DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CS3491-ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

QUESTION BANK

R-2021

Prepared by
Mrs. M. Ambika, AP/CSE Page 1
 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

II YEAR / IV SEMESTER

REGULATION 2021

CS3491-ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

Faculty in Charge Head of the Department

Mrs. M. Ambika, M.E., Dr. K. Suresh, M.E., Ph.D.,

Assistant Professor, Associate Professor,

Department of CSE. Department of CSE.

Prepared by
Mrs. M. Ambika, AP/CSE Page 2
 INSTITUTION VISION & MISION

VISION:

To become a globally recognized ‘Centre of Academic Excellence’ providing Quality

Education to all students.

MISION:

To provide Quality Education in the fields of Engineering, Management, Information

Technology and other Engineering areas.

DEPARTMENT VISION & MISION

VISION:

To provide the quality education in Computer Science and Engineering and to mould the
students into self-confident and professionally competent individuals.

MISION:

M1: To produce successful graduates enriched with professional and leadership capabilities.

M2:To impart the skills necessary to continue education and grow Professionally.

M3: To inculcate strong ethical and human values.

M4: To establish a research centre in Computer Science and Engineering.

M5: To contribute towards empowering the rural youth with computer education.

Prepared by
Mrs. M. Ambika, AP/CSE Page 3
 PROGRAM EDUCATIONAL OBJECTIVES (PEOs)

Apply their technical competence in computer science to solve real world problems,
PEO1
with technical and people leadership.
Conduct cutting edge research and develop solutions on problems of social
PEO2
relevance.
Work in a business environment, exhibiting team skills, work ethics, adaptability
PEO3
and lifelong learning.

PROGRAM OUTCOMES (POs)

Engineering knowledge: Apply the knowledge of mathematics, science,

PO1 engineering fundamentals, and an engineering specialization to the solution of
complex engineering problems.
Problem analysis: Identify, formulate, review research literature, and analyze
PO2 complex engineering problems reaching substantiated conclusions using first
principles of mathematics, natural sciences, and engineering sciences.
Design/development of solutions: Design solutions for complex engineering
problems and design system components or processes that meet the specified needs
PO3
with appropriate consideration for the public health and safety, and the cultural,
societal, and environmental considerations.
Conduct investigations of complex problems: Use research-based knowledge and
PO4 research methods including design of experiments, analysis and interpretation of
data, and synthesis of the information to provide valid conclusions.
Modern tool usage: Create, select, and apply appropriate techniques, resources, and
PO5 modern engineering and IT tools including prediction and modeling to complex
engineering activities with an understanding of the limitations.
The engineer and society: Apply reasoning informed by the contextual knowledge
PO6 to assess societal, health, safety, legal and cultural issues and the consequent
responsibilities relevant to the professional engineering practice.
Environment and sustainability: Understand the impact of the professional
PO7 engineering solutions in societal and environmental contexts, and demonstrate the
knowledge of, and need for sustainable development.
Ethics: Apply ethical principles and commit to professional ethics and
PO8
responsibilities and norms of the engineering practice.
Individual and team work: Function effectively as an individual, and as a member
PO9
or leader in diverse teams, and in multidisciplinary settings.
PO10 Communication: Communicate effectively on complex engineering activities with
the engineering community and with society at large, such as, being able to
comprehend and write effective reports and design documentation, make effective
Prepared by
Mrs. M. Ambika, AP/CSE Page 4
 presentations, and give and receive clear instructions.
Project management and finance: Demonstrate knowledge and understanding of
the engineering and management principles and apply these to one’s own work, as a
PO11
member and leader in a team, to manage projects and in multidisciplinary
environments.
Life-long learning: Recognize the need for, and have the preparation and ability to
PO12 engage in independent and life-long learning in the broadest context of
technological change.

PROGRAM SPECIFIC OUTCOMES (PSOs)

Exhibit design and programming skills to build and automate business solutions
PSO1
using cutting edge technologies.
Strong theoretical foundation leading to excellence and excitement towards
PSO2
research, to provide elegant solutions to complex problems.
Ability to work effectively with various engineering fields as a team to design, build
PSO3
and develop system applications.

