‫׀‬

‫׀‬
‫׀‬

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING
MODEL EXAM MODEL EXAM
Date :31.05.2024 Date :31.05.2024
Year/Sem:III/VI Time :3.00 hours ‫׀‬ Year/Sem:III/VI Time :3.00 hours
Subject code/Name :CS3491/ ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING Subject code/Name :CS3491/ ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
Max. Mark:100 Max. Mark:100
PART A (10x2=20) ‫׀‬ PART A (10x2=20)
1 What is adversarial search? [CO1,K1] ‫׀‬ 1 What is adversarial search? [CO1,K1]
2 State Ridge in hill climbing. [CO1,K1] ‫׀‬ 2 State Ridge in hill climbing. [CO1,K1]
3 Define uncertainty. [CO2,K1] ‫׀‬ 3 Define uncertainty. [CO2,K1]
4 Why a hybrid bayesian networks called as such? [CO2,K2] ‫׀‬ 4 Why a hybrid bayesian networks called as such? [CO2,K2]
Outline the diference between supervised learning and unsupervised Outline the diference between supervised learning and unsupervised
5 [CO3,K2] 5 [CO3,K2]
learning. learning.
6 List five popular algorithms of machine learning. [CO3,K1] ‫׀‬ 6 List five popular algorithms of machine learning. [CO3,K1]
7 What is the significance of Gaussian mixture model? [CO4,K1] ‫׀‬ 7 What is the significance of Gaussian mixture model? [CO4,K1]
8 Why is the smoothing parameter h need to be optimal? [CO4,K2] ‫׀‬ 8 Why is the smoothing parameter h need to be optimal? [CO4,K2]
9 Differentiate computer and human brain [CO5,K2] ‫׀‬ 9 Differentiate computer and human brain [CO5,K2]
10 Show the perceptron that calculates parity of it's three inputs. [CO5,K2] ‫׀‬ 10 Show the perceptron that calculates parity of it's three inputs. [CO5,K2]
PART B (5x13=65) ‫׀‬ PART B (5x13=65)
11 State the constraint satisfaction problem. Outline local search [CO1,K2] [13] 11 State the constraint satisfaction problem. Outline local [CO1,K2] [13]
a) a)
for constraint satisfaction problem with an example. search for constraint satisfaction problem with an example.
(OR) ‫׀‬ (OR)
b) Describe about min max algorithm with examples. [CO1,K2] [13] ‫׀‬ b) Describe about min max algorithm with examples. [CO1,K2] [13]

12 a) Demonstarte the use of Bayes' rule with an example in a [CO2,K2] 12 a) Demonstarte the use of Bayes' rule with an example in a [CO2,K2]
doctor finding the probability P (disease/symptoms) beforeand [13] ‫׀‬ doctor finding the probability P (disease/symptoms) [13]
after the disease becomes epidemic. beforeand after the disease becomes epidemic.

(OR) ‫׀‬ (OR)

b) What do you mean by inference in Bayesian networks? [CO2,K2] [13] b) What do you mean by inference in Bayesian networks? [CO2,K2] [13]
Outline the inference by enumeration with an example. ‫׀‬ Outline the inference by enumeration with an example.

13 a) Elaborate on logistics regression with an example. Explain the [CO3,K2] [13] 13 a) Elaborate on logistics regression with an example. Explain [CO3,K2] [13]
‫׀‬
process of computing coefficients. the process of computing coefficients.
(OR) ‫׀‬ (OR)
 b) With a suitable example explain knowledge extraction in [CO3,K2] [13] b) With a suitable example explain knowledge extraction in [CO3,K2] [13]
detail. detail.

14 a) Explain in detail about combining multiple classifiers by [CO4,K2] 14 a) Explain in detail about combining multiple classifiers by [CO4,K2]
voting. [13] voting. [13]

(OR) ‫׀‬ (OR)

b) b)
Elaborate the steps in expectation-maximization algorithm. [CO4,K2] [13] ‫׀‬ Elaborate the steps in expectation-maximization algorithm. [CO4,K2] [13]

15 a) Explain a deep feedforward network with a neat sketch. [CO5,K2] [13] ‫׀‬ 15 a) Explain a deep feedforward network with a neat sketch. [CO5,K2] [13]
(OR) (OR)
b) b)
Illustrate with examples of Gradient and Stochastic gradient Illustrate with examples of Gradient and Stochastic
[CO5,K2] [13] ‫׀‬ [CO5,K2] [13]
Descent. gradient Descent.

PART C (1x15=15) ‫׀‬ PART C (1x15=15)

Construct a training dataset. By using it, demonstrate the Construct a training dataset. By using it, demonstrate the
16 a) [CO1,K3] [15] 16 a) [CO1,K3] [15]
AdaBoost algorithm that makes an ensemble classifier. AdaBoost algorithm that makes an ensemble classifier.
(OR) ‫׀‬ (OR)

b) Discuss about K-Means and KNN with examples. [CO2,K2] [15] ‫׀‬ b) Discuss about K-Means and KNN with examples. [CO2,K2] [15]

‫׀‬

SUBJECT INCHARGE HOD IQAC PRINICIPAL ‫׀‬ SUBJECT INCHARGE HOD IQAC PRINICIPAL