Cross Domain Analogies for Learning Domain Theories

Abstract

Analogical reasoning has long been seen as a powerful way of extending the reach of ones knowledge. One product of analogical reasoning is analogical learning in which the result of the comparison increases our understanding of some domain. This work describes a method for learning new domain theories by analogy. We use analogies between pairs of problems and worked solutions to create a domain mapping between a familiar and a new domain. This mapping allows us to initialize the new domain. After this initialization, another analogy is made between the domain theories themselves providing additional conjectures about the new domain. An experiment is described where the system learns to solve rotational kinematics problems by analogy with translational kinematics problems outperforming a version of the system that is incrementally given the correct domain theory.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2007
Accession Number
ADA471251

Entities

People

  • Ken Forbus
  • Matthew Klenk

Organizations

  • Northwestern University

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Angular Acceleration
  • Artificial Intelligence
  • Automobiles
  • Cognition
  • Cognitive Science
  • Cross Domain
  • Equations
  • Kinematics
  • Language
  • Learning
  • Machine Learning
  • Mechanics
  • Models
  • Ontologies
  • Physics
  • Reasoning

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Theoretical Analysis.