Four Capacity Models for Coarse-Coded Symbol Memories

Abstract

Coarse-coded symbol memories have appeared in several neutral network symbol processing models. In order to determine how these models would scale, one must first have some understanding of the mathematics of coarse-coded representations. We define the general structure of coarse-coded symbol memories, and discuss their strengths and weaknesses. Memory schemes can be characterized by their memory size, symbol-set size and capacity. We derive mathematical relationships between these parameters for various memory schemes, using both analysis and numerical methods. Finally, we compare the predicted capacity of one of the schemes with actual measurements of the coarse-coded working memory of distributed connectionist production system (DCPS), Touretzky and Hinton's distributed connectionist production system. (jg)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 15, 1987
Accession Number
ADA218909

Entities

People

  • David S. Touretzky
  • Roni Rosenfeld

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Classification
  • Coding
  • Computer Programming
  • Computer Science
  • Computers
  • Mathematical Analysis
  • Neural Networks
  • Notation
  • Security
  • Symbols
  • Three Dimensional
  • United States
  • United States Government
  • Universities

Readers

  • Artificial Intelligence
  • Canine Service Warrior Training Program for Wounded Warriors in the Veterinary Industry, Supported by Donors.