Uncertainty in Artificial Intelligence

Uncertainty in Artificial Intelligence

by MKP
Released June 2014
Publisher(s): Morgan Kaufmann
ISBN: 9781483298603

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Uncertainty Proceedings 1994

Table of contents

  1. Front Cover
  2. Uncertainty in Artificial Intelligence
  3. Copyright Page
  4. Table of Contents
  5. Preface
  6. Acknowledgments
  7. Chapter 1. Ending-based Strategies for Part-of-speech Tagging
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 BACKGROUND
    4. 3 THE EXPERIMENTS
    5. 4 RESULTS
    6. 5 DISCUSSION AND FUTUREWORK
    7. Acknowledgments
    8. References
  8. Chapter 2. An evaluation of an algorithm for inductive learning of Bayesian belief networks using simulated data sets
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 METHODS
    4. 3 RESULTS
    5. 4 CONCLUSIONS
    6. Acknowledgements
    7. References
    8. Appendix I
  9. Chapter 3. Probabilistic Constraint Satisfaction with Non-Gaussian Noise
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 MULTICOMPONENT ALGORITHM
    4. 3. EXPERIMENTS AND RESULTS
    5. 4 DISCUSSION
    6. 5 RELATED WORK
    7. 6 CONCLUSIONS
    8. Acknowledgments
    9. References
  10. Chapter 4. A Bayesian Method Reexamined
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 THE K2 METRIC
    4. 3 EXAMPLES AND DISCUSSION
    5. 4 ANALYSIS
    6. 5 CONCLUSION
    7. Acknowledgments
    8. References
  11. Chapter 5. Laplace's Method Approximations for Probabilistic Inference in Belief Networks with Continuous Variables
    1. Abstract
    2. 1 Introduction
    3. 2 Laplace's Method and Approximations for Probabilistic Inference
    4. 3 Implementation Issues and Limitations
    5. 4 An Application to a Medical Inference Problem
    6. 5 Final Considerations
    7. Acknowlegements
    8. References
  12. Chapter 6. Generating New Beliefs From Old
    1. Abstract
    2. 1 Introduction
    3. 2 Technical preliminaries
    4. 3 The three methods
    5. 4 Discussion
    6. References
  13. Chapter 7. Counterfactual Probabilities: Computational Methods, Bounds and Applications
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 NOTATION
    4. 3 BOUNDS ONCOUNTERFACTUALS
    5. 4 APPLICATION TO CLINICAL TRIALS WITH IMPERFECT COMPLIANCE
    6. 5 APPLICATIONS TO LIABILITY JUDGMENT
    7. 6 CONCLUSION
    8. Acknowledgements
    9. References
  14. Chapter 8. Modus Ponens Generating Function in the Class of Λ-valuations of Plausibility
    1. Abstract
    2. 1 STABILITY OF DECISIONS IN INFERENCE PROCEDURES
    3. 2 STRICT MONOTONICITY OF CONCLUSIONS
    4. 3 Λ-VALUATIONS OF PLAUSIBILITY
    5. 4 NEGATION OPERATION ON F
    6. 5 MODUS PONENS GENERATING FUNCTIONS ON F
    7. 6 EXAMPLE AND APPLICATIONS
    8. Acknowledgements
    9. References
  15. Chapter 9. Approximation Algorithms for the Loop Cutset Problem
    1. Abstract
    2. 1 Introduction
    3. 2 The Loop Cutset Problem
    4. 3 Algorithms For The WVFS problem
    5. 4 Experimental Results
    6. Remark.
    7. References
  16. Chapter 10. Possibility and necessity functions over non-classical logics
    1. Abstract
    2. 1 Introduction