Prepared by
Mrs. M. Ambika, AP/CSE Page 5
 CS3491 ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING LTPC
3024
COURSE OBJECTIVES:
The main objectives of this course are to:
 Study about uninformed and Heuristic search techniques.
 Learn techniques for reasoning under uncertainty
 Introduce Machine Learning and supervised learning algorithms
 Study about ensembling and unsupervised learning algorithms
 Learn the basics of deep learning using neural networks
UNIT I PROBLEM SOLVING 9
Introduction to AI - AI Applications - Problem solving agents – search algorithms – uninformed
search strategies – Heuristic search strategies – Local search and optimization problems –
adversarial search – constraint satisfaction problems (CSP)
UNIT II PROBABILISTIC REASONING 9
Acting under uncertainty – Bayesian inference – naïve bayes models. Probabilistic reasoning –
Bayesian networks – exact inference in BN – approximate inference in BN – causal networks.
UNIT III SUPERVISED LEARNING 9
Introduction to machine learning – Linear Regression Models: Least squares, single & multiple
variables, Bayesian linear regression, gradient descent, Linear Classification Models:
Discriminant function – Probabilistic discriminative model - Logistic regression, Probabilistic
generative model – Naive Bayes, Maximum margin classifier – Support vector machine,
Decision Tree, Random forests
UNIT IV ENSEMBLE TECHNIQUES AND UNSUPERVISED LEARNING 9
Combining multiple learners: Model combination schemes, Voting, Ensemble Learning -
bagging, boosting, stacking, Unsupervised learning: K-means, Instance Based Learning: KNN,
Gaussian mixture models and Expectation maximization
UNIT V NEURAL NETWORKS 9
Perceptron - Multilayer perceptron, activation functions, network training – gradient descent
optimization – stochastic gradient descent, error backpropagation, from shallow networks to
deep networks –Unit saturation (aka the vanishing gradient problem) – ReLU, hyperparameter
tuning, batch normalization, regularization, dropout
TOTAL:
45 PERIODS

Prepared by
Mrs. M. Ambika, AP/CSE Page 6
 COURSE OUTCOMES:
At the end of this course, the students will be able to:

CO1 Use appropriate search algorithms for problem solving

CO2 Apply reasoning under uncertainty
CO3 Build supervised learning models
CO4 Build ensembling and unsupervised models
CO5 Build deep learning neural network models

CO’s-PO’s & PSO’s MAPPING

PO’s PSO’S
CO’s PO
PO1 PO2 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
3
1 3 2 2 3 1 3 2 - - - - 1 3 3 3

2 3 2 2 3 1 3 2 - - - - 1 3 3 3

3 1 2 1 3 2 3 2 - - - - 1 3 3 3

4 1 2 3 1 3 3 2 - - - - 1 3 3 3

5 2 2 2 - 3 3 2 - - - - 1 3 3 3

Avg 2 2 2 2 2 3 2 - - - - 1 3 3 3

1-Low, 2-Medium, 3-High, ‘-‘– No correlation

Text Books
1. Stuart Russell and Peter Norvig, “Artificial Intelligence – A Modern Approach”, Fourth
Edition, Pearson Education, 2021.
2. Ethem Alpaydin, “Introduction to Machine Learning”, MIT Press, Fourth Edition, 2020.

