Explanation-Based Learning: An Alternative View
Machine LearningPublished 1 June 1986Open access
Gerald DeJong, Raymond J. Mooney
Citations835
SJR quartileQ1
SJR score1.15
SNIP2.14
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.
TL;DR
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.
Abstract
In the last issue of this journal Mitchell, Keller, and Kedar-Cabelli presented a unifying framework for the explanation-based approach to machine learning. While it works well for a number of systems, the framework does not adequately capture certain aspects of the systems under development by the explanation-based learning group at Illinois. The primary inadequacies arise in the treatment of concept operationality, organization of knowledge into schemata, and learning from observation. This paper outlines six specific problems with the previously proposed framework and presents an alternative generalization method to perform explanation-based learning of new concepts.
Keywords
Computer Science
Elsevier eBooksA FRAMEWORK FOR REPRESENTING KNOWLEDGE
4,545 Citations1988Marvin Minsky
The enormous problem of the volume of background common sense knowledge required to understand even very simple natural language texts is discussed and it is suggested that networks of frames are a reasonable approach to represent such knowledge.
Principles of Artificial Intelligence
3,336 Citations1982Nils J. Nilsson
This classic introduction to artificial intelligence describes fundamental AI ideas that underlie applications such as natural language processing, automatic programming, robotics, machine vision, automatic theorem proving, and intelligent data retrieval.
The American Journal of PsychologyScripts, Plans, Goals, and Understanding: An Inquiry into Human Knowledge Structures
2,979 Citations1979Earl Hunt, Roger C. Schank +1 more
Machine LearningExplanation-Based Generalization: A Unifying View
1,175 Citations1986Tom M. Mitchell, Richard M. Keller +1 more
This paper proposes a general, domain-independent mechanism, called EBG, that unifies previous approaches to explanation-based generalization, and is illustrated in the context of several example problems, and used to contrast several existing systems for explanation- based generalization.
Artificial IntelligencePlanning in a hierarchy of abstraction spaces
1,163 Citations1974Earl D. Sacerdoti
Examples of the ABSTRIPS system's performance are presented that demonstrate the significant increases in problem-solving power that this approach provides, and some further implications of the hierarchical planning approach are explored.
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.
Machine LearningExplanation-based generalization: A unifying view
718 Citations1986Tom M. Mitchell, Richard M. Keller +1 more
This paper proposes a general, domain-independent mechanism, called EBG, that unifies previous approaches to explanation-based generalization, and is illustrated in the context of several example problems, and used to contrast several existing systems for explanation- based generalization.
Machine LearningAn Overview of Machine Learning
386 Citations1983Jaime Carbonell, Ryszard S. Michalski +1 more
The study and computer modeling of learning processes in their multiple manifestations constitutes the subject matter of machine learning.
Elsevier eBooksAchieving Several Goals Simultaneously**The research reported herein was sponsored by the National Science Foundation under Grant GJ-36146.
263 Citations1981Richard Waldinger
It is argued that skeleton modelling is valuable as a planning technique apart from its use in plan modification, particularly because it facilitates the representation of “influential actions” whose effects may be far reaching.
Elsevier eBooksExplanation-Based Generalization: A Unifying View
261 Citations1988T. M. Mitchell, Richard M. Keller +1 more
Machine LearningAN OVERVIEW OF MACHINE LEARNING
251 Citations1983Jaime Carbonell, Ryszard S. Michalski +1 more
An equally basic scientific objective of machine learning is the exploration of alternative learning mechanisms, including the discovery of different induction algorithms, the scope and limitations of certain methods, the information that must be available to the learner, the issue of coping with imperfect training data, and the creation of general techniques applicable in many task domains.
International Joint Conference on Artificial IntelligenceLEAP: a learning apprentice for VLSI design
249 Citations1985Tom M. Mitchell, Sridhar Mahadevan +1 more
ACM SIGART BulletinReview of "Principles of Artificial Intelligence by Nils J. Nilsson", Tioga Publishing Company, Palo Alto, CA, ISBN 0-935382-01-1.
202 Citations1980Keith Price
Nils Nilsson's new book on AI is now available from Tioga Publishing Company, P.O. Box 98, Palo Alto, CA 94302; (415) 854--2445.
DSpace@MIT (Massachusetts Institute of Technology)Learning physical descriptions from functional definitions, examples, and precedents
198 Citations1983Patrick Henry Winston, Thomas O. Binford +2 more
The theory is a synthesis of two sets of ideas: ideas about learning from precedents and exercises developed at MIT and ideas about physical description developed at Stanford, and is illustrated by way of representative experiments.
International Joint Conference on Artificial IntelligenceSelectively generalizing plans for problem-solving
160 Citations1985Steven Minton
MORRIS is described, a heuristic problem solver that measures the utility of plan fragments to determine whether they are worth learning and comparing the performance of MORRIS to a less selective learning system.
International Joint Conference on Artificial IntelligenceLearning and Problem Solving.
153 Citations1983Tom M. Mitchell
Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)A domain independent explanation-based generalizer
108 Citations1986Raymond J. Mooney, Scott Bennett
This method is compared and contrasted with other approaches to generalizing explanations, including an abstract version of the algorithm used in the STRIPS system and the EBG technique recently developed by Mitchell, Keller, and Kedar-Cabelli.
