A Preliminary Analysis of the Soar Architecture as a Basis for General Intelligence

Abstract

The central scientific problem of artificial intelligence is to understand what constitutes intelligent action and what processing organizations are capable of such action. Human intelligence shows, to first observation, what can only be termed general intelligence. The Soar project has been attempting to understand the functionality required to support general intelligence. In this article we take a step towards providing an analysis of the Soar architecture as a basis for general intelligence. Included are discussions of the basic assumptions underlying the development of Soar, a description of Soar cast in terms of the theoretical idea fof multiple levels of description, an example of Soar performing multi-column subtraction, and three analyses of Soar: its natural tasks, the sources of its power, and its scope and limits.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 08, 1989
Accession Number
ADA218913

Entities

People

  • Allen Newell
  • John E. Laird
  • Paul Simon Rosenbloom
  • Robert Mccarl

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Biomedical
  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Acquisition
  • Artificial Intelligence
  • California
  • Coding
  • Cognitive Science
  • Computer Science
  • Computers
  • Decoding
  • Electrical Engineering
  • Engineering
  • Expert Systems
  • Information Science
  • Language
  • Michigan
  • Procurement
  • Psychology
  • United States

Readers

  • Geospatial Intelligence and Artificial Intelligence Analytics
  • Military Science
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy