Harpoons and long sticks: the interaction of theory and similarity in rule induction

Publisher Summary This chapter presents two studies that examined the roles of theoretical expectations and empirical evidence in rule induction. These studies produced several major findings. First, theoretical expectations strongly affect the kinds of rules that people construct for a given category. These rules are qualitatively different from those constructed by people without such expectations. The theoretical expectations activate hypotheses about abstract features that could be true for a category. Second, theoretical knowledge closely interacts with empirical evidence, and these types of knowledge mutually influence each other. In particular, the two sources of knowledge interact to determine hypothetical features upon which induction operates. They also mutually influence the types of explanations that people construct for a category. The chapter describes the way in which a learning system closely integrates these sources of knowledge. The view that people's theoretical expectations closely interact with experience generally has not been emphasized in machine learning models that integrate these two sources of knowledge.

[1]  G. DeJong,et al.  A introduction to explanation-based learning , 1988 .

[2]  Michael G. Dyer,et al.  Using Prior Learning to Facilitate the Learning of New Causal Theories , 1987, IJCAI.

[3]  Douglas L. Medin,et al.  Context theory of classification learning. , 1978 .

[4]  F. Keil.  Constraints on knowledge and cognitive development. , 1981 .

[5]  Raymond J. Mooney,et al.  Induction Over the Unexplained: Integrated Learning of Concepts with Both Explainable and Conventional Aspects , 1989, ML.

[6]  Thomas Ellman,et al.  Explanation-based learning: a survey of programs and perspectives , 1989, CSUR.

[7]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[8]  L. E. Bourne,et al.  ATTRIBUTE- AND RULE-LEARNING ASPECTS OF CONCEPTUAL BEHAVIOR. , 1965, Psychological review.

[9]  David J. Mostow,et al.  Machine Transformation of Advice Into a Heuristic Search Procedure , 1983 .

[10]  Ryszard S. Michalski,et al.  A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.

[11]  Reid G. Smith,et al.  A Conceptual Clustering Program for Rule Generation , 1987, Int. J. Man Mach. Stud..

[12]  Douglas L. Hintzman,et al.  "Schema Abstraction" in a Multiple-Trace Memory Model , 1986 .

[13]  L. Adelman.  The influence of formal, substantive, and contextual task properties on the relative effectiveness of different forms of feedback in multiple-cue probability learning tasks☆ , 1981 .

[14]  Douglas H. Fryer,et al.  Personnel selection in the British Forces. , 1950 .

[15]  G. Collins,et al.  Transcending inductive category formation in learning , 1986, Behavioral and Brain Sciences.

[16]  L. Rips.  Similarity, typicality, and categorization , 1989 .

[17]  G. Murphy,et al.  The utility of theories in intuitive statistics: The robustness of theory-based judgments. , 1984 .

[18]  Douglas H. Fisher,et al.  A Computational Account of Basic Level and Typicality Effects , 1988, AAAI.

[19]  J. Ross Quinlan,et al.  Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .

[20]  Lance J. Rips,et al.  How big is big? Relative and absolute properties in memory , 1980, Cognition.

[21]  R. Nosofsky.  Attention and learning processes in the identification and categorization of integral stimuli. , 1987, Journal of experimental psychology. Learning, memory, and cognition.

[22]  Michael Lebowitz,et al.  Integrated Learning: Controlling Explanation , 1986, Cogn. Sci..

[23]  Larry A. Rendell,et al.  Substantial Constructive Induction Using Layered Information Compression: Tractable Feature Formation in Search , 1985, IJCAI.

[24]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[25]  Ryszard S. Michalski,et al.  Constraints and Preferences in Inductive Learning: An Experimental Study of Human and Machine Performance , 1987 .

[26]  P. Muchinsky,et al.  The influence of a suppressor variable and labeled stimuli on multiple cue probability learning , 1974 .

[27]  Michael Lebowitz,et al.  Not the Path to Perdition: The Utility of Similarity-Based Learning , 1986, AAAI.

[28]  Irving Biederman,et al.  Human image understanding: Recent research and a theory , 1985, Comput. Vis. Graph. Image Process..

[29]  F. Goodenough,et al.  Studies in the psychology of children's drawings , 1950 .

[30]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[31]  D. Medin,et al.  The role of theories in conceptual coherence. , 1985, Psychological review.

[32]  Tom M. Mitchell,et al.  Generalization as Search , 2002 .

[33]  Douglas L Medin,et al.  Linear separability and concept learning: Context, relational properties, and concept naturalness , 1986, Cognitive Psychology.

[34]  Thomas G. Dietterich,et al.  Learning and Inductive Inference , 1982 .

[35]  D. Medin,et al.  Linear separability in classification learning. , 1981 .

[36]  Ryszard S. Michalski,et al.  The Logic of Plausible Reasoning: A Core Theory , 1989, Cogn. Sci..

[37]  Pat Langley,et al.  Approaches to Conceptual Clustering , 1985, IJCAI.