Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
97 views

Assignment 9

This JSON contains the summary of an assignment document related to machine learning. The assignment contains multiple choice questions about concepts like conditional independence in graphs, hidden Markov models, variable elimination in graphical models, and belief propagation.

Uploaded by

Vijay
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
97 views

Assignment 9

This JSON contains the summary of an assignment document related to machine learning. The assignment contains multiple choice questions about concepts like conditional independence in graphs, hidden Markov models, variable elimination in graphical models, and belief propagation.

Uploaded by

Vijay
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Assignment 9

Introduction to Machine Learning


Prof. B. Ravindran
1. In the undirected graph given below, which nodes are conditionally independent of each other
given B? Select all that apply.

(a) A, D
(b) D, E
(c) C, D
(d) A, F
(e) None of the above

Sol. (e)
All pairs have an alternate route to each other that does not pass through B.
2. In the modified undirected graph given below, which nodes are conditionally independent of
each other given B? Select all that apply.

1
(a) C, D
(b) D, E
(c) E, C
(d) A, F
(e) None of the above

Sol. (a), (c)


There are no other paths for (a) and (c) except through B.
3. (2 marks) In the undirected graph given below, how many terms will be there in its potential
function factorization?

(a) 7
(b) 3
(c) 5
(d) 9

2
(e) None of the above

Sol. (b)
It’ll be the same as the number of max-cliques in the graph: (A, B, C, D), (A, E, D), (B, C,
F)
4. Which of these can be modeled as a HMM? Select all that apply.
(a) Machine translation
(b) Speech recognition
(c) Trajectory of a baseball
(d) Fibonacci sequence
Sol. (a), (b)
Refer to lecture
5. HMMs are used for finding these. Select all that apply.
(a) Probability of a given observation sequence
(b) All possible hidden state sequences given an observation sequence
(c) Most probable observation sequence given the hidden states
(d) Most probable hidden states given the observation sequence
Sol. (a), (d)
Refer to lecture.
6. (2 marks) For the given graphical model, what is the optimal variable elimination order when
trying to calculate P(E=e)?

(a) A, B, C, D
(b) D, C, B, A
(c) A, D, B, C
(d) D, A, C, A

Sol. (a)
XXXX
P (E = e) = P (a, b, c, d, e)
d c b a
XXXX
P (E = e) = P (a)P (b|a)P (c|b)P (d|c)P (e|d)
d c b a
X X X X
P (E = e) = P (e|d) P (d|c) P (c|b) P (a)P (b|a)
d c b a

7. What is the tree width for the GM in previous question?

3
(a) 5
(b) 4
(c) 3
(d) 2
Sol. (d)
Tree width = Size of max-clique = 2
8. Belief propagation is used for
(a) Calculating map estimate
(b) Calculating joint probability
(c) Calculating conditional marginal
(d) None of the above
Sol. (c)
Ref to lecture.

You might also like