Bayesian Networks

Material used
– Halpern: Reasoning about Uncertainty. Chapter 4
– Stuart Russell and Peter Norvig: Artificial Intelligence: A Modern
Approach

1 Random variables
2 Probabilistic independence
3 Belief networks
4 Global and local semantics
5 Constructing belief networks
6 Inference in belief networks
 1 Random variables
• Suppose that a coin is tossed five times. What is the total
number of heads?
• Intuitively, it is a variable because its value varies, and it is
random because its value is unpredictable in a certain sense
• Formally, a random variable is neither random nor a variable

Definition 1: A random variable X on a sample space (set of

possible worlds) W is a function from W to some range (e.g.
the natural numbers)
 Example

• A coin is tossed five times: W = {h,t}5.

• NH(w) = |{i: w[i] = h}| (number of heads in seq. w)
• NH(hthht) = 3
• Question: what is the probability of getting three
heads in a sequence of five tosses?
 (NH = 3) =def ({w: NH(w) = 3})
 (NH = 3) = 10 2-5 = 10/32
 Why are random variables important?
• They provide a tool for structuring possible worlds
• A world can often be completely characterized by the values
taken on by a number of random variables
• Example: W = {h,t}5, each world can be characterized
– by 5 random variables X1, …X5 where Xi designates the
outcome of the ith tosses: Xi(w) = w[i]
– an alternative way is in terms of Boolean random variables,
e.g. Hi: Hi(w) = 1 if w[i] = h, Hi(w) = 0 if w[i] = t.
– use the random variables Hi(w) for constructing a new
random variable that expresses the number of tails in 5
tosses
 2 Probabilistic Independence
• If two events U and V are independent (or unrelated) then
learning U should not affect he probability of V and learning V
should not affect the probability of U.

Definition 2: U and V are absolutely independent (with respect to

a probability measure ) if (V)  0 implies (U|V) = (U)
and (U)  0 implies (V|U) = (V)
Fact 1: the following are equivalent
a. (V)  0 implies (U|V) = (U)
b. (U)  0 implies (V|U) = (V)
c. (U  V) = (U) (V)
 Absolute independence for random variables

Definition 3: Two random variables X and Y are absolutely

independent (with respect to a probability measure ) iff for
all x Value(X) and all y Value(Y) the event X = x is
absolutely independent of the event Y = y.
Notation: I(X,Y)
Definition 4: n random variables X1 … Xn are absolutely
independent iff for all i, x1, …, xn, the events Xi= xi and
ji(Xi=xi) are absolutely independent.
Fact 2: If n random variables X1 …Xn are absolutely independent
then (X1= x1, Xn= xn ) = i (Xi= xi).
Absolute independence is a very strong requirement, seldom met
 Conditional independence: example
Example: Dentist problem with three events:
Toothache (I have a toothache)
Cavity (I have a cavity)
Catch (steel probe catches in my tooth)

• If I have a cavity, the probability that the probe catches in it

does not depend on whether I have a toothache
• i.e. Catch is conditionally independent of Toothache given
Cavity: I(Catch, Toothache|Cavity)
 (Catch|ToothacheCavity) = (Catch|Cavity)
 Conditional independence for events
Definition 5: A and B are conditionally independent given C if
(BC)  0 implies (A|BC) = (A|C) and
(AC)  0 implies (B|AC) = (B|C)

Fact 3: the following are equivalent if (C)  0

a. (A|BC)  0 implies (A|BC)= (A|C)
b. (B|AC)  0 implies (B|AC)= (B|C)
c. (AB|C)= (A|C) (B|C)
 Conditional independence for random variables

Definition 6: Two random variables X and Y are conditionally

independ. given a random variable Z iff for all x Value(X),
y Value(Y) and z Value(z) the events X = x and Y = y are
conditionally independent given the event Z = z.
Notation: I(X,Y|Z)
Important Notation: Instead of
(*) (X=xY=y|Z=z)= (X=x|Z=z) (Y=y|Z=z)
we simply write
(**) (X,Y|Z) = (X|Z) (Y|Z)
Question: How many equations are represented by (**)?
 Dentist problem with random variables
• Assume three binary (Boolean) random variables Toothache,
Cavity, and Catch
• Assume that Catch is conditionally independent of Toothache
given Cavity
• The full joint distribution can now be written as
(Toothache, Catch, Cavity) =
(Toothache, Catch|Cavity)  (Cavity) =
(Toothache|Cavity)  (Catch|Cavity)  (Cavity)
• In order to express the full joint distribution we need 2+2+1 = 5
independent numbers instead of 7; 2 are removed by the
statement of conditional independence:
(Toothache, Catch|Cavity) = (Toothache|Cavity)  (Catch|Cavity)
 3 Belief networks
• A simple, graphical notation for conditional independence
assertions and hence for compact specification of full joint
distribution.
• Syntax:
– a set of nodes, one per random variable
– a directed, acyclic graph (link  “directly influences”)
– a conditional distribution for each node given its parents
(Xi|Parents(Xi))
• Conditional distributions are represented by conditional
probability tables (CPT)
 The importance of independency statements

n binary nodes,
n binary nodes
fully connected
each node max. 3 parents

less than 23  n
2n -1 independent numbers
independent numbers
 The earthquake example

