Assignment 2: Bayesian Networks and Classifiers
CSC384H – Fall 2009
Out: October 7, 2009
Due: November 2, 1 p. m. Written work should be handed in during class.
Programming
should be handed in via CDF, before class.
Assignment is worth 15% of your final mark
1.
Bayesian Network Inference (4 points).
In the Bayesian Network shown below, all
variables are binary with values Dom(A)={A,~A}, Dom(B)={B,~B}, etc.
The probability table values are as follows:
P(A)=0.9
P(B)=0.7
P(G)=0.75
P(D

C) = 0.9 ,
P(D
 ~
C) = 0.06
P(C

A,B) = 0.95 , P(C

A,~B) = 0.01 , P(C

~A,B) = 0.6 , P(C

~A,~B) = 0.03
P(E

C,G) = 0.95 , P(E

C,~G) = 0.01 , P(E

~C,G) = 0.9 , P(E

~C,~G) = 0.3
P(F

C,G) = 0.8 , P(F

C,~G) = 1.0 , P(F

~C,G) = 0.1 , P(F

~C,~G) = 0.5
Compute the following probabilities (show your work):
a)
P(E

A) (1/2 point)
b)
P(D

A,B) (1/2 point)
c)
P(F

~E) (1.5 points)
d)
P(G

B,F) (1.5 points)