Technical Report
 

A study of explanation-based methods for inductive learning

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/technical_reports/dv140252z

Descriptions

Attribute NameValues
Creator
Abstract
  • This paper formalizes a new learning from examples problem: identifying a correct concept definition from positive examples such that the concept is some specialization of a target concept defined by a domain theory. This paper describes an empirical study that evaluates three methods for solving this problem: explanation based generalization (EBG), multiple example explanation based generalization (mEBG), and a new method, induction over explanations (IOE). The study demonstrates that the two existing methods (EBG and mEBG) exhibit two shortcomings: (a) the methods rarely identify the correct definition, and (b) the methods are brittle-their success depends greatly on the choice of encoding of the domain theory rules. The study demonstrates that the new method, IOE, does not exhibit these shortcomings. The IOE method applies the domain theory to construct explanations from multiple training examples as in mEBG, but forms the concept definition by employing a similarity-based generalization policy over the explanations. The method has the advantage that an explicit domain theory can be exploited to aid the learning process, the dependence on the initial encoding of the domain theory is significantly reduced, and the correct concepts can be learned from few examples. The study evaluates the methods in an implemented system, called Wyl2, learning a variety of concepts in chess including "skewer" and "knight-fork."
  • Key words: Learning from examples, induction over explanations, explanation based learning, inductive learning, knowledge compilation, evaluation of learning methods
Resource Type
Date Issued
Academic Affiliation
Series
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

Items

Thumbnail Title Date Uploaded Visibility Actions
file details Flann_Dietterich_88_30_11.pdf 2022-12-20 Public Download