Scribd
Upload
18 views

Unit 4 Uncertainty Measure

Uploaded by

shradha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
18 views

Unit 4 Uncertainty Measure

Uploaded by

shradha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 33

Uncertainty Measure:

Probability Theory
Introduction
• Intelligent system – have some degree of uncertainty
• Uncertainty - Not always possible to represent data in precise and
consistent manner
• Missing data, unreliable data, ambiguous due to errors in measurement ,
multiple conflicting measurements
• Default data will have exceptions leading to errors in intelligent systems
• Represented knowledge is based on best guesses of experts based on
observations and statistical conclusion – not appropriate at all situations
• Implementing uncertainty management - consider 3 issues
• 1.representation of uncertain data
• 2.combination of two or more pieces of uncertain data
• 3.drawing inference using uncertain data
• Methods for handling uncertainty includes – probability theory, fuzzy
logic , model and temporal logic
Probability Theory
• Probability – way of turning an opinion or an expectation into a number
lying between 0 and 1
• Reflects the likelihood of an event or a chance that a particular event will
occur
• Assume a set S (sample space) consisting of independent events
representing all possible outcomes of random experiment.
• Every non-empty subset A of sample space S is called an event – empty set
is called impossible event – S is called sure event
• Probability of an event A by P(A)

• The probabilities of all events P(A1) + P(A2)+… P(An)=1


• Impossible event has a probability 0 , certain event has probability 1.
Axioms of Probability
• S represents sample space
• A & B represents events
Joint Probability
• Probability of occurrence of two independent events in conjunction
• Probability of both events occurring together
• If Two events are independent, then the occurrence of one event
does not affect the probability of occurrence of the other
• The joint probability of A and B is written as P(AꓵB) or P(A and B)
P(AꓵB) = P(A) * P(B)
• Union of Probabilities P(A OR B) = P(A) +P(B) – (P(A) * P(B) )
Examples
• What is the joint probability of rolling the number five twice in a fair six-
sided dice?
• Event “A” = The probability of rolling a 5 in the first roll is 1/6 = 0.1666.
• Event “B” = The probability of rolling a 5 in the second roll is 1/6 = 0.1666.
• Therefore, the joint probability of event “A” and “B” is
P(1/6) x P(1/6) = 0.02777 = 2.8%.

• What is the joint probability of getting a head followed by a tail in a coin


toss?
• Event “A” = The probability of getting a head in the first coin toss is 1/2 = 0.5.
• Event “B” = The probability of getting a tail in the second coin toss is 1/2 = 0.5.
• Therefore, the joint probability of event “A” and “B” is
P(1/2) x P(1/2) = 0.25 = 25%.
Example 2
Conditional Probability
•
Example
• 70% of your friends like Chocolate, and 35% like Chocolate AND like
Strawberry. What percent of those who like Strawberry, given that they
also like chocolate?

• P(Strawberry|Chocolate) = P(Chocolate and Strawberry) / P(Chocolate)


0.35 / 0.7 = 50%
50% of your friends who like Chocolate also like Strawberry
Example
Example: Drawing 2 Kings from a Deck

Event A is drawing a King first, and Event B is drawing a King second.

• For the first card the chance of drawing a King is 4 out of 52 (there are 4
Kings in a deck of 52 cards):
P(A) = 4/52
• But after removing a King from the deck the probability of the 2nd card
drawn is less likely to be a King (only 3 of the 51 cards left are Kings):
P(B|A) = 3/51
And so:
P(A and B) = P(A) x P(B|A) = (4/52) x (3/51) = 12/2652 = 1/221
• So the chance of getting 2 Kings is 1 in 221, or about 0.5%
Example
Bayes’ Theorem
•
Proof
Prove
Example
Extension of Bayes Theorem
Cumulative Probabilities
Bayesian Method: Advantages & Disadvantages
• Advantages
• Bayesian method is based on a strong theoretical foundation in probability theory;
it is currently the most advanced of all certainty reasoning methods.
• This method has well-defined semantics for decision making
• Disadvantages
• The system using Bayesian approach need quite a large amount of probability data
to construct a knowledge base.
• For example a diagnostic system handling 50 detectable conclusions (H) and 300
relevant and observable characteristics E requires a minimum of 15,050(H*E+H)
probability values assuming that all of the conclusions are mutually exclusive.
Handling large amount of data not practically
possible
• Since conditional probabilities are based on statistical data the sample
sizes must be sufficient to ensure that the probabilities obtained from
them are accurate
• If conditional probabilities are based on human experts, then the
question of values being consistent and comprehensive arises
• Since associations between the hypotheses and evidences are
reduced to numbers, it eliminates the actual knowledge embedded
within the data. Therefore a system’s ability to explain its reasoning
and browsing through the hierarchy of evidences to hypothesis to
user is lost.

You might also like