USN

Model Question Paper-I with effect from 2024

Sixth Semester B.E Degree Examination

Machine Learning
(21AI63)
TIME: 03 Hours Max. Marks: 100

Note: Answer any FIVE full questions, choosing at least ONE question from each
module.
Module -1 Marks

a Define Machine Leaning? Explain the applications of Machine 10

Learning.

b Consider the “Japanese Economy Car” concept and instance the 10

hypothesis using Candidate Elimination Learning algorithm.

OR
Q. a Discuss the features of an unbiased Learner. 10
02
b Explain Find-S algorithm ad show its 10
working by taking the enjoy sport
concept and training instances given in
Table .
 Module-2
Q. a Explain the following with respect to designing a learning 10
03 system

a. Choosing the Training Example

b. Choosing the target function

c. Choosing a representation for the target function

b With the code snippets show how Grid Search and Randomized Search 10
helps in Fine Tuning a model.

OR
Q. a In context to prepare the data for Machine Learning algorithms, Write 10
04 a note on

a. Data Cleaning

b. Handling text and categorical attributes

c. Feature scaling

b With the code snippets show how data’s are discovering and 10
visualizing?
Module-3

Q. a List out Types and Important Terms used in Support Vector machine.
05
10
b Discuss various Regularized linear Models with an example graph. 10
OR
Q. a Explain various Classifications in details. 10
06
c 10
Explain Nonlinear SVM classification in short

Module-4
Q. a
07 With an example dataset examine how Decision Trees are used in
making predictions. 10

b Explain The CART Training Algorithm. Identify the features of

Regression and Instability w.r.t decision trees
10
OR
Q. a In context to Ensemble methods determine the concepts of 10
08
i) Bagging and Pasting.
 ii) Voting Classifiers

b Examine the following boosting methods along with code snippets. 10

i) AdaBoost
ii) Gradient Boosting
Module-5
Q. a Write Bayes theorem. Identify the relationship between Bayes 10
09 theorem and the
problem of concept learning?
b

Show that how Maximum Likelihood Hypothesis is helpful 10

for predicting probabilities.

OR
Q. a Construct Naïve Bayes Classifier with an Example. 10
10
b Derive the EM Algorithm in detail. 10

Table showing the Bloom’s Taxonomy Level, Course Outcome and Program Outcome

Bloom’s Course
Question Program Outcome
Taxonomy Outcom
e
Level attached

(a) L1
CO 01 PO01, PO 02

Q.1 L2 CO 01 PO 01, PO 02, PO 03

(b)

(a) L1 CO 01 PO01, PO 02

Q.2 (b) L2 CO 01 PO 01, PO 02, PO 03

(a) L2 CO 02 PO 01, PO 02, PO 03

Q.3 (b) L2 CO 02 PO 01, PO 02, PO 03

(a) L2 CO 02 PO 01, PO 02, PO 03

Q.4 (b) L2 CO 02 PO 01, PO 02, PO 03

(a) L2 CO 03 PO 01, PO 03

(b) L2 CO 03 PO 02, PO 03
Q.5 (a) L2 CO 03 PO 01, PO 03

(b) L2 CO 03 PO 02, PO 03

(a) L3 CO 04 PO 01, PO 02, PO 03

Q.7 (b) L2 CO 04 PO 01, PO 02, PO 03

(a) L3 CO 04 PO 01, PO 02, PO 03

Q.8 (b) L2 CO 04 PO 01, PO 02, PO 03

(a) L3 CO 05 PO 01, PO 02, PO 03

Q.9 (b) L2 CO 05 PO 01, PO 02, PO 03

(a) L3 CO 05 PO 01, PO 02, PO 03

(b) L2 CO 05 PO 01, PO 02, PO 03

Q.10
Lower order thinking skills
Bloom’s
Remembering Understanding Applying
Taxonom y
Levels (knowledge): (Comprehension): L2 (Application): L3
L1
Higher order thinking skills
Analyzing Valuating (Evaluation): Creating (Synthesis): L6
(Analysis):L4 L5