Machine Learning Proceedings 1989

Machine Learning Proceedings 1989

by Alberto Maria Segre
Released April 2016
Publisher(s): Morgan Kaufmann
ISBN: 9781483297408

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

Machine Learning Proceedings 1989

Table of contents

  1. Front Cover
  2. Proceedings of the Sixth International Workshop on Machine Learning
  3. Copyright Page
  4. Table of Contents (1/2)
  5. Table of Contents (2/2)
  6. PREFACE
  7. Part 1: Combining Empirical and Explanation-Based Learning
    1. Chapter 1. Unifying Themes in Empirical and Explanation-Based Learning
      1. The Need for Unified Theories of Learning
      2. Learning from One Instance and Many Instances
      3. Learning With and Without Search
      4. Learning With and Without Domain Knowledge
      5. Justified and Unjustified Learning
      6. Accuracy and Efficiency in Machine Learning
    2. CHAPTER 2. INDUCTION OVER THE UNEXPLAINED: Integrated Learning of Concepts with Both Explainable and Conventional Aspects
      1. ABSTRACT
      2. INTRODUCTION
      3. THE IOU APPROACH
      4. AN INITIAL IOU ALGORITHM
      5. IOU VERSUS PURE SBL AND IOE
      6. CONCLUSIONS AND FUTURE RESEARCH
    3. CHAPTER 3. CONCEPTUAL CLUSTERING OF EXPLANATIONS
      1. INDUCTION-BASED AND EXPLANATION-BASED LEARNING
      2. OPEN PROBLEMS
      3. CONCEPTUAL CLUSTERING OF EXPLANATIONS
      4. CONCLUDING REMARKS
      5. References
    4. Chapter 4. A Tight Integration of Deductive and Inductive Learning
      1. 1 Introduction
      2. 2 A new integration framework: generalized explanations
      3. 3 An application example
      4. References
    5. CHAPTER 5. MULTI-STRATEGY LEARNING IN NONHOMOGENEOUS DOMAIN THEORIES
      1. ABSTRACT
      2. INTRODUCTION
      3. DISCIPLE AS AN EXPERT SYSTEM
      4. THE LEARNING PROBLEM
      5. LEARNING IN A COMPLETE THEORY DOMAIN
      6. LEARNING IN A WEAK THEORY DOMAIN
      7. CONCLUSIONS
      8. References
    6. CHAPTER 6. A DESCRIPTION OF PREFERENCE CRITERION IN CONSTRUCTIVE LEARNING: A Discussion of Basic Issues
      1. 1. INTRODUCTION
      2. 2. CONSTRUCTIVE LEARNING
      3. 3. INDIVIDUAL CRITERIA AND THEIR RELATIONSHIPS
      4. Acknowledgements
      5. Reference
    7. CHAPTER 7. COMBINING CASE-BASED REASONING, EXPLANATION-BASED LEARNING, AND LEARNING FROM INSTRUCTION
      1. ABSTRACT
      2. INTRODUCTION
      3. INFERRING IN STRUCTOR'S GOAL
      4. INFERRING PLACE IN CURRENT DIAGNOSIS
      5. ADJUSTING THE SALIENCE OF FEATURES
      6. CAUSAL EXPLANATION OF ACTIONS
      7. CONCLUSION
      8. References
    8. CHAPTER 8. DEDUCTION IN TOP-DOWN INDUCTIVE LEARNING
      1. References
    9. CHAPTER 9. ONE-SIDED ALGORITHMS FOR INTEGRATING EMPIRICAL AND EXPLANATION-BASED LEARNING
      1. A FRAMEWORK FOR INTEGRATED LEARNING
      2. PERFORMANCE AND FOUNDATIONAL EXAMPLES
      3. THE IOSC and k-IOSCNF ALGORITHM
      4. CONCLUSION
      5. References
    10. CHAPTER 10. COMBINING EMPIRICAL AND ANALYTICAL LEARNING WITH VERSION SPACES
      1. ABSTRACT
      2. INTRODUCTION
      3. USING INCREMENTAL VERSION-SPACE MERGING ON THE RESULTS OF EBG
      4. PERSPECTIVES
      5. RELATED WORK
      6. SUMMARY
