SlideShare a Scribd company logo
Introduction  to Bayesian Networks   A Tutorial for the 66th MORS Symposium 23 - 25 June 1998 Naval Postgraduate School Monterey, California  Dennis M. Buede  Joseph A. Tatman Terry A. Bresnick
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Day One Outline ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Why the Excitement? ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],Visit to Asia Tuberculosis Tuberculosis or Cancer XRay Result Dyspnea Bronchitis Lung Cancer Smoking Patient Information Medical Difficulties Diagnostic Tests
Example from Medical Diagnostics ,[object Object],Patient Information Diagnostic Tests Visit to Asia Tuberculosis Tuberculosis or Cancer XRay Result Dyspnea Bronchitis Lung Cancer Smoking Tuber Present Present Absent Absent Lung Can Present Absent Present Absent Tub or Can True True True False Medical Difficulties Tub or Can True True False False Bronchitis Present Absent Present Absent Present 0.90 0.70 0.80 0.10 Absent 0.l0 0.30 0.20 0.90 Dyspnea
Example from Medical Diagnostics ,[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],[object Object]
Applications ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Definition of a Bayesian Network ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Sample Factored Joint Distribution X 1 X 3 X 2 X 5 X 4 X 6 p(x 1 , x 2 , x 3 , x 4 , x 5 , x 6 ) = p(x 6  | x 5 ) p(x 5  | x 3 , x 2 ) p(x 4  | x 2 , x 1 ) p(x 3  | x 1 ) p(x 2  | x 1 ) p(x 1 )
Bayes Rule ,[object Object],[object Object],[object Object],[object Object],[object Object],     i i i i i i i i ) )p(A A | p(E ) )p(A A | p(E p(E) ) )p(A A | p(E E) | p(A p(B) A)p(A) | p(B p(B) B) p(A, B) | p(A A 1 A 2 A 3 A 4 A 5 A 6 E
Arc Reversal - Bayes Rule p(x 1 , x 2 , x 3 ) = p(x 3   |  x 1 ) p(x 2  |  x 1 ) p(x 1 ) p(x 1 , x 2 , x 3 ) = p(x 3  |  x 2 , x 1 ) p(x 2 ) p( x 1 ) p(x 1 , x 2 , x 3 ) = p(x 3  |  x 1 ) p(x 2  ,  x 1 ) = p(x 3  |  x 1 ) p(x 1  |  x 2 ) p( x 2 ) p(x 1 , x 2 , x 3 ) = p(x 3 ,  x 2  | x 1 ) p( x 1 ) = p(x 2  |  x 3 , x 1 ) p(x 3  |  x 1 ) p( x 1 ) is equivalent to is equivalent to X 1 X 3 X 2 X 1 X 3 X 2 X 1 X 3 X 2 X 1 X 3 X 2
Inference Using Bayes Theorem Tuber- culosis Lung Cancer Tuberculosis or Cancer Dyspnea Bronchitis Lung Cancer Tuberculosis or Cancer Dyspnea Bronchitis Lung Cancer Tuberculosis or Cancer Dyspnea Lung Cancer Dyspnea Lung Cancer Dyspnea The general probabilistic inference problem is to find the probability of an event given a set of evidence This can be done in Bayesian nets with sequential applications of Bayes Theorem
Why Not this Straightforward Approach? ,[object Object],[object Object],[object Object],[object Object],[object Object]
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Introduction to Bayesian Networks   A Tutorial for the 66th MORS Symposium 23 - 25 June 1998 Naval Postgraduate School Monterey, California  Dennis M. Buede  Joseph A. Tatman Terry A. Bresnick
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Overview  of Bayesian Network Algorithms ,[object Object],[object Object],[object Object],[object Object],[object Object]
Propagation Algorithm Objective ,[object Object],Data Data
Singly Connected Networks (or Polytrees) Definition :  A directed acyclic graph (DAG) in which only one semipath (sequence of connected nodes ignoring direction of the arcs) exists between any two nodes. Do not satisfy definition Polytree structure satisfies definition Multiple parents  and/or multiple children
Notation ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],X = a random variable (a vector of dimension m);  x = a possible value of X e = evidence (or data), a vector of dimension m M y|x  = p(y|x), the likelihood matrix or conditional probability distribution p(y 1 |x 1 )  p(y 2 |x 1 )  . . .  p(y n |x 1 )  p(y 1 |x 2 )  p(y 2 |x 2 )  . . .  p(y n |x 2 ) . . .   . . .  . . .  p(y 1 |x m )  p(y 2 |x m )  . . .  p(y n |x m ) y =  x
Bi-Directional Propagation  in a Chain e + e - X Y Z ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Each node transmits a pi message to its children and a lambda message to its parents. Bel(Y) = p(y|e + , e - ) =      (y) T       (y) where  (y) = p(y|e + ), prior evidence; a row vector  (y) = p(e - |y), diagnostic or likelihood evidence; a column vector  (y) =   x  p(y|x, e + )    p(x| e + ) =   x  p(y|x)      (x) =   (x)    M y|x  (y) =   z  p(e - |y, z)    p(z| y) =   z  p(e - |z)    p(z| y) =   z    (z)    p(z| y) = M z|y       (z)