    3. 2 Non-classical necessity and possibility functions
    4. 3 Application to reasoning with uncertain and inconsistent information
    5. 4 Conclusion
    6. 5 References
  17. Chapter 11. Exploratory Model Building
    1. Abstract
    2. 1 Introduction
    3. 2 The Scenario-Building Process
    4. 3 Probabilistic Knowledge
    5. 4 The Dependency Relation
    6. 5 Structure of an Imagined Context
    7. 6 Constructing Preferred Contexts
    8. 7 Conclusion
    9. Acknowledgment
    10. References
  18. Chapter 12. Learning in Multi-Level Stochastic Games with Delayed Information
    1. Abstract
    2. 1 Introduction
    3. 2 Related Work
    4. 3 The Model
    5. 4 Experiments
    6. 5 Analysis
    7. 6 Conclusions
    8. References
  19. Chapter 13. Planning with External Events
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 THE PLANNING REPRESENTATION AND ALGORITHM
    4. 3 AN ILLUSTRATION
    5. 4 BELIEF NET CONSTRUCTION
    6. 5 ESTIMATING THE PROBABILITIES OF FAILURE SEQUENCES
    7. 6 DISCUSSION AND FUTURE DIRECTIONS
    8. Acknowledgements
    9. References
  20. Chapter 14. Properties of Bayesian Belief Network Learning Algorithms
    1. Abstract
    2. 1 Introduction
    3. 2 Preliminaries
    4. 3 Quality Measures
    5. 4 Search Algorithms
    6. 5 Learning Distributions
    7. 6 Experimental Results
    8. 7 Conclusion
    9. Acknowledgements
    10. References
  21. Chapter 15. A Stratified Simulation Scheme for Inference in Bayesian Belief Networks
    1. Abstract
    2. 1 Introduction
    3. 2 Simulation Schemes for Bayesian Belief Networks
    4. 3 A Stratified Simulation Scheme
    5. 4 Experimental Results
    6. 5 Conclusions
    7. Acknowledgement
    8. References
  22. Chapter 16. Proposal: Interactive Media for Research in Uncertainty
    1. Introduction
    2. Acknowledgments
  23. Chapter 17. Efficient Estimation of the Value of Information in Monte Carlo Models
    1. 1.0 EVI: What's so, and What's New
    2. 2.0 Framework
    3. 3.0 Complexity and Non-Additivity of EVI
    4. 4.0 Approximation of EVI
    5. 5.0 Application
    6. 6.0 Conclusions and Future Directions
    7. 7.0 References
  24. Chapter 18. Symbolic Probabilistic Inference in large BN20 networks
    1. Abstract
    2. 1 Introduction
    3. 2 Local Expression Languages
    4. 3 Inference Basics
    5. 4 Factoring posterior expressions
    6. 5 Incremental Refinement of Posteriors
    7. 6 Conclusion
    8. References
  25. Chapter 19. Action Networks: A Framework for Reasoning about Actions and Change under Uncertainty
    1. Abstract
    2. 1 Introduction
    3. 2 Action Networks (1/2)
    4. 2 Action Networks (2/2)
    5. 3 Conclusions and Future Work
    6. Acknowledgments
    7. A Appendix: A Review of The Kappa Calculus
    8. References
  26. Chapter 20. On the Relation between Kappa Calculus and Probabilistic Reasoning
    1. Abstract
    2. 1 Introduction
    3. 2 Kappa calculus
    4. 3 Kappas and probabilities
    5. 4 Experimental results
    6. 5 Formal Analysis
    7. 6 Discussion
    8. Acknowledgments
    9. References
  27. Chapter 21. A Structured, Probabilistic Representation of Action
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 MODELING WORLD STATES
    4. 3 REPRESENTING ACTIONS
    5. 4 THE ENVIRONMENT MODEL
    6. 5 STATE PROJECTION
    7. 6 PROJECTING STATES CORRECTLY
    8. 7 PROPERTIES OF ACTION MODELS
    9. 8 SUMMARY AND DISCUSSION
    10. Acknowledgments
    11. References
  28. Chapter 22. Integrating Planning and Execution in Stochastic Domains
    1. Abstract
    2. 1 Introduction
    3. 2 The Decision Model
    4. 3 The Algorithm
    5. 4 Generating Heuristic Functions
    6. 5 Theoretical and Experimental Results
    7. 6 Conclusions
    8. Acknowledgments
    9. References
  29. Chapter 23. Localized Partial Evaluation of Belief Networks
    1. Abstract
    2. 1 Introduction
    3. 2 Localized Partial Evaluation of Polytrees
    4. 3 Multiply-Connected Networks
    5. 4 Empirical Results
    6. 5 Related Work
    7. 6 Conclusion
    8. cknowledgement
    9. References
  30. Chapter 24. A Probabilistic Model of Action for Least-Commitment Planning with Information Gathering
    1. Abstract
    2. 1 Introduction
    3. 2 States, Actions, and Plans
    4. 3 Plans and planning
    5. 4 Conclusion and future work
    6. Acknowledgments
    7. References
  31. Chapter 25. Some Properties of Joint Probability Distributions
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 PRELIMINARIES
    4. 3 PROPERTIES OF THE JOINT PROBABILITY DISTRIBUTION
    5. 4 EXAMPLE: ALARM
    6. 5 CONCLUSION
    7. Acknowledgments
    8. References
  32. Chapter 26. An ordinal view of independence with application to plausible reasoning
    1. Abstract
    2. 0 INTRODUCTION
    3. 1 PROBABILISTIC INDEPENDENCE
    4. 2 POSSIBILITY THEORY
    5. 3 (UN)RELATEDNESS
    6. 4 STRONG INDEPENDENCE
    7. 5 WEAK INDEPENDENCE
    8. 6 COMPARATIVE DISCUSSION
    9. 7 APPLICATION TO EXCEPTION-TOLERANT REASONING
    10. 8 CONCLUSION
    11. REFERENCES
  33. Chapter 27. Penalty logic and its link with Dempster-Shafer theory
    1. Abstract
    2. 1 Introduction
    3. 2 Penalty logic
    4. 3 Relating penalties to Dempster-Shafer theory
    5. 4 Conclusion
    6. Acknowledgements
    7. References
  34. Chapter 28. Value of Evidence on Influence Diagrams
    1. Abstract
    2. 1. INTRODUCTION
    3. 2. EVIDENCE PROPAGATION ON INFLUENCE DIAGRAMS
    4. 3. VALUE OF EVIDENCE
    5. 4 IMPLEMENTATION AND COMPUTATIONAL ISSUES
    6. 5 SUMMARY
    7. References
  35. Chapter 29. Conditional independence in possibility theory
    1. Abstract
    2. Keywords
    3. 1 Introduction
    4. 2 Conditional independence relations
    5. 3 Possibility distributions
    6. 4 Possibilistic conditional independence relations
    7. 5 Conclusion
    8. References
  36. Chapter 30. Backward Simulation in Bayesian Networks
    1. Abstract
    2. 1 INTRODUCTION AND MOTIVATION
    3. 2 NOTATION
    4. 3 IMPORTANCE SAMPLING
    5. 4 BACKWARD SIMULATION
    6. 5 DISCUSSION
    7. 6 FUTURE RESEARCH AND APPLICATIONS
    8. Acknowledgments
    9. References
  37. Chapter 31. Learning Gaussian Networks
    1. Abstract
    2. 1 Introduction
    3. 2 Gaussian Belief Networks
    4. 3 A Metric for Gaussian Belief Networks
    5. 4 Metrics for Gaussian Causal Networks
    6. 5 Summary and Future Work
    7. Acknowledgments
    8. References