      7. References
    11. CHAPTER 11. FINDING NEW RULES FOR INCOMPLETE THEORIES: EXPLICIT BIASES FOR INDUCTION WITH CONTEXTUAL INFORMATION
      1. INTRODUCTION
      2. HEURISTICS EXPLOITING CONTEXTUAL INFORMATION AS A STRONG INDUCTIVE BIAS
      3. EMPIRICAL SELECTION OF BIASES
      4. CONCLUSION
      5. Acknowledgments
      6. REFERENCES
    12. CHAPTER 12. LEARNING FROM PLAUSIBLE EXPLANATIONS
      1. INTRODUCTION
      2. THE LEARNING METHOD
      3. CONCLUSION
      4. References
    13. CHAPTER 13. AUGMENTING DOMAIN THEORY FOR EXPLANATION-BASED GENERALISATION
      1. INTRODUCTION
      2. AUGMENTING THE DOMAIN THEORY
      3. EXPERIMENTAL ANALYSIS
      4. PROBLEMS AND FUTURE RESEARCH
      5. CONCLUSION
      6. References
    14. Chapter 14. Explanation Based Learning as Constrained Search
      1. Introduction
      2. An Example: The Mob System
      3. Conclusion
      4. References
    15. CHAPTER 15. REDUCING SEARCH AND LEARNING GOAL PREFERENCES
      1. INTRODUCTION
      2. DEPTHFIRST SEARCH
      3. FRAMEWORK FOR A SEARCH CONTROL HEURISTIC
      4. A SEARCH ALGORITHM - DEFINITION AND RESULTS
      5. References
    16. Chapter 16. Adaptation-Based Explanation: Explanations as Cases
      1. Summary
      2. References
    17. CHAPTER 17. A RETRIEVAL MODEL USING FEATURE SELECTION
      1. ABSTRACT
      2. A DISTRIBUTED MODEL OF RETRIEVAL
      3. CONTROLUNG RETRIEVAL WITH GOALS
      4. EXTENSIONS TO LEARNING
      5. REFERENCES
    18. CHAPTER 18. IMPROVING DECISION-MAKING ON THE BASIS OF EXPERIENCE
      1. References
    19. CHAPTER 19. EXPLANATION-BASED ACCELERATION OF SIMILARITY-BASED LEARNING
      1. ABSTRACT
      2. INTRODUCTION
      3. REVERSIBLE INTERPRETER
      4. EXPLANATION-BASED ACCELERATION
      5. CONCLUSION
      6. References
    20. Chapter 20. Knowledge Acquisition Planning: Results and Prospects
      1. An Introduction to KA Planning
      2. IVY: A KA Planner in Lung Tumor Pathology
      3. KA Planning for Scientific Discovery
      4. Conclusion
      5. References
    21. Chapter 21. "Learning by instruction" in connectionist systems
      1. ABSTRACT
      2. INTRODUCTION
      3. A CONNECTIONIST KNOWLEDGE REPRESENTATION SYSTEM
      4. CONCLUSION
      5. References
    22. CHAPTER 22. INTEGRATING LEARNING IN A NEURAL NETWORK
      1. ABSTRACT
      2. INTRODUCTION
      3. ARCHITECTURE AND INFERENCE
      4. SBL
      5. EBL
      6. RESULTS
      7. References
    23. Chapter 23. Explanation-based learning with weak domain theories
      1. Acknowledgements
      2. References
    24. Chapter 24. Using Domain Knowledge to Improve Inductive Learning Algorithms for Diagnosis
      1. 1 Introduction
      2. 2 Definitions
      3. 3 Algorithm
      4. 4 Example
      5. 5 Conclusion
      6. References
    25. Chapter 25. A Framework for Improving Efficiency and Accuracy
      1. Introduction
      2. Representation and Performance
      3. Learning Efficient and Accurate Domain Theories
      4. Current Status
      5. References
    26. CHAPTER 26. ERROR CORRECTION IN CONSTRUCTIVE INDUCTION
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2. INDUCTION IN AN ABSTRACTION SPACE
      4. 3. CORRECTION OF ATTRIBUTE NOISE
      5. References
    27. CHAPTER 27. IMPROVING EXPLANATION-BASED INDEXING WITH EMPIRICAL LEARNING
      1. ABSTRACT
      2. INTRODUCTION
      3. OVER-GENERLIZATION IN EBI
      4. USING EMPIRICAL TECHNIQUES WITHIN CASE MEMORY
      5. DISCUSSION
      6. References
    28. CHAPTER 28. A SCHEMA FOR AN INTEGRATED LEARNING SYSTEM
      1. ABSTRACT
      2. EMPIRICAL DATA VERSUS REASONING
      3. ANALYSIS VERSUS SYNTHESIS
      4. A PRIORI KNOWLEDGE VERSUS EMPIRICAL KNOWLEDGE
      5. CONCLUSIONS
      6. ACKNOWLEDGEMENTS
      7. REFERENCES
    29. CHAPTER 29. COMBINING EXPLANATION-BASED LEARNING AND ARTIFICIAL NEURAL NETWORKS
      1. ABSTRACT
      2. INTRODUCTION
      3. AN INTEGRATED APPROACH
      4. CONCLUSION
      5. References
  8. Part 2: Empirical Learning; Theory and Application
    1. CHAPTER 30. LEARNING CLASSIFICATION RULES USING BAYES
      1. ABSTRACT
      2. INTRODUCTION
      3. THEORY
      4. EXPERIMENTS
      5. CONCLUSION
      6. Acknowledgements
      7. References
    2. CHAPTER 31. NEW EMPIRICAL LEARNING MECHANISMS PERFORM SIGNIFICANTLY BETTER IN REAL LIFE DOMAINS
      1. ABSTRACT
      2. INTRODUCTION
      3. REAL LIFE DOMAINS
      4. EMPIRICAL LEARNING SYSTEMS
      5. REDUNDANT KNOWLEDGE
      6. GINESYS
      7. EMPIRICAL TESTS
      8. DISCUSSION
      9. ACKNOWLEDGMENTS
      10. REFERENCES
    3. CHAPTER 32. INDUCTIVE LEARNING WITH BCT
      1. ABSTRACT
      2. INTRODUCTION
      3. KNOWLEDGE REPRESENTATION
      4. LEARNING OPERATORS
      5. HEURISTIC MEASURES
      6. ALGORITHM
      7. EMPIRICAL RESULTS
      8. DISCUSSION
      9. CONCLUDING REMARKS
      10. Acknowledgments
      11. References
    4. CHAPTER 33. WHAT GOOD ARE EXPERIMENTS?
      1. ABSTRACT
      2. INTRODUCTION
      3. RESULTS
      4. REFERENCES
    5. Chapter 34. An Experimental Comparison of Human and Machine Learning Formalisms
      1. Abstract
      2. 1 Introduction
      3. 2 Definitions
      4. 3 Experiments
      5. 4 Discussion
      6. References
    6. CHAPTER 35. TWO ALGORITHMS THAT LEARN DNF BY DISCOVERING RELEVANT FEATURES
      1. INTRODUCTION
      2. DEFINITIONS
      3. FRINGE ALGORITHM
      4. GREEDY3 ALGORITHM
      5. RESULTS
      6. References
    7. CHAPTER 36. LIMITATIONS ON INDUCTIVE LEARNING
      1. ABSTRACT
      2. INTRODUCTION
      3. NOTATION
      4. EXPERIMENTAL RESULTS
      5. AN UPPER BOUND
      6. IMPLICATIONS
      7. BIBLIOGRAPHY
    8. CHAPTER 37. THE INDUCTION OF PROBABILISTIC RULE SETS — THE ITRULE ALGORITHM
      1. Abstract
      2. Introduction
      3. Motivation: why use sets of rules?
      4. Previous work on learning sets of rules
      5. The J-measure and the ITRULE algorithm
      6. Inference using probabilistic rule sets
      7. Acknowledgement
      8. References
    9. CHAPTER 38. EMPIRICAL SUBSTRUCTURE DISCOVERY
      1. Abstract
      2. 1 Introduction
      3. 2 Substructure Discovery
      4. 3 Example
      5. 4 Conclusion
      6. Acknowledgements
      7. References
    10. CHAPTER 39. LEARNING THE BEHAVIOR OF DYNAMICAL SYSTEMS FROM EXAMPLES
      1. ABSTRACT
      2. DYNAMICAL SYSTEMS
      3. TOPOLOGICAL MAPS - A BRIEF DESCRIPTION
      4. LEARNING MOVEMENTS OF A ROBOT ARM
      5. CONCLUSION
      6. ACKNOWLEDGEMENTS
      7. REFERENCES
    11. CHAPTER 40. EXPERIMENTS IN ROBOT LEARNING
      1. INTRODUCTION
      2. THE TASK DOMAIN
      3. EXPERIMENTS WITH TWO LEARNING ROBOTS
      4. FUTURE DIRECTIONS
      5. References
    12. Chapter 41. Induction of Decision Trees from Inconclusive Data
      1. Abstract
      2. 1 Introduction
      3. 2 Shortcomings of ID3
      4. 3 The INFERULE Algorithm
      5. 4 Results
      6. 5 Conclusions
      7. Acknowledgements
      8. References
    13. CHAPTER 42. KNOWLEDGE INTENSIVE INDUCTION
      1. ABSTRACT
      2. LEARNING DISJUNCTIVE CONCEPTS
      3. BEYOND ID3
      4. CONSTRAINING SEARCH USING FRAMES
      5. EXTRACTING CONCEPT DESCRIPTIONS FROM THE DECISION TREE
      6. CONCLUSION
      7. Acknowledgments
      8. References
    14. CHAPTER 43. AN OUNCE OF KNOWLEDGE IS WORTH A TON OF DATA: Quantitative Studies of the Trade-Off between Expertise and Data based on Statistically Weil-Founded Empirical Induction