An Example: Simple Chain p(Paris) = 0.9 p(Med.) = 0.1 M  TO|SM  =  M  AA |TO  = Ch Di Pa Me No Ce So Ch Di Paris Med. Chalons Dijon North Central South Strategic Mission Tactical  Objective Avenue of Approach .8  .2 .1  .9 [ ] .5  .4  .1 .1  .3  .6 [ ]
Sample Chain - Setup (1) Set all lambdas to be a vector of 1’s; Bel(SM) =      (SM)      (SM)  (SM)   Bel(SM)  (SM) Paris   0.9   0.9   1.0 Med.   0.1   0.1   1.0 (2)   (TO) =   (SM) M TO|SM ; Bel(TO) =      (TO)      (TO)  (TO)   Bel(TO)  (TO) Chalons  0.73   0.73   1.0 Dijon  0.27   0.27   1.0 (3)   (AA) =   (TO) M AA|TO ; Bel(AA) =      (AA)      (AA)  (AA)   Bel(AA)  (AA) North  0.39   0.40   1.0 Central  0.35   0.36   1.0 South  0.24   0.24   1.0 M AA|TO  = M TO|SM  = Strategic Mission Tactical  Objective Avenue of Approach .8  .2 .1  .9 [ ] .5  .4  .1 .1  .3  .6 [ ]
Sample Chain - 1st Propagation   t TR T   0 5  ( ) . 1  .6   t = 0 (lR) = .8  .2  t = 1  (SM) =   (IR)  (SM)   Bel(SM)  (SM) Paris   0.8   0.8   1.0 Med.   0.2   0.2   1.0  (TO)   Bel(TO)  (TO) Chalons   0.73   0.73   1.0 Dijon   0.27   0.27   1.0  (AA)   Bel(AA)  (AA) North   0.39   0.3   0.5 Central   0.35   0.5   1.0 South   0.24   0.2   0.6 t = 1  (AA) =   (TR) Intel. Rpt. Troop Rpt. Strategic Mission Tactical  Objective Avenue of Approach
Sample Chain - 2nd Propagation   t TR T   0 5  ( ) . 1  .6   t = 0 (lR) = .8  .2   (SM)   Bel(SM)  (SM) Paris   0.8   0.8   1.0 Med.   0.2   0.2   1.0 t = 2  (TO) =   (SM) M TO|SM  (TO)   Bel(TO)  (TO) Chalons   0.66   0.66   0.71 Dijon   0.34   0.34   0.71 t = 2  (TO) = M AA|TO   (SM)   (AA)   Bel(AA)  (AA) North   0.39   0.3   0.5 Central   0.35   0.5   1.0 South   0.24   0.2   0.6 Intel. Rpt. Troop Rpt. Strategic Mission Tactical  Objective Avenue of Approach
Sample Chain - 3rd Propagation  (SM)   Bel(SM)  (SM) Paris   0.8   0.8   0.71 Med.   0.2   0.2   0.71 t = 3  (SM) =  M TO|SM  (TO)  (TO)   Bel(TO)  (TO) Chalons   0.66   0.66   0.71 Dijon   0.34   0.34   0.71 t = 3  (AA) =   (TO) M AA|TO   (AA)   Bel(AA)  (AA) North   0.36   0.25   0.5 Central   0.37   0.52   1.0 South   0.27   0.23   0.6 Intel. Rpt. Troop Rpt. Strategic Mission Tactical  Objective Avenue of Approach
Internal Structure  of a Single Node Processor Processor for Node X Message to Parent U Message from Parent U M X|U             M X|U  k    k (X) BEL =            Message to Children of X Message from Children of X    BEL(X)  1 (X)    BEL(X)  N (X) ... ...  (X)  (X)  X (U)  1 (X)  N (X)    X (U)  N (X)  1 (X)
Propagation Example ,[object Object],“ The impact of each new piece of evidence is  viewed as a perturbation that propagates through the network via message-passing between neighboring variables . . .”  (Pearl, 1988, p 143` Data Data
Categorization of Other Algorithms ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Decision Making in Nuclear Power Plant Operations ,[object Object],[object Object],[object Object],[object Object],Monitor Environment Start Assessment ? Propagate Evidence Situation Awareness Updated Situation Belief Distribution Assess Situation Action Required ? Project Events Choose Action If Situation = S i Then Procedure = P i Situation Assessment (SA) Decision Making 1)  Monitor the environment 2)  Determine the need for situation  assessment 3)  Propagate event cues 4)  Project Events 5)  Assess Situation 6)  Make Decision
Model of Situation Assessment and Human Decision Making ,[object Object],[object Object],[object Object],[object Object],Steam Generator Tube Rupture Loss of Coolant Accident Loss of Secondary Coolant Other Emergency Steam Line Radiation Pressurizer Pressure Steam Gen- erator Level Steam Line Radiation Alarm Pressurizer Indicator Steam Generator Indicator Situations Events Sensor Outputs
Situation Assessment Bayesian Net Initial Conditions Given Emergency
Situation Assessment Bayesian Net Steam Line Radiation Alarm Goes High
Situation Assessment Bayesian Net Steam Line Radiation Alarm Goes Low
Simulation of SGTR Scenario Event Timeline
Simulation of SGTR Scenario Convergence of Situation Disparity ,[object Object],[object Object],[object Object],[object Object]
