1 / 61

CMSC 671 Fall 2010

CMSC 671 Fall 2010. Class #18/19 – Wednesday, November 3 / Monday, November 8. Some material borrowed with permission from Lise Getoor. Next two classes. Probability theory (quick review!) Bayesian networks Network structure Conditional probability tables Conditional independence

keenl
Download Presentation

CMSC 671 Fall 2010

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CMSC 671Fall 2010 Class #18/19 – Wednesday, November 3 / Monday, November 8 Some material borrowed with permission from Lise Getoor

  2. Next two classes • Probability theory (quick review!) • Bayesian networks • Network structure • Conditional probability tables • Conditional independence • Bayesian inference • From the joint distribution • Using independence/factoring • From sources of evidence

  3. Bayesian Reasoning Chapter 13

  4. Sources of uncertainty • Uncertain inputs • Missing data • Noisy data • Uncertain knowledge • Multiple causes lead to multiple effects • Incomplete enumeration of conditions or effects • Incomplete knowledge of causality in the domain • Probabilistic/stochastic effects • Uncertain outputs • Abduction and induction are inherently uncertain • Default reasoning, even in deductive fashion, is uncertain • Incomplete deductive inference may be uncertain Probabilistic reasoning only gives probabilistic results (summarizes uncertainty from various sources)

  5. Decision making with uncertainty • Rational behavior: • For each possible action, identify the possible outcomes • Compute the probability of each outcome • Compute the utility of each outcome • Compute the probability-weighted (expected) utility over possible outcomes for each action • Select the action with the highest expected utility (principle of Maximum Expected Utility)

  6. Why probabilities anyway? • Kolmogorov showed that three simple axioms lead to the rules of probability theory • De Finetti, Cox, and Carnap have also provided compelling arguments for these axioms • All probabilities are between 0 and 1: • 0 ≤ P(a) ≤ 1 • Valid propositions (tautologies) have probability 1, and unsatisfiable propositions have probability 0: • P(true) = 1 ; P(false) = 0 • The probability of a disjunction is given by: • P(a  b) = P(a) + P(b) – P(a  b) a ab b

  7. Random variables Domain Atomic event: complete specification of state Prior probability: degree of belief without any other evidence Joint probability: matrix of combined probabilities of a set of variables Alarm, Burglary, Earthquake Boolean (like these), discrete, continuous Alarm=True  Burglary=True  Earthquake=Falsealarm  burglary ¬earthquake P(Burglary) = .1 P(Alarm, Burglary) = Probability theory

  8. Conditional probability: probability of effect given causes Computing conditional probs: P(a | b) = P(a  b) / P(b) P(b): normalizing constant Product rule: P(a  b) = P(a | b) P(b) Marginalizing: P(B) = ΣaP(B, a) P(B) = ΣaP(B | a) P(a) (conditioning) P(burglary | alarm) = .47P(alarm | burglary) = .9 P(burglary | alarm) = P(burglary  alarm) / P(alarm) = .09 / .19 = .47 P(burglary  alarm) = P(burglary | alarm) P(alarm) = .47 * .19 = .09 P(alarm) = P(alarm  burglary) + P(alarm ¬burglary) = .09+.1 = .19 Probability theory (cont.)

  9. Example: Inference from the joint P(Burglary | alarm) = α P(Burglary, alarm) = α [P(Burglary, alarm, earthquake) + P(Burglary, alarm, ¬earthquake) = α [ (.01, .01) + (.08, .09) ] = α [ (.09, .1) ] Since P(burglary | alarm) + P(¬burglary | alarm) = 1, α = 1/(.09+.1) = 5.26 (i.e., P(alarm) = 1/α = .19 – quizlet: how can you verify this?) P(burglary | alarm) = .09 * 5.26 = .474 P(¬burglary | alarm) = .1 * 5.26 = .526

  10. Exercise: Inference from the joint • Queries: • What is the prior probability of smart? • What is the prior probability of study? • What is the conditional probability of prepared, given study and smart? • Save these answers for next time! 

