Proceedings of the Sixth International Workshop on Machine Learning, Cornell University, Ithaca, New York, June 26-27, 1989

Content: Front Matter, Page i Copyright, Page ii PREFACE, Page ix Unifying Themes in Empirical and Explanation-Based Learning, Pages 2-4, Pat Langley INDUCTION OVER THE UNEXPLAINED: Integrated Learning of Concepts with Both Explainable and Conventional Aspects, Pages 5-7, Raymond Mooney, Dirk Ourston CONCEPTUAL CLUSTERING OF EXPLANATIONS, Pages 8-10, Jungsoon P. Yoo, Douglas H. Fisher A Tight Integration of Deductive and Inductive Learning*, Pages 11-13, GERHARD WIDMER MULTI-STRATEGY LEARNING IN NONHOMOGENEOUS DOMAIN THEORIES, Pages 14-16, Gheorghe Tecuci, Yves Kodratoff A DESCRIPTION OF PREFERENCE CRITERION IN CONSTRUCTIVE LEARNING: A Discussion of Basic Issues, Pages 17-19, Jianping Zhang, Ryszard S. Michalski COMBINING CASE-BASED REASONING, EXPLANATION-BASED LEARNING, AND LEARNING FROM INSTRUCTION, Pages 20-22, Michael Redmond DEDUCTION IN TOP-DOWN INDUCTIVE LEARNING, Pages 23-25, F. Bergadano, A. Giordana, S. Ponsero ONE-SIDED ALGORITHMS FOR INTEGRATING EMPIRICAL AND EXPLANATION-BASED LEARNING, Pages 26-28, Wendy E. Sarrett, Michael J. Pazzani COMBINING EMPIRICAL AND ANALYTICAL LEARNING WITH VERSION SPACES, Pages 29-33, Haym Hirsh FINDING NEW RULES FOR INCOMPLETE THEORIES: EXPLICIT BIASES FOR INDUCTION WITH CONTEXTUAL INFORMATION, Pages 34-36, Andrea Pohoreckyj Danyluk LEARNING FROM PLAUSIBLE EXPLANATIONS, Pages 37-39, Tom E. Fawcett AUGMENTING DOMAIN THEORY FOR EXPLANATION-BASED GENERALISATION, Pages 40-42, Kamal M. Ali Explanation Based Learning as Constrained Search, Pages 43-45, David Haines REDUCING SEARCH AND LEARNING GOAL PREFERENCES, Pages 46-48, Steven Morris Adaptation-Based Explanation: Explanations as Cases, Pages 49-51, Alex Kass A RETRIEVAL MODEL USING FEATURE SELECTION, Pages 52-54, Colleen M. Seifert IMPROVING DECISION-MAKING ON THE BASIS OF EXPERIENCE, Pages 55-57, Bruce Krulwich, Gregg Collins, Lawrence Birnbaum EXPLANATION-BASED ACCELERATION OF SIMILARITY-BASED LEARNING, Pages 58-60, Masayuki Numao, Masamichi Shimura Knowledge Acquisition Planning: Results and Prospects, Pages 61-65, Lawrence Hunter “Learning by instruction” in connectionist systems, Pages 66-68, Joachim Diederich INTEGRATING LEARNING IN A NEURAL NETWORK, Pages 69-71, Bruce F. Katz Explanation-based learning with weak domain theories, Pages 72-74, Michael J. Pazzani Using Domain Knowledge to Improve Inductive Learning Algorithms for Diagnosis, Pages 75-77, Gerhard Friedrich, Wolfgang Nejdl A Framework for Improving Efficiency and Accuracy, Pages 78-80, James Wogulis ERROR CORRECTION IN CONSTRUCTIVE INDUCTION, Pages 81-83, George Drastal, Regine Meunier, Stan Raatz IMPROVING EXPLANATION-BASED INDEXING WITH EMPIRICAL LEARNING, Pages 84-86, Ralph Barletta, Randy Kerber A SCHEMA FOR AN INTEGRATED LEARNING SYSTEM, Pages 87-89, Michael