Symbol Structures in Connectionist Networks: Five Properties and Two Architectures

Abstract

We define five properties of symbol representations (called the Five M's) that together provide a powerful and flexible symbol processing facility. Our ideal symbol structures are Mobile, Memorable, Meaningful, Malleable, and Modifiable. Conventional symbol processing architectures, such as Lisp on von Neumann machines, support some of these properties, but others seem to require flexibility and an ability to generalize that is unique to connectionist models. Two recently-developed connectionist architectures, BoltzCONS and micro-KLONE, are described in some detail. Representations used in these two architectures satisfy different subsets of the Five M's. Artificial intelligence, Connectionism, Symbols, Computer programs, Lisp on vonNeumann machines, BoltzCONS, Micro-kLONE.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 29, 1987
Accession Number
ADA218942

Entities

People

  • David S. Touretzky
  • Mark A. Derthick

Organizations

  • Carnegie Mellon University

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Cells
  • Classification
  • Cognitive Science
  • Computations
  • Computer Programs
  • Computer Science
  • Computers
  • Content Addressable Memory
  • Neural Networks
  • Psychology
  • Security
  • Self Organizing Systems
  • United States
  • Universities

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks