Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John Wiley & Sons, 2000 with the permission of the authors and the publisher
Pattern Classification
All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John Wiley & Sons, 2000with the permission of the authors and the publisher
Chapter 2 (Part 1): Bayesian Decision Theory
(Sections 2.1-2.5, 2-7, 2.10)
• Introduction
• Bayesian Decision Theory–Continuous Features
Pattern Classification, Chapter 2 (Part 1)
2
Introduction
• The sea bass/salmon example
• State of nature, prior
• State of nature is a random variable
• The catch of salmon and sea bass is equiprobable
• P(1) = P(2) (uniform priors)
• P(1) + P( 2) = 1 (exclusivity and exhaustivity)
Pattern Classification, Chapter 2 (Part 1)
3
• Decision rule with only the prior information• Decide 1 if P(1) > P(2) otherwise decide 2
• PROBLEM!!!
• If P(1) > > P(2) correct most of the time
• If P(1) = P(2) 50% of being correct
• Probability of error?
Pattern Classification, Chapter 2 (Part 1)
4
• Use of the class –conditional information. Suppose x is the observed lightness.
• P(x | 1) and P(x | 2) describe the difference in lightness between populations of sea and salmon
Pattern Classification, Chapter 2 (Part 1)
5
Likelihood
Pattern Classification, Chapter 2 (Part 1)
6
• Posterior, likelihood, evidence
• Bayes Formula
P(j | x) = P(x | j) . P (j) / P(x)
• Where in case of two categories
• Posterior = (Likelihood. Prior) / Evidence
2j
1jjj )(P)|x(P)x(P
Pattern Classification, Chapter 2 (Part 1)
7
Pattern Classification, Chapter 2 (Part 1)
8
• Decision given the posterior probabilities
X is an observation for which:
if P(1 | x) > P(2 | x) True state of nature = 1if P(1 | x) < P(2 | x) True state of nature = 2
Therefore:whenever we observe a particular x, the probability of
error is :P(error | x) = P(1 | x) if we decide 2P(error | x) = P(2 | x) if we decide 1
Pattern Classification, Chapter 2 (Part 1)
9
• Minimizing the probability of error
• Bayes Decision (Minimize the probability of error)
Decide 1 if P(1 | x) > P(2 | x); otherwise decide 2
Therefore:
P(error | x) = min [P(1 | x), P(2 | x)]
Pattern Classification, Chapter 2 (Part 1)
10Bayesian Decision Theory –Continuous Features
• Generalization of the preceding ideas
• Use of more than one feature• Use more than two states of nature• Allowing actions and not only decide on the state of
nature
• Introduce a loss of function which is more general than the probability of error
Pattern Classification, Chapter 2 (Part 1)
11
• Allowing actions other than classification primarily allows the possibility of rejection
• Refusing to make a decision in close or bad cases!
• The loss function states how costly each action taken is
Pattern Classification, Chapter 2 (Part 1)
12
Let {1, 2,…, c} be the set of c states of nature
(or “categories”)
Let {1, 2,…, a} be the set of possible actions
Let (i | j) be the loss incurred for taking
action i when the state of nature is j
Pattern Classification, Chapter 2 (Part 1)
13
Expected Loss = R(i | x) for i = 1,…,a
Overall risk
To minimize R Choose action i (i = 1,…,a) thatminimizes R(i | x)
Bayes Risk R* - Resulting
Conditional risk
cj
1jjjii )x|(P)|()x|(R
dxxpxxRR )()|)((
Pattern Classification, Chapter 2 (Part 1)
14
• Two-category classification1 : deciding 12 : deciding 2ij = (i | j)
loss incurred for deciding i when the true state of nature is j
Conditional risk:
R(1 | x) = 11P(1 | x) + 12P(2 | x)R(2 | x) = 21P(1 | x) + 22P(2 | x)
Pattern Classification, Chapter 2 (Part 1)
15
Our rule is the following:
if R(1 | x) < R(2 | x)action 1: “decide 1” is taken
This results in the equivalent rule :
decide 1 if:
(21- 11) P(x | 1) P(1) >(12- 22) P(x | 2) P(2)
and decide 2 otherwise
Pattern Classification, Chapter 2 (Part 1)
16
Likelihood ratio:
The preceding rule is equivalent to the following rule:
Then take action 1 (decide 1)Otherwise take action 2 (decide 2)
)(P
)(P.
)|x(P)|x(P
if1
2
1121
2212
2
1
Pattern Classification, Chapter 2 (Part 1)
17
Optimal decision property
“If the likelihood ratio exceeds a threshold value independent of the input pattern x, we can take optimal actions”
Pattern Classification, Chapter 2 (Part 1)
18
Minimax Decision
Missing Features
Discriminant Functions
Pattern Classification, Chapter 2 (Part 1)
20
• Feature space divided into c decision regionsif gi(x) > gj(x) j i then x is in Ri
(Ri means assign x to i)
• The two-category case• A classifier is a “dichotomizer” that has two discriminant
functions g1 and g2
Let g(x) g1(x) – g2(x)
Decide 1 if g(x) > 0 ; Otherwise decide 2
Pattern Classification, Chapter 2 (Part 1)
21• Bayes Classifier gi(x) = - R(i | x)
(max. discriminant corresponds to min. risk!)
• For the minimum error rate, we take gi(x) = P(i | x)
(max. discrimination corresponds to max.posterior!)
gi(x) P(x | i) P(i)
gi(x) = ln P(x | i) + ln P(i)(ln: natural logarithm!)
Classifiers, Discriminant Functions
Pattern Classification, Chapter 2 (Part 1)
22
Decision Surfaces
Pattern Classification, Chapter 2 (Part 1)
23
Pattern Classification, Chapter 2 (Part 1)
24
Error Probabilities
• Two-category case
• c-Category case
dxPxpdxPxp
PRxPPRxP
RxPRxPerrorP
RR
)()()()(
)()()()(
),(),()(
2211
221112
2112
12
c
i R
iii
iii
c
ii
c
ii
i
dxPRxp
PRxPRxPcorrectP
1
11
)()(
)()(),()(
Pattern Classification, Chapter 2 (Part 1)
25Error Bounds
• Bayes Decision Rule – Lowest error rate• Question: What is the actual probability of error?
• Gaussian Case
• Chernoff Bound
• Bhattacharyya Bound