Total No. of Questions: 8] SEAT No.

8
23
P403 [6003]-703
[Total No. of Pages : 4

ic-
tat
T.E. (I.T.)

7s
MACHINE LEARNING

9:0
(2019 Pattern) (Semester-I) (314443)

02 91
0:2
0
Time : 2½ Hours] [Max. Marks : 70

31
0/0 13
Instructions to the candidates:
1) Answer Q.1 or Q.2, Q.3 or Q.4, Q.5 or Q.6, Q.7or Q.8.
0
6/2
2) Neat diagrams must be drawn whererver necessary.
.23 GP

3) Fingures to the right side indicate full marks.

4) Assume suitable data if necessary.
E
81

8
C

23
Q1) a) State and explain need of Regression analysis. [CO2, L2] [4]

ic-
16

tat
b) How gradient descent does helps to optimize linear regression model?
8.2

7s
[CO2, L2] [6]
.24

9:0
c) What are the different ways to prevent overfitting [CO2, L2] [8]
91
49

0:2
OR
30
31

Q2) a) What are different cost functions to access the performance of linear
01
02

Regression model? In the given Dataset the outliers represent anomalies.

6/2

Which cost function will be more suitable and why? [CO2, L3] [5]
GP
0/0

b) Define of Multivariate Regression and State advantages and

CE
81

disadvantages of Multivariate Regression. [CO2, L2] [5]

8
23
Consider the following data
.23

Prize in Rs Amount ic-

16

tat
8.2

Demanded
7s
.24

1 10 40
9:0
91

c) 2 11 38
49

0:2
30

3 16 48
31

4 18 40
01
02

5 20 60
6/2
GP

i) Find values 0 and 1w.r.t. linear regression model which best fits
0/0

given data.
CE
81

ii) Interpret and explain equation of regression line.

.23

iii) Estimate the likely demand when the price is Rs. 15.
16

[CO2, L3] [8]

8.2
.24

P.T.O.
49
8
23
Q3) a) Consider following data. Which feature will be selected as a root node?

ic-
Use Information Gain. Played football is dependent feature. [CO4, L3]

tat
[10]

7s
9:0
Outlook Temperature Humidity Wind Played football(yes/no)

02 91
0:2
Sunny Hot High Weak No

0
31
Sunny 0/0 13
Hot High Strong No
0
6/2
Overcast Hot High Weak Yes
.23 GP

Rain Mild High Weak Yes

E
81

8
C

23
Rain Cool Normal Weak Yes

ic-
Rain Cool Normal Strong No
16

tat
8.2

7s
Overcast Cool Normal Strong Yes
.24

9:0
91
Sunny Mild High Weak No
49

0:2
30

Sunny Cool Normal Weak Yes

31
01
02

Rain Mild Normal Weak Yes

6/2
GP

Sunny Mild Normal Strong Yes

0/0
CE

Overcast Mild High Strong Yes

81

8
23
.23

Overcast Hot Normal Weak Yes

ic-
16

tat
Rain Mild High Strong No
8.2

7s
.24

9:0
91
49

0:2

b) Define and Explain following terms [7]

30
31

i) Bayesian Network
01
02

ii)  Bayes Classifier [CO4, L2]

Advantages and disadvantages of Nalve
6/2
GP
0/0

OR
CE
81

Q4) a) For the given data set apply Naive Bayes Classifier and predict the Class
.23

for Type of Type of family structure = Single Parent, Age group = Young,
16

and Income status=Low [CO4, L3] [10]

8.2
.24
49

[6003]-703 2
8
Type of family Age group Income status will they buy a car?

23
structure

ic-
Nuclear Young Low Yes

tat
7s
Extended old Low No

9:0
Childless Middle-aged Low No

02 91
0:2
Childless Young Medium Yes

0
Single Parent Middle-aged Medium Yes

31
Childless
0/0 13 Young Low No
0
6/2
Nuclear Old High Yes
.23 GP

Nuclear Middle-aged Medium Yes

E

Extended Middle-aged High Yes

81

8
C

23
Single Parent Old Low No

ic-
b) Define and explain following terms [7]
16

tat
i) Minority Class
8.2

7s
ii) Gini Index
.24

9:0
91
iii) Entropy
49

0:2
iv) Information Gain [CO4, L2]
30
31
01
02

Q5) a) Find all association rules in the following database in the following
6/2
GP

database with minimum support = 2 and minimum confidence = 75%

0/0

[CO5, L3] [10]

CE
81

8
Transactions Data Items

23
.23

1 Bread, Milk, Diaper

ic-
16

2 Bread, Milk, Diaper, Coke

tat
8.2

7s

3 Diaper, Beer, Eggs

.24

9:0

4 Bread, Milk, Coke

91
49

0:2
30

b) State & explain with appropriate example different types of linkage use in
31
01

clustering. [CO5, L2] [8]

02
6/2

OR
GP
0/0

Q6) a) Explain following Terms [8]

CE
81

i) Rule
.23

ii) Support
16

iii) Lift
8.2

iv) Confidence
.24

[CO5, L2]
49

[6003]-703 3
b) Apply KNN on the Following data. Find class of person whose height is

8
23
170 cm and weight is 57 kg. Consider value K = 5 and use Euclidian

ic-
distance formula. [CO5, L3] [10]

tat
Height Weight

7s
(CM) (KG) Class

9:0
02 91
167 51 Underweight

0:2
182 62 Normal

0
31
176 0/0 13
69 Normal
0
173 646/2 Normal
.23 GP

172 65 Normal
174 56 Underweight
E
81

8
169 58 Normal
C

23
ic-
173 57 Normal
16

tat
170 55 Normal
8.2

7s
.24

9:0
Q7) a) With the help of suitable diagram explain Biological Neuron. [CO6, L3]
91
49

0:2
[5]
30
31

b) Explain the architecture of feed forward neural network. State its

01
02

limitations. [CO6, 12] [7]

6/2
GP

c) What is deep learning? Explain different applications of deep learning

0/0

[CO6, L1] [5]

CE
81

8
23
.23

OR
ic-
16

Q8) a) What is perceptron? Explain multilayer perceptron in detail. [CO6, L3]

tat
8.2

[5]
7s
.24

9:0

b) Explain why we use non-linearity function? State and explain three types
91
49

of neurons that add non-linearity in their computations [CO6, 12] [7]

0:2
30

c) What is ANN? Explain McCulloch Pitts Neuron [CO6, L2] [5]

31
01
02
6/2
GP


0/0
CE
81
.23
16
8.2
.24
49

[6003]-703 4