152

BE. IV EXAMINATION NOV-DEC, 2012

COMPUTER ENGINNERING
MACHINE LEARNING (4CO205)
Duration: 3 hrs.

Max Marks: 100

Min Pass Marks: 35

Note: Every UNIT has one question having three parts (a), (b) and (c). Attempt any
two parts from every question. All question carry equal marks.
1 a.
b(i).
(ii).
(c).

2a(i).
(ii)
b(i).
(ii)
c.

UNIT-I
Define Machine Learning? What are the applications of machine Learning?
What is market basket analysis? How is it used?
What is the Rote Learning? And Define the Inductive Bias??
Write down the Candidate elimination-learning algorithm.
Consider the following sequence of positive and negative training examples
describing the concept Japanese Economy Car. Each training example
describes an order of car, with each car described by their Country of origin,
Manufacturer (Honda Toyota, Chrysler), Color (Blue, Green ,Red , White),
Decade, and Type(Economy, Sports).
Origin
Manufacturer Color
Type
Example
Decade
Type
Japan
Honda
Blue
1980
Economy Positive
Japan
Toyota
Green
1970
Sports
Negative
Japan
Toyota
Blue
1990
Economy Positive
USA
Chrysler
Red
1980
Economy Negative
Japan
Honda
White
1980
Economy Positive
Provide a hand trace of Candidate Elimination Algorithm learning from the
above training examples and hypothesis language. In particular, show the
specific and general boundaries of the version space after it has processed the
first training example, then the second training example, etc.
UNIT-II
What are the characteristics of decision tree learning?
What is the concept of over fitting in decision tree learning?
How many steps involves in rule post pruning.

10
05
05
10

05
05
05

Why prefer short hypotheses in decision tree Learning?

05
Use the table of examples below :
10
Exam Use Calculator Duration(hrs) Lecturer Term Difficulty
1
Yes
3
Jones
Summer Easy
2
Yes
3
Jones
Spring Difficulty
3
No
3
Smith
Spring Difficulty
4
No
2
Armstrong Summer Easy
5
Yes
2
Jones
Summer Easy
(i). Calculate the entropy of the set of five examples with respect to the binary
categorization into difficult and easy problems.
P.T.O.
(ii). Suppose an agent using the ID3 algorithm has chosen to use the Lecturer

3(a)

attribute of the Problem as the top node in the decision tree it is learning .In
English , why would the algorithm have chosen that attribute ? What would
the partially learned decision tree look like after that choice?
UNIT-III
Explain the followings :- PAC Learning, Bayesian belief networks
10

b.

What is the mistake bound for the Find-S Algorithm?

10

c.

Define Vapnik Chervonenkis Dimension. What are uses of VC dimension?

UNIT-IV
What are the difficulties in WSD? Write down the application of WSD?
Explain the following terms:-Application of HMMs, Formal Languages.
What is the Support Vector Machine? And Also Explain maximum margin
classifier?
UNIT-V
Suppose a genetic algorithm uses chromosomes of the form x = abcdefgh
with a fixed length of eight genes. Each gene can be any digit between 0
and 9. Let the fitness of individual x be calculated as:
f(x) = (a + b) (c + d) + (e + f) (g + h) ,
and let the initial population consist of four individuals with the following
chromosomes:
x1 = 6 5 4 1 3 5 3 2
x2 = 8 7 1 2 6 6 0 1
x3 = 2 3 9 2 1 2 8 5
x4 = 4 1 8 5 2 0 9 4
I.
Evaluate the fitness of each individual, showing all your workings, and
arrange them in order with the fittest first and the least fit last.
II.
Perform the following crossover operation:
(i)
Cross the fittest two individuals using onepoint crossover at
the middle point.
(ii)
Cross the second and third fittest individuals using a twopoint
crossover
How many selection methods to select the best chromosomes? Explain two?
Define the following:( Any two)
(i)
Parameter of Genetic Algorithm
(ii)
Permutation Encoding of Chromosome
(iii)
Michigan Approach

10

4 a.
b.
c.
5 a.

b.
c.

10
10
10
10

10
10