Wollowski COMBINING EXPLANATION-BASED LEARNING AND ARTIFICIAL NEURAL NETWORKS, Pages 90-92, Jude W. Shavlik, Geoffrey G. Towell LEARNING CLASSIFICATION RULES USING BAYES, Pages 94-98, Wray Buntine NEW EMPIRICAL LEARNING MECHANISMS PERFORM SIGNIFICANTLY BETTER IN REAL LIFE DOMAINS, Pages 99-103, Matjaz Gams, Aram Karalic INDUCTIVE LEARNING WITH BCT, Pages 104-108, Philip K. Chan WHAT GOOD ARE EXPERIMENTS?, Pages 109-112, Ritchey A. Ruff, Thomas G. Dietterich An Experimental Comparison of Human and Machine Learning Formalisms, Pages 113-118, Stephen Muggleton, Michael Bain, Jean Hayes-Michie, Donald Michie TWO ALGORITHMS THAT LEARN DNF BY DISCOVERING RELEVANT FEATURES, Pages 119-123, Giulia Pagallo, David Haussler LIMITATIONS ON INDUCTIVE LEARNING, Pages 124-128, Thomas G. Dietterich THE INDUCTION OF PROBABILISTIC RULE SETS– THE ITRULE ALGORITHM, Pages 129-132, Rodney M. Goodman, Padhraic Smyth EMPIRICAL SUBSTRUCTURE DISCOVERY, Pages 133-136, Lawrence B. Holder LEARNING THE BEHAVIOR OF DYNAMICAL SYSTEMS FROM EXAMPLES, Pages 137-140, Jan Paredis EXPERIMENTS IN ROBOT LEARNING, Pages 141-145, Matthew T. Mason, Alan D. Christiansen, Tom M. Mitchell Induction of Decision Trees from Inconclusive Data, Pages 146-150, Scott Spangler, Usama M. Fayyad, Ramasamy Uthurusamy KNOWLEDGE INTENSIVE INDUCTION, Pages 151-155, MICHEL MANAGO AN OUNCE OF KNOWLEDGE IS WORTH A TON OF DATA: Quantitative Studies of the Trade-Off between Expertise and Data based on Statistically Well-Founded Empirical Induction, Pages 156-159, Brian R Gaines SIGNAL DETECTION THEORY: VALUABLE TOOLS FOR EVALUATING INDUCTIVE LEARNING, Pages 160-163, Kent A. Spackman UNKNOWN ATTRIBUTE VALUES IN INDUCTION, Pages 164-168, J.R. Quinlan PROCESSING ISSUES IN COMPARISONS OF SYMBOLIC AND CONNECTIONIST LEARNING SYSTEMS, Pages 169-173, Douglas Fisher, Kathleen McKusick, Raymond Mooney, Jude W. Shavlik, Geoffrey Towell BACON, DATA ANALYSIS AND ARTIFICIAL INTELLIGENCE, Pages 174-178, Cullen Schaffer LEARNING TO PLAN IN COMPLEX DOMAINS, Pages 180-182, DAVID RUBY, DENNIS KIBLER AN EMPIRICAL ANALYSIS OF EBL APPROACHES FOR LEARNING PLAN SCHEMATA, Pages 183-187, Jude W. Shavlik LEARNING DECISION RULES FOR SCHEDULING PROBLEMS: A CLASSIFIER HYBRID APPROACH, Pages 188-190, M.R. Hilliard, G. Liepins, G. Rangarajan, M. Palmer LEARNING TACTICAL PLANS FOR PILOT AIDING, Pages 191-193, Keith R. Levi, David Perschbacher, Valerie L. Shalin ISSUES IN THE JUSTIFICATION-BASED DIAGNOSIS OF PLANNING FAILURES, Pages 194-196, Lawrence Birnbaum, Gregg Collins, Bruce Krulwich LEARNING PROCEDURAL KNOWLEDGE IN THE EBG CONTEXT, Pages 197-199, Stan Matwin LEARNING INVARIANTS FROM EXPLANATIONS, Pages 200-204, Jean-Francois PUGET Using Learning to Recover Side-Effects of Operators in Robotics, Pages 205-208, Ralph P. Sobek, Jean-Paul Laumond LEARNING TO RECOGNIZE PLANS INVOLVING AFFECT, Pages 209-211, Paul O'Rorke, Timothy Cain, Andrew Ortony Learning to Retrieve Useful Information for Problem Solving, Pages 212-214, Randolph Jones Discovering problem solving strategies: What humans do and machines don't (yet), Pages 215-217, Kurt VanLehn Approximating Learned Search Control Knowledge, Pages 218-220, Melissa P. Chase, Monte Zweben, Richard L. Piazza, John D. Burger, Paul P. Maglio, Haym Hirsh Planning in Games Using Approximately Learned Macros, Pages 221-223, Prasad Tadepalli LEARNING APPROXIMATE PLANS FOR USE IN THE REAL WORLD, Pages 224-228, Scott W. Bennett Using Concept Hierarchies to Organize Plan Knowledge, Pages 229-231, John A. Allen, Pat Langley Conceptual Clustering of Mean-Ends Plans, Pages 232-234, Hua Yang, Douglas H. Fisher LEARNING APPROPRIATE ABSTRACTIONS FOR PLANNING IN FORMATION PROBLEMS, Pages 235-239, Nicholas S. Flann Discovering Admissible Search Heuristics by Abstracting and Optimizing, Page 240, Jack Mostow, Armand E. Prieditis LEARNING HIERARCHIES OF ABSTRACTION SPACES, Pages 241-245, Craig A. Knoblock LEARNING FROM OPPORTUNITY, Pages 246-248, Tim Converse, Kristian Hammond, Mitchell Marks LEARNING BY ANALYZING FORTUITOUS OCCURRENCES, Pages 249-251, Steve A. Chien EXPLANATION-BASED LEARNING OF REACTIVE OPERATORS, Pages 252-254, Melinda T. Gervasio, Gerald F. DeJong ON BECOMING REACTIVE, Pages 255-257, Jim Blythe, Tom M. Mitchell KNOWLEDGE BASE REFINEMENT AND THEORY REVISION, Pages 260-265, Allen Ginsberg THEORY FORMATION BY ABDUCTION: INITIAL RESULTS OF A CASE STUDY BASED ON THE CHEMICAL REVOLUTION, Pages 266-271, Paul O'Rorke, Steven Morris, David Schulenburg USING DOMAIN KNOWLEDGE TO AID SCIENTIFIC THEORY REVISION, Pages 272-277, DONALD ROSE The Role of Experimentation in Scientific Theory Revision, Pages 278-283, Deepak Kulkarni, Herbert A. Simon EXEMPLAR-BASED THEORY REJECTION: AN APPROACH TO THE EXPERIENCE CONSISTENCY PROBLEM, Pages 284-289, Shankar A. Rajamoney CONTROLLING SEARCH FOR THE CONSEQUENCES OF NEW INFORMATION DURING KNOWLEDGE INTEGRATION, Pages 290-295, Kenneth S. Murray, Bruce W. Porter IDENTIFYING KNOWLEDGE BASE DEFICIENCIES BY OBSERVING USER BEHAVIOR, Pages 296-301, Keith R. Levi, Valerie L. Shalin, David L. Perschbacher Toward automated rational reconstruction: A case study, Pages 302-307, Chris Tong, Phil Franklin DISCOVERING MATHEMATICAL OPERATOR DEFINITIONS, Pages 308-313, Michael H. Sims, John L. Bresina IMPRECISE CONCEPT LEARNING WITHIN A GROWING LANGUAGE, Pages 314-319, Zbigniew W. Ras, Maria Zemankova USING DETERMINATIONS IN EBL: A SOLUTION TO THE INCOMPLETE THEORY PROBLEM, Pages 320-325, Sridhar Mahadevan Some results on the complexity of knowledge-base refinement, Pages 326-331, Marco Valtorta KNOWLEDGE BASE REFINEMENT AS IMPROVING AN INCORRECT, INCONSISTENT AND INCOMPLETE DOMAIN THEORY, Pages 332-337, David C. Wilkins, Kok-Wah Tan INCREMENTAL LEARNING OF CONTROL STRATEGIES WITH GENETIC ALGORITHMS, Pages 340-344, John J. Grefenstette TOWER OF HANOI WITH CONNECTIONIST NETWORKS: LEARNING NEW FEATURES, Pages 345-349, Charles W. Anderson A Formal Framework for Learning in Embedded Systems, Pages 350-353, Leslie Pack Kaelbling A Role for Anticipation in Reactive Systems that Learn, Pages 354-357, Steven D. Whitehead, Dana H. Ballard UNCERTAINTY BASED SELECTION OF LEARNING EXPERIENCES, Pages 358-361, Paul D. Scott, Shaul Markovitch IMPROVED TRAINING VIA INCREMENTAL LEARNING, Pages 362-365, Paul E. Utgoff INCREMENTAL BATCH LEARNING, Pages 366-370, Scott H. Clearwater, Tze-Pin Cheng, Haym Hirsh, Bruce G. Buchanan INCREMENTAL CONCEPT FORMATION WITH COMPOSITE OBJECTS, Pages 371-374, Kevin Thompson, Pat Langley USING MULTIPLE REPRESENTATIONS TO IMPROVE INDUCTIVE BIAS: GRAY AND BINARY CODING FOR GENETIC ALGORITHMS, Pages 375-378, Richard A. Caruana, J. David Schaffer, Larry J. Eshelman FOCUSED CONCEPT FORMATION, Pages 379-382, John H. Gennari An Exploration into Incremental Learning : the INFLUENCE system, Pages 383-386, Antoine CORNUEJOLS INCREMENTAL, INSTANCE-BASED LEARNING OF INDEPENDENT AND GRADED CONCEPT DESCRIPTIONS, Pages 387-391, David W. Aha Cost-Sensitive Concept Learning of Sensor Use in Approach and Recognition, Pages 392-395, MING TAN, JEFFREY C. SCHLIMMER REDUCING REDUNDANT LEARNING, Pages 396-399, Joel D. Martin INCREMENTAL CLUSTERING BY MINIMIZING REPRESENTATION LENGTH, Pages 400-403, JAKUB SEGEN INFORMATION FILTERS AND THEIR IMPLEMENTATION IN THE SYLLOG SYSTEM, Pages 404-407, Shaul Markovitch, Paul D. Scott ADAPTIVE LEARNING OF DECISION-THEORETIC SEARCH CONTROL KNOWLEDGE, Pages 408-411, Eric H. Wefald, Stuart J. Russell ADAPTIVE STRATEGIES OF LEARNING A STUDY OF TWO-PERSON ZERO-SUM COMPETITION, Pages 412-415, Oliver G. Selfridge AN INCREMENTAL GENETIC ALGORITHM FOR REAL-TIME LEARNING, Pages 416-419, Terence C. Fogarty PARTICIPATORY LEARNING: A CONSTRUCTIVIST MODEL, Pages 420-423, Ronald R. Yager, Kenneth M. Ford REPRESENTATIONAL ISSUES IN MACHINE LEARNING, Pages 426-429, Devika Subramanian Labor Saving New Distinctions, Pages 430-433, John Woodfll A THEORY OF JUSTIFIED REFORMULATIONS, Pages 434-438, Devika Subramanian REFORMULATION FROM STATE SPACE TO REDUCTION SPACE, Pages 439-440, Patricia J. Riddle KNOWLEDGE-BASED FEATURE GENERATION, Pages 441-443, James P. Callan ENRICHING VOCABULARIES BY GENERALIZING EXPLANATION STRUCTURES, Pages 444-446, Richard Maclin, Jude W. Shavlik Higher-Order and Modal Logic as a Framework for Explanation-Based Generalization, Pages 447-449, Scott Dietzen, Frank Pfenning Towards A Formal Analysis of EBL, Pages 450-453, Russell Greiner A MATHEMATICAL FRAMEWORK FOR STUDYING REPRESENTATION, Pages 454-456, Robert C. Holte, Robert M. Zimmer Refining Representations to Improve Problem Solving Quality, Pages 457-460, JEFFREY C. SCTILIMMER COMPARING SYSTEMS AND ANALYZING FUNCTIONS TO IMPROVE CONSTRUCTIVE