    9. Appendix
  38. Chapter 32. On testing whether an Embedded Bayesian Network represents a probability model
    1. Abstract
    2. 1 Introduction
    3. 2 Preliminaries
    4. 3 Embedded Bayesian Nets
    5. 4 Verifying Embedded Bayesian Nets
    6. 5 Verifying Embedded Bayesian Trees
    7. 6 Learning Embedded Bayesian Trees
    8. 7 Discussion
    9. References
  39. Chapter 33. Epsilon-Safe Planning
    1. Abstract
    2. 1 Introduction
    3. 2 CNLP
    4. 3 Plinth
    5. 4 e-safe planning with simple model
    6. 5 Building more complex models
    7. 6 Summary
    8. Acknowledgements
    9. References
  40. Chapter 34. Generating Bayesian Networks from Probability Logic Knowledge Bases
    1. Abstract
    2. 1 Introduction
    3. 2 Representation Language
    4. 3 Bayesian Knowledge Bases
    5. 4 Network Generation Algorithm
    6. 5 Example
    7. 6 Related Work
    8. 7 Current and Future Research
    9. Acknowledgements
    10. References
  41. Chapter 35. Abstracting Probabilistic Actions
    1. Abstract
    2. 1 Introduction
    3. 2 Preliminaries
    4. 3 Abstracting Actions
    5. 4 Applying the Techniques
    6. 5 Related Work
    7. 6 Current and Future Research
    8. Acknowledgements
    9. References
  42. Chapter 36. On Modal Logics for Qualitative Possibility in a Fuzzy Setting
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 MANY-VALUED PROPOSITIONAL CALCULUS USED
    4. 3 KRIPKE MODELS, POSSIBILITIES
    5. 4 SOME MODALITIES, THE FUZZY LOGIC QFL2 AND ITS RELATION TO THE MODAL MANY-VALUED LOGIC MV S5
    6. 5 THE LOGIC QFL2 AND A MANY-VALUED BELIEF LOGIC
    7. 6 CONCLUDING REMARKS AND FUTURE WORK
    8. References
  43. Chapter 37. A New Look at Causal Independence
    1. Abstract
    2. 1 Introduction
    3. 2 Temporal Definition of Causal Independence
    4. 3 An Atemporal Representation of Causal Independence
    5. 4 Classes of Causal Interaction
    6. 5 Causal Independence and Assessment
    7. 6 Causal Independence and Inference
    8. 7 Conclusions
    9. References
  44. Chapter 38. Learning Bayesian Networks: The Combination of Knowledge and Statistical Data
    1. Abstract
    2. 1 Introduction
    3. 2 Belief Networks and Notation
    4. 3 Metrics for Belief Networks: Previous Work
    5. 4 Event Equivalence and Score Equivalence
    6. 5 The Prior Belief Network
    7. 6 The BDe Metric
    8. 7 Causal Networks
    9. 8 Limitations of the BDe Metric
    10. 9 Priors for Network Structures
    11. 10 Evaluation
    12. Acknowledgments
    13. References
  45. Chapter 39. A Decision-Based View of Causality
    1. Abstract
    2. 1 Introduction
    3. 2 Background
    4. 3 Fixed Sets and Cause
    5. 4 Graphical Representation of Cause: Causal Influence Diagrams
    6. 5 Howard Canonical Form and Causal Mechanisms
    7. 6 Counterfactual Reasoning
    8. 7 Global Causal Models
    9. 8 Future Work and Conclusions
    10. Acknowledgments
    11. References
  46. Chapter 40. Probabilistic Description Logics
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 THE TERMINOLOGICAL FORMALISM
    4. 3 PROBABILISTIC CONDITIONING
    5. 4 THE FORMAL MODEL
    6. 5 PROBABILISTIC CONSTRAINTS
    7. 6 RELATED WORK
    8. 7 CONCLUSIONS
    9. Acknowledgements
    10. References
  47. Chapter 41. An Experimental Comparison of Numerical and Qualitative Probabilistic Reasoning
    1. Abstract
    2. Keywords
    3. 1 BACKGROUND AND GOALS
    4. 2 MAPPINGS BETWEEN NUMERICA LAND INFINITESIMAL PROBABILITIES
    5. 3 APPLICATION DOMAIN: WHY YOUR CAR DOES NOT START
    6. 4 EXPERIMENTAL DESIGN
    7. 5 RESULTS
    8. 6 CONCLUSIONS
    9. Acknowledgments
    10. References
  48. Chapter 42. An Alternative Proof Method for Possibilistic Logic and its Application to Terminological Logics
    1. Abstract
    2. 1 Introduction
    3. 2 Possibilistic Logic
    4. 3 An Alternative Proof Method for Possibilistic Logic
    5. 4 A Possibilistic Extension of Terminological Logics
    6. 5 Conclusion
    7. Acknowledgements
    8. References
  49. Chapter 43. Possibilistic Conditioning and Propagation
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 AN AXIOMATIC JUSTIFICATION OF CONFIDENCE TRANSFER
    4. 3 BELIEF INDEPENDENCE AND DEMPSTERS RULE OFCONDITIONING
    5. 4 POSSIBILISTIC PROPAGATION
    6. 5 CONCLUSION
    7. Acknowledgements
    8. References
  50. Chapter 44. The Automated Mapping of Plans for Plan Recognition
    1. Abstract
    2. 1 Introduction
    3. 2 Related Work
    4. 3 PRS and Belief Networks
    5. 4 The Mapping Method
    6. 5 An Example
    7. 6 Conclusions
    8. References
  51. Chapter 45. A Logic for Default Reasoning About Probabilities
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 SYNTAX
    4. 3 SEMANTICS
    5. 4 WHY CROSS ENTROPY?
    6. 5 RELATED WORK
    7. 6 CONCLUSION
    8. Acknowledgement
    9. References
  52. Chapter 46. Optimal Junction Trees
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 JUNCTION TREES AND MAXIMAL SPANNING TREES
    4. 3 OPTIMAL JUNCTION TREES
    5. 4 ALMOND TREES
    6. 5 THE NECESSITY OF TRIANGULATION
    7. Acknowledgements
    8. References
  53. Chapter 47. From Influence Diagrams to Junction Trees
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 INFLUENCE DIAGRAMS
    4. 3 DECISION MAKING
    5. 4 COMPILATION OF INFLUENCE DIAGRAMS
    6. 5 USING THE STRONG JUNCTION TREE FOR COMPUTATIONS
    7. 6 CONCLUSION
    8. Acknowledgements
    9. References
  54. Chapter 48. Reduction of Computational Complexity in Bayesian Networks through Removal of Weak Dependences
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 GRAPHICAL CHAIN MODELS AND JUNCTION TREES
    4. 3 ENFORCING INDEPENDENCE ASSUMPTIONS
    5. 4 EXPERIMENTS
    6. 5 DISCUSSION
    7. Acknowledgements
    8. References
  55. Chapter 49. Using New Data to Refine a Bayesian Network
    1. Abstract
    2. 1 Introduction
    3. 2 The Refinement Problem
    4. 3 Our Approach
    5. 4 The Existent Network Structure
    6. 5 Learning the Partial Network Structure
    7. Acknowledgments
    8. References
  56. Chapter 50. Syntax-based default reasoning as probabilistic model-based diagnosis
    1. Abstract
    2. 1 Introduction
    3. 2 Inconsistent knowledge bases as systems to diagnose
    4. 3 From syntactical knowledge bases to belief functions
    5. 4 Inducing consequence relations
    6. 5 Extension to the prioritized case
