16 a)
b)

17 a)
b)

18 a)

b)

19 a)

b)

G192151 Pages:3

६६६ Competition Type Class (profit)
Old Yes Software Down
Old No Software Down
Old No Hardware Down
Mid Yes Software Down
Mid Yes Hardware Down
Mid No Hardware Up
Mid No Software Up
New Yes Software Up
New No Hardware Up
New No Software Up

Explain back propagation algorithm for a multilayer Perceptron.
Explain the concept of Reduced Error pruning
PART D

Answer any two full questions, each carries 12 marks.
Explain Learning problem in Hidden Markov model and how it can be solved.
Describe the significance of soft margin hyperplane and explain how they are
computed.
Find the three clusters after one epoch for the following eight examples using
the k-means algorithm and Euclidean distance
Al=(2,10), A2=(2,5), A3=(8,4), A4=(5,8), A5=(7,5), A6=(6,4), A7=(1,2),
A8=(4,9). Suppose that the initial seeds (centers of each cluster) are Al, A4 and
A7.
Show the final result of hierarchical clustering with single link by drawing a

dendrogram.

1 0

8012 0

© | 0.51 0.25 0

2 | 0.84 0.16 0.14 0

६ | 0.28 0.77 070 045 0

F | 0.34 0.61 0.93 0.20 0.67 0

Explain DBSCAN algorithm for density based clustering. List out its
advantages compared to K-means.
State the mathematical formulation of the SVM problem. Give an outline of the

method for solving the problem.
‏بد بد‎ मर मर

Page 3of 3

(5)
(4)

(6)
(6)

(6)

(6)

(6)

(6)