Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Upcoming SlideShare
×

# Basic Concept Of Probability

65,855 views

Published on

Published in: Technology, Spiritual
• Full Name
Comment goes here.

Are you sure you want to Yes No
Your message goes here

Are you sure you want to  Yes  No
Your message goes here

Are you sure you want to  Yes  No
Your message goes here

Are you sure you want to  Yes  No
Your message goes here

Are you sure you want to  Yes  No
Your message goes here

Are you sure you want to  Yes  No
Your message goes here

### Basic Concept Of Probability

1. 1. Basic Probability
2. 2. Introduction <ul><li>Probability is the study of randomness and uncertainty. </li></ul><ul><li>In the early days, probability was associated with games of chance (gambling). </li></ul>
3. 3. Simple Games Involving Probability <ul><li>Game: A fair die is rolled. If the result is 2, 3, or 4, you win \$1; if it is 5, you win \$2; but if it is 1 or 6, you lose \$3. </li></ul><ul><li>Should you play this game? </li></ul>
4. 4. Random Experiment <ul><li>a random experiment is a process whose outcome is uncertain. </li></ul><ul><li>Examples: </li></ul><ul><li>Tossing a coin once or several times </li></ul><ul><li>Picking a card or cards from a deck </li></ul><ul><li>Measuring temperature of patients </li></ul><ul><li>... </li></ul>
5. 5. Events & Sample Spaces Sample Space The sample space is the set of all possible outcomes. Simple Events The individual outcomes are called simple events. Event An event is any collection of one or more simple events
6. 6. Example <ul><li>Experiment: Toss a coin 3 times. </li></ul><ul><li>Sample space  </li></ul><ul><li> = {HHH, HHT, HTH, HTT, THH, THT, TTH, TTT}. </li></ul><ul><li>Examples of events include </li></ul><ul><ul><li>A = {HHH, HHT,HTH, THH} </li></ul></ul><ul><ul><li>= {at least two heads} </li></ul></ul><ul><ul><li>B = {HTT, THT,TTH} </li></ul></ul><ul><ul><li>= {exactly two tails.} </li></ul></ul>
7. 7. Basic Concepts (from Set Theory) <ul><li>The union of two events A and B , A  B , is the event consisting of all outcomes that are either in A or in B or in both events. </li></ul><ul><li>The complement of an event A , A c , is the set of all outcomes in  that are not in A . </li></ul><ul><li>The intersection of two events A and B , A  B , is the event consisting of all outcomes that are in both events. </li></ul><ul><li>When two events A and B have no outcomes in common, they are said to be mutually exclusive, or disjoint, events. </li></ul>
8. 8. Example <ul><li>Experiment: toss a coin 10 times and the number of heads is observed. </li></ul><ul><li>Let A = { 0, 2, 4, 6, 8, 10}. </li></ul><ul><li>B = { 1, 3, 5, 7, 9}, C = {0, 1, 2, 3, 4, 5}. </li></ul><ul><li>A  B = {0, 1, …, 10} =  . </li></ul><ul><li>A  B contains no outcomes. So A and B are mutually exclusive. </li></ul><ul><li>C c = {6, 7, 8, 9, 10}, A  C = {0, 2, 4}. </li></ul>
9. 9. Rules <ul><li>Commutative Laws: </li></ul><ul><ul><li>A  B = B  A , A  B = B  A </li></ul></ul><ul><li>Associative Laws: </li></ul><ul><ul><li>(A  B)  C = A  ( B  C ) </li></ul></ul><ul><ul><li>(A  B)  C = A  ( B  C) . </li></ul></ul><ul><li>Distributive Laws: </li></ul><ul><ul><li>(A  B)  C = ( A  C)  ( B  C) </li></ul></ul><ul><ul><li>(A  B)  C = ( A  C)  ( B  C) </li></ul></ul>
10. 10. Venn Diagram <ul><li> </li></ul>A B A ∩B
11. 11. Probability <ul><li>A Probability is a number assigned to each subset (events) of a sample space  . </li></ul><ul><li>Probability distributions satisfy the following rules: </li></ul>
12. 12. Axioms of Probability <ul><li>For any event A , 0  P ( A )  1. </li></ul><ul><li>P(  ) =1. </li></ul><ul><li>If A 1 , A 2 , … A n is a partition of A , then </li></ul><ul><li>P(A) = P( A 1 ) + P( A 2 ) + ...+ P( A n ) </li></ul><ul><li>( A 1 , A 2 , … A n is called a partition of A if A 1  A 2  …  A n = A and A 1 , A 2 , … A n are mutually exclusive.) </li></ul>
13. 13. Properties of Probability <ul><li>For any event A , P( A c ) = 1 - P( A ). </li></ul><ul><li>If A  B , then P( A )  P( B ). </li></ul><ul><li>For any two events A and B , </li></ul><ul><li>P( A  B ) = P( A ) + P( B ) - P( A  B ). </li></ul><ul><li>For three events, A , B , and C , </li></ul><ul><li>P( A  B  C ) = P( A ) + P( B ) + P( C ) - </li></ul><ul><li>P( A  B ) - P( A  C ) - P( B  C ) + P( A  B  C ). </li></ul>
14. 14. Example <ul><li>In a certain population, 10% of the people are rich, 5% are famous, and 3% are both rich and famous. A person is randomly selected from this population. What is the chance that the person is </li></ul><ul><ul><li>not rich? </li></ul></ul><ul><ul><li>rich but not famous? </li></ul></ul><ul><ul><li>either rich or famous? </li></ul></ul>
15. 15. Intuitive Development (agrees with axioms) <ul><li>Intuitively, the probability of an event a could be defined as: </li></ul>Where N(a) is the number that event a happens in n trials
16. 16. Here We Go Again: Not So Basic Probability