      1. ABSTRACT
      2. INTRODUCTION
      3. INDUCT: A STATISTICALLY WELL-FOUNDED EMPIRICAL INDUCTION PROCEDURE FOR DERIVING DECISION RULES FROM DATASETS
      4. THE TRADE-OF BETWEEN KNOWLEDGE AND DATA
      5. CONCLUSIONS
      6. References
    15. CHAPTER 44. SIGNAL DETECTION THEORY: VALUABLE TOOLS FOR EVALUATING INDUCTIVE LEARNING
      1. ABSTRACT
      2. SIGNAL DETECTION THEORY AND ROC CURVES
      3. SIGNAL DETECTION THEORY
      4. EVALUATING MONOTONE DNF RULES
      5. COMPARISON OF CONNECTIONIST MODELS
      6. DEFINING EVALUATION FUNCTIONS FOR GENETIC SEARCH
      7. References
    16. CHAPTER 45. UNKNOWN ATTRIBUTE VALUES IN INDUCTION
      1. ABSTRACT
      2. INTRODUCTION
      3. DESCRIPTION OF DATASETS
      4. DESCRIPTION OF APPROACHES
      5. UNKNOWN VALUES WHEN PARTITIONING
      6. UNKNOWN VALUES WHEN CLASSIFYING
      7. UNKNOWN VALUES IN SELECTING TESTS
      8. CONCLUSIONS
      9. Acknowledgement
      10. References
    17. CHAPTER 46. PROCESSING ISSUES IN COMPARISONS OF SYMBOLIC AND CONNECTIONIST LEARNING SYSTEMS
      1. ABSTRACT
      2. Introduction
      3. ID3 and Back-Propagation
      4. Training conventions
      5. Behavioral Characterizations
      6. Concluding Remarks
      7. References
    18. CHAPTER 47. BACON, DATA ANALYSIS AND ARTIFICIAL INTELLIGENCE
      1. ABSTRACT
      2. AN EXAMPLE
      3. BACON VERSUS THE EVIDENCE
      4. DOMAIN-INDEPENDENT DATA ANALYSIS
      5. References
  9. Part 3: Learning Plan Knowledge
    1. CHAPTER 48. LEARNING TO PLAN IN COMPLEX DOMAINS
      1. ABSTRACT
      2. LEARNING SUBGOAL SEQUENCES FOR PLANNING
      3. SUMMARY OF RESULTS
      4. References
    2. CHAPTER 49. AN EMPIRICAL ANALYSIS OF EBL APPROACHES FOR LEARNING PLAN SCHEMATA
      1. ABSTRACT
      2. SCHEMA-BASED PLANNING AND EXPLANATION-BASED LEARNING
      3. EXPERIMENTAL METHODOLOGY
      4. EXPERIMENTAL RESULTS AND DISCUSSION
      5. CONCLUSION
      6. Acknowledgements
      7. References
    3. CHAPTER 50. LEARNING DECISION RULES FOR SCHEDULING PROBLEMS: A CLASSIFIER HYBRID APPROACH
      1. ABSTRACT
      2. INTRODUCTION
      3. SCHEDULING PROBLEMS
      4. THE PREDICATE CLASSIFIER SYSTEM
      5. MINIMUM LATENESS SCHEDULING PROBLEMS
      6. MINIMUM WEIGHTED TARDINESS SCHEDULING
      7. CONCLUSION
      8. REFERENCES
    4. CHAPTER 51. LEARNING TACTICAL PLANS FOR PILOT AIDING
      1. ABSTRACT
      2. THE LEARNING DOMAIN AND PERFORMANCE PROBLEM
      3. PERFORMANCE SYSTEM
      4. REPRESENTATION OF INPUTS AND OUTPUTS OF LEARNING
      5. LEARNING ALGORITHM
      6. SUMMARY
      7. REFERENCES
    5. CHAPTER 52. ISSUES IN THE JUSTIFICATION-BASED DIAGNOSIS OF PLANNING FAILURES
      1. Reference
    6. CHAPTER 53. LEARNING PROCEDURAL KNOWLEDGE IN THE EBG CONTEXT
      1. ABSTRACT
      2. INTRODUCTION
      3. THE LEARNING METHOD
      4. DESCRIPTION OF THE LEARNING METHOD
      5. RESULTS OF LEARNING
      6. CONCLUSION
      7. Acknowledgements
      8. References
    7. CHAPTER 54. LEARNING INVARIANTS FROM EXPLANATIONS
      1. ABSTRACT
      2. 1. INTRODUCTION
      3. 2 OVERVIEW OF THE LIFE SYSTEM
      4. 3. REASONING ABOUT IMPOSSIBILITY
      5. 4 THE BLOCKING GRAPH
      6. 5 THE FRAME PROBLEM
      7. 6 CONCLUSIONS
      8. Acknowledgements
      9. References
    8. Chapter 55. Using Learning to Recover Side-Effects of Operators in Robotics
      1. Abstract
      2. 1 INTRODUCTION
      3. 2 METHODOLOGY
      4. 3 EXAMPLE PROBLEM
      5. 4 CONCLUSIONS
      6. References
    9. CHAPTER 56. LEARNING TO RECOGNIZE PLANS INVOLVING AFFECT
      1. INTRODUCTION
      2. THE SYSTEM
      3. AN EXAMPLE
      4. CONCLUSION; CURRENT AND FUTURE WORK
      5. References
    10. Chapter 57. Learning to Retrieve Useful Information for Problem Solving
      1. Eureka's components
      2. Accounting for psychological phenomena
      3. Current status of the model
      4. References
    11. CHAPTER 58. Discovering problem solving strategies: What humans do and machines don't (yet)
      1. The experiment and the protocol
      2. Classification of the learning events
      3. Conclusions
      4. References
    12. Chapter 59. Approximating Learned Search Control Knowledge
      1. 1 Introduction
      2. 2 Our Approach
      3. 3 Experiments
      4. 4 Discussion
      5. References
    13. Chapter 60. Planning in Games Using Approximately Learned Macros
      1. 1 Introduction
      2. 2 Lazy Explanation-Based Learning
      3. 3 Knowledge Enabled Planning
      4. 4 Conclusion
      5. Acknowledgments
      6. References
    14. CHAPTER 61. LEARNING APPROXIMATE PLANS FOR USE IN THE REAL WORLD
      1. ABSTRACT
      2. INTRODUCTION
      3. THE MODEL
      4. AN EXAMPLE
      5. RELATED WORK AND CONCLUSIONS
      6. REFERENCES
    15. Chapter 62. Using Concept Hierarchies to Organize Plan Knowledge
      1. 1. Introduction
      2. 2. Representation and Planning in Daedalus
      3. 3. Acquiring and Using Plan Knowledge
      4. 5. Behavior of Daedalus
      5. References
    16. CHAPTER 63. Conceptual Clustering of Mean-Ends Plans
      1. ABSTRACT
      2. INTRODUCTION
      3. CONCEPTUAL CLUSTERING OF OPERATORS
      4. PLAN GENERATION and REUSE
      5. CONCLUDING REMARKS
      6. Acknowledgements
      7. References
    17. CHAPTER 64. LEARNING APPROPRIATE ABSTRACTIONS FOR PLANNING IN FORMATION PROBLEMS
      1. ABSTRACT
      2. Introduction
      3. The PLACE system
      4. Learning new abstractions
      5. Concluding remarks
      6. References
    18. Chapter 65. Discovering Admissible Search Heuristics by Abstracting and Optimizing
      1. Abstract
    19. CHAPTER 66. LEARNING HIERARCHIES OF ABSTRACTION SPACES
      1. ABSTRACT
      2. INTRODUCTION
      3. ABSTRIPS
      4. ALPINE
      5. PROPERTIES OF ABSTRACT PLANS
      6. THE LEARNING METHOD
      7. CONCLUSIONS
      8. Acknowledgments
      9. References
    20. CHAPTER 67. LEARNING FROM OPPORTUNITY
      1. ABSTRACT
      2. PLANNING AND LEARNING
      3. OPPORTUNISTIC MEMORY
      4. AN EXAMPLE
      5. CONCLUSION
      6. REFERENCES
    21. CHAPTER 68. LEARNING BY ANALYZING FORTUITOUS OCCURRENCES
      1. ABSTRACT
      2. INTRODUCTION
      3. DETECTION
      4. REFINEMENT
      5. AN EXAMPLE
      6. DISCUSSION AND CONCLUSION
      7. ACKNOWLEDGEMENTS
      8. REFERENCES
    22. CHAPTER 69. EXPLANATION-BASED LEARNING OF REACTIVE OPERATORS
      1. ABSTRACT
      2. INTRODUCTION
      3. REACTIVITY IN PLANNING
      4. REACTIVE OPERATORS
      5. DISCUSSION
      6. ACKNOWLEDGMENTS
      7. REFERENCES
    23. CHAPTER 70. ON BECOMING REACTIVE
      1. INTRODUCTION
      2. LEARNING
      3. DISCUSSION
      4. Acknowledgements
      5. References
  10. Part 4: Knowledge-Base Refinement and Theory Revision
    1. CHAPTER 71. KNOWLEDGE BASE REFINEMENT AND THEORY REVISION
      1. INTRODUCTION
      2. THEORIES AND EXPERT SYSTEMS
      3. THEORETICAL TERMS AND BRIDGE LAWS
      4. GOALS OF THEORY REVISION
      5. ELEMENTS OF THEORY REVISION
      6. REDUCTION OF THEORETICAL TERMS AND THEORY REVISION
      7. Acknowledgments
      8. References
    2. CHAPTER 72. THEORY FORMATION BY ABDUCTION: INITIAL RESULTS OF A CASE STUDY BASED ON THE CHEMICAL REVOLUTION
      1. ABSTRACT
      2. ABDUCTION, HYPOTHESIS FORMATION, AND THEORY REVISION
      3. THE CHEMICAL REVOLUTION
      4. SOME ASPECTS OF THE PHLOGISTON THEORY ENCODED AS RULES
      5. ABDUCTION OF ASPECTS OF THE OXYGEN THEORY
      6. CONCLUSION
      7. Acknowledgments
      8. References
    3. CHAPTER 73. USING DOMAIN KNOWLEDGE TO AID SCIENTIFIC THEORY REVISION
      1. ABSTRACT
      2. INTRODUCTION
      3. AN OVERVIEW OF THE REVOLVER SYSTEM
      4. ADDING DOMAIN KNOWLEDGE TO THE EVALUATION FUNCTION
      5. EVALUATING REVOLVER'S LEARNING BEHAVIOR
      6. DISCUSSION
      7. References
    4. Chapter 74. The Role of Experimentation in Scientific Theory Revision
      1. Abstract
      2. 1. Motivation
      3. 2. Question addressed in this research
      4. 3. Methodology
      5. 4. The Structure of KEKADA
      6. 5. Evaluation of KEKADA performance
      7. 6. Conclusion
      8. 7. Acknowledgement
      9. References
    5. CHAPTER 75. EXEMPLAR-BASED THEORY REJECTION: AN APPROACH TO THE EXPERIENCE CONSISTENCY PROBLEM
      1. Abstract
      2. 1 Introduction
      3. 2 Explanation-based Theory Revision - An Overview
      4. 3 Exemplar-based Theory Rejection
      5. 4 Discussion
      6. References
    6. CHAPTER 76. CONTROLLING SEARCH FOR THE CONSEQUENCES OF NEW INFORMATION DURING KNOWLEDGE INTEGRATION
      1. ABSTRACT
      2. INTRODUCTION
      3. KI: A TOOL FOR KNOWLEDGE INTEGRATION
      4. CONTROLLING THE SEARCH FOR CONSEQUENCES
      5. SUMMARY
      6. References
    7. CHAPTER 77. IDENTIFYING KNOWLEDGE BASE DEFICIENCIES BY OBSERVING USER BEHAVIOR
      1. ABSTRACT
      2. INTRODUCTION
      3. THE PERFORMANCE PROBLEM: AN INTELLIGENT AUTOMATED PILOT'S ASSISTANT
      4. REFINEMENT OF THE PA KNOWLEDGE BASE
