Refactored Characteristics of Intelligent Computing Systems

Abstract

We have discussed the following measurable characteristics of intelligent behavior in computing systems: (1) speed and scope of adaptability to unforeseen situations; (2) rate of effective learning of observations; (3) accurate modeling and prediction of the relevant external environment; (4) speed and clarity of problem identification and formulation; (5) effective association and evaluation of disparate information; (6) identification of more important assumptions and prerequisites; (7) creation and use of symbolic language. In this paper, we isolate some common underlying capabilities for these characteristics, and show how they can all be produced using those capabilities. We describe the architecture of a system that has all of these underlying capabilities, using our Wrapping integration infrastructure to coordinate and organize a large collection of models and other computational resources. In particular, these models include complete models of the system's resources and processing strategies, and therefore a model of its own behavior, which it can use to affect that behavior.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2002
Accession Number
ADA516021

Entities

People

  • Christopher Landauer
  • Kirstie L. Bellman

Organizations

  • The Aerospace Corporation

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Autonomous Systems
  • Autonomy
  • Complex Systems
  • Computations
  • Computer Programming
  • Computer Programs
  • Computers
  • Digital Computers
  • Identification
  • Information Operations
  • Language
  • Personality
  • Systems Biology
  • Theorems
  • Video Games

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.
  • Systems Analysis and Design