Reference Books
1. Dan W. Patterson, “Introduction to Artificial Intelligence and Expert Systems”, Pearson
Education,200
2. Kevin Night, Elaine Rich, and Nair B., “Artificial Intelligence”, McGraw Hill, 2008
3. Patrick H. Winston, "Artificial Intelligence", Third Edition, Pearson Education, 2006
4. Deepak Khemani, “Artificial Intelligence”, Tata McGraw Hill Education, 2013
(http://nptel.ac.in/)
Prepared by
Mrs. M. Ambika, AP/CSE Page 7
 5. Christopher M. Bishop, “Pattern Recognition and Machine Learning”, Springer, 2006.
6. Tom Mitchell, “Machine Learning”, McGraw Hill, 3rd Edition,1997.
7. Charu C. Aggarwal, “Data Classification Algorithms and Applications”, CRC Press,
2014
8. Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar, “Foundations of Machine
Learning”, MIT Press, 2012.
9. Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2016

Prepared by
Mrs. M. Ambika, AP/CSE Page 8
 UNIT I

PROBLEM SOLVING

PART -A
CO
Q.
Questions Mappin BT Level Complexity
No
g
1 Define artificial intelligence. CO1 Remember Low
2 What is adversarial search? CO1 Understand Low
3 List the characteristics of AI. CO1 Remember Low
4 What are agents for AI and software doing? CO1 Understand Low
How will you measure the performance of AI
5 CO1 Understand Low
application?
Differentiate between uninformed and
6 CO1 Understand Low
informed search algorithms
List the steps involved in simple problem
7 CO1 Remember Low
solving agent
8 Give example for real world end toy problems. CO1 Remember Low
State on which basis search algorithms are
9 CO1 Remember Low
chosen?
Evaluate performance of problem-solving
10 CO1 Evaluate High
method based on depth-first search algorithm?
11 Why does one go for heuristics search? CO1 Understand Low
When a heuristic function h is said to be
12 admissible? Give an admissible heuristic CO1 Understand Low
function for TSP?
How can we avoid ridge and plateau in hill
13 CO1 Understand Low
climbing?
How can minimax also be extended for game
14 CO1 Understand Low
of chance?

PART B
CO
Q. Complexit
Questions Mappin BT Level
No y
g
1 (i) Explain any two Informed Search CO1 Understand Medium
Prepared by
Mrs. M. Ambika, AP/CSE Page 9
 Strategies
(ii) Explain the heuristic functions with
examples.
Explain the following types of hill climbing
search techniques.
2 (i) Simple hill climbing CO1 Understand Medium
(ii) Steepest- Ascent hill climbing
(iii) Simulated Annealing
3 Discuss AO* algorithm in detail with example. CO1 Understand Medium
4 Describe Minmax algorithm in detail CO1 Understand Medium
Solve crypt arithmetic problem for the below
problem
SEND
+MORE
5 CO1 Create High
----------------------------
MONEY
No two letters have the same value. The sums
of the digits must be shown in the problem.
Evaluate Alpha-Beta pruning and Alpha-Beta
algorithm

6 CO1 Evaluate High

Explain iterative deepening search algorithm

7 CO1 Understand Medium
with an example
Apply hill climbing algorithm to solve 8-
8 CO1 Apply Medium
queens problem.
Define Artificial Intelligence. Explain the
9 techniques of AI and describe the CO1 Understand Medium
characteristics of AI.
Discuss Constraint Satisfaction problem with
10 an algorithm for solving a Crypt arithmetic CO1 Understand Medium
problem.

Prepared by
Mrs. M. Ambika, AP/CSE Page 10
 UNIT II

PROBABILISTIC REASONING

PART -A
CO
Q.
Questions Mappin BT Level Complexity
No
g
1 Define Uncertainty. CO2 Remember Low
2 State Bayes’ rule. CO2 Remember Low
3 Differentiate logical and probabilistic assertions. CO2 Understand Low
4 Why a hybrid Bayesian network is called as such? CO2 Understand Low
Mention the needs of probabilistic reasoning in
5 CO2 Remember Low
AI.
Given that P(A)=0.3, P(A/B)=0.4 and P(B)=0.5,
6 CO2 Create High
Compute P(B/A).
Define principle of maximum expected utility
7 CO2 Remember Low
(MEU)?
What does the full joint probability distribution
8 CO2 Understand Low
specify?
What is the difference between stochastic gradient
9 CO2 Understand Low
descent (SGD) and gradient descent (GD)?
10 Why does uncertainty arise? CO2 Understand Low
11 What is the need for utility theory in uncertainty? CO2 Understand Low