      5. REFINEMENT OF THE EBL DOMAIN THEORY
      6. SUMMARY
      7. REFERENCES
    8. Chapter 78. Toward automated rational reconstruction: A case study
      1. 1 Introduction
      2. 2 A Boolean Function Design System
      3. 3 A System Development Sequence
      4. 4 Conclusions
      5. Acknowledgements
    9. CHAPTER 79. DISCOVERING MATHEMATICAL OPERATOR DEFINITIONS
      1. ABSTRACT
      2. INTRODUCTION
      3. GENERATE, PRUNE, AND PROVE METHOD
      4. CONCLUDING REMARKS
      5. References
    10. CHAPTER 80. IMPRECISE CONCEPT LEARNING WITHIN A GROWING LANGUAGE
      1. ABSTRACT
      2. INTRODUCTION
      3. BASIC DEFINITIONS
      4. LEARNING PROCESS
      5. References
    11. CHAPTER 81. USING DETERMINATIONS IN EBL: A SOLUTION TO THE INCOMPLETE THEORY PROBLEM
      1. ABSTRACT
      2. 1 Introduction
      3. 2 Determinations
      4. 3 One View of the Incomplete Theory Problem
      5. 4 A Technique for Refining Incomplete Theories
      6. 5 Conclusions
      7. Acknowledgements
      8. References
    12. Chapter 82. Some results on the complexity of knowledge-base refinement
      1. 1. Introduction
      2. 2. Learning protocols and a model of a rule base
      3. 3. Some NP-Complete refinement problems
      4. 4. Rule-based systems as classifiers
      5. 5. Gradualness
      6. 6. Conclusions
      7. Acknowledgements
      8. References
    13. CHAPTER 83. KNOWLEDGE BASE REFINEMENT AS IMPROVING AN INCORRECT, INCONSISTENT AND INCOMPLETE DOMAIN THEORY
      1. ABSTRACT
      2. INTRODUCTION
      3. ProHC HEURISTIC CLASSIFICATION SHELL
      4. INCORRECT DOMAIN THEORY
      5. INCONSISTENT DOMAIN THEORY
      6. INCOMPLETE DOMAIN THEORY
      7. EXPERIMENTAL RESULTS
      8. SUMMARY AND CONCLUSIONS
      9. Acknowledgements
      10. References
  11. Part 5: Incremental Learning
    1. CHAPTER 84. INCREMENTAL LEARNING OF CONTROL STRATEGIES WITH GENETIC ALGORITHMS
      1. INTRODUCTION
      2. THE EVASIVE MANEUVERS PROBLEM
      3. THE PERFORMANCE MODULE: CPS
      4. THE LEARNING MODULE
      5. A CASE STUDY
      6. DISCUSSION
      7. References
    2. CHAPTER 85. TOWER OF HANOI WITH CONNECTIONIST NETWORKS: LEARNING NEW FEATURES
      1. ABSTRACT
      2. INTRODUCTION
      3. CREDIT ASSIGNMENT
      4. THE NETWORKS
      5. RESULTS
      6. DISCUSSION
      7. CONCLUSION
      8. References
    3. Chapter 86. A Formal Framework for Learning in Embedded Systems
      1. Learning to Act
      2. Performance Criteria
      3. Related Work
      4. Acknowledgments
      5. References
    4. Chapter 87. A Role for Anticipation in Reactive Systems that Learn
      1. 1 Acting and Reasoning
      2. 2 The Reactive Component
      3. 3 Adding Projection
      4. 4 Discussion
      5. References
    5. CHAPTER 88. UNCERTAINTY BASED SELECTION OF LEARNING EXPERIENCES
      1. ABSTRACT
      2. STRATEGIES FOR SELECTING EXPERIENCES
      3. UNCERTAINTY AS AN EXPERIENCE SELECTION HEURISTIC
      4. UNCERTAINTY BASED EXPERIENCE SELECTION IN DIDO
      5. DISCUSSION
      6. References
    6. CHAPTER 89. IMPROVED TRAINING VIA INCREMENTAL LEARNING
      1. ABSTRACT
      2. INTRODUCTION
      3. INSTANCE SELECTION STRATEGIES OF ID3 AND ID5R
      4. AN EXPERIMENT
      5. CONCLUSION
      6. Acknowledgements
      7. References
    7. CHAPTER 90. INCREMENTAL BATCH LEARNING
      1. INTRODUCTION
      2. INCREMENTAL BATCH LEARNING TESTBED
      3. INFLUENCE OF BATCH SIZE
      4. INSTANCE STORAGE AND CONCEPT DRIFT
      5. COMPARISON OF INCREMENTAL BATCH LEARNING METHODS
      6. TIME CONSTRAINTS, NOISY AND ANOMALOUS DATA
      7. CONCLUSIONS
      8. References
    8. CHAPTER 91. INCREMENTAL CONCEPT FORMATION WITH COMPOSITE OBJECTS
      1. 1. INTRODUCTION
      2. 2. REPRESENTATION AND ORGANIZATION IN LABYRINTH
      3. 3. CLASSIFICATION AND LEARNING IN LABYRINTH
      4. 4. DISCUSSION
      5. Acknowledgment
      6. References
    9. CHAPTER 92. USING MULTIPLE REPRESENTATIONS TO IMPROVE INDUCTIVE BIAS: GRAY AND BINARY CODING FOR GENETIC ALGORITHMS
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. MULTIPLE REPRESENTATIONS
      5. DISCUSSION
      6. Acknowledgements
      7. References
    10. CHAPTER 93. FOCUSED CONCEPT FORMATION
      1. 1. Introduction
      2. 2. Previous Work
      3. 3. An Incremental Algorithm for Attention
      4. 4. Performance Tasks and Planned Experiments
      5. 5. Summary
      6. Acknowlegments
      7. References