    7. 6 Related work and conclusion
    8. Acknowledgements
    9. References
  57. Chapter 51. Induction of Selective Bayesian Classifiers
    1. Abstract
    2. Introduction
    3. The Naive Bayesian Classifier
    4. Experiments with Bayesian Classifiers
    5. Related Work on Bayesian Induction
    6. Concluding Remarks
    7. Acknowledgements
    8. References
  58. Chapter 52. Fuzzy Geometric Relations to Represent Hierarchical Spatial Information
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 BASIC CONCEPTS
    4. 3 REPRESENTATION MODEL
    5. 4 RECOGNITION OF TEMPLATE INSTANCES
    6. 5 APPLICATION
    7. 6 FURTHER WORK
    8. 7 CONCLUSION
    9. Acknowledgments
    10. References
  59. Chapter 53. Constructing Belief Networks to Evaluate Plans
    1. Abstract
    2. 1. INTRODUCTION
    3. 2. BASIC APPROACH
    4. 3. PLAN FEATURES THAT COM-PLICATE PE-NET CONSTRUCTION
    5. 4. DISCUSSION
    6. References
  60. Chapter 54. Operator Selection While Planning Under Uncertainty
    1. Abstract
    2. 1 INTRODUCTION TO U-PLAN
    3. 2 STATE REPRESENTATION
    4. 3 REDUCTION OPERATORS
    5. 4 OPERATOR SELECTION
    6. 5 PLAN REAPPLICATION
    7. 6 SUPER-PLANS
    8. 9 CONCLUSION
    9. References
  61. Chapter 55. Model-Based Diagnosis with Qualitative Temporal Uncertainty
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 PRELIMINARIES
    4. 3 BEHAVIORAL MODEL
    5. 4 OBSERVATIONS AND ABSTRACT OBSERVATIONS
    6. 5 CANDIDATE GENERATION
    7. 6 ABSTRACT TEMPORAL DIAGNOSES
    8. 7 CONCLUSION
    9. References
  62. Chapter 56. Incremental Dynamic Construction of Layered Polytree Networks
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 LAYERED BELIEF NETWORKS
    4. 3 INCREMENTAL DYNAMIC CONSTRUCTION OF POLYTREES
    5. 4 INCREMENTAL POLYTREEALGORITHM
    6. 5 CONCLUSION
    7. Acknowledgments
    8. References
  63. Chapter 57. Models of Consensus for Multiple Agent Systems
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 A CONSTANT PROBABILITY MODEL
    4. 3 EXTENSIONS OF THE BASIC MODEL
    5. 4 IMPLICATIONS AND IMPLEMENTA TION
    6. 5 SUMMARY AND EXTENSIONS
    7. Acknowledgements
    8. References
  64. Chapter 58. A Probabilistic Calculus of Actions
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 THE MANIPULATIVE READING OF CAUSAL NETWORKS: A REVIEW
    4. 3 A CALCULUS OF ACTIONS
    5. 4 CONCLUSIONS
    6. cknowledgment
    7. References
  65. Chapter 59. Robust Planning in Uncertain Environments
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 FORMALISM FOR ROBUST PLANNING
    4. 3 ROBUSTNESS-PARAMETERIZED EXPECTED UTILITY
    5. 4 PLANNING ALGORITHM
    6. 5 EXAMPLE DOMAIN: SLIPPERY BLOCKS WORLD
    7. 6 RELATED WORK
    8. References
  66. Chapter 60. Anytime Decision Making with Imprecise Probabilities
    1. Abstract
    2. 1 ANYTIME ALGORITHMS FOR DECISION MAKING
    3. 2 ANYTIME DEDUCTION AND DECISIONS
    4. 3 NILSSON'S PROBABILISTIC LOGIC AND DECISION MAKING
    5. 4 DECISIONS WITH MULTIPLE CONDITIONS
    6. 5 MAXIMUM ENTROPY AND PROBABILISTIC LOGIC
    7. 6 ANYTIME DECISION MAKING WITH PROBABILISTIC DATABASES
    8. 7 CONCLUSION
    9. References
  67. Chapter 61. Three Approaches to Probability Model Selection
