Download presentation

Presentation is loading. Please wait.

Published bySalvatore Wasden Modified over 2 years ago

1
Bucket Elimination: A unifying framework for Probabilistic inference Rina Dechter presented by Anton Bezuglov, Hrishikesh Goradia CSCE 582 Fall02 Instructor: Dr. Marco Valtorta

2
Contributions For a Bayesian network, the paper presents algorithms for –Belief Assessment –Most Probable Explanation (MPE) –Maximum Aposteriori Hypothesis (MAP) All of the above are bucket elimination algorithms.

3
Belief Assessment Definition –The belief assessment task of X k = x k is to find In the Visit to Asia example, the belief assessment problem answers questions like –What is the probability that a person has tuberculosis, given that he/she has dyspnea and has visited Asia recently ? where k – normalizing constant

4
Most Probable Explanation (MPE) Definition –The MPE task is to find an assignment x o = (x o 1, …, x o n ) such that In the Visit to Asia example, the MPE problem answers questions like –What are the most probable values for all variables such that a person doesn’t catch dyspnea ?

5
Maximum Aposteriori Hypothesis (MAP) Definition –Given a set of hypothesized variables A = {A 1, …, A k },, the MAP task is to find an assignment a o = (a o 1, …, a o k ) such that In the Visit to Asia example, the MAP problem answers questions like –What are the most probable values for a person having both lung cancer and bronchitis, given that he/she has dyspnea and that his/her X-ray is positive?

6
Ordering the Variables Method 1 (Minimum deficiency) Begin elimination with the node which adds the fewest number of edges 1. , , (nothing added) 2. (nothing added) 3. ,, , (one edge added) Method 2 (Minimum degree) Begin elimination with the node which has the lowest degree 1. , (degree = 1) 2. , , (degree = 2) 3., , (degree = 2)

7
Elimination Algorithm for Belief Assessment Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : P( | ) P( | )*P( ), =“yes” P( | , ) P( | , ), =“yes” P( | =“yes”, =“yes”) = X\ { } (P( | )* P( | )* P( | , )* P( | , )* P( )*P( | )*P( | )*P( )) P( | ) P( | )*P( ) H()H() H()H() H(,)H(,) H ( ,, ) H ( , , ) H()H() H(,)H(,) P( | =“yes”, =“yes”) H n (u)= xn П j i=1 C i (x n,u si ) *k k-normalizing constant

8
Elimination Algorithm for Most Probable Explanation Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : P( | ) P( | )*P( ) P( | , ) P( | , ), =“no” MPE= MAX { , , , ,, , , } (P( | )* P( | )* P( | , )* P( | , )* P( )*P( | )*P( | )*P( )) P( | ) P( | )*P( ) H()H() H()H() H(,)H(,) H ( ,, ) H ( , , ) H()H() H(,)H(,) MPE probability Finding MPE = max , , , ,, , , P( , , , ,, , , ) H n (u)=max xn ( П xn Fn C(x n |x pa ))

9
Elimination Algorithm for Most Probable Explanation Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : Bucket : P( | ) P( | )*P( ) P( | , ) P( | , ), =“no” P( | ) P( | )*P( ) H()H() H()H() H(,)H(,) H ( ,, ) H ( , , ) H()H() H(,)H(,) Forward part ’ = arg max H ( )* H ( ) ’ = arg max H ( ’, ) ’ = arg max P( ’| )*P( )* H ( ’, ’, ) ’ = arg max P( | ’)*H ( ’,, ’) ’ = arg max P( | ’, ’)*H ( , ’)*H ( ) ’ = “no” ’ = arg max P( | ’) ’ = arg max P( ’| )*P( ) Return: ( ’, ’, ’, ’, ’, ’, ’, ’)

Similar presentations

OK

1 Structure Learning (The Good), The Bad, The Ugly Inference Graphical Models – 10708 Carlos Guestrin Carnegie Mellon University October 13 th, 2008 Readings:

1 Structure Learning (The Good), The Bad, The Ugly Inference Graphical Models – 10708 Carlos Guestrin Carnegie Mellon University October 13 th, 2008 Readings:

© 2018 SlidePlayer.com Inc.

All rights reserved.

Ads by Google

Ppt on venture capital for mba students Ppt on op amp circuits applications Ppt on op amp circuits schematics Ppt on index of industrial production of india Ppt on intellectual property rights and global business Ppt on water conservation in industries Ppt on bond length of n2 Ppt on abstract art prints Ppt on biodiversity and its conservation Ppt on law against child marriage in africa