Scribd
Upload
24 views4 pages

MID_SEM_QP_2024_MARCH_final

The document outlines the structure and content of the IV Semester BTech DSE Internal Examinations for March 2024, specifically for the subject 'Fundamentals of Machine Learning'. It includes a list of questions covering various machine learning concepts such as K-Nearest Neighbors, Naïve Bayes, logistic regression, and support vector machines, along with practical applications and theoretical comparisons. The exam is scheduled for March 19, 2024, and consists of multiple-choice questions and descriptive problems totaling a maximum of 30 marks.

Uploaded by

khushpatel1222
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
24 views4 pages

MID_SEM_QP_2024_MARCH_final

The document outlines the structure and content of the IV Semester BTech DSE Internal Examinations for March 2024, specifically for the subject 'Fundamentals of Machine Learning'. It includes a list of questions covering various machine learning concepts such as K-Nearest Neighbors, Naïve Bayes, logistic regression, and support vector machines, along with practical applications and theoretical comparisons. The exam is scheduled for March 19, 2024, and consists of multiple-choice questions and descriptive problems totaling a maximum of 30 marks.

Uploaded by

khushpatel1222
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

IV SEMESTER BTECH DSE INTERNAL EXAMINATIONS MARCH 2024

MID-TERM Examination
SUBJECT: Fundamentals of Machine Learning [DSE 2222]

Date of Exam: 19/03/2024 Max. Marks: 30

Q. Question Marks
No
1 Which of the following statements is not true about K-Nearest 0.5
Neighbour?
a)It belongs to the supervised learning domain
b)It has an application in data mining and intrusion detection
c)It is Non-parametric
d) It is not an instance-based learning algorithm
2 Which of the following statements is not a feature of KNN? 0.5
a) Very easy to implement for multi-class problem
b) One Hyper Parameter
c) Variety of distance criteria to be chosen from
d) Fast algorithm for large dataset

3 The assumption of the Naïve Bayesian classifier is 0.5


a) It assumes that features of a data are completely dependent on each
other
b) It assumes that each input variable is dependent, and the model is not
generative
c) It assumes that each input attributes are independent of each other and
the model is generative
d) It assumes that the data dimensions are dependent and the model is
generative

4 Which one of the following terms is not used in the Bayes’ Theorem? 0.5
a) Prior
b) Unlikelihood
c) Posterior
d) Evidence

5 The generalized form of a Bayesian network that represents and solves 0.5
decision problems under uncertain knowledge is known as an?
A. Directed Acyclic Graph
B. Table of conditional probabilities
C. Influence diagram
D. None of the above
6 If we have variables x1, x2, x3,....., xn, then the probabilities of a different 0.5
combination of x1, x2, x3.. xn, are known as?
A. Table of conditional probabilities
B. Causal Component
C. Actual numbers
D. Joint probability distribution
7 Using logistic regression model to predict whether an email is spam or 0.5
not, the learned parameters are b0=−2 and b1=0.5. Given a new email
with a spam score x=0.8 and a threshold of 0.3, what is the predicted class
of the email?
a) Spam
b) Not spam
c) Insufficient information to determine
d) Promotional email
8 A Polynomial Regression algorithm is also called Polynomial Linear 0.5
Regression because it does not depend on the variables, instead, it
depends on the -----------.
a) Predicate
b) Degree of polynomial
c) Coefficients
d) Residual error

9 Ridge regression adds the -------of the coefficient as a penalty term to the 0.5
loss function(L).
a) Absolute value of magnitude
b) Squared magnitude
c) Exponential of magnitude
d) Mean of magnitude

10 Number of trees the algorithm builds before averaging the predictions is 0.5
represented with ------hyperparameter.
a) n_estimators
b) n_trees
c) max_depth
d) n_features

11 Demonstrate your understanding of the KNN algorithm by outlining the 4


key steps involved in its application. Apply the K-Nearest Neighbours
(KNN) algorithm to make predictions based on this dataset and predict the
class, of the following instance, X considering K values for 3, 4, and 6.
NAME AGE GENDER SPORT
A 32 Male Hockey
B 40 Male Neither
C 16 Female Volleyball
D 34 Female Volleyball
E 55 Male Neither
F 40 Male Volleyball
G 20 Female Neither
H 15 Male Volleyball
I 55 Female Hockey
J 15 Male Hockey

X = { NAME = ABC, AGE=5, GENDER = F }


12 Consider the dataset given in Table as training data for the Support Vector 4
Machine, which has positive and negatively labeled data points.
Considering this data as input, answer the following questions.
a) Plot these the given training points and identify the number of
support vectors from the given data points. Justify your answer
whether the classes {+, −} are linearly separable or not.
b) Find the weight and bias values that can estimate the optimal
hyperplane for the given data points.

Class X1 X2
1 4 1
1 4 -1
1 6 0
-1 1 0
-1 0 1
-1 0 -1

13 3
Compare and contrast logistic and polynomial regression algorithms,
highlighting their unique characteristics, strengths, and weaknesses.

14 Consider the following Bayesian network. A, B, C, and D are Boolean 3


random variables. If we know that A is true, what is the probability of D
being true?
15 Given a training dataset comprising the number of hours a student studies 3
(x₁), the number of hours a student sleeps (x₂), and the corresponding score
obtained, the objective is to develop a multiple linear regression model. The
model will predict the score (target variable) based on the features x₁ and
x₂. Based on this information answer the following questions.

Studied hours Sleep hours Score


7 9 91
4 4 65
8 7 45
5 5 36
7 8 ?

a) Determine the coefficients of the multiple linear regression model


using the provided dataset.
b) Given a new instance, where a student studies for 7 hours (x₁ = 7)
and sleeps for 8 hours (x₂ = 8), what is the predicted score obtained
based on the computed multiple regression model parameters?

16 Analyze how Random Forest leverages ensemble learning to improve 3


predictive performance.

17 What role does Bayes' Theorem play in updating beliefs or predictions with 3
new evidence, and how does it offer a structured framework for making
decisions when faced with uncertainty?
18 Imagine you are tasked with implementing sentiment analysis using a Naive 2
Bayes classifier. Describe how does Laplace smoothing address the issue
of zero probabilities for words not seen in the training data for a particular
sentiment category? Provide a detailed explanation with a hypothetical
example.

You might also like