Integrated Learning: Controlling Explanation

Similarity-based learning, which involves largely structural comparisons of instances, and explanation-based learning, a knowledge-intensive method for analyzing instances to build generalized schemata, are two major inductive learning techniques in use in Artificial Intelligence. In this paper, we propose a combination of the two methods—applying explanation-based techniques during the course of similiarity-based learning. For domains lacking detailed explanatory rules, this combination can achieve the power of explanationbased learning without some of the computational problems that can otherwise arise. We show how the ideas of predictability and interest can be particularly valuable in this context. We include an example of the computer program UNIMEM applying explanation to a generalization formed using similaritybased methods.

[1]  Carl G. Hempel,et al.  A purely syntactical definition of confirmation , 1943, Journal of Symbolic Logic.

[2]  N. Goodman.  Fact, Fiction, and Forecast , 1955 .

[3]  F RESTLE,et al.  The selection of strategies in cue learning. , 1962, Psychological review.

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

[5]  Murray S. Davis,et al.  That's Interesting! , 1971 .

[6]  Roger C. Schank,et al.  Computer Models of Thought and Language , 1974 .

[7]  Allen Newell,et al.  Production Systems: Models of Control Structures , 1973 .

[8]  W. Chase,et al.  Visual information processing. , 1974 .

[9]  D. Bobrow,et al.  Representation and Understanding: Studies in Cognitive Science , 1975 .

[10]  Frederick Hayes-Roth,et al.  AN OVERVIEW OF PATTERN-DIRECTED INFERENCE SYSTEMS , 1978 .

[11]  Roger C. Schank,et al.  Interestingness: Controlling Inferences , 1979, Artif. Intell..

[12]  Michael Lebowitz,et al.  Generalization and memory in an integrated understanding system , 1980 .

[13]  Patrick Henry Winston,et al.  Learning and reasoning by analogy , 1980, CACM.

[14]  Ryszard S. Michalski,et al.  Pattern Recognition as Rule-Guided Inductive Inference , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  J. Carbonell.  Subjective understanding, computer models of belief systems , 1981 .

[16]  Michael Lebowitz.  Cancelled Due To Lack Of Interest , 1981, IJCAI.

[17]  Douglas B. Lenat,et al.  Knowledge-based systems in artificial intelligence , 1981 .

[18]  Barr and Feigenbaum Edward A. Avron,et al.  The Handbook of Artificial Intelligence , 1981 .

[19]  Avron Barr,et al.  The Handbook of Artificial Intelligence , 1982 .

[20]  Douglas B. Lenat,et al.  EURISKO: A Program That Learns New Heuristics and Domain Concepts , 1983, Artif. Intell..

[21]  Michael Lebowitz.  Classifying Numeric Information for Generalization , 1983 .

[22]  Roger C. Schank,et al.  Dynamic memory - a theory of reminding and learning in computers and people , 1983 .

[23]  C SchankRoger,et al.  Dynamic Memory: A Theory of Reminding and Learning in Computers and People , 1983 .

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

[25]  Steven Salzberg.  Generating Hypotheses to Explain Prediction Failures , 1983, AAAI.

[26]  Michael Lebowitz,et al.  Generalization From Natural Language Text , 1983, Cogn. Sci..

[27]  Tom M. Mitchell,et al.  Learning and Problem Solving , 1983, IJCAI.

[28]  Steven Minton,et al.  Constraint-Based Generalization: Learning Game-Playing Plans From Single Examples , 1984, AAAI.

[29]  Michael Lebowitz,et al.  Concept Learning in a Rich Input Domain: Generalization-Based Memory , 1984 .

[30]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[31]  Thomas Ellman,et al.  Generalizing Logic Circuit Designs by Analyzing Proofs of Correctness , 1985, IJCAI.

[32]  Michael Lebowitz.  Categorizing numeric information for generalization , 1985 .

[33]  Roger C. Schank,et al.  SCRIPTS, PLANS, GOALS, AND UNDERSTANDING , 1988 .

[34]  R C Schank.  The Explanation Game. , 1984 .