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Introduction to Bayesian Networks   A Tutorial for the 66th MORS Symposium 23 - 25 June 1998 Naval Postgraduate School Monterey, California  Dennis M. Buede, dbuede@gmu.edu  Joseph A. Tatman, jatatman@aol.com Terry A. Bresnick, bresnick@ix.netcom.com http://www.gmu.edu -  Depts (Info Tech & Eng) - Sys. Eng. - Buede
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Building BN Structures Bayesian Network Bayesian Network Bayesian Network Problem Domain Problem Domain Problem Domain Expert Knowledge Expert Knowledge Training Data Training Data Probability Elicitor Learning Algorithm Learning Algorithm
Learning Probabilities from Data ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Beta Distribution 1) n(n m/n) m(1 variance n m mean x) (1 x m) (n (m) (n) n) m, | (x p 1 m n 1 m Beta             
Multivariate Dirichlet Distribution 1) m ( m ) m / m (1 m state i the of variance m m state i the of mean  ...x x x ) (m )... (m ) (m ) m ( ) m ,..., m , m | (x p N 1 i i N 1 i i N 1 i i i i th N 1 i i i th 1 m 1 - m 1 m N 2 1 N 1 i i N 2 1 Dirichlet N 2 1                     
Updating with Dirichlet ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Learning BN Structure from Data ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Sample Score Metrics ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Features for Adding Knowledge to Learning Structure ,[object Object],[object Object],[object Object]
Demonstration of Bayesian Network Power Constructor ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Enemy Intent Trafficability of S. AA Trafficability of C. AA Trafficability of N. AA Troops @ NAI 1 Troops @ NAI 2 AA  - Avenue of Approach NAI - Named Area of Interest Intelligence Reports Observations on Troop Movements Weather Forecast & Feasibility Analysis Strategic Mission Weather Tactical Objective Enemy’s Intelligence on Friendly Forces Avenue of Approach Deception Plan
Original Network
Learned Network with 1000 Cases Missing Arcs:  2 Added Arcs:  0 Arcs Misdirected: 5 Arcs Unspecified: 3 Missing Arcs:  2 Added Arcs:  0 Arcs Misdirected: 5 Arcs Unspecified: 3
Learned Network with 10,000 Cases Missing Arcs:  1 Added Arcs:  1 Arcs Misdirected: 4
Comparison of Learned Networks  with Truth p(AoA) Truth 1 K 10 K Prior .37, .37, .26 .37, .35, .28 .38, .36, .26 “ Clear” .41, .37, .22 .38, .36, .26 .41, .36, .23 “ Rainy” .30, .36, .34 .35, .32, .33 .30, .36, .34 “ NAI 1 True” .15, .13, .71 .17, .12, .71 .16, .12, .71 “ Rain, NAI 1 True” .10, .11, .79 .15, .10, .75 .11, .11, .78 “ Rain, NAI 1 & 2 True” .56, .02, .43 .59, .05, .36 .56, .03, .40
Summary of Comparison ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Continuous Variables Example ,[object Object]
Continuous Variables Example Entering values for the three discrete random variables shifts the sensor mean values
Continuous Variables Example ,[object Object]
Continuous Variables Example ,[object Object]
Continuous Variables Example ,[object Object]
Software ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Basic References ,[object Object],[object Object],[object Object],[object Object],[object Object]
Algorithm References ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Backup
The Propagation Algorithm ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],T BEL(t)  (t)   (t) U BEL(t)  (t)   (t) X BEL(t)  (t)   (t) Y BEL(t)  (t)   (t) Z BEL(t)  (t)   (t) M u|t M x|u M y|x M z|y
Key Events in Development of Bayesian Nets ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],[object Object],[object Object]
Example from Medical Diagnostics ,[object Object],[object Object]
Tuberculosis XRay Result Tuberculosis or Cancer Lung Cancer Dyspnea Bronchitis
Inference Using Bayes Theorem ,[object Object],[object Object],Tuber- culosis Lung Cancer Smoker Tuberculosis or Cancer Tuber- culosis Lung Cancer Smoker Tuberculosis or Cancer Lung Cancer Smoker Tuberculosis or Cancer Lung Cancer Smoker Tuberculosis or Cancer Smoker Tuberculosis or Cancer Smoker
Sample Chain - Setup (1) Set all lambdas to be a vector of 1’s;  Bel(SM) =      (SM)      (SM)  (SM)   Bel(SM)  (SM) Paris   0.9   0.9   1.0 Med.   0.1   0.1   1.0 (2)   (TO) =   (SM) M TO|SM ; Bel(TO) =      (TO)      (TO)  (TO)   Bel(TO)  (TO) Chalons  0.73   0.73   1.0 Dijon  0.27   0.27   1.0 (3)   (AA) =   (TO) M AA|TO ; Bel(AA) =      (AA)      (AA)  (AA)   Bel(AA)  (AA) North  0.39   0.73   1.0 Central  0.35   0.27   1.0 South  0.24   0.24   1.0 Strategic Mission Tactical  Objective Avenue of Approach M AA|TO  = M TO|SM  =