17. 17. More Formal: <ul><li> is the Sample Space: </li></ul><ul><ul><li>Contains all possible outcomes of an experiment </li></ul></ul><ul><li> in  is a single outcome </li></ul><ul><li>A in  is a set of outcomes of interest </li></ul>
18. 18. Independence <ul><li>The probability of independent events A, B and C is given by: </li></ul><ul><ul><ul><li>P(A,B,C) = P(A)P(B)P(C) </li></ul></ul></ul>A and B are independent, if knowing that A has happened does not say anything about B happening
19. 19. Bayes Theorem <ul><li>Provides a way to convert a-priori probabilities to a-posteriori probabilities: </li></ul>
20. 20. Conditional Probability <ul><li>One of the most useful concepts! </li></ul>A B 
21. 21. Bayes Theorem <ul><li>Provides a way to convert a-priori probabilities to a-posteriori probabilities: </li></ul>
22. 22. Using Partitions: <ul><li>If events A i are mutually exclusive and partition  </li></ul>
23. 23. Random Variables <ul><li>A (scalar) random variable X is a function that maps the outcome of a random event into real scalar values </li></ul>  X(  )
24. 24. Random Variables Distributions <ul><li>Cumulative Probability Distribution (CDF): </li></ul><ul><li>Probability Density Function (PDF): </li></ul>
25. 25. Random Distributions: <ul><li>From the two previous equations: </li></ul>
26. 26. Uniform Distribution <ul><li>A R.V. X that is uniformly distributed between x 1 and x 2 has density function: </li></ul>X 1 X 2
27. 27. Gaussian (Normal) Distribution <ul><li>A R.V. X that is normally distributed has density function: </li></ul>
28. 28. Statistical Characterizations <ul><li>Expectation (Mean Value, First Moment): </li></ul><ul><li>Second Moment: </li></ul>
29. 29. Statistical Characterizations <ul><li>Variance of X: </li></ul><ul><li>Standard Deviation of X: </li></ul>
30. 30. Mean Estimation from Samples <ul><li>Given a set of N samples from a distribution, we can estimate the mean of the distribution by: </li></ul>
31. 31. Variance Estimation from Samples <ul><li>Given a set of N samples from a distribution, we can estimate the variance of the distribution by: </li></ul>
32. 32. Pattern Classification
33. 33. Chapter 1: Introduction to Pattern Recognition (Sections 1.1-1.6) <ul><li>Machine Perception </li></ul><ul><li>An Example </li></ul><ul><li>Pattern Recognition Systems </li></ul><ul><li>The Design Cycle </li></ul><ul><li>Learning and Adaptation </li></ul><ul><li>Conclusion </li></ul>
34. 34. Machine Perception <ul><li>Build a machine that can recognize patterns: </li></ul><ul><ul><li>Speech recognition </li></ul></ul><ul><ul><li>Fingerprint identification </li></ul></ul><ul><ul><li>OCR (Optical Character Recognition) </li></ul></ul><ul><ul><li>DNA sequence identification </li></ul></ul>
35. 35. An Example <ul><li>“Sorting incoming Fish on a conveyor according to species using optical sensing” </li></ul><ul><li>Sea bass </li></ul><ul><li>Species </li></ul><ul><li>Salmon </li></ul>
36. 36. <ul><li>Problem Analysis </li></ul><ul><ul><li>Set up a camera and take some sample images to extract features </li></ul></ul><ul><ul><ul><li>Length </li></ul></ul></ul><ul><ul><ul><li>Lightness </li></ul></ul></ul><ul><ul><ul><li>Width </li></ul></ul></ul><ul><ul><ul><li>Number and shape of fins </li></ul></ul></ul><ul><ul><ul><li>Position of the mouth, etc… </li></ul></ul></ul><ul><ul><ul><li>This is the set of all suggested features to explore for use in our classifier! </li></ul></ul></ul>
37. 37. <ul><li>Preprocessing </li></ul><ul><ul><li>Use a segmentation operation to isolate fishes from one another and from the background </li></ul></ul><ul><li>Information from a single fish is sent to a feature extractor whose purpose is to reduce the data by measuring certain features </li></ul><ul><li>The features are passed to a classifier </li></ul>
38. 39. <ul><li>Classification </li></ul><ul><ul><li>Select the length of the fish as a possible feature for discrimination </li></ul></ul>
39. 41. <ul><li>The length is a poor feature alone! </li></ul><ul><li>Select the lightness as a possible feature. </li></ul>
40. 43. <ul><li>Threshold decision boundary and cost relationship </li></ul><ul><ul><li>Move our decision boundary toward smaller values of lightness in order to minimize the cost (reduce the number of sea bass that are classified salmon!) </li></ul></ul><ul><ul><li>Task of decision theory </li></ul></ul>
41. 44. <ul><li>Adopt the lightness and add the width of the fish </li></ul><ul><li>Fish x T = [ x 1 , x 2 ] </li></ul>Lightness Width
42. 46. <ul><li>We might add other features that are not correlated with the ones we already have. A precaution should be taken not to reduce the performance by adding such “noisy features” </li></ul><ul><li>Ideally, the best decision boundary should be the one which provides an optimal performance such as in the following figure: </li></ul>
43. 48. <ul><li>However, our satisfaction is premature because the central aim of designing a classifier is to correctly classify novel input </li></ul><ul><li>Issue of generalization! </li></ul>