Printed Page: 1 of 2 

Subject Code: KCS055

0Roll No: 0 0 0 0 0 0 0 0 0 0 0 0 0
 
B. TECH
(SEM-V) THEORY EXAMINATION 2020-21
MACHINE LEARNING TECHNIQUES
Time: 3 Hours Total Marks: 100
Note: 1. Attempt all Sections. If require any missing data; then choose suitably.
SECTION A
1. Attempt all questions in brief. 2 x 10 = 20
Qno. Question Marks CO
a. Explain the concept of machine learning. 2 1
b. Compare ANN and Bayesian networks. 2 4
c. What is the difference between linear and logistic regression? 2 2
d. Discuss support vectors in SVM? 2 2
e. Discuss overfitting and underfitting situation in decision tree learning. 2 3
f. What is the task of the E-step of the EM-algorithm? 2 2
g. Define the learning classifiers. 2 2
h. What is the difference between machine learning and deep learning? 2 1
i. What objective function do regression trees minimize? 2 2
j. What is the difference between Q learning and deep Q learning? 2 5
SECTION B

1
0Q
2. Attempt any three of the following:

13
Qno. Question Marks CO
29

2.
a. Apply KNN for following dataset and predict class of test example 10 3

24
0E

(A1=3, A2=7).Assume K=3

A1 A2 Class

5.
P2

7 7 True

.5
_Q

7 4 True
3 4 False 17
TU

|1
1 4 True
5 3 False
AK

AM

6 3 True
b. Describe the Kohonen Self-Organizing Maps and its algorithm. 10 4
55

c. Explain the various learning models for reinforcement learning. 10 5

1:

d. Explain the role of genetic algorithm? Discuss the various phases 10 5

1

considered in genetic algorithm.

9:

e. Describe BPN algorithm in ANN along with a suitable example. 10 4

1
02

SECTION C
-2

3. Attempt any one part of the following:

ar

Qno. Question Marks CO

M

a. Why SVM is an example of a large margin classifier? Discuss the different 10 2

1-

kernels functions used in SVM.

|0

b. Explain the relevance of CBR. How CADET tool employs CBR? 10 3

4. Attempt any one part of the following:
Qno. Question Marks CO
a. Discuss the applications, properties, issues, and disadvantages of SVM. 10 2
b. Explain the Confusion Matrix with respect to Machine Learning 10 1
Algorithms.

1 | P a g e  
 
AKTU_QP20E290QP | 01-Mar-2021 9:11:55 AM | 117.55.242.131
 Printed Page: 2 of 2 
Subject Code: KCS055
0Roll No: 0 0 0 0 0 0 0 0 0 0 0 0 0
 
5. Attempt any one part of the following:
a. Illustrate the operation of the ID3 training example. Consider 10 3
information gain as attribute measure.

1
0Q

13
29

2.
24
0E

5.
P2

b. Describe Markov Decision Process in reinforcement learning. 10 5

.5
6. Attempt any one part of the following:
_Q

Qno. Question 17 Marks CO

TU

|1
a. What is instance based learning? How Locally Weighted Regression is 10 3
different from Radial basis function networks?
AK

AM

b. How is Bayes theorem used in machine learning? How naive Bayes algorithm 10 2
is different from Bayes theorem?
55

7. Attempt any one part of the following:

Qno. Question Marks CO
11:

a. Compare regression, classification and clustering in machine learning 10 1

9:

along with suitable real life applications?

b. Given below is an input matrix named I, kernel matrix, calculate the 10 4
1
02

Convoluted matrix C using stride =1 also apply max pooling on C.

-2
ar
M
1-
|0

2 | P a g e  
 
AKTU_QP20E290QP | 01-Mar-2021 9:11:55 AM | 117.55.242.131