More Related Content

What's hot

'ACCOST' for differential HiC analysis
'ACCOST' for differential HiC analysis'ACCOST' for differential HiC analysis
'ACCOST' for differential HiC analysis
tuxette
 
Belief Networks & Bayesian Classification
Belief Networks & Bayesian ClassificationBelief Networks & Bayesian Classification
Belief Networks & Bayesian Classification
Adnan Masood
 
Declarative data analysis
Declarative data analysisDeclarative data analysis
Declarative data analysis
South West Data Meetup
 
Graph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype PredictionGraph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype Prediction
tuxette
 
Data science
Data scienceData science
Data science
Rakibul Hasan Pranto
 
On Machine Learning and Data Mining
On Machine Learning and Data MiningOn Machine Learning and Data Mining
On Machine Learning and Data Miningbutest
 
Drug Target Interaction (DTI) prediction (MSc. thesis)
Drug Target Interaction (DTI) prediction (MSc. thesis) Drug Target Interaction (DTI) prediction (MSc. thesis)
Drug Target Interaction (DTI) prediction (MSc. thesis)
Dimitris Papadopoulos
 
TPCMFinalACone
TPCMFinalAConeTPCMFinalACone
TPCMFinalAConeAdam Cone
 
32_Nov07_MachineLear..
32_Nov07_MachineLear..32_Nov07_MachineLear..
32_Nov07_MachineLear..butest
 
Combining co-expression and co-location for gene network inference in porcine...
Combining co-expression and co-location for gene network inference in porcine...Combining co-expression and co-location for gene network inference in porcine...
Combining co-expression and co-location for gene network inference in porcine...
tuxette
 
Selective inference and single-cell differential analysis
Selective inference and single-cell differential analysisSelective inference and single-cell differential analysis
Selective inference and single-cell differential analysis
tuxette
 
Module 4 part_1
Module 4 part_1Module 4 part_1
Module 4 part_1
ShashankN22
 
Artificial Intelligence - Reasoning in Uncertain Situations
Artificial Intelligence - Reasoning in Uncertain SituationsArtificial Intelligence - Reasoning in Uncertain Situations
Artificial Intelligence - Reasoning in Uncertain Situations
Laguna State Polytechnic University
 
2018 Modern Math Workshop - Nonparametric Regression and Classification for M...
2018 Modern Math Workshop - Nonparametric Regression and Classification for M...2018 Modern Math Workshop - Nonparametric Regression and Classification for M...
2018 Modern Math Workshop - Nonparametric Regression and Classification for M...
The Statistical and Applied Mathematical Sciences Institute
 
Contrast Pattern Aided Regression and Classification
Contrast Pattern Aided Regression and ClassificationContrast Pattern Aided Regression and Classification
Contrast Pattern Aided Regression and Classification
Artificial Intelligence Institute at UofSC
 
A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...
A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...
A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...
ijaia
 
METHODS FOR INCREMENTAL LEARNING: A SURVEY
METHODS FOR INCREMENTAL LEARNING: A SURVEYMETHODS FOR INCREMENTAL LEARNING: A SURVEY
METHODS FOR INCREMENTAL LEARNING: A SURVEY
IJDKP
 
Joint causal inference on observational and experimental data - NIPS 2016 "Wh...
Joint causal inference on observational and experimental data - NIPS 2016 "Wh...Joint causal inference on observational and experimental data - NIPS 2016 "Wh...
Joint causal inference on observational and experimental data - NIPS 2016 "Wh...
Sara Magliacane
 
Stock markets and_human_genomics
Stock markets and_human_genomicsStock markets and_human_genomics
Stock markets and_human_genomicsShyam Sarkar
 
An Introduction to Mis-Specification (M-S) Testing
An Introduction to Mis-Specification (M-S) TestingAn Introduction to Mis-Specification (M-S) Testing
An Introduction to Mis-Specification (M-S) Testing
jemille6
 

What's hot (20)

