Machine Learning Proceedings 1992

Generalizing from Case Studies: A Case StudyOn Learning More ConceptsThe Principal Axes Method for Constructive InductionLearning by Incomplete Explanations of Failures in Recursive DomainsEliminating Redundancy in Explanation-Based LearningTrading Off Consistency and Efficiency in Version-Space InductionPeepholing: Choosing Attributes Efficiently for MegainductionImproving Path Planning with LearningThe Right Representation for Discovery: Finding the Conservation of MomentumLearning to Predict in Uncertain Continuous TasksLazy Partial Evaluation: An Integration of Explanation-Based Generalisation and Partial EvaluationA Teaching Method for Reinforcement LearningCompiling Prior Knowledge into an Explicit BiasSpatial Analogy and SubsumptionLearning to Satisfy Conjunctive GoalsMultistrategy Learning with Introspective Meta-ExplanationsAn Asymptotic Analysis of Speedup LearningWhy EBL Produces Overly-Specific Knowledge: A Critique of the PRODIGY ApproachesAutomatic Feature Generation for Problem Solving SystemsTowards Inductive Generalisation in Higher Order LogicOrdering Effects in ClusteringLearning Structured Concepts Using Genetic AlgorithmsAn Analysis of Learning to Plan as a Search ProblemAn Approach to Anytime LearningArtificial Universes-Towards a Systematic Approach to Evaluating Algorithms Which Learn from ExamplesAverage Case Analysis of Learning k-CNF ConceptsThe MENTLE Approach to Learning Heuristics for the Control of Logic ProgramsFuzzy Substructure DiscoveryEfficient Classification of Massive, Unsegmented DatastreamsInduction of One-Level Decision TreesCombining Competition and Cooperation in Supervised Inductive LearningA Practical Approach to Feature SelectionLearning as Optimization: Stochastic Generation of Multiple KnowledgeDynamic OptimizationSub-Unification: A Tool for Efficient Induction of Recursive ProgramsAugmenting and Efficiently Utilizing Domain Theory in Explanation-Based Natural Language AcquisitionEnhancing Transfer in Reinforcement Learning by Building Stochastic Models of Robot ActionsTHOUGHT: An Integrated Learning System for Acquiring Knowledge StructureAn Approach to Concept Learning Based on Term GeneralizationUsing Transitional Proximity for Faster Reinforcement LearningNFDT: A System that Learns Flexible Concepts Based on Decision Trees for Numerical AttributesA Symbolic Algorithm for Computing Coefficients' Accuracy in RegressionCompression, Significance, and AccuracyGuiding Example Acquisition by Generating ScenariosConstructive Induction Using a Non-Greedy Strategy for Feature SelectionTraining Second-Order Recurrent Neural Networks Using HintsDYNAMIC: A New Role for Training Problems in EBLA Framework for Discovering Discrete Event ModelsLearning Episodes for OptimizationLearning to FlyDeconstructing the Digit Recognition ProblemOn Combining Multiple Speedup TechniquesScaling Reinforcement Learning Algorithms by Learning Variable Temporal Resolution ModelsDetecting Novel Classes with Applications to Fault DiagnosisMeasuring Utility and the Design of Provably Good EBL AlgorithmsRefining a Relational Theory with Multiple Faults in the Concept and SubconceptsCooperation in Knowledge Base RefinementTemporal Difference Learning of Backgammon StrategyAGIL: Solving the Exploration Versus Exploitation Dilemma in a Simple Classifier System Applied to Simulated RoboticsConceptual Clustering with Systematic Missing ValuesSelecting Typical Instances in Instance-Based LearningThe First Phase of Real-World Discovery: Determining Repeatability and Error of ExperimentsAuthor IndexSubject Index