This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: CSE 250A. Assignment 2 Out: Tue Oct 5 Due: Tue Oct 12 Reading : Russell & Norvig, Chapters 1314. 2.1 Probabilistic inference Recall the alarm belief network described in class. The directed acyclic graph (DAG) and conditional probability tables (CPTs) are shown below: Alarm Earthquake Burglar John Calls Mary Calls P(E=1) = 0.002 P(B=1) = 0.001 P(A=1E=0,B=0) = 0.001 P(A=1E=0,B=1) = 0.94 P(A=1E=1,B=0) = 0.29 P(A=1E=1,B=1) = 0.95 P(J=1A=0) = 0.05 P(J=1A=1) = 0.90 P(M=1A=0) = 0.01 P(M=1A=1) = 0.70 Compute numeric values for the following probabilities, exploiting relations of conditional independence as much as possible to simplify your calculations. Show your work. (a) P ( M =1) (d) P ( E =1  A =1 ,M =0) (g) P ( B =1  J =1 ,E =1) (b) P ( M =1  E =0 ,B =1) (e) P ( E =1  A =1 ,J =1) (h) P ( J =0  A =0 ,M =1) (c) P ( E =0  A =1) (f) P ( B =1  J =1) (i) P ( J =0  M =1 ,B =1) 2.2 Nonmonotonic reasoning A patient is known to have contracted a rare disease which comes in two forms, represented by the values of a binary random variable X { , 1 } . Symptoms of the disease are represented by the binary random variables Y k { , 1 } , and knowledge of the disease is summarized by the belief network: X Y 1 Y 2 Y 3 Y n ... 1 The conditional probability tables (CPTs) for this belief network are as follows. In the absence of evidence, both forms of the disease are equally likely, with prior probabilities: P ( X =0) = P ( X =1) = 1 2 . In the first form of the disease ( X =0) , the first symptom occurs with probability one, P ( Y 1 =1  X =0) = 1 , while the k th symptom (with k 2 ) occurs with probability P ( Y k =1  X =0) = f ( k 1) f ( k ) , where the function...
View
Full
Document
This note was uploaded on 11/20/2010 for the course CSE 250a taught by Professor Lawrence during the Spring '10 term at UCSD.
 Spring '10
 lawrenCe

Click to edit the document details