PART B
CO
Q.
Questions Mappin BT Level Complexity
No
g
(i) Elaborate on unconditional probability and
conditional probability with an example.
Understan
1 (ii) What is a Bayesian network? Explain the steps CO2 Medium
d
followed to construct a Bayesian network with
an example.
Prepared by
Mrs. M. Ambika, AP/CSE Page 11
 What do you mean by inference in Bayesian
Understan
2 networks? Outline inference by enumeration with CO2 Medium
d
an example.
Demonstrate the use of Bayes’ rule with an
example in a doctor finding the probability
3 CO2 Create High
P(disease /Symptoms) before and after the
decease becomes epidemic.
Briefly explain about how the sustainability of Understan
4 CO2 Medium
enumeration algorithm can be improved. d
Consider the following set of propositions:
 Patient has spots
 Patient has measles
 Patient has high fever
 The patient has Rocky Mountain spotted
fever.
 The patient has previously been inoculated
5 CO2 Create High
against measles.
 Patient was recently bitten by a tick
 Patient has an allergy.
(i) Create a network that defines the casual
connections among these nodes
(ii) Make it a Bayesian network by constructing
the necessary conditional probability matrix.
Construct a Bayesian Network and define the
necessary CPTs for the given scenario. We have a
bag of tree biased coins a, b and c with
probabilities of coming up heads of 20%, 60%
and 80%, respectively. One coin is drawn
randomly from the bag ( with equal likelihood of
6 drawing each of the three coins) and then the coin CO2 Create High
is flipped three times to generate the outcomes
X1, X2, and X3.
(i) Draw a Bayesian network corresponding to
this setup and define the relevant CPTs.
(ii) Calculate which coin is most likely to have
been drawn if the flips come up HHT.
Define uncertain knowledge, prior probability and
conditional probability. State the Bayes’ theorem. Understan
7 CO2 Medium
How it is useful for decision making under d
uncertainty? Explain belief networks briefly?
Prepared by
Mrs. M. Ambika, AP/CSE Page 12
 How to get the exact inference form Bayesian Understan
8 CO2 Medium
network? d
How to get the approximate inference from Understan
9 CO2 Medium
Bayesian network? d
Understan
10 Explain Naïve Bayes Classifier with an Example CO2 Medium
d
Explain variable elimination algorithm for Understan
11 CO2 Medium
answering queries on Bayesian networks? d
12 Harry installed a new burglar alarm at his home to CO2 Create High
detect burglary. The alarm reliably responds at
detecting a burglary but also responds for minor
earthquakes. Harry has two neighbors David and
Sophia, who have taken a responsibility to inform
Harry at work when they hear the alarm. David
always calls Harry when he hears the alarm, but
sometimes he got confused with the phone ringing
and calls at that time too. On the other hand,
Sophia likes to listen to high music, so sometimes
she misses to hear the alarm. Here we would like
to compute the probability of Burglary Alarm.
Calculate the probability that alarm has sounded,
but there is neither a burglary, nor an earthquake
occurred, and David and Sophia both called the
Harry.

Prepared by
Mrs. M. Ambika, AP/CSE Page 13
 The following table gives data set about stolen
vehicles. Using Naive Bayes classifier classify, the
new data {Color: Red, Type: SUV, Origin:
Domestic}

Color Type Origin Stolen

Red Sports Domestic Yes
Red Sports Domestic No
13 CO2 Analyze Medium
Red Sports Domestic Yes
Yellow Sports Domestic No
Yellow Sports Imported Yes
Yellow SUV Imported No
Yellow SUV Imported Yes
Yellow SUV Domestic No
Red SUV Imported No
Red Sports Imported Yes