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 SOME STATISTICAL CRITERIA FOR MODEL SELECTION
    4. 3 A MAP APPROACH
    5. 4 AN EFFECTIVENESS RATIOAPPROACH
    6. 5 A SEARCH HEURISTIC AND A COMPARISON USING MIXTURE MODELS
    7. 6 CONCLUDING REMARKS
    8. Acknowledgments
    9. References
  68. Chapter 62. Knowledge Engineering for Large Belief Networks
    1. Abstract
    2. 1 INTRODUCTION
    3. KNOWLEDGE BASE TO BELIEF NETWORK
    4. 3 GENERALIZATION OF THE NOISY-OR
    5. 4 LEAKS
    6. 5 TOOLS FOR KNOWLEDGE ENGINEERING
    7. 6 RELATED WORK
    8. 7 CONCLUSION
    9. Acknowledgments
    10. References
  69. Chapter 63. Solving Asymmetric Decision Problems with Influence Diagrams
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 INFLUENCE DIAGRAMS
    4. 3 WHY INFLUENCE DIAGRAMS ARE NOT GOOD FORASYMMETRIC DECISION PROBLEMS
    5. 4 OUR SOLUTION
    6. 5 HOW WELL OUR ALGORITHM DOES FOR THE USED CAR BUYER PROBLEM
    7. 6 RELATED WORK ON HANDLING ASYMMETRIC DECISION PROBLEMS
    8. 7 CONCLUSIONS
    9. Acknowledgement
    10. References
  70. Chapter 64. Belief Maintenance in Bayesian Networks
    1. Abstract
    2. 1 Introduction
    3. 2 Logic-based Belief Maintenance
    4. 3 Ignorant Belief Networks
    5. 4 Conclusions
    6. Acknowledgment
    7. References
  71. Chapter 65. Belief Updating by Enumerating High-Probability Independence-Based Assignments
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 COMPUTING MARGINALS
    4. 3 REDUCTION TO ILP
    5. 4 EXPERIMENTAL RESULTS
    6. 5 RELATED WORK
    7. 6 SUMMARY
    8. References
  72. Chapter 66. Global Conditioning for Probabilistic Inference in Belief Networks
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 NOTATION AND BASIC FRAMEWORK
    4. 3 THE CLUSTERING ALGORITHM
    5. 4 GLOBAL CONDITIONING
    6. 5 PARALLEL IMPLEMENTATION OF GLOBAL CONDITIONING
    7. 6 RECOGNIZING NEW CLUSTERTREES
    8. 7 Conclusions
    9. Acknowledgements
    10. References
  73. Chapter 67. Belief Induced by the Partial Knowledge of the Probabilities
    1. Abstract
    2. 1. INTRODUCTION
    3. 2. IMPACT OF HACKING FREQUENCY PRINCIPLE
    4. 3. THE CASE WHERE
    5. 4. CASE WITH
    6. 5. PIGNISTIC PROBABILITY
    7. 6. CONCLUSIONS
    8. Acknowledgment
    9. Bibliography
  74. Chapter 68. Ignorance and the Expressiveness of Single- and Set-Valued Probability Models of Belief
    1. Abstract
    2. 1. INTRODUCTION
    3. 2. NOTATION AND ASSUMPTIONS ABOUT IGNORANCE
    4. 3. COMMENTARY ON THE ASSUMPTIONS
    5. 4. ENSEMBLE OF SETS REPRESENTATION
    6. 5· DECIDING ORDERINGS IN AN ENSEMBLE OF SETS
    7. 6. THE ENSEMBLE OF SETS FORMALISM IS A MODEL OF THE ASSUMPTIONS
    8. 7. SOME OTHER PROBABILISTIC FORMALISMS WHICH ARE NOT MODELS OF THE ASSUMPTIONS
    9. 8. PARTIAL QUALITATIVEPROBABILITY
    10. 9. THE ENSEMBLE OF SETS FORMALISM IS A PARTIAL QUALITATIVE PROBABILITY
    11. 10. A NOTE ON ASSUMPTION A5
    12. 11. CONCLUSIONS
  75. Chapter 69. A probabilistic approach to hierarchical model-based diagnosis
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 THE TRANSLATION SCHEME
    4. 3 HIERARCHICAL MODELS
    5. 4 RELATED WORK
    6. 5 CONCLUSION
