USN : 1 D A Sub Code: 18CS62

Dr. Ambedkar Institute of Technology

(An Autonomous Institution, Aided by Government of Karnataka
Affiliated to Visvesvaraya Technological University, Belgaum & Approved by AICTE, New Delhi)
BDA Outer Ring Road, Near Jnana Bharathi Campus, Mallathahalli, Bengaluru-560056, Karnataka

Department of Computer Science & Engineering

Sixth Semester B.E. Degree (Autonomous) Continuous Internal Evaluation (CIE – I )
2021
Date : 17/05/2021 Sub. Title : Machine Learning Timings : 1.30-2.30
Day : Monday Sub. Code :18CS62 Time duration : 60 Mins
Branch : CSE Max marks : 25
Staff in-charge:
Semester : 6 CIE – I Asha K N
Asha Rani K P
Q. Course Blooms
No.
Note : Answer ALL the questions Marks
Outcome Level
1. a) Describe the following problems with respect to Tasks, 5M CO1 L2
Performance and Experience:
a. A Checkers learning problem
b. A Handwritten recognition learning problem
c. A Weather Prediction problem
b) Write FIND-S algorithm. Using Find-S Algorithm find the 5M CO2 L3
hypothesis to figure out if a person is Covid Positive or not
using the data given below with:

2. a) The Bank wants to decide whether or not an individual 5M CO2 L3

should be given a bank loan or not. Use Candidate -
Elimination Algorithm on the data below to find the
decision.

Page 1 of 4
b) Give Decision Tree representations for following Boolean 5M CO2 L3
Functions
a) A ˄ (B ˅ C)
b) A NAND B
OR
2 Construct the decision tree for the following training
c) 5M CO2 L3
examples using ID3 Algorithm.

Page 2 of 4
QUIZ Note : Answer ALL the questions 10X0.5=05 Marks
1. In general, to have a well-defined learning problem, we must identity which of the following

The measure of
The source of All of the
A The class of tasks B performance to be C D
experience above
improved
2. Concept learning inferred a ______ valued function from training examples of its input and
output.

All of the
A Decimal B Hexadecimal C Boolean D
above
3. FIND-S Algorithm starts from the most specific hypothesis and generalize it by considering
only ________ examples.

Negative or None of the

A Negative B Positive C D
Positive above
4. The Candidate-Elimination Algorithm represents the _____.

Elimination All of the

A Solution Space B Version Space C D
Space above
5. Inductive learning involves finding a __________.

Consistent Inconsistent Regular Irregular

A B C D
Hypothesis Hypothesis Hypothesis Hypothesis
6.
Which of the following is a valid production rule for the decision tree below?

IF Business
IF Business Appointment =
IF Business
Appointment = No &
Appointment = IF Temp above 70 =No No & Temp
Yes & Temp
A Temp above 70 = No B C THEN Decision = D above 70 = No
above 70 = Yes THEN Decision
THEN Decision = wear shorts
THEN Decision = wear jeans
wear slacks
= wear shorts

Page 3 of 4
7. Which of these is a reasonable definition of machine learning?

Machine
learning is the
Machine field of study
Machine learning is learning is the that gives
Machine learning
the science of field of computers the
A B learns from labeled C D
programming allowing robots ability to learn
data.
computers. to act without being
intelligently. explicitly
programmed.

8. Some of the problems below are best addressed using a supervised learning algorithm, and the
others with an unsupervised learning algorithm. Which of the following would you apply
supervised learning to?
Given a large
dataset of
Take a collection of medical records
1000 essays written from patients
Examine a large
on the US Economy, Given genetic suffering from
collection of
and find a way to (DNA) data from a heart disease,
emails that are
automatically group person, predict the try to learn
known to be
A these essays into a B odds of him/her C D whether there
spam email, to
small number of developing might be
discover if there
groups of essays that diabetes over the different
are sub-types of
are somehow next 10 years. clusters of such
spam mail.
“similar” or patients for
“related”. which we might
tailor separate
treatments.
9. Consider a dataset with Attrib1 and Attrib2 are two features (attributes) with two possible
values for each feature or attribute. How many hypotheses (Semantically Distinct
Hypothesis) can be expressed by the hypothesis language?
A 2 B 4 C 16 D 10
10. Amazon Movie Recommendation is__________________learning

A Supervised B Unsupervised C Reinforcement D None

Faculty Incharge: Dr. Siddaraju

Asha K N Dean(A),HOD, CSE
Asha Rani K P

Page 4 of 4