Machine LearningMachine Transformation of Advice Into a Heuristic Search Procedure
98 Citations1983David J. Mostow
This chapter is a case study in the mechanical mapping of domain-specific problems onto general methods, using as a detailed example the derivation of a heuristic search procedure for the advice “avoid taking points.”
Learning schemata for natural language processing
97 Citations1985Raymond J. Mooney, Gerald DeJong
A natural language system which improves its own performance through learning and is able to acquire, from a single narrative, a new schema for a stereotypical set of actions.
Generalizations based on explanations
94 Citations1981Gerald DeJong
The system described here is designed to grasp some p r i n c i p l e under ly ing a na tu ra l language i n p u t in a new schema in the system.
Cognitive ScienceA framed painting: The representation of a common sense knowledge fragment
82 Citations1977Eugene Charniak
National Conference on Artificial IntelligenceConstraint-based generalization: learning game-playing plans from single examples
61 Citations1984Steven Minton
It is shown how this technique can be used for learning tactical combinations in games and an implementation which learns forced wins in tic-tac-toe, go-moku, and chess is discussed.
Columbia Academic Commons (Columbia University)Generalizing Logic Circuit Designs by Analyzing Proofs of Correctness
59 Citations1985Thomas Ellman
The method utilizes proofs of design correctness to guide the process of generalization and can generalize a rotational shift register into a schema describing devices capable of computing arbitrary permutations.
Explanation-based manipulator learning: Acquisition of planning ability through observation
44 Citations2005Alberto M. Segre, Gerald DeJong
A robot manipulator system currently under development which learns from observation improves its problem-solving capabilities through the acquisition of task-related concepts via knowledge-based analysis of how the observed command sequence achieved the goal.
International Joint Conference on Artificial IntelligenceAcquiring schemata through understanding and generalizing plans
40 Citations1983Gerald DeJong
This paper discusses explanatory schema acquisition, a learning technique with several interesting properties that can acquire a new concept based on only one input example, although later inputs might result in refinement of learned concepts.
Artificial IntelligenceWhy am and eurisko appear to work
34 Citations1984Douglas B. Lenat, John Seely Brown
International Joint Conference on Artificial IntelligenceTowards a model of conceptual knowledge acquisition through directed experimentation
28 Citations1985Shankar A. Rajamoney, Gerald DeJong +1 more
The main thrust of this project is to build a system that can continuously update its model through a constant monitoring of the real world and revise its beliefs to accommodate the previously inconsistent observations.
International Joint Conference on Artificial IntelligenceVerification-based learning: a generalisation strategy for inferring problem-reduction methods
28 Citations1985Sridhar Mahadevan
It was observed that combining neuroleptics with clonidine was superior to thioridazine, levomepromazine, or sulpiride for controlling the dyskinesia.
Cognitive ScienceFramed PAINTING: The Representation of a Common Sense Knowledge Fragment
22 Citations1977Eugene Charniak
This paper presents a “frame” representation for common sense knowledge and uses it to formalize the authors' knowledge of “mundane” painting and introduces system of interframe pointers which explain how or why something is done in terms of knowledge given in other frames.
National Conference on Artificial IntelligenceGeneralization for explanation-based schema acquisition
17 Citations1984Paul O’Rorke
This paper is about explanation-based learning for heuristic problem solvers which "build" solutions using schemata (frames like scripts) as both "bricks" and "mortar".
Machine LearningMACHINE TRANSFORMATION OF ADVICE INTO A HEURISTIC SEARCH PROCEDURE
14 Citations1983David J. Mostow
International Joint Conference on Artificial IntelligenceLearning about momentum conservation
14 Citations1985Jude Shavlik
An overview of the fully-implemented system and an example run by it are presented, and a general formula describing how the momentum of a collection of objects changes over time is acquired.
Some thoughts on schemata
13 Citations1975Wallace Chafe
Some ideas and questions that have arisen from efforts over the past few years to develop a model of what I call verbalization: the set of processes by which a person converts nonverbal knowledge into a verbal output are summarized.
eScholarship (California Digital Library)Explanation and Generalization Based Memory
10 Citations1985Pazzani, Michael J.
International Joint Conference on Artificial IntelligenceA comparison of analytic and experimental goal regression for machine learning
10 Citations1985Bruce Porter, Dennis Kibler
This paper critically examines research and identifies essential applicability conditions for the technique and defines an alternative, called experimental goal regression, which approximates the results of analytic goal regression without suffering from these limitations.
Kluwer international series in engineering and computer scienceOverview of the Prodigy Learning Apprentice
4 Citations1986Steven Minton
The PRODIGY system, a learning apprentice for robot construction tasks currently being developed at Carnegie-Mellon University, re-examines the search tree and analyzes its mistakes to find efficient tests for determining if a problem solving method is applicable.
Kluwer international series in engineering and computer scienceComplex Learning Environments: Hierarchies and the Use of Explanation
3 Citations1986Michael Lebowitz
Three areas of recent research are described: generalizing hierarchically structured representations; an experiment in explanation-based learning; and first steps at integrating explanation and similarity-based methods.
Kluwer international series in engineering and computer scienceLearning and Problem Solving
1 Citations1988Alberto M. Segre
From a machine-learning perspective, the most interesting aspects of the ARMS system are in the learning and performance elements.