'ACCOST' for differential HiC analysis
'ACCOST' for differential HiC analysis'ACCOST' for differential HiC analysis
'ACCOST' for differential HiC analysis
 
Belief Networks & Bayesian Classification
Belief Networks & Bayesian ClassificationBelief Networks & Bayesian Classification
Belief Networks & Bayesian Classification
 
Declarative data analysis
Declarative data analysisDeclarative data analysis
Declarative data analysis
 
Graph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype PredictionGraph Neural Network for Phenotype Prediction
Graph Neural Network for Phenotype Prediction
 
Data science
Data scienceData science
Data science
 
On Machine Learning and Data Mining
On Machine Learning and Data MiningOn Machine Learning and Data Mining
On Machine Learning and Data Mining
 
Drug Target Interaction (DTI) prediction (MSc. thesis)
Drug Target Interaction (DTI) prediction (MSc. thesis) Drug Target Interaction (DTI) prediction (MSc. thesis)
Drug Target Interaction (DTI) prediction (MSc. thesis)
 
TPCMFinalACone
TPCMFinalAConeTPCMFinalACone
TPCMFinalACone
 
32_Nov07_MachineLear..
32_Nov07_MachineLear..32_Nov07_MachineLear..
32_Nov07_MachineLear..
 
Combining co-expression and co-location for gene network inference in porcine...
Combining co-expression and co-location for gene network inference in porcine...Combining co-expression and co-location for gene network inference in porcine...
Combining co-expression and co-location for gene network inference in porcine...
 
Selective inference and single-cell differential analysis
Selective inference and single-cell differential analysisSelective inference and single-cell differential analysis
Selective inference and single-cell differential analysis
 
Module 4 part_1
Module 4 part_1Module 4 part_1
Module 4 part_1
 
Artificial Intelligence - Reasoning in Uncertain Situations
Artificial Intelligence - Reasoning in Uncertain SituationsArtificial Intelligence - Reasoning in Uncertain Situations
Artificial Intelligence - Reasoning in Uncertain Situations
 
2018 Modern Math Workshop - Nonparametric Regression and Classification for M...
2018 Modern Math Workshop - Nonparametric Regression and Classification for M...2018 Modern Math Workshop - Nonparametric Regression and Classification for M...
2018 Modern Math Workshop - Nonparametric Regression and Classification for M...
 
Contrast Pattern Aided Regression and Classification
Contrast Pattern Aided Regression and ClassificationContrast Pattern Aided Regression and Classification
Contrast Pattern Aided Regression and Classification
 
A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...
A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...
A SYSTEM OF SERIAL COMPUTATION FOR CLASSIFIED RULES PREDICTION IN NONREGULAR ...
 
METHODS FOR INCREMENTAL LEARNING: A SURVEY
METHODS FOR INCREMENTAL LEARNING: A SURVEYMETHODS FOR INCREMENTAL LEARNING: A SURVEY
METHODS FOR INCREMENTAL LEARNING: A SURVEY
 
Joint causal inference on observational and experimental data - NIPS 2016 "Wh...
Joint causal inference on observational and experimental data - NIPS 2016 "Wh...Joint causal inference on observational and experimental data - NIPS 2016 "Wh...
Joint causal inference on observational and experimental data - NIPS 2016 "Wh...
 
Stock markets and_human_genomics
Stock markets and_human_genomicsStock markets and_human_genomics
Stock markets and_human_genomics
 
An Introduction to Mis-Specification (M-S) Testing
An Introduction to Mis-Specification (M-S) TestingAn Introduction to Mis-Specification (M-S) Testing
An Introduction to Mis-Specification (M-S) Testing
 

Similar to Basen Network

IRJET- Disease Prediction using Machine Learning
IRJET-  Disease Prediction using Machine LearningIRJET-  Disease Prediction using Machine Learning
IRJET- Disease Prediction using Machine Learning
IRJET Journal
 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...butest
 
Multivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological dataMultivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological dataDmitry Grapov
 
Artificial Intelligence in Medical Imaging
Artificial Intelligence in Medical ImagingArtificial Intelligence in Medical Imaging
Artificial Intelligence in Medical Imaging
ZahidulIslamJewel2
 
Biosurveillance 2.0: Lecture at Emory University
Biosurveillance 2.0: Lecture at Emory UniversityBiosurveillance 2.0: Lecture at Emory University
Biosurveillance 2.0: Lecture at Emory University
Taha Kass-Hout, MD, MS
 
Classifiers
ClassifiersClassifiers
Classifiers
Ayurdata
 
Survival Analysis With Generalized Additive Models
Survival Analysis With Generalized Additive ModelsSurvival Analysis With Generalized Additive Models
Survival Analysis With Generalized Additive Models
Christos Argyropoulos
 
Bayesian statistics
Bayesian statisticsBayesian statistics
Bayesian statistics
Sagar Kamble
 