  11. Independence • When two sets of propositions do not affect each others’ probabilities, we call them independent, and can easily compute their joint and conditional probability: • Independent (A, B) → P(A  B) = P(A) P(B), P(A | B) = P(A) • For example, {moon-phase, light-level} might be independent of {burglary, alarm, earthquake} • Then again, it might not: Burglars might be more likely to burglarize houses when there’s a new moon (and hence little light) • But if we know the light level, the moon phase doesn’t affect whether we are burglarized • Once we’re burglarized, light level doesn’t affect whether the alarm goes off • We need a more complex notion of independence, and methods for reasoning about these kinds of relationships

  12. Exercise: Independence • Queries: • Is smart independent of study? • Is prepared independent of study?

  13. Conditional independence • Absolute independence: • A and B are independent if P(A  B) = P(A) P(B); equivalently, P(A) = P(A | B) and P(B) = P(B | A) • A and B are conditionally independent given C if • P(A  B | C) = P(A | C) P(B | C) • This lets us decompose the joint distribution: • P(A  B  C) = P(A | C) P(B | C) P(C) • Moon-Phase and Burglary are conditionally independent given Light-Level • Conditional independence is weaker than absolute independence, but still useful in decomposing the full joint probability distribution

  14. Exercise: Conditional independence • Queries: • Is smart conditionally independent of prepared, given study? • Is study conditionally independent of prepared, given smart?

  15. Bayes’s rule • Bayes’s rule is derived from the product rule: • P(Y | X) = P(X | Y) P(Y) / P(X) • Often useful for diagnosis: • If X are (observed) effects and Y are (hidden) causes, • We may have a model for how causes lead to effects (P(X | Y)) • We may also have prior beliefs (based on experience) about the frequency of occurrence of effects (P(Y)) • Which allows us to reason abductively from effects to causes (P(Y | X)).

  16. Bayesian inference • In the setting of diagnostic/evidential reasoning • Know prior probability of hypothesis conditional probability • Want to compute the posterior probability • Bayes’ theorem (formula 1):

  17. Simple Bayesian diagnostic reasoning • Knowledge base: • Evidence / manifestations: E1, … Em • Hypotheses / disorders: H1, … Hn • Ej and Hi are binary; hypotheses are mutually exclusive (non-overlapping) and exhaustive (cover all possible cases) • Conditional probabilities: P(Ej | Hi), i = 1, … n; j = 1, … m • Cases (evidence for a particular instance): E1, …, El • Goal: Find the hypothesis Hi with the highest posterior • Maxi P(Hi | E1, …, El)

  18. Bayesian diagnostic reasoning II • Bayes’ rule says that • P(Hi | E1, …, El) = P(E1, …, El | Hi) P(Hi) / P(E1, …, El) • Assume each piece of evidence Ei is conditionally independent of the others, given a hypothesis Hi, then: • P(E1, …, El | Hi) = lj=1 P(Ej | Hi) • If we only care about relative probabilities for the Hi, then we have: • P(Hi | E1, …, El) = αP(Hi) lj=1 P(Ej | Hi)

  19. Limitations of simple Bayesian inference • Cannot easily handle multi-fault situation, nor cases where intermediate (hidden) causes exist: • Disease D causes syndrome S, which causes correlated manifestations M1 and M2 • Consider a composite hypothesis H1 H2, where H1 and H2 are independent. What is the relative posterior? • P(H1  H2 | E1, …, El) = αP(E1, …, El | H1  H2) P(H1  H2) = αP(E1, …, El | H1  H2) P(H1) P(H2) = αlj=1 P(Ej | H1  H2)P(H1) P(H2) • How do we compute P(Ej | H1  H2) ??

  20. Limitations of simple Bayesian inference II • Assume H1 and H2 are independent, given E1, …, El? • P(H1  H2 | E1, …, El) = P(H1 | E1, …, El) P(H2 | E1, …, El) • This is a very unreasonable assumption • Earthquake and Burglar are independent, but not given Alarm: • P(burglar | alarm, earthquake) << P(burglar | alarm) • Another limitation is that simple application of Bayes’s rule doesn’t allow us to handle causal chaining: • A: this year’s weather; B: cotton production; C: next year’s cotton price • A influences C indirectly: A→ B → C • P(C | B, A) = P(C | B) • Need a richer representation to model interacting hypotheses, conditional independence, and causal chaining • Next time: conditional independence and Bayesian networks!

  21. Bayesian Networks Chapter 14.1-14.3 Some material borrowedfrom Lise Getoor

  22. Bayesian Belief Networks (BNs) • Definition: BN = (DAG, CPD) • DAG: directed acyclic graph (BN’s structure) • Nodes: random variables (typically binary or discrete, but methods also exist to handle continuous variables) • Arcs: indicate probabilistic dependencies between nodes (lack of link signifies conditional independence) • CPD: conditional probability distribution (BN’s parameters) • Conditional probabilities at each node, usually stored as a table (conditional probability table, or CPT) • Root nodes are a special case – no parents, so just use priors in CPD:

  23. a b c d e Example BN P(A) = 0.001 P(C|A) = 0.2 P(C|A) = 0.005 P(B|A) = 0.3 P(B|A) = 0.001 P(D|B,C) = 0.1 P(D|B,C) = 0.01 P(D|B,C) = 0.01 P(D|B,C) = 0.00001 P(E|C) = 0.4 P(E|C) = 0.002 Note that we only specify P(A) etc., not P(¬A), since they have to add to one

  24. Conditional independence and chaining • Conditional independence assumption where q is any set of variables (nodes) other than and its successors • blocks influence of other nodes on and its successors (q influences only through variables in ) • With this assumption, the complete joint probability distribution of all variables in the network can be represented by (recovered from) local CPDs by chaining these CPDs: q

  25. a b c d e Chaining: Example Computing the joint probability for all variables is easy: P(a, b, c, d, e) = P(e | a, b, c, d) P(a, b, c, d) by the product rule = P(e | c) P(a, b, c, d) by cond. indep. assumption = P(e | c) P(d | a, b, c) P(a, b, c) = P(e | c) P(d | b, c) P(c | a, b) P(a, b) = P(e | c) P(d | b, c) P(c | a) P(b | a) P(a)

  26. Topological semantics • A node is conditionally independent of its non-descendants given its parents • A node is conditionally independent of all other nodes in the network given its parents, children, and children’s parents (also known as its Markov blanket) • The method called d-separation can be applied to decide whether a set of nodes X is independent of another set Y, given a third set Z

  27. Inference in Bayesian Networks Chapter 14.4-14.5 Some material borrowedfrom Lise Getoor

  28. Inference tasks • Simple queries: Computer posterior marginal P(Xi | E=e) • E.g., P(NoGas | Gauge=empty, Lights=on, Starts=false) • Conjunctive queries: • P(Xi, Xj | E=e) = P(Xi | e=e) P(Xj | Xi, E=e) • Optimal decisions:Decision networks include utility information; probabilistic inference is required to find P(outcome | action, evidence) • Value of information: Which evidence should we seek next? • Sensitivity analysis:Which probability values are most critical? • Explanation: Why do I need a new starter motor?

  29. Approaches to inference • Exact inference • Enumeration • Belief propagation in polytrees • Variable elimination • Clustering / join tree algorithms • Approximate inference • Stochastic simulation / sampling methods • Markov chain Monte Carlo methods • Genetic algorithms • Neural networks • Simulated annealing • Mean field theory

  30. Direct inference with BNs • Instead of computing the joint, suppose we just want the probability for one variable • Exact methods of computation: • Enumeration • Variable elimination • Join trees: get the probabilities associated with every query variable

  31. Inference by enumeration • Add all of the terms (atomic event probabilities) from the full joint distribution • If E are the evidence (observed) variables and Y are the other (unobserved) variables, then: P(X|e) = α P(X, E) = α ∑ P(X, E, Y) • Each P(X, E, Y) term can be computed using the chain rule • Computationally expensive!

  32. a b c d e Example: Enumeration • P(xi) = Σπi P(xi | πi) P(πi) • Suppose we want P(D=true), and only the value of E is given as true • P (d|e) =  ΣABCP(a, b, c, d, e) =  ΣABCP(a) P(b|a) P(c|a) P(d|b,c) P(e|c) • With simple iteration to compute this expression, there’s going to be a lot of repetition (e.g., P(e|c) has to be recomputed every time we iterate over C=true)

  33. Exercise: Enumeration p(smart)=.8 p(study)=.6 smart study p(fair)=.9 prepared fair pass Query: What is the probability that a student studied, given that they pass the exam?

  34. Variable elimination • Basically just enumeration, but with caching of local calculations • Linear for polytrees (singly connected BNs) • Potentially exponential for multiply connected BNs • Exact inference in Bayesian networks is NP-hard! • Join tree algorithms are an extension of variable elimination methods that compute posterior probabilities for all nodes in a BN simultaneously

  35. Variable elimination General idea: • Write query in the form • Iteratively • Move all irrelevant terms outside of innermost sum • Perform innermost sum, getting a new term • Insert the new term into the product

  36. Cloudy Rain Sprinkler WetGrass Variable elimination: Example

  37. Smoking Visit to Asia Tuberculosis Lung Cancer Abnormality in Chest Bronchitis Dyspnea X-Ray A more complex example • “Asia” network:

  38. S V L T B A X D • We want to compute P(d) • Need to eliminate: v,s,x,t,l,a,b Initial factors

  39. S V L T B A X D Compute: • We want to compute P(d) • Need to eliminate: v,s,x,t,l,a,b Initial factors Eliminate: v Note: fv(t) = P(t) In general, result of elimination is not necessarily a probability term

  40. S V L T B A X D Compute: • We want to compute P(d) • Need to eliminate: s,x,t,l,a,b • Initial factors Eliminate: s Summing on s results in a factor with two arguments fs(b,l) In general, result of elimination may be a function of several variables

  41. S V L T B A X D Compute: • We want to compute P(d) • Need to eliminate: x,t,l,a,b • Initial factors Eliminate: x Note: fx(a) = 1 for all values of a !!

  42. S V L T B A X D Compute: • We want to compute P(d) • Need to eliminate: t,l,a,b • Initial factors Eliminate: t

  43. S V L T B A X D Compute: • We want to compute P(d) • Need to eliminate: l,a,b • Initial factors Eliminate: l

  44. S V L T B A X D Compute: • We want to compute P(d) • Need to eliminate: b • Initial factors Eliminate: a,b

  45. S V L T B A X D Dealing with evidence • How do we deal with evidence? • Suppose we are give evidence V = t, S = f, D = t • We want to compute P(L, V = t, S = f, D = t)

  46. S V L T B A X D Dealing with evidence • We start by writing the factors: • Since we know that V = t, we don’t need to eliminate V • Instead, we can replace the factors P(V) and P(T|V) with • These “select” the appropriate parts of the original factors given the evidence • Note that fp(V) is a constant, and thus does not appear in elimination of other variables

  47. S V L T B A X D Dealing with evidence • Given evidence V = t, S = f, D = t • Compute P(L, V = t, S = f, D = t ) • Initial factors, after setting evidence:

  48. S V L T B A X D Dealing with evidence • Given evidence V = t, S = f, D = t • Compute P(L, V = t, S = f, D = t ) • Initial factors, after setting evidence: • Eliminating x, we get

  49. S V L T B A X D Dealing with evidence • Given evidence V = t, S = f, D = t • Compute P(L, V = t, S = f, D = t ) • Initial factors, after setting evidence: • Eliminating x, we get • Eliminating t, we get

  50. S V L T B A X D Dealing with evidence • Given evidence V = t, S = f, D = t • Compute P(L, V = t, S = f, D = t ) • Initial factors, after setting evidence: • Eliminating x, we get • Eliminating t, we get • Eliminating a, we get

More Related