Answers to Exercises 2

CSE443 Reasoning Under Uncertainty

A. Nicholson & K. Korb

1 Bayesian Networks: Syntax and Semantics

Problem 1
Orville the Juggler. Orville, the robot juggler, drops balls quite often when its battery is low. In
previous trials, it has been determined that the probability that it will drop a ball when its battery
is low is 0.9. On the other hand when its battery is not low, the probability that it drops a ball is
only 0.01. The battery was recharged not so long ago, so there is only a 5% chance that the battery
is low. A robot observor, with a somewhat unreliable vision system, reports on whether or not Orville
has dropped the ball. This question involves constructing a belief network, containing only Boolean
variables, to represent and draw inferences about whether the battery is low depending on how well
Orville is juggling.
(a) Draw a belief network to represent the problem. Label the network nodes and indicate clearly the
direction of the arcs between the nodes.
(b) Write down the probability tables showing where the information on how Orville's success is
related to the battery level, and the robot observer's accuracy, are encoded in the network.
(c) Suppose the robot observer reports that Orville has dropped the ball. What e ect does this have
on your belief that the battery is low. What type of reasoning is being done?

Solution. The following is one possible model.

(a) Three Boolean nodes: BatteryLow!OrvilleDrops !ObserverSeesDrop.
(b) P(BL) =0.05, P(ODjBL)=0.9,P(ODj:BL) = 0.01. Not specied in question, but reasonable values
might be something like P(OSDjOD) = 0.8, P(OSDj:OD)=0.7.
(c) Observes drop, so Bel(OD) increases, so Bel(BL) increases: example of diagnostic reasoning.

Problem 2
Conditional Independence. Consider the following belief network for another medical diagnosis exam-
ple, where B=Bronchitis, S=Smoker, C=Cough, X=Positive X-ray and L=Lung cancer Suppose that
the prior for a patient being a smoker is 0.25, and the prior for the patient having bronchitis (during
winter in Melbourne!) is 0.05.
S

L B

X C

List the pairs of nodes that are conditionally independent in the following situations: (a) There is no
evidence for any of the nodes.
(b) The cancer node is set to true (and there is no other evidence).

1
(c) The smoker node is set to true (and there is no other evidence).
(d) The cough node is set to true (and there is no other evidence).

Solution. (a) Pairs of nodes that are c.i.: (X,B),(S,B),(L,B)

(b) Pairs of nodes that are c.i.: (X,S),(X,L),(X,B),(S,B)
(c) Pairs of nodes that are c.i.: (X,B),(L,B)
(d) Pairs of nodes that are c.i.: none

Problem 3
Variable ordering. (a) What variable ordering(s) would have been used to produce the above network
using the network construction algorithm described in lectures (Lecture 2, slide 10)?
(b) Given di erent variable orderings, what network structure would result from this algorithm?

Solution. (a) Parents must be before children in the order: (B,S),L,(X,C)

Problem 4
D-separation. (a) Find all the sets of nodes that d-separate X and Y in the graph below (not including
either X or Y in such sets).
X C Y

A B

(b) Try to come up with a real-world scenario that might be modelled with such a network struc-
ture.</li>

Solution. (a) The following sets of nodes DO d-separate X & Y: fg, fAg, fCg, fA,Cg, fA,B,Cg.
The rest do not: fBg,fA,Bg,fC,Bg.
(b) X = friend has cold virus A = you get cold C = weather is cold B = you cough Y = you have
lung cancer.