American Statistical Association October 23 2009 Presentation Part 1
American Statistical Association October 23 2009 Presentation Part 1American Statistical Association October 23 2009 Presentation Part 1
American Statistical Association October 23 2009 Presentation Part 1
Double Check ĆŐNSULTING
 
Biosurveillance 2.0
Biosurveillance 2.0Biosurveillance 2.0
Biosurveillance 2.0
Taha Kass-Hout, MD, MS
 
Data mining
Data mining Data mining
Data mining
Jhadesunil
 
Estimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample SetsEstimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample Sets
Förderverein Technische Fakultät
 
Perspective of feature selection in bioinformatics
Perspective of feature selection in bioinformaticsPerspective of feature selection in bioinformatics
Perspective of feature selection in bioinformatics
Gianluca Bontempi
 
Project Presentation
Project PresentationProject Presentation
Project Presentationbutest
 
Introduction
IntroductionIntroduction
Introductionbutest
 
Optimistic decision making using an
Optimistic decision making using anOptimistic decision making using an
Optimistic decision making using an
ijaia
 
MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...
MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...
MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...
The Statistical and Applied Mathematical Sciences Institute
 
Using model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolutionUsing model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolution
Erick Matsen
 
Kernel methods for data integration in systems biology
Kernel methods for data integration in systems biologyKernel methods for data integration in systems biology
Kernel methods for data integration in systems biology
tuxette
 

Similar to Basen Network (20)

08 entropie
08 entropie08 entropie
08 entropie
 
IRJET- Disease Prediction using Machine Learning
IRJET-  Disease Prediction using Machine LearningIRJET-  Disease Prediction using Machine Learning
IRJET- Disease Prediction using Machine Learning
 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...
 
Multivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological dataMultivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological data
 
Artificial Intelligence in Medical Imaging
Artificial Intelligence in Medical ImagingArtificial Intelligence in Medical Imaging
Artificial Intelligence in Medical Imaging
 
Biosurveillance 2.0: Lecture at Emory University
Biosurveillance 2.0: Lecture at Emory UniversityBiosurveillance 2.0: Lecture at Emory University
Biosurveillance 2.0: Lecture at Emory University
 
Classifiers
ClassifiersClassifiers
Classifiers
 
Survival Analysis With Generalized Additive Models
Survival Analysis With Generalized Additive ModelsSurvival Analysis With Generalized Additive Models
Survival Analysis With Generalized Additive Models
 
Bayesian statistics
Bayesian statisticsBayesian statistics
Bayesian statistics
 
American Statistical Association October 23 2009 Presentation Part 1
American Statistical Association October 23 2009 Presentation Part 1American Statistical Association October 23 2009 Presentation Part 1
American Statistical Association October 23 2009 Presentation Part 1
 
Biosurveillance 2.0
Biosurveillance 2.0Biosurveillance 2.0
Biosurveillance 2.0
 
Data mining
Data mining Data mining
Data mining
 
Estimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample SetsEstimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample Sets
 
Perspective of feature selection in bioinformatics
Perspective of feature selection in bioinformaticsPerspective of feature selection in bioinformatics
Perspective of feature selection in bioinformatics
 
Project Presentation
Project PresentationProject Presentation
Project Presentation
 
Introduction
IntroductionIntroduction
Introduction
 
Optimistic decision making using an
Optimistic decision making using anOptimistic decision making using an
Optimistic decision making using an
 
MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...
MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...
MUMS Opening Workshop - Principles of Predictive Computational Science: Predi...
 
Using model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolutionUsing model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolution
 
Kernel methods for data integration in systems biology
Kernel methods for data integration in systems biologyKernel methods for data integration in systems biology
Kernel methods for data integration in systems biology
 

Recently uploaded

From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 

Recently uploaded (20)