• You have a new burglar alarm installed

• It is reliable about detecting burglary, but responds to minor
earthquakes
• Two neighbors (John, Mary) promise to call you at work when
they hear the alarm
– John always calls when hears alarm, but confuses alarm
with phone ringing (and calls then also)
– Mary likes loud music and sometimes misses alarm!
• Given evidence about who has and hasn’t called, estimate the
probability of a burglary
 The network

I´m at work,
John calls to say
my alarm is
ringing, Mary
doesn´t call. Is
there a burglary?
5 Variables
network topol-
ogy reflects
causal
knowledge
 4 Global and local semantics
• Global semantics (corresponding to Halpern´s quantitative
Bayesian network) defines the full joint distribution as the
product of the local conditional distributions
• For defining this product, a linear ordering of the nodes of the
network has to be given: X1 … Xn

 (X1 … Xn) = ni=1 (Xi|Parents(Xi))

• ordering in the example: B, E, A, J, M
 (J  M  A  B   E) =
(B) ( E)(A|B E)(J|A)(M|A)
 Local semantics
• Local semantics (corresponding to Halpern´s qualitative
Bayesian network) defines a series of statements of
conditional independence
• Each node is conditionally independent of its nondescendants
given its parents: I(X, Nondescentents(X)|Parents(X))
• Examples
– X Y Z I (X, Y) ? I (X, Z) ?
– X Y Z I (X, Z|Y) ?
– XYZ I (X, Y) ? I (X, Z) ?
 The chain rule

 (X, Y, Z) = (X)  (Y, Z |X) = (X)  (Y|X)  (Z| X, Y)

• In general: (X1, …, Xn) = ni=1 (Xi|X1, …, Xi 1)

• a linear ordering of the nodes of the network has to be given:
X1, …, Xn

• The chain rule is used to prove

the equivalence of local and global semantics
 Local and global semantics are equivalent

• If a local semantics in form of the independeny statements is

given, i.e.
I(X, Nondescendants(X)|Parents(X)) for each node X of the
network,
then the global semantics results:
(X1 … Xn) = ni=1 (Xi|Parents(Xi)),
and vice versa.
• For proving local semantics  global semantics, we assume
an ordering of the variables that makes sure that parents
appear earlier in the ordering: Xi parent of Xj then Xi < Xj
 Local semantics  global semantics

 (X1, …, Xn) = ni=1 (Xi|X1, …, Xi 1) chain rule

• Parents(Xi)  {X1, …, Xi 1}

 (Xi|X1, …, Xi 1) = (Xi|Parents(Xi), Rest)

• local semantics: I(X, Nondescendants(X)|Parents(X))
• The elements of Rest are nondescendants of Xi, hence we can
skip Rest
• Hence, (X1 … Xn) = ni=1 (Xi|Parents(Xi)),
 5 Constructing belief networks
Need a method such that a series of locally testable assertions of
conditional independence guarantees the required global
semantics
1. Chose an ordering of variables X1, …, Xn
2. For i = 1 to n
add Xi to the network
select parents from X1, …, Xi 1 such that
(Xi|Parents(Xi)) = (Xi|X1, …, Xi 1)
This choice guarantees the global semantics:
(X1, …, Xn) = ni=1 (Xi|X1, …, Xi 1) (chain rule)
= ni=1 (Xi|Parents(Xi)) by construction
 Earthquake example with canonical ordering

• What is an appropriate ordering?

• In principle, each ordering is allowed!

• heuristic rule: start with causes, go to direct effects

• (B, E), A, (J, M) [4 possible orderings]

 Earthquake example with noncanonical ordering
• Suppose we chose the ordering M, J, A, B, E

MaryCalls
JohnCalls

Alarm

Burglary
Earthquake
 (J|M) = (J) ? No
 (A|J,M) = (A|J) ? (A|J,M) = (A) ? No
 (B|A,J,M) = (B|A) ? Yes
 (B|A,J,M) = (B) ? No
 (E|B, A,J,M) = (E|A) ? No
 (E|B,A,J,M) = (E|A,B) ? Yes
6 Inference in belief networks
Types of inference:
Q quary variable, E evidence variable
Kinds of inference