Accession Number:

AD1144946

Title:

Learning by Analogical Replay in Prodigy: First Results

Descriptive Note:

[Technical Report, Research Report]

Corporate Author:

Carnegie Mellon University

Report Date:

1974-01-01

Pagination or Media Count:

16

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.

Descriptors:

Subject Categories:

  • Psychology

Distribution Statement:

[A, Approved For Public Release]