probabilistic (bayesian) representations of knowledge have had a major impact on ai

15
Probabilistic (Bayesian) representations of knowledge have had a major impact on AI contrast with symbolic/logical knowledge bases necessity to handle uncertainty in real world apps recent advances allow scaling up to larger networks Example applications of Bayesian networks HCI: inferring intent in conversation/action, plan recognition, intelligent tutoring vision – image interpretation, de-noising control – variables that influence flight – medicine – economics

Upload: calum

Post on 14-Jan-2016

27 views

Category:

Documents


0 download

DESCRIPTION

Probabilistic (Bayesian) representations of knowledge have had a major impact on AI contrast with symbolic/logical knowledge bases necessity to handle uncertainty in real world apps recent advances allow scaling up to larger networks Example applications of Bayesian networks - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

• Probabilistic (Bayesian) representations of knowledge have had a major impact on AI– contrast with symbolic/logical knowledge bases– necessity to handle uncertainty in real world apps– recent advances allow scaling up to larger networks

• Example applications of Bayesian networks– HCI: inferring intent in conversation/action, plan

recognition, intelligent tutoring– vision – image interpretation, de-noising– control – variables that influence flight– medicine– economics

Page 2: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

Structure and Semantics of BN• draw causal nodes first• draw directed edges to effects (“direct causes”)• links encode conditional probability tables

(CPT over parents)• fewer parameters than full joint PDF• absence of link is related to independence

Page 3: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI
Page 4: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

• types of independence– A is indep of non-descendants given parents– Markov blanket– d-separation – all paths between A and B are

“blocked”– useful for determining if obtaining knowledge of B

would change belief about A

Page 5: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

• child is cond.dep. on parent: P(B|A)

• parent is cond.dep. on child:– P(A|B)=P(B|A)P(A)/P(B)

• what about when one node is not an ancestor of the other? e.g. siblings

A

B

A and B are only conditionally independent given C

Page 6: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

simple treespoly-trees (singly connected, one path between any pair of nodes)“cyclic” (using undirected edges) – much harder to do computations

explaining away: P(sprinkler | wetGrass) = 0.43P(sprinkler | wetGrass,rain) = 0.19

Page 7: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

• Compact representations of CPT– Noisy-Or– prob. version of: cold flu malaria fever– only have to represent 3 numbers (“strengths”)

instead of 8

Page 8: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI
Page 9: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

Network Engineering for Complex Belief Networks, Mahoney and Laskey

Page 10: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

A Bayesian network approach to threat valuation with application to an air defense scenario, Johansson and Falkman

Page 11: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

Lumiere – Office Assistant

Page 12: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

Inference Tasks• posterior: P(Xi|{Zi})

– Zi observed vars, with unobserved variables Yi, marginalized out– prediction vs. diagnosis– evidence combination is crucial– handling unobserved variables is crucial

• all marginals: P(Ai) – like priors, but for interior nodes too• subjoint: P(A,B)• boolean queries• most-probable explanation:

– argmax{Yi} P(Yi U Zi) – state with highest joint probability

Page 13: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

(see slides 4-10 in http://aima.eecs.berkeley.edu/slides-pdf/chapter14b.pdffor discussion of Enumeration and VariableElimination)

Page 14: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

Inference in Bayesian Networks, D’Ambrosio

Page 15: Probabilistic (Bayesian) representations of knowledge have had a major impact on AI

Belief Propagation (this figure happens to come from http://www.pr-owl.org/basics/bn.php)see also: wiki, Ch. 8 in Bishop PR&ML