Total No. of Questions : 8] SEAT No.
8
23
PB2530 [6263]-428
[Total No. of Pages :2
ic-
B.E. (Computer Engineering) (Honors in Data Science)
tat
MACHINE LEARNING AND DATA SCIENCE
6s
9:1
(2019 Pattern) (Semester-VII) (410501)
02 91
3:5
Time : 2½ Hours] [Max. Marks : 70
0
41
Instructions to the candidates:
5/0 13
1) Attempt Q.1 or Q.2, Q.3 or Q.4, Q.5 or Q.6 and Q.7 or Q.8.
0
2) Figures to the right indicate full marks.
5/2
.23 GP
3) Neat diagrams must be drawn wherever necessary.
4) Assume suitable data, if necessary.
E
82
8
C
23
ic-
16
Q1) a) Explain various types of Hierarchical Clustering. [6]
tat
8.2
6s
.24
b) Cluster the following dataset using Agglomerative Hierarchical clustering
9:1
91
technique- [6]
49
3:5
X1 X2
30
41
A 185 72
01
02
B 170 56
5/2
GP
C 168 60
5/0
D 179 68
CE
82
8
E 182 72
23
.23
F 188 77
ic-
16
tat
8.2
Also show intermediate steps.
6s
c) What do you mean by unsupervised learning? Explain in detail. [6]
.24
9:1
91
OR
49
3:5
Q2) a) How to measure the quality of clustering? Explain any three measures.[6]
30
41
b) What are different types of partitional clustering? Explain any two of
01
02
them. [6]
5/2
GP
c) What do you mean by Density-Based Spatial Clustering? Explain in detail.
5/0
[6]
CE
82
Q3) a) Explain a biological neuron along with its parts. [4]
.23
b) What are the types of artificial neural network? [6]
16
c) Explain Generalized Delta Learning Rule. [7]
8.2
OR
.24
[6263]-428 1 P.T.O.
49
Q4) a) What are the limitations of MLP? [4]
8
23
b) Explain the process of training a perceptron. [6]
ic-
tat
c) How does the learning rate affect the training of the Neural Network?
6s
What do you mean by Hyperparameters? [7]
9:1
02 91
3:5
0
41
Q5) a) Illustrate Gradient descent optimization using an example. [6]
5/0 13
b) Explain Recursive Neural Network. [6]
0
5/2
.23 GP
c) What are the different types of filters used in CNNs? [6]
OR
E
82
8
C
23
Q6) a) Does the size of the feature map always reduce upon applying the filters?
ic-
Explain why or why not. [6]
16
tat
8.2
6s
b) Explain CNN architecture along with diagram. [6]
.24
c) Explain Recursive Neural Network.
9:1 [6]
91
49
3:5
30
41
01
Q7) a) Write short note on document representation. [6]
02
5/2
GP
b) Illustrate tokenization with an example. [6]
5/0
CE
c) What are the practical uses of feature extraction? [5]
82
8
23
.23
OR
ic-
16
tat
Q8) a) Write short note on - [6]
8.2
6s
.24
9:1
i) Stemming
91
49
3:5
ii) Lemmatization
30
41
b) What are various text similarity measures? Explain any two of them. [6]
01
02
5/2
GP
c) What do you mean by topic modelling? Explain Latent Dirichlet
5/0
Allocation. [5]
CE
82
.23
16
8.2
.24
[6263]-428 2
49