Prepared by
Mrs. M. Ambika, AP/CSE Page 14
 UNIT III

SUPERVISED LEARNING

PART –A
CO
Q.
Questions Mappin BT Level Complexity
No
g
Outline the difference between supervised
1 CO3 Understand Low
learning and unsupervised learning.
2 What is a random forest? CO3 Understand Low
3 What is the niche of machine learning? CO3 Understand Low
4 State the logic behind Gaussian processes. CO3 Remember Low
5 How can overfitting be avoided? CO3 Understand Low
6 Assume a disease so rare that it is seen in only CO3 Create High
one person out of every million. Also assume that
we have a test that is effective in that if a person

Prepared by
Mrs. M. Ambika, AP/CSE Page 15
 has the disease, there is a 99 percent chance that
the test result will be positive; however, the test is
not perfect, and there is a one in a thousand
chance that the test result will be positive on a
healthy person. Assume that a new patient arrives
and the test result is positive. What is the
probability that the patient has the disease?
7 What is training set and test set? CO3 Understand Low
Compare and Contrast supervised learning and
8 CO3 Evaluate High
unsupervised learning.
Is linear discriminant analysis classification or
9 CO3 Understand Low
regression?
What Is Pruning in Decision Trees, and How Is It
10 CO3 Understand Low
Done?
You’ve built a random forest model with 10000
trees. You got delighted after getting training
11 error as 0.00. But, the validation error is 34.23. CO3 Create High
What is going on? Haven’t you trained your
model perfectly?
Is linear discriminant analysis classification or
12 CO3 Understand Low
regression?

PART B
Q. CO
N Questions Mappin BT Level Complexity
o g
Elaborate on logistics regression with an
1 example. Explain the process of computing CO3 Understand Medium
coefficients.
What is a classification tree? Explain the steps
2 to construct a classification tree. List and CO3 Understand Medium
explain about the different procedures used.
Describe the general procedure of random forest
3 CO3 Understand Medium
algorithm.
With a suitable example explain knowledge
4 CO3 Understand Medium
extraction in detail.
5 State when and why you would use random CO3 Understand Medium

Prepared by
Mrs. M. Ambika, AP/CSE Page 16
 forests vs SVM?
Explain the principles of the gradient descent
6 algorithm. Accompany your explanation with a CO3 Understand Medium
diagram.
What is a classification tree? Explain the steps
to construct a classification tree. List and
explain about the different procedures used.
You have to examine the relationship between
the age and price for used cars sold in the last
year by a car dealership company. Here is the
table of the data:

Car Age (in years) Price(in dollars)

4 6300
7 CO3 Analyze Medium
4 5800
5 5700
5 4500
7 4500
7 4200
8 4100
9 3100
10 2100
11 2500
12 2200
Explain the principle of the gradient descent
algorithm. Accompany your explanation with a
8 diagram. Explain the use of all the terms and CO3 Understand Medium
constants that you introduce and comment on
the range of values that they can take.
The values of x and their corresponding values
of y are shown in the table below.
9 X 1 2 3 4 5 6 7 CO3 Create High
Y 3 4 5 5 6 8 10
i) Find the least square regression line y=ax+b
ii) Estimate the value of y when x=10

Prepared by
Mrs. M. Ambika, AP/CSE Page 17
 UNIT IV

ENSEMBLE TECHNIQUES AND UNSUPERVISED LEARNING

PART -A
CO
Q.
Questions Mappin BT Level Complexity
No
g
1 Define ensemble Learning. CO4 Remember Low
What is the significance of Gaussian mixture
2 CO4 Understand Low
model?
3 When does an algorithm become unstable? CO4 Understand Low
Why is the smoothing parameter h need to be CO4
4 Understand Low
optimal?
5 Write the three types of ensemble learning. CO4 Understand Low
6 How expectation maximization is used in CO4 Understand Low
Prepared by
Mrs. M. Ambika, AP/CSE Page 18
 Gaussian mixture models?
7 Compare K means and Gaussian mixture? CO4 Evaluate High
What are Gaussian mixture models? How is CO4
8 Understand Low
expectation maximization used in it?
9 State the principle of maximum likelihood? CO4 Remember Low
How do you implement expectation maximization CO4
10 Understand Low
algorithm?

