Pattern Classification, Chapter 1 1 Basic Probability

Pattern Classification, Chapter 1 2 Introduction Probability is the study of randomness and uncertainty. In the early days, probability was associated with games of chance (gambling).

Pattern Classification, Chapter 1 3 Simple Games Involving Probability 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. Should you play this game?

Pattern Classification, Chapter 1 4 Random Experiment a random experiment is a process whose outcome is uncertain. Examples: Tossing a coin once or several times Picking a card or cards from a deck Measuring temperature of patients...

Pattern Classification, Chapter 1 5 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 Events & Sample Spaces

Pattern Classification, Chapter 1 6 Example Experiment: Toss a coin 3 times. Sample space   = {HHH, HHT, HTH, HTT, THH, THT, TTH, TTT}. Examples of events include A = {HHH, HHT,HTH, THH} = {at least two heads} B = {HTT, THT,TTH} = {exactly two tails.}

Pattern Classification, Chapter 1 7 Basic Concepts (from Set Theory) 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. The complement of an event A, A c, is the set of all outcomes in  that are not in A. The intersection of two events A and B, A  B, is the event consisting of all outcomes that are in both events. When two events A and B have no outcomes in common, they are said to be mutually exclusive, or disjoint, events.

Pattern Classification, Chapter 1 8 Example Experiment: toss a coin 10 times and the number of heads is observed. Let A = { 0, 2, 4, 6, 8, 10}. B = { 1, 3, 5, 7, 9}, C = {0, 1, 2, 3, 4, 5}. A  B= {0, 1, …, 10} = . A  B contains no outcomes. So A and B are mutually exclusive. C c = {6, 7, 8, 9, 10}, A  C = {0, 2, 4}.

Pattern Classification, Chapter 1 9 Rules Commutative Laws: A  B = B  A, A  B = B  A Associative Laws: (A  B)  C = A  (B  C ) (A  B)  C = A  (B  C). Distributive Laws: (A  B)  C = (A  C)  (B  C) (A  B)  C = (A  C)  (B  C) DeMorgan’s Laws:

Pattern Classification, Chapter 1 10 Venn Diagram  A B A∩B

Pattern Classification, Chapter 1 11 Probability A Probability is a number assigned to each subset (events) of a sample space . Probability distributions satisfy the following rules:

Pattern Classification, Chapter 1 12 Axioms of Probability For any event A, 0  P(A)  1. P(  ) =1. If A 1, A 2, … A n is a partition of A, then P(A) = P(A 1 ) + P(A 2 ) P(A n ) (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.)

Pattern Classification, Chapter 1 13 Properties of Probability For any event A, P(A c ) = 1 - P(A). If A  B, then P(A)  P(B). For any two events A and B, P(A  B) = P(A) + P(B) - P(A  B). For three events, A, B, and C, P(A  B  C) = P(A) + P(B) + P(C) - P(A  B) - P(A  C) - P(B  C) + P(A  B  C).

Pattern Classification, Chapter 1 14 Example 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 not rich? rich but not famous? either rich or famous?

Pattern Classification, Chapter 1 15 Intuitive Development (agrees with axioms) Intuitively, the probability of an event a could be defined as: Where N(a) is the number that event a happens in n trials

Here We Go Again: Not So Basic Probability

Pattern Classification, Chapter 1 17 More Formal:  is the Sample Space: Contains all possible outcomes of an experiment  in  is a single outcome A in  is a set of outcomes of interest

Pattern Classification, Chapter 1 18 Independence The probability of independent events A, B and C is given by: P(A,B,C) = P(A)P(B)P(C) A and B are independent, if knowing that A has happened does not say anything about B happening

Pattern Classification, Chapter 1 19 Bayes Theorem Provides a way to convert a-priori probabilities to a- posteriori probabilities:

Pattern Classification, Chapter 1 20 Conditional Probability One of the most useful concepts! A B 

Pattern Classification, Chapter 1 21 Bayes Theorem Provides a way to convert a-priori probabilities to a- posteriori probabilities:

Pattern Classification, Chapter 1 22 Using Partitions: If events A i are mutually exclusive and partition 

Pattern Classification, Chapter 1 23 Random Variables A (scalar) random variable X is a function that maps the outcome of a random event into real scalar values   X(  )

Pattern Classification, Chapter 1 24 Random Variables Distributions Cumulative Probability Distribution (CDF): Probability Density Function (PDF): Probability Density Function (PDF):

Pattern Classification, Chapter 1 25 Random Distributions: From the two previous equations:

Pattern Classification, Chapter 1 26 Uniform Distribution A R.V. X that is uniformly distributed between x 1 and x 2 has density function: X1X1X1X1 X2X2X2X2

Pattern Classification, Chapter 1 27 Gaussian (Normal) Distribution A R.V. X that is normally distributed has density function: 

Pattern Classification, Chapter 1 28 Statistical Characterizations Expectation (Mean Value, First Moment): Second Moment:Second Moment:

Pattern Classification, Chapter 1 29 Statistical Characterizations Variance of X: Standard Deviation of X:

Pattern Classification, Chapter 1 30 Mean Estimation from Samples Given a set of N samples from a distribution, we can estimate the mean of the distribution by:

Pattern Classification, Chapter 1 31 Variance Estimation from Samples Given a set of N samples from a distribution, we can estimate the variance of the distribution by:

Pattern Classification

Chapter 1: Introduction to Pattern Recognition (Sections ) Machine Perception An Example Pattern Recognition Systems The Design Cycle Learning and Adaptation Conclusion

Pattern Classification, Chapter 1 34 Machine Perception Build a machine that can recognize patterns: Speech recognition Fingerprint identification OCR (Optical Character Recognition) DNA sequence identification

Pattern Classification, Chapter 1 35 An Example “Sorting incoming Fish on a conveyor according to species using optical sensing” Sea bass Species Salmon

Pattern Classification, Chapter 1 36 Problem Analysis Set up a camera and take some sample images to extract features Length Lightness Width Number and shape of fins Position of the mouth, etc… This is the set of all suggested features to explore for use in our classifier!

Pattern Classification, Chapter 1 37 Preprocessing Use a segmentation operation to isolate fishes from one another and from the background Information from a single fish is sent to a feature extractor whose purpose is to reduce the data by measuring certain features The features are passed to a classifier

Pattern Classification, Chapter 1 38

Pattern Classification, Chapter 1 39 Classification Select the length of the fish as a possible feature for discrimination

Pattern Classification, Chapter 1 40

Pattern Classification, Chapter 1 41 The length is a poor feature alone! Select the lightness as a possible feature.

Pattern Classification, Chapter 1 42

Pattern Classification, Chapter 1 43 Threshold decision boundary and cost relationship 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!) Task of decision theory

Pattern Classification, Chapter 1 44 Adopt the lightness and add the width of the fish Fish x T = [x 1, x 2 ] Lightness Width

Pattern Classification, Chapter 1 45

Pattern Classification, Chapter 1 46 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 “noisy features” Ideally, the best decision boundary should be the one which provides an optimal performance such as in the following figure:

Pattern Classification, Chapter 1 47

Pattern Classification, Chapter 1 48 However, our satisfaction is premature because the central aim of designing a classifier is to correctly classify novel input Issue of generalization!

Pattern Classification, Chapter 1 49