From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 

Basen Network

  • 1. Introduction to Bayesian Networks A Tutorial for the 66th MORS Symposium 23 - 25 June 1998 Naval Postgraduate School Monterey, California Dennis M. Buede Joseph A. Tatman Terry A. Bresnick
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14. Sample Factored Joint Distribution X 1 X 3 X 2 X 5 X 4 X 6 p(x 1 , x 2 , x 3 , x 4 , x 5 , x 6 ) = p(x 6 | x 5 ) p(x 5 | x 3 , x 2 ) p(x 4 | x 2 , x 1 ) p(x 3 | x 1 ) p(x 2 | x 1 ) p(x 1 )
  • 15.
  • 16. Arc Reversal - Bayes Rule p(x 1 , x 2 , x 3 ) = p(x 3 | x 1 ) p(x 2 | x 1 ) p(x 1 ) p(x 1 , x 2 , x 3 ) = p(x 3 | x 2 , x 1 ) p(x 2 ) p( x 1 ) p(x 1 , x 2 , x 3 ) = p(x 3 | x 1 ) p(x 2 , x 1 ) = p(x 3 | x 1 ) p(x 1 | x 2 ) p( x 2 ) p(x 1 , x 2 , x 3 ) = p(x 3 , x 2 | x 1 ) p( x 1 ) = p(x 2 | x 3 , x 1 ) p(x 3 | x 1 ) p( x 1 ) is equivalent to is equivalent to X 1 X 3 X 2 X 1 X 3 X 2 X 1 X 3 X 2 X 1 X 3 X 2
  • 17. Inference Using Bayes Theorem Tuber- culosis Lung Cancer Tuberculosis or Cancer Dyspnea Bronchitis Lung Cancer Tuberculosis or Cancer Dyspnea Bronchitis Lung Cancer Tuberculosis or Cancer Dyspnea Lung Cancer Dyspnea Lung Cancer Dyspnea The general probabilistic inference problem is to find the probability of an event given a set of evidence This can be done in Bayesian nets with sequential applications of Bayes Theorem
  • 18.
  • 19.
  • 20. Introduction to Bayesian Networks A Tutorial for the 66th MORS Symposium 23 - 25 June 1998 Naval Postgraduate School Monterey, California Dennis M. Buede Joseph A. Tatman Terry A. Bresnick
  • 21.
  • 22.
  • 23.
  • 24. Singly Connected Networks (or Polytrees) Definition : A directed acyclic graph (DAG) in which only one semipath (sequence of connected nodes ignoring direction of the arcs) exists between any two nodes. Do not satisfy definition Polytree structure satisfies definition Multiple parents and/or multiple children
  • 25.
  • 26.
  • 27. An Example: Simple Chain p(Paris) = 0.9 p(Med.) = 0.1 M TO|SM = M AA |TO = Ch Di Pa Me No Ce So Ch Di Paris Med. Chalons Dijon North Central South Strategic Mission Tactical Objective Avenue of Approach .8 .2 .1 .9 [ ] .5 .4 .1 .1 .3 .6 [ ]
  • 28. Sample Chain - Setup (1) Set all lambdas to be a vector of 1’s; Bel(SM) =   (SM)   (SM)  (SM) Bel(SM)  (SM) Paris 0.9 0.9 1.0 Med. 0.1 0.1 1.0 (2)  (TO) =  (SM) M TO|SM ; Bel(TO) =   (TO)   (TO)  (TO) Bel(TO)  (TO) Chalons 0.73 0.73 1.0 Dijon 0.27 0.27 1.0 (3)  (AA) =  (TO) M AA|TO ; Bel(AA) =   (AA)   (AA)  (AA) Bel(AA)  (AA) North 0.39 0.40 1.0 Central 0.35 0.36 1.0 South 0.24 0.24 1.0 M AA|TO = M TO|SM = Strategic Mission Tactical Objective Avenue of Approach .8 .2 .1 .9 [ ] .5 .4 .1 .1 .3 .6 [ ]
  • 29. Sample Chain - 1st Propagation   t TR T   0 5  ( ) . 1 .6   t = 0 (lR) = .8 .2  t = 1  (SM) =  (IR)  (SM) Bel(SM)  (SM) Paris 0.8 0.8 1.0 Med. 0.2 0.2 1.0  (TO) Bel(TO)  (TO) Chalons 0.73 0.73 1.0 Dijon 0.27 0.27 1.0  (AA) Bel(AA)  (AA) North 0.39 0.3 0.5 Central 0.35 0.5 1.0 South 0.24 0.2 0.6 t = 1  (AA) =  (TR) Intel. Rpt. Troop Rpt. Strategic Mission Tactical Objective Avenue of Approach
  • 30. Sample Chain - 2nd Propagation   t TR T   0 5  ( ) . 1 .6   t = 0 (lR) = .8 .2   (SM) Bel(SM)  (SM) Paris 0.8 0.8 1.0 Med. 0.2 0.2 1.0 t = 2  (TO) =  (SM) M TO|SM  (TO) Bel(TO)  (TO) Chalons 0.66 0.66 0.71 Dijon 0.34 0.34 0.71 t = 2  (TO) = M AA|TO  (SM)  (AA) Bel(AA)  (AA) North 0.39 0.3 0.5 Central 0.35 0.5 1.0 South 0.24 0.2 0.6 Intel. Rpt. Troop Rpt. Strategic Mission Tactical Objective Avenue of Approach
