Total No. of Questions : 10] SEAT No.

:
P3994 [5561]-701
[Total No. of Pages : 3

B.E. (IT)
MACHINE LEARNINGAND APPLICATIONS
(2015 Course) (414454) (Semester - I)
Time : 2½ Hours] [Max. Marks : 70
Instructions to the candidates:
1) Answer Q.1 or Q.2, Q.3 or Q.4, Q.5 or Q.6, Q.7 or Q.8, Q.9 or Q.10.

m
2) Neat diagrams must be drawn wherever necessary.
3) Figures to the right side indicate full marks.

co
4) Assume suitable data if necessary.

Q1) a) What is the need if dimensionality reduction? Explain subset selection.

s.
[6]
b) Write short note on PCA. [4]

Q2) a)
OR
on
Compare Supervised, Unsupervised, Semi-Supervised Learning with
iti
examples. [6]
b) What is training, testing and cross validation of machine learning models.
ttu

[4]
en

Q3) a) What are the support vectors and margins? Explain soft SVM and hard
SVM. [6]
b) What is overfitting and underfitting? What are the catalysts of overfitting?
om

[4]
OR
Q4) a) Elaborate Bias Variance dilemma. [6]
m

b) How the performance of regression is assessed? Write various

performance metrics used for it. [4]
st

Q5) a) Consider following 8 points P1 = [0.1, 0.6], P2 = [0.15, 0.71],

la

P3 = [0.08, 0.9], P4 = [0.16, 0.85], P5 = [0.2, 0.3], P6 = [0.25, 0.5],

P7 = [0.24, 0.1], P8 = [0.3, 0.2].
Apply K-Means clustering with initial centroids m1 & m2 where
m1 = P1, m2 = P8 and clusters are C1 & C2. Which cluster point P6
belongs to? What is updated value of m1 & m2. [10]
b) Write short note on feature tree & write best split algorithm. [6]
OR
P.T.O.
Q6) a) Apply apriori algorithm for following set of transactions and find all the
association rules with min support = 1 and min confidence = 60%. [10]
Tr. ID Transactions
1 1,3,4
2 2,3,5
3 1,2,3,5
4 2,5

m
b) Explain following impurity measures of classifiers. [6]
i) Gini Index.

co
ii) Entropy.

s.
Q7) a) Consider following dataset and predict the class of new instance X using
Navie Bayes Classification algorithm.
Tid Refund Marital Statuson Taxable Amount Evade
[10]
iti
1 Yes Single 125K No
ttu

2 No Married 100K No
3 No Single 70K No
en

4 Yes Married 120K No

5 No Divorced 95K Yes
om

6 No Married 60K No
7 Yes Divorced 220K No
m

8 No Single 85K Yes

st

9 No Married 75K No
la

10 No Single 90K Yes

X = (Refund = No, Marital Status = Married, Income = 120K).
b) Explain Expectation - maximization algorithm. [8]
OR

[5561]-701 2
Q8) a) Consider following dataset and predict the class of new instance X using
Navie Bayes. [10]
Day Outlook Temperatuer Humidity Wind Play Tennis
D1 Sunny Hot High Weak No
D2 Sunny Hot High Strong No
D3 Overcast Hot High Weak Yes
D4 Rain Mild High Weak Yes
D5 Rain Cool Normal Weak Yes
D6 Rain Cool Normal Strong No
D7 Overcast Cool Normal Strong Yes

m
D8 Sunny Mild High Weak No

co
D9 Sunny Cool Normal Weak Yes
D10 Rain Mild Normal Weak Yes
D11 Sunny Mild Normal Strong Yes

s.
D12 Overcast Mild High Strong Yes
D13 Overcast Hot Normal Weak Yes
D14 Rain Mild
Classification algorithm. on
High Strong No
iti
X = (Outlook = Sunny, Temp = Cool, Humidity = High, Wind = Strong).
b) Explain one dimensional and N-dimensional Gaussian Mixture. [8]
ttu

Q9) a) Implement AND function using perceptron network using following

en

bipolar inputs and target. [8]

X1 X2 T
om

1 1 1
1 –1 –1
–1 1 –1
m

–1 –1 –1
st

b) Explain deep learning with applications. [8]

OR
la

Q10)a) What is ensemble learning? Explain bagging and boosting, stacking in

brief. [8]
b) Explain the architecture of feed forward neural network. Give its
limitations. [8]



[5561]-701 3