theorem with an example. 5 M5 CO BT4

) 4
 QUESTION BANK

b Explain Naïve Bayes Classifier with an Example. 5 M6 CO BT3

) 2

c Discuss the major drawbacks of K-nearest Neighbour 5 M2 CO BT5

) learning Algorithm and how it can be corrected. 4

9. a Define the following terms with respect to K - Nearest 3+3 M2 CO BT1

) Neighbour Learning: +3 1

i) Regression ii) Residual iii) Kernel Function.

b Define the following terms: 6 M4 CO BT1

) 1
a. Sample error b. True error c. Random Variable

d. Expected value e. Variance f. standard Deviation

10 a How is KNN different from k-means clustering? 5 M2 CO BT5

. ) 4

b What is the difference between a generative and 5 M6 CO BT2

) discriminative model? 2

c When should you use classification over regression? 5 M3 CO BT5

) 4

11 a Explain Logistic Regression. Also, explain its types 8 M2 CO BT2

. ) 3

b Write the assumptions made in simple linear regression. 7 M2 CO BT2

) Explain the properties of least-square estimators. 3

12 a Explain the DBSCAN algorithm for density based 8 M3 CO BT2

. ) clustering. List out its advantages compared to K-means 3

b Define clustering. Explain K-means clustering with 7 M3 CO BT2

) algorithm and flowchart. 3

13 a What is Data pre-processing? Why is Data Preprocessing 5 M1 CO BT2

. ) important? 3

b What is over fitting? How can you avoid it? 5 M3 CO BT2

) 3

c Difference between Bias and Variance? 5 M1 CO BT3

) 3

14 a Explain Regression and Classification with an example. 8 M2 CO BT2

. ) 3

b What are Linear Regression and Logistic Regression? 7 M2 CO BT2

 QUESTION BANK

) Explain with an example. 4

15 a What is under fitting in Machine Learning? 2 M1 CO BT2

. ) 3

b What is Cross-Validation? 3 M2 CO BT2

) 3

c Define Confusion Matrix. 4 M1 CO BT3

) 3

d What is Regularization in Machine Learning? 3 M3 CO BT3

) 2

e What is Feature Scaling? 3 M3 CO BT2

) 3

* Please don’t add any column in the above table. However, you may add rows as per requirement.