probabilistic reasoning; network-based reasoning

70
Probabilistic Reasoning; Probabilistic Reasoning; Network-based reasoning Network-based reasoning Set 7 Set 7 ICS 179, ICS 179, Spring 2010 Spring 2010

Upload: phyllis-mcneil

Post on 31-Dec-2015

72 views

Category:

Documents


1 download

DESCRIPTION

Probabilistic Reasoning; Network-based reasoning. Set 7 ICS 179, Spring 2010. = A. = B. = A. = C. Propositional Reasoning. Example: party problem. If Alex goes, then Becky goes: If Chris goes, then Alex goes: Question: - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Probabilistic Reasoning; Network-based reasoning

Probabilistic Reasoning;Probabilistic Reasoning;Network-based reasoning Network-based reasoning

Set 7Set 7

ICS 179, Spring ICS 179, Spring 20102010

Page 2: Probabilistic Reasoning; Network-based reasoning

Chavurah 5/8/2010

Propositional Reasoning

If Alex goes, then Becky goes: If Chris goes, then Alex goes:

Question: Is it possible that Chris goes to

the party but Becky does not?

Example: party problem

BA

A C

e?satisfiabl ,,

theIs

C B, ACBA

theorynalpropositio

= A

= B

= C

= A

Page 3: Probabilistic Reasoning; Network-based reasoning

Chavurah 5/8/2010

Probabilistic ReasoningParty example: the weather effect

Alex is-likely-to-go in bad weather Chris rarely-goes in bad weather Becky is indifferent but unpredictable

Questions: Given bad weather, which group of

individuals is most likely to show up at the party?

What is the probability that Chris goes to the party but Becky does not?

P(W,A,C,B) = P(B|W) · P(C|W) · P(A|W) · P(W)

P(A,C,B|W=bad) = 0.9 · 0.1 · 0.5

P(A|W=bad)=.9W A

P(C|W=bad)=.1W C

P(B|W=bad)=.5W B

W

P(W)

P(A|W)P(C|W)P(B|W)

B CA

W A P(A|W)

good 0 .01

good 1 .99

bad 0 .1

bad 1 .9

Page 4: Probabilistic Reasoning; Network-based reasoning

Chavurah 5/8/2010

Mixed Probabilistic and Deterministic networks

P(C|W)P(B|W)

P(W)

P(A|W)

W

B A C

Query:Is it likely that Chris goes to the party if Becky does not but the weather is bad?

PN

CN

Semantics?

Algorithms?),,|,( ACBAbadwBCP

A→B C→A

B A CP(C|W)P(B|W)

P(W)

P(A|W)

W

B A C

A→B C→A

B A C

Page 5: Probabilistic Reasoning; Network-based reasoning

5

The problem

All men are mortal T

All penguins are birds T

Socrates is a man

Men are kind p1

Birds fly p2

T looks like a penguin

Turn key –> car starts P_n

Q: Does T fly?P(Q)?

True propositions

Uncertain propositions

Logic?....but how we handle exceptionsProbability: astronomical

Page 6: Probabilistic Reasoning; Network-based reasoning

6

Page 7: Probabilistic Reasoning; Network-based reasoning
Page 8: Probabilistic Reasoning; Network-based reasoning
Page 9: Probabilistic Reasoning; Network-based reasoning
Page 10: Probabilistic Reasoning; Network-based reasoning
Page 11: Probabilistic Reasoning; Network-based reasoning
Page 12: Probabilistic Reasoning; Network-based reasoning

12

Page 13: Probabilistic Reasoning; Network-based reasoning

13

Page 14: Probabilistic Reasoning; Network-based reasoning

Alpha and beta are events

Page 15: Probabilistic Reasoning; Network-based reasoning

15

Page 16: Probabilistic Reasoning; Network-based reasoning
Page 17: Probabilistic Reasoning; Network-based reasoning

Burglary is independent of EarthquakeBurglary is independent of Earthquake

Page 18: Probabilistic Reasoning; Network-based reasoning

Earthquake is independent of burglary

Page 19: Probabilistic Reasoning; Network-based reasoning
Page 20: Probabilistic Reasoning; Network-based reasoning

20

Page 21: Probabilistic Reasoning; Network-based reasoning
Page 22: Probabilistic Reasoning; Network-based reasoning
Page 23: Probabilistic Reasoning; Network-based reasoning
Page 24: Probabilistic Reasoning; Network-based reasoning
Page 25: Probabilistic Reasoning; Network-based reasoning
Page 26: Probabilistic Reasoning; Network-based reasoning

26

Page 27: Probabilistic Reasoning; Network-based reasoning

27

Page 28: Probabilistic Reasoning; Network-based reasoning

28

Page 29: Probabilistic Reasoning; Network-based reasoning

29

Page 30: Probabilistic Reasoning; Network-based reasoning

30

Page 31: Probabilistic Reasoning; Network-based reasoning

31

Page 32: Probabilistic Reasoning; Network-based reasoning

32

Page 33: Probabilistic Reasoning; Network-based reasoning

33

Page 34: Probabilistic Reasoning; Network-based reasoning

34

Page 35: Probabilistic Reasoning; Network-based reasoning

35

Bayesian Networks: Representation

= P(S) P(C|S) P(B|S) P(X|C,S) P(D|C,B)

lung Cancer

Smoking

X-ray

Bronchitis

DyspnoeaP(D|C,B)

P(B|S)

P(S)

P(X|C,S)

P(C|S)

P(S, C, B, X, D)

Conditional Independencies Efficient Representation

Θ) (G,BN

CPD: C B D=0 D=10 0 0.1 0.90 1 0.7 0.31 0 0.8 0.21 1 0.9 0.1

Page 36: Probabilistic Reasoning; Network-based reasoning

Bayesian networks

Chapter 14 , Russel and Norvig

Section 1 – 2

Page 37: Probabilistic Reasoning; Network-based reasoning

Outline

Syntax Semantics

Page 38: Probabilistic Reasoning; Network-based reasoning

Example Topology of network encodes conditional

independence assertions:

Weather is independent of the other variables Toothache and Catch are conditionally

independent given Cavity

Page 39: Probabilistic Reasoning; Network-based reasoning

Example I'm at work, neighbor John calls to say my alarm is ringing, but

neighbor Mary doesn't call. Sometimes it's set off by minor earthquakes. Is there a burglar?

Variables: Burglary, Earthquake, Alarm, JohnCalls, MaryCalls

Network topology reflects "causal" knowledge: A burglar can set the alarm off An earthquake can set the alarm off The alarm can cause Mary to call The alarm can cause John to call

Page 40: Probabilistic Reasoning; Network-based reasoning

Example contd.

Page 41: Probabilistic Reasoning; Network-based reasoning

Compactness A CPT for Boolean Xi with k Boolean parents has 2k rows for

the combinations of parent values

Each row requires one number p for Xi = true(the number for Xi = false is just 1-p)

If each variable has no more than k parents, the complete network requires O(n · 2k) numbers

I.e., grows linearly with n, vs. O(2n) for the full joint distribution

For burglary net, 1 + 1 + 4 + 2 + 2 = 10 numbers (vs. 25-1 = 31)

Page 42: Probabilistic Reasoning; Network-based reasoning

SemanticsThe full joint distribution is defined as the product of the

local conditional distributions:P (X1, … ,Xn) = πi = 1 P (Xi | Parents(Xi))

e.g., P(j m a b e)= P (j | a) P (m | a) P (a | b, e) P (b) P (e)

n

Page 43: Probabilistic Reasoning; Network-based reasoning
Page 44: Probabilistic Reasoning; Network-based reasoning
Page 45: Probabilistic Reasoning; Network-based reasoning

Constructing Bayesian networks 1. Choose 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

P (Xi | Parents(Xi)) = P (Xi | X1, ... Xi-1)

This choice of parents guarantees:P (X1, … ,Xn) = πi =1 P (Xi | X1, … , Xi-1)

= πi =1P (Xi | Parents(Xi))

(by construction)(chain rule)

Page 46: Probabilistic Reasoning; Network-based reasoning

Suppose we choose the ordering M, J, A, B, E

P(J | M) = P(J)?

Example

Page 47: Probabilistic Reasoning; Network-based reasoning

Suppose we choose the ordering M, J, A, B, E

P(J | M) = P(J)?P(A | J, M) = P(A | J)? P(A | J, M) = P(A)?

No

Example

Page 48: Probabilistic Reasoning; Network-based reasoning

Suppose we choose the ordering M, J, A, B, E

P(J | M) = P(J)?P(A | J, M) = P(A | J)? P(A | J, M) = P(A)? NoP(B | A, J, M) = P(B | A)? P(B | A, J, M) = P(B)? No

Example

Page 49: Probabilistic Reasoning; Network-based reasoning

Suppose we choose the ordering M, J, A, B, E

P(J | M) = P(J)?P(A | J, M) = P(A | J)? P(A | J, M) = P(A)? NoP(B | A, J, M) = P(B | A)? YesP(B | A, J, M) = P(B)? NoP(E | B, A ,J, M) = P(E | A)?P(E | B, A, J, M) = P(E | A, B)?

No

Example

Page 50: Probabilistic Reasoning; Network-based reasoning

Suppose we choose the ordering M, J, A, B, E

P(J | M) = P(J)?P(A | J, M) = P(A | J)? P(A | J, M) = P(A)? NoP(B | A, J, M) = P(B | A)? YesP(B | A, J, M) = P(B)? NoP(E | B, A ,J, M) = P(E | A)? NoP(E | B, A, J, M) = P(E | A, B)? Yes No

Example

Page 51: Probabilistic Reasoning; Network-based reasoning

Example contd.

Deciding conditional independence is hard in noncausal directions

(Causal models and conditional independence seem hardwired for humans!)

Network is less compact: 1 + 2 + 4 + 2 + 4 = 13 numbers needed

Page 52: Probabilistic Reasoning; Network-based reasoning
Page 53: Probabilistic Reasoning; Network-based reasoning
Page 54: Probabilistic Reasoning; Network-based reasoning
Page 55: Probabilistic Reasoning; Network-based reasoning
Page 56: Probabilistic Reasoning; Network-based reasoning
Page 57: Probabilistic Reasoning; Network-based reasoning
Page 58: Probabilistic Reasoning; Network-based reasoning
Page 59: Probabilistic Reasoning; Network-based reasoning
Page 60: Probabilistic Reasoning; Network-based reasoning
Page 61: Probabilistic Reasoning; Network-based reasoning
Page 62: Probabilistic Reasoning; Network-based reasoning
Page 63: Probabilistic Reasoning; Network-based reasoning
Page 64: Probabilistic Reasoning; Network-based reasoning
Page 65: Probabilistic Reasoning; Network-based reasoning
Page 66: Probabilistic Reasoning; Network-based reasoning
Page 67: Probabilistic Reasoning; Network-based reasoning
Page 68: Probabilistic Reasoning; Network-based reasoning
Page 69: Probabilistic Reasoning; Network-based reasoning
Page 70: Probabilistic Reasoning; Network-based reasoning