Explanation-Based Generalization: A Unifying View
Elsevier eBooksPublished 1 January 1988
T. M. Mitchell, Richard M. Keller, Smadar T. Kedar-Cabelli
Citations261
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
Abstract. The problem of formulating general concepts from specific training examples has long been a major focus of machine learning research. While most previous research has focused on empirical methods for generalizing from a large number of training examples using no domain-specific knowledge, in the past few years new methods have been developed for applying domain-specific knowledge to for-mulate valid generalizations from single training examples. The characteristic common to these methods is that their ability to generalize from a single example follows from their ability to explain why the training example is a member of the concept being learned. This paper proposes a general, domain-independent mechanism, called EBG, that unifies previous approaches to explanation-based generalization. The EBG method is illustrated in the context of several example problems, and used to contrast several existing systems for explanation-based generalization. The perspective on explanation-based generalization af-forded by this general method is also used to identify open research problems in this area. 1. Introduction and
Keywords
Computer Science
Artificial IntelligenceLearning and executing generalized robot plans
1,035 Citations1972Richard Fikes, Peter E. Hart +1 more
Some major new additions to the STRIPS robot problem-solving system are described, including a process for generalizing a plan produced by STriPS so that problem-specific constants appearing in the plan are replaced by problem-independent parameters.
Artificial IntelligenceA theory and methodology of inductive learning
1,006 Citations1983Ryszard S. Michalski
The presented theory views inductive learning as a heuristic search through a space of symbolic descriptions, generated by an application of various inference rules to the initial observational statements.
BMC NursingThe Need for Biases in Learning Generalizations
527 Citations2007Tom M. Mitchell
The current study showed that the Digital Education Package (DEP) is an effective method for reducing children’s anxiety during hospitalization and recommended it as a preferred and simple method rather than routine education for pediatric nurses.
Machine LearningExplanation-based learning: An alternative view
488 Citations1986Gerald DeJong, Raymond J. Mooney
Six specific problems with the previously proposed framework for the explanation-based approach to machine learning are outlined and an alternative generalization method to perform explanation- based learning of new concepts is presented.
Machine LearningChunking in Soar: The anatomy of a general learning mechanism
298 Citations1986John E. Laird, Paul S. Rosenbloom +1 more
The anatomy of chunking in Soar is examined and a new demonstration of its learning capabilities involving the acquisition and use of macro-operators is provided.
Columbia Academic Commons (Columbia University)Concept Learning in a Rich Input Domain: Generalization-Based Memory
91 Citations1984Michael Lebowitz
A characterization of the use of Generalization-Based Memory in two programs under development at Columbia, UNIMEM and RESEARCHER, and how they perform concept evaluation and generalization of complex structural descriptions are presented.
DSpace@MIT (Massachusetts Institute of Technology)Learning by Augmenting Rules and Accumulating Censors.
66 Citations1982Patrick Henry Winston
A synthesis of several sets of ideas enables two extensions to an implemented system that solves problems involving precedents and exercises and that generates if-then rules as a byproduct.
Kluwer international series in engineering and computer scienceA Brief Overview of Explanatory Schema Acquisition
43 Citations1986Gerald DeJong
This paper presents a brief overview of the learning approach to formalize explanatory schema acquisition in a domain-independent fashion and compares explanatory Schema Acquisition systems implemented for a number of different concrete domains.
Kluwer international series in engineering and computer scienceLearning in Intractable Domains
13 Citations1986Prasad Tadepalli
The importance of recognizing the goal structure of the players to learn useful and tractable heuristics in chess is illustrated.
Kluwer international series in engineering and computer scienceGeneralizing Explanations of Narratives into Schemata
12 Citations1986Raymond J. Mooney
A natural language system which improves its performance through learning and from a single narrative acquires a new schema for a stereotypical set of actions which is used by the system to process narratives which were previously beyond its capabilities.
Kluwer international series in engineering and computer scienceExplanation-Based Learning in Logic Circuit Design
8 Citations1986Thomas Ellman
This research is focused on a technique known as explanation-based learning, which has been demonstrated in a program which generalizes a circular shift register into a schema describing devices capable of computing arbitrary permutations.
Kluwer international series in engineering and computer scienceExplanation-Based Manipulator Learning
7 Citations1986Alberto M. Segre
A robot manipulator system under development which learns from observation that observes manipulator command sequences that solve problems currently beyond its own planning abilities and acquires general problem-solving schemata which allow the system to solve problems that were previously unsolvable.
Kluwer international series in engineering and computer scienceLearning from Exceptions in Databases
6 Citations1986Keith E. Williamson
To utilize database management systems, a database designer must construct a schema, which is used to validate the data stored and help set up efficient access structures, including so-called "semantic integrity constraints,” which are first-order assertions about consistent database states.
Kluwer international series in engineering and computer scienceAn Investigation of the Nature of Mathematical Discovery
5 Citations1986Michael H. Sims
This paper discusses an analytic technique which can be coupled usefully with empirical techniques of discovery and indicates that in some domains of mathematics a purely empirical approach is insufficient to model the discovery process.
Kluwer international series in engineering and computer scienceDevelopment of a Framework for Contextual Concept Learning
5 Citations1986Richard M. Keller
This paper shows how several limitations of inductive concept learning methods can be overcome by giving the learning system explicit knowledge of the context in which learning occurs.
Kluwer international series in engineering and computer scienceLearning Classical Physics
5 Citations1986Jude Shavlik
A computational model of learning in a complex domain that determines why the human-provided solution to a specific problem suffices to solve the problem, and then extends the solution technique to more general situations.
Kluwer international series in engineering and computer scienceLearning Evaluation Functions
4 Citations1986Patricia A. Schooley
This research proposes a scheme for learning state evaluation functions for heuristic search problem solving systems that employs both empirical and analytical learning techniques.
Kluwer international series in engineering and computer scienceRecent Progress on the Mathematician’s Apprentice Project
3 Citations1986Paul O’Rorke
The “Mathematician’s Apprentice” project is a case study of explanation-based schema acquisition in the context of an experimental automated apprentice (called MA) and the focus of the project is on the development, demonstration and formalization of explanations-based generalization methods.
Kluwer international series in engineering and computer scienceLearning Implementation Rules with Operating-Conditions Depending on Internal Structures in VLSI Design
2 Citations1986M. Watanabe
The problem of expertise acquisition by observing user’s solutions in the Learning Apprentice Systems is here considered as learning implementation rules in VLSI circuit design.