INDUCTION, Pages 461-464, Larry Rendell EVALUATING ALTERNATIVE INSTANCE REPRESENTATIONS, Pages 465-468, Sharad Saxena EVALUATING BIAS DURING PAC-LEARNING, Pages 469-471, Lonnie Chrisman CONSTRUCTING REPRESENTATIONS USING INVERTED SPACES, Pages 472-473, Pankaj Mehra A CONSTRUCTIVE INDUCTION FRAMEWORK, Pages 474-475, Christopher J. Matheus CONSTRUCTIVE INDUCTION BY ANALOGY, Pages 476-477, Luc De Raedt, Maurice Bruynooghe CONCEPT DISCOVERY THROUGH UTILIZATION OF INVARIANCE EMBEDDED IN THE DESCRIPTION LANGUAGE, Pages 478-479, Mieczyslaw M. Kokar DECLARATIVE BIAS FOR STRUCTURAL DOMAINS, Pages 480-482, Benjamin N. Grosof, Stuart J. Russell Automatic Construction of a Hierarchical Generate-and-Test Algorithm, Pages 483-484, Sunil Mohan, Chris Tong A Knowledge-level Analysis of Informing, Pages 485-488, Jane Yung-jen Hsu AN OBJECT-ORIENTED REPRESENTATION FOR SEARCH ALGORITHMS, Pages 489-491, Jack Mostow COMPILING LEARNING VOCABULARY FROM A PERFORMANCE SYSTEM DESCRIPTION, Pages 492-495, Richard M. Keller GENERALIZED RECURSIVE SPLITTING ALGORITHMS FOR LEARNING HYBRID CONCEPTS, Pages 496-498, Bruce Lambert, David Tcheng, Stephen C-Y Lu SCREENING HYPOTHESES WITH EXPLICIT BIAS, Pages 499-500, Diana Gordon BUILDING A LEARNING BIAS FROM PERCEIVED DEPENDENCIES, Pages 501-502, Ch. de Sainte Marie A BOOTSTRAPPING APPROACH TO CONCEPTUAL CLUSTERING, Pages 503-504, Katharina Morik, Joerg-Uwe Kietz OVERCOMING FEATURE SPACE BIAS IN A REACTIVE ENVIRONMENT, Pages 505-507, Hans Tallis AUTHOR INDEX, Pages 509-510 Proceedings of the Sixth International Workshop on Machine Learning covers the papers presented at the Sixth International Workshop of Machine Learning, held at Cornell University, Ithaca, New York (USA) on June 26-27, 1989. The book focuses on the processes, methodologies, techniques, and approaches involved in machine learning. The selection first offers information on unifying themes in empirical and explanation-based learning; integrated learning of concepts with both explainable and conventional aspects; conceptual clustering of explanations; and tight integration of deductive and inductive learning. The text then examines multi-strategy learning in nonhomogeneous domain theories; description of preference criterion in constructive learning; and combining case-based reasoning, explanation-based learning, and learning from instruction. Discussions focus on causal explanation of actions, constructive learning, learning in a weak theory domain, learning problem, and individual criteria and their relationships. The book elaborates on learning from plausible explanations, augmenting domain theory for explanation-based generalization, reducing search and learning goal preferences, and using domain knowledge to improve inductive learning algorithms for diagnosis. The selection is a dependable reference for researchers interested in the dynamics of machine learning.