PART B
CO
Q.
Questions Mappin BT Level Complexity
No
g
(i) What is bagging and boosting? Give
example.
1 CO4 Understand Medium
(ii) Outline the steps in the AdaBoost algorithm
with an example.
Elaborate on the steps in expectation-
2 CO4 Understand Medium
maximization algorithm.
Assume an image has pixel size 240X180.
3 Elaborate how K means clustering can be used to CO4 Apply Medium
achieve lossy data compression of that image.
Explain in detail about combine multiple
4 CO4 Understand Medium
classifiers by voting.
Discuss various learning techniques involved in
5 CO4 Understand Medium
unsupervised learning.
List the applications of clustering and identify the
6 advantages and disadvantages of clustering CO4 Understand Medium
algorithms.
What is a Gaussian process? And explain in detail
7 of Gaussian parameter estimates with suitable CO4 Understand Medium
examples.
8 Explain details about KNN algorithm? CO4 Understand Medium
Describe briefly about unsupervised learning
9 CO4 Understand Medium
structure?
10 Consider five points {x1, x2, x3, x4, x5} with the CO4 Analyze Medium
following coordinates as a two dimensional sample
for clustering:
X1= (0.5, 1.75), x2= (1, 2), x3= (1.75, 0.25),
x4= (4, 1), x5= (6,3).

Prepared by
Mrs. M. Ambika, AP/CSE Page 19
 Illustrate the k-means algorithm on the above data
set. The required number of clusters is two and
initially, clusters are formed from random
distribution of samples: C1={x1, x2, x4} and
C2={x3, x5}

UNIT V

NEURAL NETWORKS

PART -A
CO
Q.
Questions Mappin BT Level Complexity
No
g
1 State the architecture of multilayer perceptron. CO5 Remember Low
2 Name any two activation functions CO5 Remember Low
3 Differentiate computer and human brain. CO5 Understand Low
Show the perceptron that calculates parity of its CO5
4 Understand Low
three inputs.
Prepared by
Mrs. M. Ambika, AP/CSE Page 20
 What is stochastic gradient descent and why is it CO5
5 Understand Low
used in the training of neural networks?
Why is ReLU better than Softmax? Give the CO5
6 Understand Low
equation for both.
7 Define perception and its types. CO5 Remember Low
8 What are the activation functions of MLP? CO5 Understand Low
9 Why do you need activation function? CO5 Understand Low
How do you solve the vanishing gradient problem CO5
10 Understand Low
within a deep neural network?
Does stochastic gradient descent lead to faster CO5
11 Understand Low
training?
12 What are the limitations of perceptron? CO5 Understand Low

PART B
CO
Q.
Questions Mappin BT Level Complexity
No
g
Explain the step in the back propagation learning
1 algorithm. What is the importance of it in CO5 Understand Medium
designing neural networks?
Explain a deep feed forward network with neat
2 CO5 Understand Medium
sketch.
Elaborate the process of training hidden layers by
3 CO5 Understand Medium
ReLU in deep networks.
Briefly explain hints and the different ways it can
4 CO5 Understand Medium
be used
Draw the architecture of a single layer perceptron
5 (SLP) and explain its operation. Mention its CO5 Understand Medium
advantages and disadvantages.
How do you tune hyper parameters for better
6 CO5 Understand Medium
neural network performance? Explain in detail.
Compare and contrast shallow net and deep
7 CO5 Evaluate High
learning net.
List the factors that affect the performance of
8 CO5 Understand Medium
multilayer feed-forward neural network.
Discuss the architecture of a multilayer perceptron
9 (MLP) and explain its operation. Mention its CO5 Understand Medium
advantages and disadvantages.

Prepared by
Mrs. M. Ambika, AP/CSE Page 21
 THANK YOU
Prepared by
Mrs. M. Ambika, AP/CSE Page 22
 ALL THE BEST

Prepared by
Mrs. M. Ambika, AP/CSE Page 23