    7. References
  76. Chapter 70. Semigraphoids are Two-Antecedental Approximations of Stochastic Conditional Independence Models
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 BASIC DEFINITIONS AND FACTS
    4. 3 MAIN RESULTS
    5. 4 CONCLUSION
    6. Acknowledgements
    7. References
  77. Chapter 71. Exceptional Subclasses in Qualitative Probability
    1. Abstract
    2. 1 Introduction
    3. 2 System
    4. 3 Ceteris Paribum Admissibility
    5. 4 Related Work
    6. 5 Conclusion
    7. Acknowledgements
    8. A Proofs
    9. References
  78. Chapter 72. A Defect in Dempster-Shafer Theory
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 A SIMPLIFIED SITUATION
    4. 3 A PROBLEM
    5. 4 POSSIBLE SOLUTIONS
    6. 5 AN ALTERNATIVE APPROACH
    7. 6 CONCLUSION
    8. Acknowledgment
    9. References
  79. Chapter 73. State-Space Abstraction for Anytime Evaluation of Probabilistic Networks
    1. Abstract
    2. 1. INTRODUCTION
    3. 2. BACKGROUND AND EXAMPLE
    4. 3. STATE-SPACE ABSTRACTION
    5. 4. MODEL STRUCTURE ABSTRACTION
    6. 5. MORE RELATED WORK
    7. 6. CONCLUSION
    8. Acknowledgments
    9. References
  80. Chapter 74. General Belief Measures
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 QUASI-MEASURES
    4. 3 RANKING MEASURES
    5. 4 CUMULATIVE MEASURES
    6. 5 BELIEF STRUCTURES
    7. Acknowledgements
    8. References
  81. Chapter 75. Generating Graphoids from Generalised Conditional Probability
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 INDEPENDENCE STRUCTURES
    4. 3 GENERALISED CONDITIONAL PROBABILITY ON PRODUCT SPACES (GCPPs)
    5. 4 THE INTERSECTION PROPERTY
    6. 5 SUFFICIENT CONDITIONS FOR GCPPS TO GENERATE GRAPHOIDS
    7. 6 QUALITATIVE CONDITIONAL PROBABILITY
    8. 7 COMPUTATION OF GCPPS
    9. 8 DISCUSSION
    10. Acknowledgements
    11. References
  82. Chapter 76. On Axiomatization of Probabilistic Conditional Independencies
    1. Abstract
    2. 1 Introduction
    3. 2 Basic Notions in Relational Models
    4. 3 Probabilistic Conditional Independence
    5. 4 Axiomatization of Embedded Multivalued Dependencies
    6. 5 Conclusions
    7. References
  83. Chapter 77. Evidential Reasoning with Conditional Belief Functions
    1. Abstract
    2. 1. INTRODUCTION
    3. 2. BELIEF FUNCTIONS AND THEIR RULES OF COMBINATIONS
    4. 3. KNOWLEDGE REPRESENTATION USING BELIEF FUNCTIONS
    5. 4. REASONING WITH CONDITIONAL BELIEFS
    6. 5. CONCLUSIONS
    7. Acknowledgments
  84. Chapter 78. Intercausal Independence and Heterogeneous Factorization
    1. Abstract
    2. 1 INTRODUCTION
    3. 2 CONSTRUCTIVE INTERCAUSAL INDEPENDENCE
    4. 3 FACTORIZATION OF JOINT PROBABILITIES
    5. 4 DEPUTATION OF BASTARD NODES
    6. 5 COMBINING FACTORS THAT INVOLVE MORE THAN ONE BASTARD VARIABLE
    7. 6 HETEROGENEOUS FACTORIZATION
    8. 7 SUMMING OUT VARIABLES FROM TIDY HF'S
    9. 8 AN ALGORITHM
    10. 9 An example
    11. 10 RELATED WORK
    12. 11 CONCLUSION
    13. Acknowledgement
    14. References
  85. Author Index

Product information

  • Title: Uncertainty in Artificial Intelligence
  • Author(s): MKP
  • Release date: June 2014
  • Publisher(s): Morgan Kaufmann
  • ISBN: 9781483298603