Learning by Analogical Replay in Prodigy: First Results

Abstract

Robust reasoning requires learning from problem solving episodes. Past experience must be compiled to provide adaptation to new contingencies and intelligent modification of solutions to past problems. This paper presents a comprehensive computational model of analogical reasoning that transitions smoothly between case reply, case adaptation, and general problem solving, exploiting and modifying past experience when available and resorting to general problem-solving methods when required.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1974
Accession Number
AD1144946

Entities

People

  • Jaime Carbonell
  • Manuela M. Veloso

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Human Systems
  • Weapons Technologies

DTIC Thesaurus Topics

  • Acquisition
  • Aeronautical Laboratories
  • Air Force
  • Algorithms
  • Analogies
  • Artificial Intelligence
  • Computer Science
  • Computers
  • Guidance
  • Intelligent Systems
  • Language
  • Learning
  • Machine Learning
  • Reasoning
  • Sequences
  • Skeleton
  • Trees (Data Structures)

Readers

  • Artificial Intelligence
  • Systems Analysis and Design