    11. CHAPTER 94. An Exploration into Incremental Learning: the INFLUENCE system
      1. Abstract
      2. 1. INTRODUCTION
      3. 2. THE INFLUENCE SYSTEM
      4. 3. EXPERIMENTS
      5. 4. CONCLUSION
      6. Acknowledgements
      7. References
    12. CHAPTER 95. INCREMENTAL, INSTANCE-BASED LEARNING OF INDEPENDENT AND GRADED CONCEPT DESCRIPTIONS
      1. ABSTRACT
      2. 1. MOTIVATION
      3. 2. THE INSTANCE-BASED PROCESS FRAMEWORK
      4. 3. BLOOM: LEARNING CONCEPT-DEPENDENT ATTRIBUTE WEIGHTS
      5. 4. EMPIRICAL STUDIES AND RESULTS
      6. 5. LIMITATIONS AND SUMMARY
      7. Acknowledgements
      8. References
    13. Chapter 96. Cost-Sensitive Concept Learning of Sensor Use in Approach and Recognition
      1. 1 Introduction
      2. 2 Building and using cost decision trees
      3. 3 Learning cost versus application cost
      4. 4 Tradeoff among environmental costs
      5. Acknowledgements
      6. References
    14. CHAPTER 97. REDUCING REDUNDANT LEARNING
      1. ABSTRACT
      2. INTRODUCTION
      3. NONREDUNDANT LEARNING
      4. CORA
      5. CORA'S EMPIRICAL BEHAVIOR
      6. SUMMARY AND FUTURE DIRECTIONS
      7. References
    15. CHAPTER 98. INCREMENTAL CLUSTERING BY MINIMIZING REPRESENTATION LENGTH
      1. ABSTRACT
      2. Introduction
      3. Cluster configuration quality
      4. Incremental clustering strategy
      5. Implementation and test results
      6. References
    16. CHAPTER 99. INFORMATION FILTERS AND THEIR IMPLEMENTATION IN THE SYLLOG SYSTEM
      1. INTRODUCTION
      2. INFORMATION FILTERING
      3. INFORMATION FILTERS IN THE SYLLOG SYSTEM
      4. CONCLUSIONS
      5. References
    17. CHAPTER 100. ADAPTIVE LEARNING OF DECISION-THEORETIC SEARCH CONTROL KNOWLEDGE
      1. ABSTRACT
      2. DTA: DECISION-THEORETIC REAL-TIME HEURISTIC SEARCH
      3. INCREMENTAL LEARNING OF PARAMETERS
      4. CONCLUSIONS
      5. Acknowledgments
      6. References
    18. CHAPTER 101. ADAPTIVE STRATEGIES OF LEARNING A STUDY OF TWO-PERSON ZERO-SUM COMPETITION
      1. ABSTRACT
      2. INTRODUCTION: ADAPTIVE STRATEGIES IN ZERO-SUM GAMES
      3. ADAPTATION AND LEARNING
      4. EXPERIMENTS AND DISCUSSION
      5. BIBLIOGRAPHY
    19. CHAPTER 102. AN INCREMENTAL GENETIC ALGORITHM FOR REAL-TIME LEARNING
      1. ABSTRACT
      2. INTRODUCTION
      3. THE GENETIC ALGORITHMS
      4. THE EXPERIMENTS
      5. THE RESULTS
      6. References
    20. CHAPTER 103. PARTICIPATORY LEARNING: A CONSTRUCTIVIST MODEL
      1. INTRODUCTION
      2. A CONSTRUCTIVIST MODEL OF PARTICIPATORY LEARNING
      3. REFERENCES
  12. Part 6: Representational Issues in Machine Learning
    1. CHAPTER 104. REPRESENTATIONAL ISSUES IN MACHINE LEARNING
      1. OBJECTIVES
      2. ISSUES AND APPROACHES
      3. FUTURE DIRECTIONS
      4. References
    2. CHAPTER 105. Labor Saving New Distinctions
      1. Abstract
      2. 1 Introduction
      3. 2 Framework
      4. 3 New Relations
      5. 4 Complexity of Introducing New Relations
      6. 5 New Objects
      7. 6 Conclusions
      8. Acknowledgements
      9. References
    3. CHAPTER 106. A THEORY OF JUSTIFIED REFORMULATIONS
      1. ABSTRACT
      2. REFORMULATION
      3. JUSTIFYING REFORMULATIONS
      4. IRRELEVANCE REFORMULATIONS
      5. THE RELEVANCE OF IRRELEVANCE
      6. CONCLUSIONS
      7. References
    4. CHAPTER 107. REFORMULATION PROM STATE SPACE TO REDUCTION SPACE
      1. INTRODUCTION
      2. THE PROBLEM
      3. THE SOLUTION
      4. REFERENCES
    5. CHAPTER 108. KNOWLEDGE-BASED FEATURE GENERATION
      1. ABSTRACT
      2. INTRODUCTION
      3. CREATING NEW TERMS FROM SEARCH PROBLEM SPECIFICATIONS
      4. FUTURE WORK
      5. CONCLUSIONS
      6. Acknowledgement
      7. References
    6. CHAPTER 109. ENRICHING VOCABULARIES BY GENERALIZING EXPLANATION STRUCTURES
      1. ABSTRACT
      2. INTRODUCTION
      3. PLEESE: AN AUTOMATIC PROGRAMMING SYSTEM
      4. CURRENT RESEARCH DIRECTIONS
      5. CONCLUSION
      6. References
    7. Chapter 110. Higher-Order and Modal Logic as a Framework for Explanation-Based Generalization
      1. Abstract
      2. 1 Introduction
      3. 2 Higher-order EBG and Representation Domains
      4. 3 EBG and Modal Logic
      5. References
    8. CHAPTER 111. Towards A Formal Analysis of EBL
      1. 1 Motivation
      2. 2 Framework
      3. 3 Finding the Optimal Strategy in a Redundant KB
      4. 4 Conclusion
      5. References
    9. CHAPTER 112. A MATHEMATICAL FRAMEWORK FOR STUDYING REPRESENTATION
