X
(https://swayam.gov.in) (https://swayam.gov.in/nc_details/NPTEL)
nandu544@gmail.com
NPTEL (https://swayam.gov.in/explorer?ncCode=NPTEL) » Introduction to Machine Learning (course)
Click to register
for Certification
exam
Week 9 : Assignment 9
(https://examform.nptel.ac.in/2025_01/exam_form/dashboard)
The due date for submitting this assignment has passed.
If already Due on 2025-03-26, 23:59 IST.
registered, click
to check your Assignment submitted on 2025-03-19, 12:09 IST
payment status
1) Consider the Markov Random Field given below. We need to delete one edge 1 point
(without deleting any nodes) so that in the resulting graph, B and F are independent given A.
Which of these edges could be deleted to achieve this independence?
Course Note: In each option, we only delete one edge from the original graph.
outline
About
NPTEL ()
How does an
NPTEL
online
course
work? ()
Week 0 ()
AC
Week 1 () BE
CE
Week 2 ()
AE
Week 3 () Yes, the answer is correct.
Score: 1
Accepted Answers:
Week 4 ()
BE
CE
Week 5 ()
2) Consider the Markov Random Field from question 1. We need to delete one node 1 point
Week 6 ()
(and also delete the edges incident with that node) so that in the resulting graph, B and C are
independent given A. Which of these nodes could be deleted to achieve this independence?
Week 7 ()
Note: In each option, we only delete one node and its incident edges from the original graph.
Week 8 () D
E
Week 9 ()
F
Undirected None of the above
Graphical
Yes, the answer is correct.
Models -
Score: 1
Introduction
Accepted Answers:
and
E
Factorization
(unit?
unit=104&less 3) Consider the Markov Random Field from question 1. Which of the nodes has / have 1 point
on=105) the largest Markov blanket (i.e. the Markov blanket with the most number of nodes)?
Undirected A
Graphical
B
Models -
Potential C
Functions D
(unit?
E
unit=104&less
on=106) F
Hidden Yes, the answer is correct.
Markov
Score: 1
Models (unit? Accepted Answers:
unit=104&less A
on=107) C
Variable
4) Consider the Bayesian Network given below. Which of the following independence 1 point
Elimination
relations hold?
(unit?
unit=104&less
on=108)
Tree Width
and Belief
Propagation
(unit?
unit=104&less
on=109)
Week 9
Feedback
Form:Introduct
ion to Machine A and B are independent if C is given
Learning!! A and B are independent if no other variables are given
(unit?
C and D are not independent if A is given
unit=104&less
on=290) A and F are independent if C is given
Quiz: Week 9 Yes, the answer is correct.
: Assignment
9
(assessment? Score: 1
name=316) Accepted Answers:
A and B are independent if no other variables are given
Week 10 () A and F are independent if C is given
Week 11 () 5) In the Bayesian Network from question 4, assume that every variable is binary. 1 point
What is the number of independent parameters required to represent all the probability tables for
the distribution?
Week 12 ()
8
Text
12
Transcripts
() 16
24
Download 36
Videos ()
Yes, the answer is correct.
Score: 1
Books ()
Accepted Answers:
12
Problem
Solving
6) In the Bayesian Network from question 4, suppose variables A, C, E can take four 1 point
Session -
possible values, while variables B, D, F are binary. What is the number of independent
Jan 2025 ()
parameters required to represent all the probability tables for the distribution?
24
36
48
64
84
Yes, the answer is correct.
Score: 1
Accepted Answers:
48
7) In the Bayesian Network from question 4, suppose all variables can take 4 values. 1 point
What is the number of independent parameters required to represent all the probability tables for
the distribution?
72
90
108
128
144
Yes, the answer is correct.
Score: 1
Accepted Answers:
90
8) Consider the Bayesian Network from question 4. which of the given options are 1 point
valid factorizations to calculate the marginal P (E = e) using variable elimination (need not be the
optimal order)?
∑ BP(B) ∑ AP(A) ∑ DP(D | A) ∑ CP(C | A, B) ∑ FP(E = e | C)P(F | C)
∑ AP(A) ∑ DP(D | A) ∑ BP(B) ∑ CP(C | A, B) ∑ FP(E = e | C)P(F | C)
∑ BP(B) ∑ AP(D | A) ∑ DP(A) ∑ FP(C | A, B) ∑ CP(E = e | C)P(F | C)
∑ AP(B) ∑ BP(D | A) ∑ DP(A) ∑ FP(C | A, B) ∑ CP(E = e | C)P(F | C)
∑ AP(A) ∑ BP(B) ∑ CP(C | A, B) ∑ DP(D | A) ∑ FP(E = e | C)P(F | C)
No, the answer is incorrect.
Score: 0
Accepted Answers:
∑ BP(B) ∑ AP(A) ∑ DP(D | A) ∑ CP(C | A, B) ∑ FP(E = e | C)P(F | C)
∑ AP(A) ∑ DP(D | A) ∑ BP(B) ∑ CP(C | A, B) ∑ FP(E = e | C)P(F | C)
∑ AP(A) ∑ BP(B) ∑ CP(C | A, B) ∑ DP(D | A) ∑ FP(E = e | C)P(F | C)
9) Consider the MRF given below. Which of the following factorization(s) of P (a, b, c, 1 point
d, e) satisfies/satisfy the independence assumptions represented by this MRF?
1
P(a, b, c, d, e) = ψ (a, b, c, d)ψ 2(b, e)
Z 1
1
P(a, b, c, d, e) = ψ (b)ψ 2(a, c, d)ψ 3(a, b, e)
Z 1
1
P(a, b, c, d, e) = ψ (a, b)ψ 2(c, d)ψ 3(b, e)
Z 1
1
P(a, b, c, d, e) = Z ψ 1(a, b)ψ 2(c, d)ψ 3(b, d, e)
1
P(a, b, c, d, e) = Z ψ 1(a, c)ψ 2(b, d)ψ 3(b, e)
1
P(a, b, c, d, e) = Z ψ 1(c)ψ 2(b, e)ψ 3(b, a, d)
Partially Correct.
Score: 0.25
Accepted Answers:
1
P(a, b, c, d, e) = ψ (a, b, c, d)ψ 2(b, e)
Z 1
1
P(a, b, c, d, e) = ψ (a, b)ψ 2(c, d)ψ 3(b, e)
Z 1
1
P(a, b, c, d, e) = ψ (a, c)ψ 2(b, d)ψ 3(b, e)
Z 1
1
P(a, b, c, d, e) = ψ (c)ψ 2(b, e)ψ 3(b, a, d)
Z 1
10) The following figure shows an HMM for three time steps i = 1, 2, 3. Suppose that it 1 point
is used to perform part-of-speech tagging for a sentence. Which of the following statements
is/are true?
The X i variables represent parts-of-speech and the Y i variables represent the words in the
sentence.
The Y i variables represent parts-of-speech and the X i variables represent the words in the
sentence.
The X i variables are observed and the Y i variables need to be predicted.
The Y i variables are observed and the X i variables need to be predicted.
Yes, the answer is correct.
Score: 1
Accepted Answers:
The X i variables represent parts-of-speech and the Y i variables represent the words in the
sentence.
The Y i variables are observed and the X i variables need to be predicted.