  • 31. Sample Chain - 3rd Propagation  (SM) Bel(SM)  (SM) Paris 0.8 0.8 0.71 Med. 0.2 0.2 0.71 t = 3  (SM) = M TO|SM  (TO)  (TO) Bel(TO)  (TO) Chalons 0.66 0.66 0.71 Dijon 0.34 0.34 0.71 t = 3  (AA) =  (TO) M AA|TO  (AA) Bel(AA)  (AA) North 0.36 0.25 0.5 Central 0.37 0.52 1.0 South 0.27 0.23 0.6 Intel. Rpt. Troop Rpt. Strategic Mission Tactical Objective Avenue of Approach
  • 32. Internal Structure of a Single Node Processor Processor for Node X Message to Parent U Message from Parent U M X|U     M X|U  k  k (X) BEL =     Message to Children of X Message from Children of X  BEL(X)  1 (X)  BEL(X)  N (X) ... ...  (X)  (X)  X (U)  1 (X)  N (X)  X (U)  N (X)  1 (X)
  • 33.
  • 34.
  • 35.
  • 36.
  • 37. Situation Assessment Bayesian Net Initial Conditions Given Emergency
  • 38. Situation Assessment Bayesian Net Steam Line Radiation Alarm Goes High
  • 39. Situation Assessment Bayesian Net Steam Line Radiation Alarm Goes Low
  • 40. Simulation of SGTR Scenario Event Timeline
  • 41.
  • 42.
  • 43. Introduction to Bayesian Networks A Tutorial for the 66th MORS Symposium 23 - 25 June 1998 Naval Postgraduate School Monterey, California Dennis M. Buede, dbuede@gmu.edu Joseph A. Tatman, jatatman@aol.com Terry A. Bresnick, bresnick@ix.netcom.com http://www.gmu.edu - Depts (Info Tech & Eng) - Sys. Eng. - Buede
  • 44.
  • 45. Building BN Structures Bayesian Network Bayesian Network Bayesian Network Problem Domain Problem Domain Problem Domain Expert Knowledge Expert Knowledge Training Data Training Data Probability Elicitor Learning Algorithm Learning Algorithm
  • 46.
  • 47. Beta Distribution 1) n(n m/n) m(1 variance n m mean x) (1 x m) (n (m) (n) n) m, | (x p 1 m n 1 m Beta             
  • 48. Multivariate Dirichlet Distribution 1) m ( m ) m / m (1 m state i the of variance m m state i the of mean ...x x x ) (m )... (m ) (m ) m ( ) m ,..., m , m | (x p N 1 i i N 1 i i N 1 i i i i th N 1 i i i th 1 m 1 - m 1 m N 2 1 N 1 i i N 2 1 Dirichlet N 2 1                     
  • 49.
  • 50.
  • 51.
  • 52.
  • 53.
  • 54. Enemy Intent Trafficability of S. AA Trafficability of C. AA Trafficability of N. AA Troops @ NAI 1 Troops @ NAI 2 AA - Avenue of Approach NAI - Named Area of Interest Intelligence Reports Observations on Troop Movements Weather Forecast & Feasibility Analysis Strategic Mission Weather Tactical Objective Enemy’s Intelligence on Friendly Forces Avenue of Approach Deception Plan
  • 56. Learned Network with 1000 Cases Missing Arcs: 2 Added Arcs: 0 Arcs Misdirected: 5 Arcs Unspecified: 3 Missing Arcs: 2 Added Arcs: 0 Arcs Misdirected: 5 Arcs Unspecified: 3
  • 57. Learned Network with 10,000 Cases Missing Arcs: 1 Added Arcs: 1 Arcs Misdirected: 4
  • 58. Comparison of Learned Networks with Truth p(AoA) Truth 1 K 10 K Prior .37, .37, .26 .37, .35, .28 .38, .36, .26 “ Clear” .41, .37, .22 .38, .36, .26 .41, .36, .23 “ Rainy” .30, .36, .34 .35, .32, .33 .30, .36, .34 “ NAI 1 True” .15, .13, .71 .17, .12, .71 .16, .12, .71 “ Rain, NAI 1 True” .10, .11, .79 .15, .10, .75 .11, .11, .78 “ Rain, NAI 1 & 2 True” .56, .02, .43 .59, .05, .36 .56, .03, .40
  • 59.
  • 60.
  • 61. Continuous Variables Example Entering values for the three discrete random variables shifts the sensor mean values
  • 62.
  • 63.
  • 64.
  • 65.
  • 66.
  • 67.
  • 69.
  • 70.
  • 71.
  • 72.
  • 73. Tuberculosis XRay Result Tuberculosis or Cancer Lung Cancer Dyspnea Bronchitis
  • 74.
  • 75. Sample Chain - Setup (1) Set all lambdas to be a vector of 1’s; Bel(SM) =   (SM)   (SM)  (SM) Bel(SM)  (SM) Paris 0.9 0.9 1.0 Med. 0.1 0.1 1.0 (2)  (TO) =  (SM) M TO|SM ; Bel(TO) =   (TO)   (TO)  (TO) Bel(TO)  (TO) Chalons 0.73 0.73 1.0 Dijon 0.27 0.27 1.0 (3)  (AA) =  (TO) M AA|TO ; Bel(AA) =   (AA)   (AA)  (AA) Bel(AA)  (AA) North 0.39 0.73 1.0 Central 0.35 0.27 1.0 South 0.24 0.24 1.0 Strategic Mission Tactical Objective Avenue of Approach M AA|TO = M TO|SM =