      1. ABSTRACT
      2. MOTIVATION
      3. INTUITIONS ABOUT THE NATURE OF REPRESENTATION
      4. FORMALIZING "REPRESENTATION"
      5. References
    10. Chapter 113. Refining Representations to Improve Problem Solving Quality
      1. 1 Introduction
      2. 2 Changing Representations with Bumble
      3. 3 The Good News and The Bad News
      4. Acknowledgements
      5. References
    11. CHAPTER 114. COMPARING SYSTEMS AND ANALYZING FUNCTIONS TO IMPROVE CONSTRUCTIVE INDUCTION
      1. 1. INTRODUCTION: CONSTRUCTION IN CONCEPT LEARNING
      2. 2. ONE BENEFIT OF JUXTAPOSING TWO SYSTEMS
      3. 3. BROAD BENEFITS OF COMPARING MANY SYSTEMS
      4. References
    12. CHAPTER 115. EVALUATING ALTERNATIVE INSTANCE REPRESENTATIONS
      1. ABSTRACT
      2. INTRODUCTION
      3. WHAT IS A GOOD REPRESENTATION?
      4. CHOOSING A GOOD REPRESENTATION
      5. EXPERIMENT
      6. CONCLUSIONS
      7. Acknowledgement
      8. References
    13. CHAPTER 116. EVALUATING BIAS DURING PAC-LEARNING
      1. INTRODUCTION
      2. PAC-LEARNING
      3. DETECTING INCORRECT BIAS
      4. RELATED WORK
      5. CONCLUSION
      6. Acknowledgements
      7. References
    14. CHAPTER 117. CONSTRUCTING REPRESENTATIONS USING INVERTED SPACES
      1. ABSTRACT
      2. INTRODUCTION
      3. LINEAR SEPARABILITY
      4. FEATURE CONSTRUCTION
      5. INTEGRATION WITH DIMENSIONALITY REDUCTION TECHNIQUES
      6. FUTURE WORK
      7. References
    15. CHAPTER 118. A CONSTRUCTIVE INDUCTION FRAMEWORK
      1. INTRODUCTION
      2. THE FRAMEWORK
      3. CHAPTER 119. CONSTRUCTIVE INDUCTION BY ANALOGY
      4. ABSTRACT
      5. THE TECHNIQUE
      6. References
    16. CHAPTER 120. CONCEPT DISCOVERY THROUGH UTILIZATION OF INVARIANCE EMBEDDED IN THE DESCRIPTION LANGUAGE
      1. ABSTRACT
      2. THE LEARNING PROBLEM
      3. INVARIANCE AND CONSTRUCTIVE INDUCTION
      4. THE CONSTRUCTIVE INDUCTION PROCEDURE
      5. CONCLUSIONS
      6. REFERENCES
    17. CHAPTER 121. DECLARATIVE BIAS FOR STRUCTURAL DOMAINS
      1. ABSTRACT
      2. Situation Identification and Declarative Bias
      3. Structural Domains
      4. Isomorphic Determinations
      5. Discussion
      6. Acknowledgments
      7. References
    18. Chapter 122. Automatic Construction of a Hierarchical Generate-and-Test Algorithm
      1. References
    19. Chapter 123. A Knowledge-level Analysis of Informing
      1. 1 Introduction
      2. 2 Programming by Informing
      3. 3 A Knowledge-level Description of Agents
      4. 4 Analysis
      5. 5 Conclusion
      6. References
    20. CHAPTER 124. AN OBJECT-ORIENTED REPRESENTATION FOR SEARCH ALGORITHMS
      1. ABSTRACT
      2. INTRODUCTION
      3. AN OBJECT-ORIENTED REPRESENTATION FOR GENERATORS
      4. CURRENT STATUS
      5. References
    21. CHAPTER 125. COMPILING LEARNING VOCABULARY FROM A PERFORMANCE SYSTEM DESCRIPTION
      1. ABSTRACT
      2. INTRODUCTION
      3. A LANGUAGE FOR DESCRIBING SOLVER'S BEHAVIOR
      4. SYNTHESIZING THE "USEFUL" PREDICATE
      5. CONCLUSIONS
      6. References
    22. CHAPTER 126. GENERALIZED RECURSIVE SPLITTING ALGORITHMS FOR LEARNING HYBRID CONCEPTS
      1. ABSTRACT
      2. INTRODUCTION
      3. GENERALIZED RECURSIVE SPLITTING ALGORITHMS
      4. THE CRL ALGORITHM
      5. EXPERIMENTAL RESULTS
      6. CONCLUSIONS
      7. Acknowledgements
      8. References
    23. CHAPTER 127. SCREENING HYPOTHESES WITH EXPLICIT BIAS
      1. INTRODUCTION
      2. PREDICTOR: A SYSTEM THAT USES EXPLICIT BIAS
      3. Acknowledgements
      4. References
    24. CHAPTER 128. BUILDING A LEARNING BIAS FROM PERCEIVED DEPENDENCIES
      1. INTRODUCTION
      2. THE NOTION OF A PERCEIVED DEPENDENCY
      3. THE LEARNING BIAS
      4. BUILDING A LEARNING BIAS USING PERCEIVED DEPENDENCIES
      5. CONCLUSION
      6. Reference
    25. CHAPTER 129. A BOOTSTRAPPING APPROACH TO CONCEPTUAL CLUSTERING
      1. Text
    26. CHAPTER 130. OVERCOMING FEATURE SPACE BIAS IN A REACTIVE ENVIRONMENT
      1. ABSTRACT
      2. THE SEMANTICS OF INDEFINABLE TERMS IN SELF-REFLECTIVE ARCHITECTURES
      3. OVERVIEW OF NOME'S ENVIRONMENT
      4. DIMENSIONS AND THE DIMENSION STUDIER
      5. EVALUATING DIMENSIONAL I/O PAIRINGS AGAINST THE EXTERNAL WORLD
      6. ACKNOWLEDGMENTS
      7. References
  13. AUTHOR INDEX

Product information

  • Title: Machine Learning Proceedings 1989
  • Author(s): Alberto Maria Segre
  • Release date: April 2016
  • Publisher(s): Morgan Kaufmann
  • ISBN: 9781483297408